Authors: Yufa Zhou, Yixiao Wang, Xunjian Yin, Shuyan Zhou, Anru R. Zhang
Abstract: We study how large language models (LLMs) ``think'' through their representation space. We propose a novel geometric framework that models an LLM's reasoning as flows -- embedding trajectories evolving where logic goes. We disentangle logical structure from semantics by employing the same natural deduction propositions with varied semantic carriers, allowing us to test whether LLMs internalize logic beyond surface form. This perspective connects reasoning with geometric quantities such as position, velocity, and curvature, enabling formal analysis in representation and concept spaces. Our theory establishes: (1) LLM reasoning corresponds to smooth flows in representation space, and (2) logical statements act as local controllers of these flows' velocities. Using learned representation proxies, we design controlled experiments to visualize and quantify reasoning flows, providing empirical validation of our theoretical framework. Our work serves as both a conceptual foundation and practical tools for studying reasoning phenomenon, offering a new lens for interpretability and formal analysis of LLMs' behavior.
Authors: Valerie Chen, Rohit Malhotra, Xingyao Wang, Juan Michelini, Xuhui Zhou, Aditya Bharat Soni, Hoang H. Tran, Calvin Smith, Ameet Talwalkar, Graham Neubig
Abstract: LLM-powered agents are both a promising new technology and a source of complexity, where choices about models, tools, and prompting can affect their usefulness. While numerous benchmarks measure agent accuracy across domains, they mostly assume full automation, failing to represent the collaborative nature of real-world use cases. In this paper, we make two major steps towards the rigorous assessment of human-agent interactions. First, we propose PULSE, a framework for more efficient human-centric evaluation of agent designs, which comprises collecting user feedback, training an ML model to predict user satisfaction, and computing results by combining human satisfaction ratings with model-generated pseudo-labels. Second, we deploy the framework on a large-scale web platform built around the open-source software agent OpenHands, collecting in-the-wild usage data across over 15k users. We conduct case studies around how three agent design decisions -- choice of LLM backbone, planning strategy, and memory mechanisms -- impact developer satisfaction rates, yielding practical insights for software agent design. We also show how our framework can lead to more robust conclusions about agent design, reducing confidence intervals by 40\% compared to a standard A/B test. Finally, we find substantial discrepancies between in-the-wild results and benchmark performance (e.g., the anti-correlation between results comparing claude-sonnet-4 and gpt-5), underscoring the limitations of benchmark-driven evaluation. Our findings provide guidance for evaluations of LLM agents with humans and identify opportunities for better agent designs.
Authors: Eric Schwitzgebel
Abstract: This is a skeptical overview of the literature on AI consciousness. We will soon create AI systems that are conscious according to some influential, mainstream theories of consciousness but are not conscious according to other influential, mainstream theories of consciousness. We will not be in a position to know which theories are correct and whether we are surrounded by AI systems as richly and meaningfully conscious as human beings or instead only by systems as experientially blank as toasters. None of the standard arguments either for or against AI consciousness takes us far. Table of Contents Chapter One: Hills and Fog Chapter Two: What Is Consciousness? What Is AI? Chapter Three: Ten Possibly Essential Features of Consciousness Chapter Four: Against Introspective and Conceptual Arguments for Essential Features Chapter Five: Materialism and Functionalism Chapter Six: The Turing Test and the Chinese Room Chapter Seven: The Mimicry Argument Against AI Consciousness Chapter Eight: Global Workspace Theories and Higher Order Theories Chapter Nine: Integrated Information, Local Recurrence, Associative Learning, and Iterative Natural Kinds Chapter Ten: Does Biological Substrate Matter? Chapter Eleven: The Problem of Strange Intelligence Chapter Twelve: The Leapfrog Hypothesis and the Social Semi-Solution
Authors: Junyuan Liu, Quan Qin, Guangsheng Dong, Xinglei Wang, Jiazhuang Feng, Zichao Zeng, Tao Cheng
Abstract: General-purpose spatial representations are essential for building transferable geospatial foundation models (GFMs). Among them, the AlphaEarth Foundation (AE) represents a major step toward a global, unified representation of the Earth's surface, learning 10-meter embeddings from multi-source Earth Observation (EO) data that capture rich physical and environmental patterns across diverse landscapes. However, such EO-driven representations remain limited in capturing the functional and socioeconomic dimensions of cities, as they primarily encode physical and spectral patterns rather than human activities or spatial functions. We propose AETHER (AlphaEarth-POI Enriched Representation Learning), a lightweight framework that adapts AlphaEarth to human-centered urban analysis through multimodal alignment guided by Points of Interest (POIs). AETHER aligns AE embeddings with textual representations of POIs, enriching physically grounded EO features with semantic cues about urban functions and socioeconomic contexts. In Greater London, AETHER achieves consistent gains over the AE baseline, with a 7.2% relative improvement in land-use classification F1 and a 23.6% relative reduction in Kullback-Leibler divergence for socioeconomic mapping. Built upon pretrained AE, AETHER leverages a lightweight multimodal alignment to enrich it with human-centered semantics while remaining computationally efficient and scalable for urban applications. By coupling EO with human-centered semantics, it advances geospatial foundation models toward general-purpose urban representations that integrate both physical form and functional meaning.
Authors: Lianhao Zhou, Hongyi Ling, Cong Fu, Yepeng Huang, Michael Sun, Wendi Yu, Xiaoxuan Wang, Xiner Li, Xingyu Su, Junkai Zhang, Xiusi Chen, Chenxing Liang, Xiaofeng Qian, Heng Ji, Wei Wang, Marinka Zitnik, Shuiwang Ji
Abstract: Computing has long served as a cornerstone of scientific discovery. Recently, a paradigm shift has emerged with the rise of large language models (LLMs), introducing autonomous systems, referred to as agents, that accelerate discovery across varying levels of autonomy. These language agents provide a flexible and versatile framework that orchestrates interactions with human scientists, natural language, computer language and code, and physics. This paper presents our view and vision of LLM-based scientific agents and their growing role in transforming the scientific discovery lifecycle, from hypothesis discovery, experimental design and execution, to result analysis and refinement. We critically examine current methodologies, emphasizing key innovations, practical achievements, and outstanding limitations. Additionally, we identify open research challenges and outline promising directions for building more robust, generalizable, and adaptive scientific agents. Our analysis highlights the transformative potential of autonomous agents to accelerate scientific discovery across diverse domains.
Authors: Xi Fang, Weijie Xu, Yuchong Zhang, Stephanie Eckman, Scott Nickleach, Chandan K. Reddy
Abstract: When an AI assistant remembers that Sarah is a single mother working two jobs, does it interpret her stress differently than if she were a wealthy executive? As personalized AI systems increasingly incorporate long-term user memory, understanding how this memory shapes emotional reasoning is critical. We investigate how user memory affects emotional intelligence in large language models (LLMs) by evaluating 15 models on human validated emotional intelligence tests. We find that identical scenarios paired with different user profiles produce systematically divergent emotional interpretations. Across validated user independent emotional scenarios and diverse user profiles, systematic biases emerged in several high-performing LLMs where advantaged profiles received more accurate emotional interpretations. Moreover, LLMs demonstrate significant disparities across demographic factors in emotion understanding and supportive recommendations tasks, indicating that personalization mechanisms can embed social hierarchies into models emotional reasoning. These results highlight a key challenge for memory enhanced AI: systems designed for personalization may inadvertently reinforce social inequalities.
Authors: Olivia Peiyu Wang, Tashvi Bansal, Ryan Bai, Emily M. Chui, Leilani H. Gilpin
Abstract: Large Language Models (LLMs) suffer from critical reasoning gaps, including a tendency to hallucinate and poor accuracy in classifying logical fallacies. This limitation stems from their default System 1 processing, which is fast and intuitive, whereas reliable reasoning requires the deliberate, effortful System 2 approach (Kahneman, 2011; Li et al., 2025). Since full System 2 training is often prohibitively expensive, we explore a low-cost, instruction-based intervention to bridge this gap. Our methodology introduces a novel stepwise instruction dataset that decomposes fallacy classification into a series of atomic procedural steps (simple binary questions). We further augment this with a final verification step where models consult a relational knowledge graph of related fallacies. This procedural, rule-based intervention yields a significant improvement in LLM logical fallacy classification. Crucially, the approach also provides enhanced transparency into the LLMs' decision-making, highlighting a practical pathway for Neuro-symbolic architectures to address LLM reasoning deficits.
Authors: Pratik S. Sachdeva, Tom van Nuenen
Abstract: As large language models (LLMs) are increasingly deployed in sensitive everyday contexts - offering personal advice, mental health support, and moral guidance - understanding their elicited values in navigating complex moral reasoning is essential. Most evaluations study this sociotechnical alignment through single-turn prompts, but it is unclear if these findings extend to multi-turn settings where values emerge through dialogue, revision, and consensus. We address this gap using LLM debate to examine deliberative dynamics and value alignment in multi-turn settings by prompting subsets of three models (GPT-4.1, Claude 3.7 Sonnet, and Gemini 2.0 Flash) to collectively assign blame in 1,000 everyday dilemmas from Reddit's "Am I the Asshole" community. We use both synchronous (parallel responses) and round-robin (sequential responses) formats to test order effects and verdict revision. Our findings show striking behavioral differences. In the synchronous setting, GPT showed strong inertia (0.6-3.1% revision rates) while Claude and Gemini were far more flexible (28-41%). Value patterns also diverged: GPT emphasized personal autonomy and direct communication, while Claude and Gemini prioritized empathetic dialogue. Certain values proved especially effective at driving verdict changes. We further find that deliberation format had a strong impact on model behavior: GPT and Gemini stood out as highly conforming relative to Claude, with their verdict behavior strongly shaped by order effects. These results show how deliberation format and model-specific behaviors shape moral reasoning in multi-turn interactions, underscoring that sociotechnical alignment depends on how systems structure dialogue as much as on their outputs.
Authors: Meng Xi, Sihan Lv, Yechen Jin, Guanjie Cheng, Naibo Wang, Ying Li, Jianwei Yin
Abstract: Retrieval-Augmented Generation (RAG) systems based on Large Language Models (LLMs) have become a core technology for tasks such as question-answering (QA) and content generation. However, by injecting poisoned documents into the database of RAG systems, attackers can manipulate LLMs to generate text that aligns with their intended preferences. Existing research has primarily focused on white-box attacks against simplified RAG architectures. In this paper, we investigate a more complex and realistic scenario: the attacker lacks knowledge of the RAG system's internal composition and implementation details, and the RAG system comprises components beyond a mere retriever. Specifically, we propose the RIPRAG attack framework, an end-to-end attack pipeline that treats the target RAG system as a black box, where the only information accessible to the attacker is whether the poisoning succeeds. Our method leverages Reinforcement Learning (RL) to optimize the generation model for poisoned documents, ensuring that the generated poisoned document aligns with the target RAG system's preferences. Experimental results demonstrate that this method can effectively execute poisoning attacks against most complex RAG systems, achieving an attack success rate (ASR) improvement of up to 0.72 compared to baseline methods. This highlights prevalent deficiencies in current defensive methods and provides critical insights for LLM security research.
Authors: Jusheng Zhang, Kaitong Cai, Qinglin Zeng, Ningyuan Liu, Stephen Fan, Ziliang Chen, Keze Wang
Abstract: Optimizing LLM-based workflows is typically formulated as a global search, where candidate workflows are evaluated based on a scalar metric. This paradigm, however, suffers from a critical flaw: information collapse. By reducing rich, multi-step execution traces to simple success/failure signals, existing methods are rendered blind to the underlying structure of failures, fundamentally preventing them from modeling the workflow's failure distribution. We reconceptualize this challenge as a distributional problem. We propose a new paradigm where the optimization goal is not to maximize a scalar score, but to directly minimize a workflow's Expected Failure Mass, i.e., the integral of its failure probability density function defined over a high-dimensional Failure Signature Space (FSS). This distributional lens allows us to move from inefficient, zero-order optimization to a principled, gradient-like descent on the failure landscape itself. We introduce CE-Graph, a framework that operationalizes this paradigm through a novel, failure-driven refinement process. CE-Graph approximates the failure distribution from a pool of counterexamples, identifies its densest regions as recurring failure modes, and applies targeted, operator-constrained graph edits via a Propose-and-Verify mechanism to greedily reduce the failure mass. On math, code, and QA benchmarks, our CE-Graph achieves higher robustness at a significantly lower cost than strong baselines. This suggests that a system's reliability emerges not from avoiding failures, but from systematically learning and reshaping the geometric structure of its failure distributions.
Authors: Saleh Nikooroo, Thomas Engel
Abstract: Belief systems are rarely globally consistent, yet effective reasoning often persists locally. We propose a novel graph-theoretic framework that cleanly separates credibility--external, a priori trust in sources--from confidence--an internal, emergent valuation induced by network structure. Beliefs are nodes in a directed, signed, weighted graph whose edges encode support and contradiction. Confidence is obtained by a contractive propagation process that mixes a stated prior with structure-aware influence and guarantees a unique, stable solution. Within this dynamics, we define reasoning zones: high-confidence, structurally balanced subgraphs on which classical inference is safe despite global contradictions. We provide a near-linear procedure that seeds zones by confidence, tests balance using a parity-based coloring, and applies a greedy, locality-preserving repair with Jaccard de-duplication to build a compact atlas. To model belief change, we introduce shock updates that locally downscale support and elevate targeted contradictions while preserving contractivity via a simple backtracking rule. Re-propagation yields localized reconfiguration-zones may shrink, split, or collapse--without destabilizing the entire graph. We outline an empirical protocol on synthetic signed graphs with planted zones, reporting zone recovery, stability under shocks, and runtime. The result is a principled foundation for contradiction-tolerant reasoning that activates classical logic precisely where structure supports it.
Authors: Ruohao Li, Hongjun Liu, Leyi Zhao, Zisu Li, Jiawei Li, Jiajun Jiang, Linning Xu, Chen Zhao, Mingming Fan, Chen Liang
Abstract: Large language model (LLM) agents have shown remarkable reasoning abilities. However, existing multi-agent frameworks often rely on fixed roles or centralized control, limiting scalability and adaptability in long-horizon reasoning. We introduce SwarmSys, a closed-loop framework for distributed multi-agent reasoning inspired by swarm intelligence. Coordination in SwarmSys emerges through iterative interactions among three specialized roles, Explorers, Workers, and Validators, that continuously cycle through exploration, exploitation, and validation. To enable scalable and adaptive collaboration, we integrate adaptive agent and event profiles, embedding-based probabilistic matching, and a pheromone-inspired reinforcement mechanism, supporting dynamic task allocation and self-organizing convergence without global supervision. Across symbolic reasoning, research synthesis, and scientific programming tasks, SwarmSys consistently outperforms baselines, improving both accuracy and reasoning stability. These findings highlight swarm-inspired coordination as a promising paradigm for scalable, robust, and adaptive multi-agent reasoning, suggesting that coordination scaling may rival model scaling in advancing LLM intelligence.
Authors: Zeyu Ling, Xiaodong Gu, Jiangnan Tang, Changqing Zou
Abstract: We introduce SyncLipMAE, a self-supervised pretraining framework for talking-face video that learns synchronization-aware and transferable facial dynamics from unlabeled audio-visual streams. Our approach couples masked visual modeling with cross-modal contrastive alignment and employs three per-frame prompt tokens that explicitly encode the essential factors of a talking-face frame - identity, vocal motion (speech-synchronized facial dynamics), and ambient motion (audio-agnostic movements such as blinks and head pose). The contrastive objective uses time-aligned vocal-motion and audio tokens as positives and misaligned pairs as negatives, driving both modalities into a shared embedding space and yielding token-level audio-visual stream synchronization. After pretraining, the aligned audio tokens together with the visual prompt tokens (identity, vocal motion, ambient motion) form a unified interface for four disparate downstream settings: (i) audio-visual stream synchronization; (ii) facial emotion and head/face action recognition; (iii) visual speech recognition; and (iv) visual dubbing, for which we enable indistinguishable audio- or video-driven control within a single model. Across four task families that require distinct capabilities, SyncLipMAE achieves state-of-the-art results, underscoring the effectiveness of synchronization-aware, factorized self-supervised pretraining.
Authors: Jiayi Mao, Liqun Li, Yanjie Gao, Zegang Peng, Shilin He, Chaoyun Zhang, Si Qin, Samia Khalid, Qingwei Lin, Saravan Rajmohan, Sitaram Lanka, Dongmei Zhang
Abstract: Effective incident management in large-scale IT systems relies on troubleshooting guides (TSGs), but their manual execution is slow and error-prone. While recent advances in LLMs offer promise for automating incident management tasks, existing LLM-based solutions lack specialized support for several key challenges, including managing TSG quality issues, interpreting complex control flow, handling data-intensive queries, and exploiting execution parallelism. We first conducted an empirical study on 92 real-world TSGs, and, guided by our findings, we present StepFly, a novel end-to-end agentic framework for troubleshooting guide automation. Our approach features a three-stage workflow: the first stage provides a comprehensive guide together with a tool, TSG Mentor, to assist SREs in improving TSG quality; the second stage performs offline preprocessing using LLMs to extract structured execution DAGs from unstructured TSGs and to create dedicated Query Preparation Plugins (QPPs); and the third stage executes online using a DAG-guided scheduler-executor framework with a memory system to guarantee correct workflow and support parallel execution of independent steps. Our empirical evaluation on a collection of real-world TSGs and incidents demonstrates that StepFly achieves a ~94% success rate on GPT-4.1, outperforming baselines with less time and token consumption. Furthermore, it achieves a remarkable execution time reduction of 32.9% to 70.4% for parallelizable TSGs.
Authors: Yunxiang Mo, Tianshi Zheng, Qing Zong, Jiayu Liu, Baixuan Xu, Yauwai Yim, Chunkit Chan, Jiaxin Bai, Yangqiu Song
Abstract: Multimodal abductive reasoning--the generation and selection of explanatory hypotheses from partial observations--is a cornerstone of intelligence. Current evaluations of this ability in vision-language models (VLMs) are largely confined to static, single-agent tasks. Inspired by Dixit, we introduce DixitWorld, a comprehensive evaluation suite designed to deconstruct this challenge. DIXITWORLD features two core components: DixitArena, a dynamic, multi-agent environment that evaluates both hypothesis generation (a "storyteller" crafting cryptic clues) and hypothesis selection ("listeners" choosing the target image from decoys) under imperfect information; and DixitBench, a static QA benchmark that isolates the listener's task for efficient, controlled evaluation. Results from DixitArena reveal distinct, role-dependent behaviors: smaller open-source models often excel as creative storytellers, producing imaginative yet less discriminative clues, whereas larger proprietary models demonstrate superior overall performance, particularly as listeners. Performance on DixitBench strongly correlates with listener results in DixitArena, validating it as a reliable proxy for hypothesis selection. Our findings reveal a key trade-off between generative creativity and discriminative understanding in multimodal abductive reasoning, a central challenge for developing more balanced and capable vision-language agents.
Authors: Zhongsheng Wang, Ming Lin, Zhedong Lin, Yaser Shakib, Qian Liu, Jiamou Liu
Abstract: Ensuring character identity consistency across varying prompts remains a fundamental limitation in diffusion-based text-to-image generation. We propose CharCom, a modular and parameter-efficient framework that achieves character-consistent story illustration through composable LoRA adapters, enabling efficient per-character customization without retraining the base model. Built on a frozen diffusion backbone, CharCom dynamically composes adapters at inference using prompt-aware control. Experiments on multi-scene narratives demonstrate that CharCom significantly enhances character fidelity, semantic alignment, and temporal coherence. It remains robust in crowded scenes and enables scalable multi-character generation with minimal overhead, making it well-suited for real-world applications such as story illustration and animation.
Authors: Chengqian Gao, Haonan Li, Taylor W. Killian, Jianshu She, Renxi Wang, Liqun Ma, Zhoujun Cheng, Shibo Hao, Zhiqiang Xu
Abstract: Concise reasoning in large language models seeks to generate only essential intermediate steps needed to arrive at a final answer, thereby alleviating issues of overthinking. Most proposed approaches hinge on carefully hand-crafted heuristics, struggling to balance concision with performance, often failing to adapt across domains and model scales. In this work, we address these challenges by introducing a principled and pragmatic strategy, performance-aware length updating (PALU). As a principled algorithm, PALU formulates concise reasoning as a constrained optimization problem, minimizing response length subject to a performance constraint, and then applies Lagrangian optimization to convert it into a tractable unconstrained problem. As a pragmatic solution, PALU streamlines complicated update rules through three approximations: (i) estimating performance with off-policy rollouts, (ii) truncating the Lagrange multiplier to two extremes, and (iii) replacing gradient-based updates with quantile-driven length adjustments. PALU reduces output length by 65% while improving accuracy by 15% when applied to DeepSeek-Distill-Qwen-1.5B, averaged over five benchmarks, outperforming a range of alternative methods. Furthermore, PALU is demonstrated to adapt across both domain (logic, STEM and math) and model scale (1.5B, 7B, 14B) entrenching the algorithm as a practical and effective concise reasoning approach.
Authors: Qingni Wang, Yue Fan, Xin Eric Wang
Abstract: As large language models (LLMs) are increasingly deployed in risk-sensitive applications such as real-world open-ended question answering (QA), ensuring the trustworthiness of their outputs has become critical. Existing selective conformal prediction (SCP) methods provide statistical guarantees by constructing prediction sets with a constrained miscoverage rate for correct answers. However, prior works unrealistically assume that admissible answers for all instances can be obtained via finite sampling, even for open-ended QA scenarios that lack a fixed and finite solution space. To address this, we introduce a two-stage risk control framework comprising abstention-aware sampling and conformalized filtering (SAFER). Firstly, on a held-out calibration set, SAFER calibrates a sampling budget within the maximum sampling cap, using the Clopper-Pearson exact method at a user-desired risk level (i.e., the maximum allowable miscoverage rate of the sampling sets). If the risk level cannot be satisfied within the cap, we abstain; otherwise, the calibrated sampling budget becomes the minimum requirements at test time. Then, we employ calibration instances where correct answers are attainable under the calibrated budget and apply the conformal risk control method to determine a statistically valid uncertainty threshold, which filters unreliable distractors from the candidate set for each test data point. In this stage, SAFER introduces an additional risk level to guide the calculation of the threshold, thereby controlling the risk of correct answers being excluded. Furthermore, we show that SAFER is compatible with various task-specific admission criteria and calibration-test split ratios, highlighting its robustness and high data efficiency.
Authors: Siyuan Lu, Zechuan Wang, Hongxuan Zhang, Qintong Wu, Leilei Gan, Chenyi Zhuang, Jinjie Gu, Tao Lin
Abstract: Large Language Model (LLM) agents show great promise for complex, multi-turn tool-use tasks, but their development is often hampered by the extreme scarcity of high-quality training data. Supervised fine-tuning (SFT) on synthetic data leads to overfitting, whereas standard reinforcement learning (RL) struggles with a critical cold-start problem and training instability. To address these challenges, we introduce $\textbf{Environment Tuning}$, a novel training paradigm that enables agents to learn complex behaviors directly from problem instances without relying on pre-collected expert trajectories. $\textbf{Environment Tuning}$ orchestrates this learning process through a structured curriculum, actionable environment augmentation that provides corrective feedback, and fine-grained progress rewards to ensure stable and efficient exploration. Using only 400 problem instances from Berkeley Function-Calling Leaderboard (BFCL) benchmark, our method not only achieves competitive in-distribution performance against strong baselines but also demonstrates superior out-of-distribution generalization, overcoming the performance collapse common to SFT-based approaches. Our work presents a paradigm shift from supervised fine-tuning on static trajectories to dynamic, environment-based exploration, paving the way for training more robust and data-efficient agents.
Authors: Manjiang Yu, Hongji Li, Priyanka Singh, Xue Li, Di Wang, Lijie Hu
Abstract: Reliable behavior control is central to deploying large language models (LLMs) on the web. Activation steering offers a tuning-free route to align attributes (e.g., truthfulness) that ensure trustworthy generation. Prevailing approaches rely on coarse heuristics and lack a principled account of where to steer and how strongly to intervene. To this end, we propose Position-wise Injection with eXact Estimated Levels (PIXEL), a position-wise activation steering framework that, in contrast to prior work, learns a property-aligned subspace from dual views (tail-averaged and end-token) and selects intervention strength via a constrained geometric objective with a closed-form solution, thereby adapting to token-level sensitivity without global hyperparameter tuning. PIXEL further performs sample-level orthogonal residual calibration to refine the global attribute direction and employs a lightweight position-scanning routine to identify receptive injection sites. We additionally provide representation-level guarantees for the minimal-intervention rule, supporting reliable alignment. Across diverse models and evaluation paradigms, PIXEL consistently improves attribute alignment while preserving model general capabilities, offering a practical and principled method for LLMs' controllable generation. Our code is available at https://github.com/V1centNevwake/PIXEL-Adaptive-Steering
URLs: https://github.com/V1centNevwake/PIXEL-Adaptive-Steering
Authors: Yujian Zhang, Keyu Chen, Zhifeng Shen, Ruizhi Qiao, Xing Sun
Abstract: Although Long Reasoning Models (LRMs) have achieved superior performance on various reasoning scenarios, they often suffer from increased computational costs and inference latency caused by overthinking. To address these limitations, we propose Adaptive Dual Reasoner, which supports two reasoning modes: fast thinking and slow thinking. ADR dynamically alternates between these modes based on the contextual complexity during reasoning. ADR is trained in two stages: (1) A cold-start stage using supervised fine-tuning (SFT) to equip the model with the ability to integrate both fast and slow reasoning modes, in which we construct a hybrid reasoning dataset through a dedicated pipeline to provide large-scale supervision. (2) A reinforcement learning stage for optimizing reasoning effort, where we introduce Entropy-guided Hybrid Policy Optimization EHPO, an RL training framework employing an entropy-guided dynamic rollout strategy for branching at high-entropy units and a difficulty-aware penalty to balance fast and slow reasoning. Across challenging mathematical reasoning benchmarks, ADR achieves an effective balance between reasoning performance and efficiency among state-of-the-art approaches. Specifically, ADR yields a performance gain of up to 6.1%, while reducing the reasoning output length by 49.5% to 59.3%.
Authors: Zixuan Qin, Kunlin Lyu, Qingchen Yu, Yifan Sun, Zhaoxin Fan
Abstract: Large Language Models (LLMs) have become foundational tools in natural language processing, powering a wide range of applications and research. Many studies have shown that LLMs share significant similarities with the human brain. Recent neuroscience research has found that a small subset of biological neurons in the human brain are crucial for core cognitive functions, which raises a fundamental question: do LLMs also contain a small subset of critical neurons? In this paper, we investigate this question by proposing a Perturbation-based Causal Identification of Critical Neurons method to systematically locate such critical neurons in LLMs. Our findings reveal three key insights: (1) LLMs contain ultra-sparse critical neuron sets. Disrupting these critical neurons can cause a 72B-parameter model with over 1.1 billion neurons to completely collapse, with perplexity increasing by up to 20 orders of magnitude; (2) These critical neurons are not uniformly distributed, but tend to concentrate in the outer layers, particularly within the MLP down\_proj components; (3) Performance degradation exhibits sharp phase transitions, rather than a gradual decline, when these critical neurons are disrupted. Through comprehensive experiments across diverse model architectures and scales, we provide deeper analysis of these phenomena and their implications for LLM robustness and interpretability. These findings can offer guidance for developing more robust model architectures and improving deployment security in safety-critical applications.
Authors: Haolang Lu, Bolun Chu, WeiYe Fu, Guoshun Nan, Junning Liu, Minghui Pan, Qiankun Li, Yi Yu, Hua Wang, Kun Wang
Abstract: Multimodal large reasoning models (MLRMs) are rapidly advancing vision-language reasoning and are emerging as a foundation for cross-modal intelligence. Hallucination remains a persistent failure mode, manifesting itself as erroneous reasoning chains and misinterpretation of visual content. In this study, we observe that attention heads exhibit a staged division: shallow heads predominantly serve perception, while deeper heads shift toward symbolic reasoning, revealing two major causes of hallucination, namely perceptual bias and reasoning drift. To address these issues, we propose a lightweight and interpretable two-step plugin, Functional Head Identification and Class-conditioned Rescaling, which locates perception- and reasoning-oriented heads and regulates their contributions without retraining. Evaluations on three real-world MLRMs (Kimi-VL, Ocean-R1, R1-Onevision), six benchmarks across three domains, and four baselines show that our plugin achieves an average improvement of 5% and up to 15%, with only <1% additional computation and 9% of baseline latency. Our approach is completely model-agnostic and significantly enhances both the reliability and interpretability of the off-the-shelf MLRMs, thereby enabling their safe deployment in high-stakes applications. Our code is available at https://anonymous.4open.science/r/Functional-Attention-Control.
URLs: https://anonymous.4open.science/r/Functional-Attention-Control.
Authors: Hanchen Su, Wei Luo, Wei Han, Yu Elaine Liu, Yufeng Wayne Zhang, Cen Mia Zhao, Ying Joy Zhang, Yashar Mehdad
Abstract: We propose a practical approach by integrating Large Language Models (LLMs) with a framework designed to navigate the complexities of Airbnb customer support operations. In this paper, our methodology employs a novel reformatting technique, the Intent, Context, and Action (ICA) format, which transforms policies and workflows into a structure more comprehensible to LLMs. Additionally, we develop a synthetic data generation strategy to create training data with minimal human intervention, enabling cost-effective fine-tuning of our model. Our internal experiments (not applied to Airbnb products) demonstrate that our approach of restructuring workflows and fine-tuning LLMs with synthetic data significantly enhances their performance, setting a new benchmark for their application in customer support. Our solution is not only cost-effective but also improves customer support, as evidenced by both accuracy and manual processing time evaluation metrics.
Authors: Balagopal Unnikrishnan, Ariel Guerra Adames, Amin Adibi, Sameer Peesapati, Rafal Kocielnik, Shira Fischer, Hillary Clinton Kasimbazi, Rodrigo Gameiro, Alina Peluso, Chrystinne Oliveira Fernandes, Maximin Lange, Lovedeep Gondara, Leo Anthony Celi
Abstract: While ethical arguments for fairness in healthcare AI are well-established, the economic and strategic value of inclusive design remains underexplored. This perspective introduces the ``inclusive innovation dividend'' -- the counterintuitive principle that solutions engineered for diverse, constrained use cases generate superior economic returns in broader markets. Drawing from assistive technologies that evolved into billion-dollar mainstream industries, we demonstrate how inclusive healthcare AI development creates business value beyond compliance requirements. We identify four mechanisms through which inclusive innovation drives returns: (1) market expansion via geographic scalability and trust acceleration; (2) risk mitigation through reduced remediation costs and litigation exposure; (3) performance dividends from superior generalization and reduced technical debt, and (4) competitive advantages in talent acquisition and clinical adoption. We present the Healthcare AI Inclusive Innovation Framework (HAIIF), a practical scoring system that enables organizations to evaluate AI investments based on their potential to capture these benefits. HAIIF provides structured guidance for resource allocation, transforming fairness and inclusivity from regulatory checkboxes into sources of strategic differentiation. Our findings suggest that organizations investing incrementally in inclusive design can achieve expanded market reach and sustained competitive advantages, while those treating these considerations as overhead face compounding disadvantages as network effects and data advantages accrue to early movers.
Authors: Siddartha Devic, Charlotte Peale, Arwen Bradley, Sinead Williamson, Preetum Nakkiran, Aravind Gollakota
Abstract: Uncertainty quantification for LLMs is a key research direction towards addressing hallucination and other issues that limit their reliable deployment. In this work, we show that reasoning trace length is a simple and useful confidence estimator in large reasoning models. Through comprehensive experiments across multiple models, datasets, and prompts, we show that trace length performs in comparable but complementary ways to other zero-shot confidence estimators such as verbalized confidence. Our work reveals that reasoning post-training fundamentally alters the relationship between trace length and accuracy, going beyond prior work that had shown that post-training causes traces to grow longer in general (e.g., "overthinking"). We investigate the mechanisms behind trace length's performance as a confidence signal, observing that the effect remains even after adjusting for confounders such as problem difficulty and GRPO-induced length bias. We identify high-entropy or "forking" tokens as playing a key role in the mechanism. Our findings demonstrate that reasoning post-training enhances uncertainty quantification beyond verbal expressions, and establish trace length as a practical confidence measure for large reasoning models.
Authors: Sihang Zeng, Yujuan Fu, Sitong Zhou, Zixuan Yu, Lucas Jing Liu, Jun Wen, Matthew Thompson, Ruth Etzioni, Meliha Yetisgen
Abstract: Large language models (LLMs) offer a generalizable approach for modeling patient trajectories, but suffer from the long and noisy nature of electronic health records (EHR) data in temporal reasoning. To address these challenges, we introduce Traj-CoA, a multi-agent system involving chain-of-agents for patient trajectory modeling. Traj-CoA employs a chain of worker agents to process EHR data in manageable chunks sequentially, distilling critical events into a shared long-term memory module, EHRMem, to reduce noise and preserve a comprehensive timeline. A final manager agent synthesizes the worker agents' summary and the extracted timeline in EHRMem to make predictions. In a zero-shot one-year lung cancer risk prediction task based on five-year EHR data, Traj-CoA outperforms baselines of four categories. Analysis reveals that Traj-CoA exhibits clinically aligned temporal reasoning, establishing it as a promisingly robust and generalizable approach for modeling complex patient trajectories.
Authors: Hongjie Zheng, Zesheng Shi, Ping Yi
Abstract: Autonomous agents utilizing Large Language Models (LLMs) have demonstrated remarkable capabilities in isolated medical tasks like diagnosis and image analysis, but struggle with integrated clinical workflows that connect diagnostic reasoning and medication decisions. We identify a core limitation: existing medical AI systems process tasks in isolation without the cross-validation and knowledge integration found in clinical teams, reducing their effectiveness in real-world healthcare scenarios. To transform the isolation paradigm into a collaborative approach, we propose MedCoAct, a confidence-aware multi-agent framework that simulates clinical collaboration by integrating specialized doctor and pharmacist agents, and present a benchmark, DrugCareQA, to evaluate medical AI capabilities in integrated diagnosis and treatment workflows. Our results demonstrate that MedCoAct achieves 67.58\% diagnostic accuracy and 67.58\% medication recommendation accuracy, outperforming single agent framework by 7.04\% and 7.08\% respectively. This collaborative approach generalizes well across diverse medical domains, proving especially effective for telemedicine consultations and routine clinical scenarios, while providing interpretable decision-making pathways.
Authors: Martina G. Vilas, Safoora Yousefi, Besmira Nushi, Eric Horvitz, Vidhisha Balachandran
Abstract: Reasoning models improve their problem-solving ability through inference-time scaling, allocating more compute via longer token budgets. Identifying which reasoning traces are likely to succeed remains a key opportunity: reliably predicting productive paths can substantially reduce wasted computation and improve overall efficiency. We introduce Latent-Trajectory signals that characterize the temporal evolution of a model's internal representations during the generation of intermediate reasoning tokens. By measuring the overall change in latent representations between the start and end of reasoning, the change accumulated across intermediate steps, and the extent to which these changes advance toward the final state, we show that these signals predict solution accuracy more reliably than both cross-layer metrics and output-based confidence measures. When used to guide answer selection across multiple sampled generations, Latent-Trajectory signals make test-time scaling more effective and efficient than majority voting, reducing token usage by up to 70% while preserving and even improving accuracy by 2.6% on average. Moreover, these predictive signals often emerge early in the reasoning trace, enabling early selection and allocation of compute to the most promising candidates. Our findings contribute not only practical strategies for inference-time efficiency, but also a deeper interpretability perspective on how reasoning processes are represented and differentiated in latent space.
Authors: Xinbang Dai, Huikang Hu, Yongrui Chen, Jiaqi Li, Rihui Jin, Yuyang Zhang, Xiaoguang Li, Lifeng Shang, Guilin Qi
Abstract: While large language models (LLMs) excel at many domain-specific tasks, their ability to deeply comprehend and reason about full-length academic papers remains underexplored. Existing benchmarks often fall short of capturing such depth, either due to surface-level question design or unreliable evaluation metrics. To address this gap, we introduce ELAIPBench, a benchmark curated by domain experts to evaluate LLMs' comprehension of artificial intelligence (AI) research papers. Developed through an incentive-driven, adversarial annotation process, ELAIPBench features 403 multiple-choice questions from 137 papers. It spans three difficulty levels and emphasizes non-trivial reasoning rather than shallow retrieval. Our experiments show that the best-performing LLM achieves an accuracy of only 39.95%, far below human performance. Moreover, we observe that frontier LLMs equipped with a thinking mode or a retrieval-augmented generation (RAG) system fail to improve final results-even harming accuracy due to overthinking or noisy retrieval. These findings underscore the significant gap between current LLM capabilities and genuine comprehension of academic papers.
Authors: Hong Su
Abstract: Existing studies have introduced method-based reasoning and scope extension as approaches to enhance Large Language Model (LLM) performance beyond direct matrix mappings. Building on these foundations, this paper summarizes and integrates these ideas into a unified Intuition-Method Layered Model with Scope Extension, designed to address indirected (unseen) issues more systematically. In this framework, intuition-based thinking provides rapid first-reaction answers, while method-based thinking decouples questions and solutions into transferable reasoning units. Scope extension is then applied to broaden applicability, including vertical (cause analysis), horizontal (parallel and generalized issues), and for the first time, temporal and spatial extensions, which expand reasoning across time and contextual dimensions. These extensions are organized into systematic knowledge trees that interconnect into a knowledge network, thereby increasing adaptability. To quantitatively evaluate this process, we propose the entropy of method extension, which measures the independence and diversity of extensions as an indicator of the system's capacity to solve unseen questions. By logically connecting existing approaches with new extensions and introducing an entropy-based evaluation framework, this work advances toward a more robust and extensible reasoning paradigm for LLMs in real-world problem-solving.
Authors: Ruolan Cheng, Yong Deng, Seraf\'in Moral, Jos\'e Ram\'on Trillo
Abstract: Random permutation set (RPS) is a recently proposed framework designed to represent order-structured uncertain information. Measuring the distance between permutation mass functions is a key research topic in RPS theory (RPST). This paper conducts an in-depth analysis of distances between RPSs from two different perspectives: random finite set (RFS) and transferable belief model (TBM). Adopting the layer-2 belief structure interpretation of RPS, we regard RPST as a refinement of TBM, where the order in the ordered focus set represents qualitative propensity. Starting from the permutation, we introduce a new definition of the cumulative Jaccard index to quantify the similarity between two permutations and further propose a distance measure method for RPSs based on the cumulative Jaccard index matrix. The metric and structural properties of the proposed distance measure are investigated, including the positive definiteness analysis of the cumulative Jaccard index matrix, and a correction scheme is provided. The proposed method has a natural top-weightiness property: inconsistencies between higher-ranked elements tend to result in greater distance values. Two parameters are provided to the decision-maker to adjust the weight and truncation depth. Several numerical examples are used to compare the proposed method with the existing method. The experimental results show that the proposed method not only overcomes the shortcomings of the existing method and is compatible with the Jousselme distance, but also has higher sensitivity and flexibility.
Authors: WenTao Liu, Siyu Song, Hao Hao, Aimin Zhou
Abstract: In recent years, large language models (LLMs) have made remarkable progress, with model optimization primarily relying on gradient-based optimizers such as Adam. However, these gradient-based methods impose stringent hardware requirements, demanding high-concurrency, high-memory GPUs. Moreover, they require all neural network operations to be differentiable, thereby excluding many promising non-differentiable architectures from practical use. To address these limitations, we propose a method for optimizing LLMs using evolutionary algorithms (EA4LLM) and, for the first time, successfully demonstrate its capability to train a 1-billion-parameter LLM from the pre-trained stage. We conduct extensive experiments and provide key insights into how evolutionary algorithms can effectively optimize neural networks. Our work challenges the prevailing assumption that gradient-based optimization is the only viable approach for training neural networks. It also holds significant potential to reduce the computational cost of training large language models, thereby enabling groups with limited computational resources to participate in deep learning research.
Authors: Jiabao Shi, Minfeng Qi, Lefeng Zhang, Di Wang, Yingjie Zhao, Ziying Li, Yalong Xing, Ningran Li
Abstract: Multimodal text-to-image generation remains constrained by the difficulty of maintaining semantic alignment and professional-level detail across diverse visual domains. We propose a multi-agent reinforcement learning framework that coordinates domain-specialized agents (e.g., focused on architecture, portraiture, and landscape imagery) within two coupled subsystems: a text enhancement module and an image generation module, each augmented with multimodal integration components. Agents are trained using Proximal Policy Optimization (PPO) under a composite reward function that balances semantic similarity, linguistic visual quality, and content diversity. Cross-modal alignment is enforced through contrastive learning, bidirectional attention, and iterative feedback between text and image. Across six experimental settings, our system significantly enriches generated content (word count increased by 1614%) while reducing ROUGE-1 scores by 69.7%. Among fusion methods, Transformer-based strategies achieve the highest composite score (0.521), despite occasional stability issues. Multimodal ensembles yield moderate consistency (ranging from 0.444 to 0.481), reflecting the persistent challenges of cross-modal semantic grounding. These findings underscore the promise of collaborative, specialization-driven architectures for advancing reliable multimodal generative systems.
Authors: Haemin Choi, Gayathri Nadarajan
Abstract: Although student learning satisfaction has been widely studied, modern techniques such as interpretable machine learning and neural networks have not been sufficiently explored. This study demonstrates that a recent model that combines boosting with interpretability, automatic piecewise linear regression(APLR), offers the best fit for predicting learning satisfaction among several state-of-the-art approaches. Through the analysis of APLR's numerical and visual interpretations, students' time management and concentration abilities, perceived helpfulness to classmates, and participation in offline courses have the most significant positive impact on learning satisfaction. Surprisingly, involvement in creative activities did not positively affect learning satisfaction. Moreover, the contributing factors can be interpreted on an individual level, allowing educators to customize instructions according to student profiles.
Authors: Piyush Pant, Marcellius William Suntoro, Ayesha Siddiqua, Muhammad Shehryaar Sharif, Daniyal Ahmed
Abstract: This paper presents EA-GeoAI, an integrated framework for demand forecasting and equitable hospital planning in Germany through 2030. We combine district-level demographic shifts, aging population density, and infrastructure balances into a unified Equity Index. An interpretable Agentic AI optimizer then allocates beds and identifies new facility sites to minimize unmet need under budget and travel-time constraints. This approach bridges GeoAI, long-term forecasting, and equity measurement to deliver actionable recommendations for policymakers.
Authors: Yi Zhang, Yushen Long, Yun Ni, Liping Huang, Xiaohong Wang, Jun Liu
Abstract: Online ride-hailing platforms aim to deliver efficient mobility-on-demand services, often facing challenges in balancing dynamic and spatially heterogeneous supply and demand. Existing methods typically fall into two categories: reinforcement learning (RL) approaches, which suffer from data inefficiency, oversimplified modeling of real-world dynamics, and difficulty enforcing operational constraints; or decomposed online optimization methods, which rely on manually designed high-level objectives that lack awareness of low-level routing dynamics. To address this issue, we propose a novel hybrid framework that integrates large language model (LLM) with mathematical optimization in a dynamic hierarchical system: (1) it is training-free, removing the need for large-scale interaction data as in RL, and (2) it leverages LLM to bridge cognitive limitations caused by problem decomposition by adaptively generating high-level objectives. Within this framework, LLM serves as a meta-optimizer, producing semantic heuristics that guide a low-level optimizer responsible for constraint enforcement and real-time decision execution. These heuristics are refined through a closed-loop evolutionary process, driven by harmony search, which iteratively adapts the LLM prompts based on feasibility and performance feedback from the optimization layer. Extensive experiments based on scenarios derived from both the New York and Chicago taxi datasets demonstrate the effectiveness of our approach, achieving an average improvement of 16% compared to state-of-the-art baselines.
Authors: Can Xie, Ruotong Pan, Xiangyu Wu, Yunfei Zhang, Jiayi Fu, Tingting Gao, Guorui Zhou
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has shown significant promise for enhancing the reasoning capabilities of large language models (LLMs). However, prevailing algorithms like GRPO broadcast a uniform advantage signal across all tokens in a sequence. This coarse-grained approach overlooks the pivotal role of uncertain, high-stakes decisions during reasoning, leading to inefficient exploration and the well-documented problem of entropy collapse. To address this, we introduce UnCertainty-aware Advantage Shaping (UCAS), a model-free method that refines credit assignment by leveraging the model's internal uncertainty signals. UCAS operates in two stages: it first modulates the response-level advantage using the model's overall self-confidence, and then applies a token-level penalty based on raw logit certainty. This dual mechanism encourages exploration of high-uncertainty paths that yield correct answers while penalizing overconfident yet erroneous reasoning, effectively balancing the exploration-exploitation trade-off. Extensive experiments on five mathematical reasoning benchmarks show that UCAS significantly outperforms strong RLVR baselines across multiple model scales, including 1.5B and 7B. Our analysis confirms that UCAS not only achieves higher rewards but also promotes greater reasoning diversity and successfully mitigates entropy collapse.
Authors: Deven Panchal
Abstract: Generative Agentic AI systems are emerging as a powerful paradigm for automating complex, multi-step tasks. However, many existing frameworks for building these systems introduce significant complexity, a steep learning curve, and substantial boilerplate code, hindering rapid prototyping and deployment. This paper introduces simpliflow, a lightweight, open-source Python framework designed to address these challenges. simpliflow enables the rapid development and orchestration of linear, deterministic agentic workflows through a declarative, JSON-based configuration. Its modular architecture decouples agent management, workflow execution, and post-processing, promoting ease of use and extensibility. By integrating with LiteLLM, it supports over 100 Large Language Models (LLMs) out-of-the-box. We present the architecture, operational flow, and core features of simpliflow, demonstrating its utility through diverse use cases ranging from software development simulation to real-time system interaction. A comparative analysis with prominent frameworks like LangChain and AutoGen highlights simpliflow's unique position as a tool optimized for simplicity, control, and speed in deterministic workflow environments.
Authors: Caorui Li, Yu Chen, Yiyan Ji, Jin Xu, Zhenyu Cui, Shihao Li, Yuanxing Zhang, Jiafu Tang, Zhenghao Song, Dingling Zhang, Ying He, Haoxiang Liu, Yuxuan Wang, Qiufeng Wang, Zhenhe Wu, Jiehui Luo, Zhiyu Pan, Weihao Xie, Chenchen Zhang, Zhaohui Wang, Jiayi Tian, Yanghai Wang, Zhe Cao, Minxin Dai, Ke Wang, Runzhe Wen, Yinghao Ma, Yaning Pan, Sungkyun Chang, Termeh Taheri, Haiwen Xia, Christos Plachouras, Emmanouil Benetos, Yizhi Li, Ge Zhang, Jian Yang, Tianhao Peng, Zili Wang, Minghao Liu, Junran Peng, Zhaoxiang Zhang, Jiaheng Liu
Abstract: Recent advances in multimodal large language models (MLLMs) have demonstrated substantial potential in video understanding. However, existing benchmarks fail to comprehensively evaluate synergistic reasoning capabilities across audio and visual modalities, often neglecting either one of the modalities or integrating them in a logically inconsistent manner. To bridge this gap, we introduce OmniVideoBench, a large-scale and rigorously designed benchmark dedicated to assessing synergistic audio-visual understanding, with a strong emphasis on modality complementarity and logical consistency. Specifically, OmniVideoBench comprises 1000 high-quality question-answer(QA) pairs, each annotated with step-by-step reasoning traces, derived from 628 diverse videos ranging from several seconds to 30 minutes, and manually verified to guarantee complete correctness and uniqueness. Moreover, OmniVideoBench encompasses 13 carefully designed question types, covering temporal reasoning, spatial localization, counting, causal inference, summarization, and beyond, thereby capturing the essential challenges of video understanding. Evaluation of multiple MLLMs on OmniVideoBench reveals a pronounced gap between model performance and human reasoning, with open-source models lagging significantly behind their closed-source counterparts, underscoring the inherent difficulty of genuine audio-visual reasoning. We will release OmniVideoBench to foster the development of MLLMs with stronger and more generalizable reasoning capabilities.
Authors: Yang Xu, Shuwei Chen, Jun Liu, Feng Cao, Xingxing He
Abstract: Automated deduction lies at the core of Artificial Intelligence (AI), underpinning theorem proving, formal verification, and logical reasoning. Despite decades of progress, reconciling deductive completeness with computational efficiency remains an enduring challenge. Traditional reasoning calculi, grounded in binary resolution, restrict inference to pairwise clause interactions and thereby limit deductive synergy among multiple clauses. The Contradiction Separation Extension (CSE) framework, introduced in 2018, proposed a dynamic multi-clause reasoning theory that redefined logical inference as a process of contradiction separation rather than sequential resolution. While that work established the theoretical foundation, its algorithmic realization remained unformalized and unpublished. This work presents the Extended Triangular Method (ETM), a generalized contradiction-construction algorithm that formalizes and extends the internal mechanisms of contradiction separation. The ETM unifies multiple contradiction-building strategies, including the earlier Standard Extension method, within a triangular geometric framework that supports flexible clause interaction and dynamic synergy. ETM serves as the algorithmic core of several high-performance theorem provers, CSE, CSE-E, CSI-E, and CSI-Enig, whose competitive results in standard first-order benchmarks (TPTP problem sets and CASC 2018-2015) empirically validate the effectiveness and generality of the proposed approach. By bridging theoretical abstraction and operational implementation, ETM advances the contradiction separation paradigm into a generalized, scalable, and practically competitive model for automated reasoning, offering new directions for future research in logical inference and theorem proving.
Authors: Xiangyu Wang, Haocheng Yang, Fengxiang Cheng, Fenrong Liu
Abstract: Large Language Models (LLMs) still struggle with complex logical reasoning. While previous works achieve remarkable improvements, their performance is highly dependent on the correctness of translating natural language (NL) problems into a symbolic language (SL). Though numerous works focusing on improving this translation accuracy, they only consider the similarity between the meaning of SL and NL, overlooking another crucial influencing factor, the selection of the target SL type itself. For example, first-order logic language specializes in logical reasoning with categorical syllogisms and complex quantifiers, while Boolean satisfiability formalism excels at representing constraint satisfaction like partial problems. To our knowledge, this is the first paper to claim and verify that different NL logical reasoning problem corresponds to different optimal SL formalization for translation. Based on this, we propose a methods to improve the logical reasoning performance of LLMs by adaptively selecting the most suitable SL for each problem prior to translation. Specifically, we leverage LLMs to select the target SL among first-order logic, logic programming and Boolean satisfiability and then translate the problem in NL to target SL expressions as well as employ the corresponding logical solver to derive the final answer. Experimental results on benchmarks show that our adaptive selection method significantly outperforms translating all into single SL and randomly selecting the SL. On a mixed dataset of these benchmarks, our approach achieves 96% accuracy, which improving performance by 25% compared to the second highest accuracy from the first-order logic translation.
Authors: Enric Junque de Fortuny, Veronica Roberta Cappelli
Abstract: Large Language Models (LLMs) are increasingly applied to domains that require reasoning about other agents' behavior, such as negotiation, policy design, and market simulation, yet existing research has mostly evaluated their adherence to equilibrium play or their exhibited depth of reasoning. Whether they display genuine strategic thinking, understood as the coherent formation of beliefs about other agents, evaluation of possible actions, and choice based on those beliefs, remains unexplored. We develop a framework to identify this ability by disentangling beliefs, evaluation, and choice in static, complete-information games, and apply it across a series of non-cooperative environments. By jointly analyzing models' revealed choices and reasoning traces, and introducing a new context-free game to rule out imitation from memorization, we show that current frontier models exhibit belief-coherent best-response behavior at targeted reasoning depths. When unconstrained, they self-limit their depth of reasoning and form differentiated conjectures about human and synthetic opponents, revealing an emergent form of meta-reasoning. Under increasing complexity, explicit recursion gives way to internally generated heuristic rules of choice that are stable, model-specific, and distinct from known human biases. These findings indicate that belief coherence, meta-reasoning, and novel heuristic formation can emerge jointly from language modeling objectives, providing a structured basis for the study of strategic cognition in artificial agents.
Authors: Meiru Zhang, Philipp Borchert, Milan Gritta, Gerasimos Lampouras
Abstract: Automating the formalization of mathematical statements for theorem proving remains a major challenge for Large Language Models (LLMs). LLMs struggle to identify and utilize the prerequisite mathematical knowledge and its corresponding formal representation in languages like Lean. Current retrieval-augmented autoformalization methods query external libraries using the informal statement directly, but overlook a fundamental limitation: informal mathematical statements are often complex and offer limited context on the underlying math concepts. To address this, we introduce DRIFT, a novel framework that enables LLMs to decompose informal mathematical statements into smaller, more tractable ''sub-components''. This facilitates targeted retrieval of premises from mathematical libraries such as Mathlib. Additionally, DRIFT retrieves illustrative theorems to help models use premises more effectively in formalization tasks. We evaluate DRIFT across diverse benchmarks (ProofNet, ConNF, and MiniF2F-test) and find that it consistently improves premise retrieval, nearly doubling the F1 score compared to the DPR baseline on ProofNet. Notably, DRIFT demonstrates strong performance on the out-of-distribution ConNF benchmark, with BEq+@10 improvements of 37.14% and 42.25% using GPT-4.1 and DeepSeek-V3.1, respectively. Our analysis shows that retrieval effectiveness in mathematical autoformalization depends heavily on model-specific knowledge boundaries, highlighting the need for adaptive retrieval strategies aligned with each model's capabilities.
Authors: Daniel Howard
Abstract: We present a framework for characterizing neurosis in embodied AI: behaviors that are internally coherent yet misaligned with reality, arising from interactions among planning, uncertainty handling, and aversive memory. In a grid navigation stack we catalogue recurrent modalities including flip-flop, plan churn, perseveration loops, paralysis and hypervigilance, futile search, belief incoherence, tie break thrashing, corridor thrashing, optimality compulsion, metric mismatch, policy oscillation, and limited-visibility variants. For each we give lightweight online detectors and reusable escape policies (short commitments, a margin to switch, smoothing, principled arbitration). We then show that durable phobic avoidance can persist even under full visibility when learned aversive costs dominate local choice, producing long detours despite globally safe routes. Using First/Second/Third Law as engineering shorthand for safety latency, command compliance, and resource efficiency, we argue that local fixes are insufficient; global failures can remain. To surface them, we propose genetic-programming based destructive testing that evolves worlds and perturbations to maximize law pressure and neurosis scores, yielding adversarial curricula and counterfactual traces that expose where architectural revision, not merely symptom-level patches, is required.
Authors: Renxuan Tan, Rongpeng Li, Fei Wang, Chenghui Peng, Shaoyun Wu, Zhifeng Zhao, Honggang Zhang
Abstract: Medium Access Control (MAC) protocols, essential for wireless networks, are typically manually configured. While deep reinforcement learning (DRL)-based protocols enhance task-specified network performance, they suffer from poor generalizability and resilience, demanding costly retraining to adapt to dynamic environments. To overcome this limitation, we introduce a game-theoretic LLM-empowered multi-agent DRL (MARL) framework, in which the uplink transmission between a base station and a varying number of user equipments is modeled as a dynamic multi-follower Stackelberg game (MFSG), capturing the network's natural hierarchical structure. Within this game, LLM-driven agents, coordinated through proximal policy optimization (PPO), synthesize adaptive, semantic MAC protocols in response to network dynamics. Protocol action grammar (PAG) is employed to ensure the reliability and efficiency of this process. Under this system, we further analyze the existence and convergence behavior in terms of a Stackelberg equilibrium by studying the learning dynamics of LLM-empowered unified policies in response to changing followers. Simulations corroborate that our framework achieves a 77.6% greater throughput and a 65.2% fairness improvement over conventional baselines. Besides, our framework generalizes excellently to a fluctuating number of users without requiring retraining or architectural changes.
Authors: Daoyu Wang, Mingyue Cheng, Qi Liu, Shuo Yu, Zirui Liu, Ze Guo
Abstract: Understanding and reasoning on the web-scale scientific literature is a crucial touchstone for large language model (LLM) based agents designed to support complex knowledge-intensive tasks. However, existing works are mainly restricted to tool-free tasks within isolated papers, largely due to the lack of a benchmark for cross-paper reasoning and multi-tool orchestration in real research scenarios. In this work, we propose PaperArena, an evaluation benchmark for agents to address real-world research questions that typically require integrating information across multiple papers with the assistance of external tools. Given a research question, agents should integrate diverse formats across multiple papers through reasoning and interacting with appropriate tools, thereby producing a well-grounded answer. To support standardized evaluation, we provide a modular and extensible platform for agent execution, offering tools such as multimodal parsing, context retrieval, and programmatic computation. Experimental results reveal that even the most advanced LLM powering a well-established agent system achieves merely 38.78% average accuracy. On the hard subset, accuracy drops to only 18.47%, highlighting great potential for improvement. We also present several empirical findings, including that all agents tested exhibit inefficient tool usage, often invoking more tools than necessary to solve a task. We invite the community to adopt PaperArena to develop and evaluate more capable agents for scientific discovery. Our code and data are available https://github.com/Melmaphother/PaperArena.
Authors: SHengjie Ma, Chenlong Deng, Jiaxin Mao, Jiadeng Huang, Teng Wang, Junjie Wu, Changwang Zhang, Jun wang
Abstract: Retrieval-augmented generation (RAG) agents, such as recent DeepResearch-style systems, extend large language models (LLMs) with autonomous information-seeking capabilities through external tools. While reinforcement learning (RL) has enabled impressive multi-step reasoning, we identify a previously overlooked failure mode, Tool-Call Hacking, where agents inflate reward signals by issuing superficially correct tool calls without genuinely leveraging the retrieved evidence. This results in (i) mode collapse into repetitive reliance on a single source and (ii) spurious grounding, where answers are only weakly supported by cited content. To address this, we propose Proof-of-Use (PoU), an evidence-grounded RL framework that enforces verifiable causal links between retrieved evidence, reasoning traces, and final answers. PoU operationalizes this through a unified step-wise contract combining syntactic citation validation, perturbation-based sensitivity rewards, and answer-evidence alignment objectives, ensuring that tool usage remains both interpretable and functionally grounded. Across seven QA benchmarks spanning in-domain, out-of-domain, and out-of-tool-distribution settings, PoU consistently outperforms strong DeepResearch baselines in factual accuracy, evidence faithfulness, and tool-routing balance. These findings highlight the necessity of grounding RL-trained agents not merely in task outcomes but in the causal use of retrieved information, offering a principled path toward trustworthy retrieval-augmented reasoning.
Authors: Nilima Rao, Jagriti Srivastava, Pradeep Kumar Sharma, Hritvik Shrivastava
Abstract: Modern enterprises manage vast knowledge distributed across heterogeneous systems such as Jira, Git repositories, Confluence, and wikis. Conventional retrieval methods based on keyword search or static embeddings often fail to answer complex queries that require contextual reasoning and multi-hop inference across artifacts. We present a modular hybrid retrieval framework for adaptive enterprise information access that integrates Knowledge Base Language-Augmented Models (KBLam), DeepGraph representations, and embedding-driven semantic search. The framework builds a unified knowledge graph from parsed repositories including code, pull requests, and commit histories, enabling semantic similarity search, structural inference, and multi-hop reasoning. Query analysis dynamically determines the optimal retrieval strategy, supporting both structured and unstructured data sources through independent or fused processing. An interactive interface provides graph visualizations, subgraph exploration, and context-aware query routing to generate concise and explainable answers. Experiments on large-scale Git repositories show that the unified reasoning layer improves answer relevance by up to 80 percent compared with standalone GPT-based retrieval pipelines. By combining graph construction, hybrid reasoning, and interactive visualization, the proposed framework offers a scalable, explainable, and user-centric foundation for intelligent knowledge assistants in enterprise environments.
Authors: Wentao Wang, Heqing Zou, Tianze Luo, Rui Huang, Yutian Zhao, Zhuochen Wang, Hansheng Zhang, Chengwei Qin, Yan Wang, Lin Zhao, Huaijian Zhang
Abstract: Recent progress in Multimodal Large Language Models (MLLMs) has demonstrated strong semantic understanding capabilities, but struggles to perform precise spatio-temporal understanding. Existing spatio-temporal methods primarily focus on the video itself, while overlooking the physical information within the video, such as multi-object layouts and motion. Such limitations restrict the use of MLLMs in downstream applications that demand high precision, including embodied intelligence and VR. To address this issue, we present Video-STR, a novel graph-based reinforcement method for precise Video Spatio-Temporal Reasoning. Building upon the capacity of Reinforcement Learning with Verifiable Reward (RLVR) to improve model abilities, we introduce a reasoning mechanism using graph-based Group Relative Policy Optimization (GRPO) method to guide the model in inferring the underlying spatio-temporal topology of scenarios during the thinking process. To resolve the lack of spatio-temporal training data, we construct the STV-205k dataset with 205k question-answering pairs, covering dynamic multi-object scenes in both indoor and outdoor environments, to support the model training. Experiments show that Video-STR achieves state-of-the-art results on various benchmarks, outperforming the base model by 13% on STI-Bench, and demonstrating the effectiveness of our approach and dataset. Code, model, and data will be released.
Authors: Taiqiang Wu, Runming Yang, Tao Liu, Jiahao Wang, Ngai Wong
Abstract: Model merging, typically on Instruct and Thinking models, has shown remarkable performance for efficient reasoning. In this paper, we systematically revisit the simplest merging method that interpolates two weights directly. Particularly, we observe that model interpolation follows a three-stage evolutionary paradigm with distinct behaviors on the reasoning trajectory. These dynamics provide a principled guide for navigating the performance-cost trade-off. Empirical results demonstrate that a strategically interpolated model surprisingly surpasses sophisticated model merging baselines on both efficiency and effectiveness. We further validate our findings with extensive ablation studies on model layers, modules, and decoding strategies. Ultimately, this work demystifies model interpolation and offers a practical framework for crafting models with precisely targeted reasoning capabilities. Code is available at \href{https://github.com/wutaiqiang/MI}{Github}.
Authors: Takuma Fujiu, Sho Okazaki, Kohei Kaminishi, Yuji Nakata, Shota Hamamoto, Kenshin Yokose, Tatsunori Hara, Yasushi Umeda, Jun Ota
Abstract: In manufacturing systems, identifying the causes of failures is crucial for maintaining and improving production efficiency. In knowledge-based failure-cause inference, it is important that the knowledge base (1) explicitly structures knowledge about the target system and about failures, and (2) contains sufficiently long causal chains of failures. In this study, we constructed Diagnostic Knowledge Ontology and proposed a Function-Behavior-Structure (FBS) model-based maintenance-record accumulation method based on it. Failure-cause inference using the maintenance records accumulated by the proposed method showed better agreement with the set of candidate causes enumerated by experts, especially in difficult cases where the number of related cases is small and the vocabulary used differs. In the future, it will be necessary to develop inference methods tailored to these maintenance records, build a user interface, and carry out validation on larger and more diverse systems. Additionally, this approach leverages the understanding and knowledge of the target in the design phase to support knowledge accumulation and problem solving during the maintenance phase, and it is expected to become a foundation for knowledge sharing across the entire engineering chain in the future.
Authors: Andrada Iulia Prajescu, Roberto Confalonieri
Abstract: Artificial Intelligence (AI) systems are increasingly deployed in legal contexts, where their opacity raises significant challenges for fairness, accountability, and trust. The so-called ``black box problem'' undermines the legitimacy of automated decision-making, as affected individuals often lack access to meaningful explanations. In response, the field of Explainable AI (XAI) has proposed a variety of methods to enhance transparency, ranging from example-based and rule-based techniques to hybrid and argumentation-based approaches. This paper promotes computational models of arguments and their role in providing legally relevant explanations, with particular attention to their alignment with emerging regulatory frameworks such as the EU General Data Protection Regulation (GDPR) and the Artificial Intelligence Act (AIA). We analyze the strengths and limitations of different explanation strategies, evaluate their applicability to legal reasoning, and highlight how argumentation frameworks -- by capturing the defeasible, contestable, and value-sensitive nature of law -- offer a particularly robust foundation for explainable legal AI. Finally, we identify open challenges and research directions, including bias mitigation, empirical validation in judicial settings, and compliance with evolving ethical and legal standards, arguing that computational argumentation is best positioned to meet both technical and normative requirements of transparency in the law domain.
Authors: Yuxinyue Qian, Jun Liu
Abstract: With the rapid development of artificial intelligence (AI) technology, socio-economic systems are entering a new stage of "human-AI co-creation." Building upon a previously established multi-level intelligent agent economic model, this paper conducts simulation-based comparisons of macroeconomic output evolution in China and the United States under different mechanisms-AI collaboration, network effects, and AI autonomous production. The results show that: (1) when AI functions as an independent productive entity, the overall growth rate of social output far exceeds that of traditional human-labor-based models; (2) China demonstrates clear potential for acceleration in both the expansion of intelligent agent populations and the pace of technological catch-up, offering the possibility of achieving technological convergence or even partial surpassing. This study provides a systematic, model-based analytical framework for understanding AI-driven production system transformation and shifts in international competitiveness, as well as quantitative insights for relevant policy formulation.
Authors: Andrea Marinoni, Sai Shivareddy, Pietro Lio', Weisi Lin, Erik Cambria, Clare Grey
Abstract: The steady growth of artificial intelligence (AI) has accelerated in the recent years, facilitated by the development of sophisticated models such as large language models and foundation models. Ensuring robust and reliable power infrastructures is fundamental to take advantage of the full potential of AI. However, AI data centres are extremely hungry for power, putting the problem of their power management in the spotlight, especially with respect to their impact on environment and sustainable development. In this work, we investigate the capacity and limits of solutions based on an innovative approach for the power management of AI data centres, i.e., making part of the input power as dynamic as the power used for data-computing functions. The performance of passive and active devices are quantified and compared in terms of computational gain, energy efficiency, reduction of capital expenditure, and management costs by analysing power trends from multiple data platforms worldwide. This strategy, which identifies a paradigm shift in the AI data centre power management, has the potential to strongly improve the sustainability of AI hyperscalers, enhancing their footprint on environmental, financial, and societal fields.
Authors: Chuke Chen, Biao Luo, Nan Li, Boxiang Wang, Hang Yang, Jing Guo, Ming Xu
Abstract: The rapid expansion of scientific data has widened the gap between analytical capability and research intent. Existing AI-based analysis tools, ranging from AutoML frameworks to agentic research assistants, either favor automation over transparency or depend on manual scripting that hinders scalability and reproducibility. We present ARIA (Automated Research Intelligence Assistant), a spec-driven, human-in-the-loop framework for automated and interpretable data analysis. ARIA integrates six interoperable layers, namely Command, Context, Code, Data, Orchestration, and AI Module, within a document-centric workflow that unifies human reasoning and machine execution. Through natural-language specifications, researchers define analytical goals while ARIA autonomously generates executable code, validates computations, and produces transparent documentation. Beyond achieving high predictive accuracy, ARIA can rapidly identify optimal feature sets and select suitable models, minimizing redundant tuning and repetitive experimentation. In the Boston Housing case, ARIA discovered 25 key features and determined XGBoost as the best performing model (R square = 0.93) with minimal overfitting. Evaluations across heterogeneous domains demonstrate ARIA's strong performance, interpretability, and efficiency compared with state-of-the-art systems. By combining AI for research and AI for science principles within a spec-driven architecture, ARIA establishes a new paradigm for transparent, collaborative, and reproducible scientific discovery.
Authors: Gautier Dagan, Frank Keller, Alex Lascarides
Abstract: An agent facing a planning problem can use answers to how-to questions to reduce uncertainty and fill knowledge gaps, helping it solve both current and future tasks. However, their open ended nature, where valid answers to "How do I X?" range from executable actions to high-level descriptions of X's sub-goals, makes them challenging for AI agents to ask, and for AI experts to answer, in ways that support efficient planning. We introduce $How^{2}$, a memory agent framework that enables agents to ask how-to questions, store the answers, and reuse them for lifelong learning in interactive environments. We evaluate our approach in Plancraft, a Minecraft crafting environment, where agents must complete an assembly task by manipulating inventory items. Using teacher models that answer at varying levels of abstraction, from executable action sequences to high-level subgoal descriptions, we show that lifelong learning agents benefit most from answers that are abstracted and decoupled from the current state. $How^{2}$ offers a way for LLM-based agents to improve their planning capabilities over time by asking questions in interactive environments.
Authors: Peiming Li, Zhiyuan Hu, Yang Tang, Shiyu Li, Xi Chen
Abstract: Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including unstated goals, semantic context and risk tolerances), and they lack the defensive reasoning required to navigate real-world ambiguity. This cognitive gap leads to responses that are superficial, brittle and short-sighted. To address this, we propose Critique-Driven Reasoning Alignment (CDRA), which reframes alignment from a scalar reward-matching task into a structured reasoning process. First, to bridge the preference inference gap, we introduce the DeepPref benchmark. This dataset, comprising 3000 preference-query pairs across 20 topics, is curated by simulating a multi-faceted cognitive council that produces critique-annotated reasoning chains to deconstruct query semantics and reveal latent risks. Second, to instill defensive reasoning, we introduce the Personalized Generative Process Reward Model (Pers-GenPRM), which frames reward modeling as a personalized reasoning task. It generates a critique chain to evaluate a response's alignment with user preferences before outputting a final score based on this rationale. Ultimately, this interpretable, structured reward signal guides policy model through Critique-Driven Policy Alignment, a process-level online reinforcement learning algorithm integrating both numerical and natural language feedback. Experiments demonstrate that CDRA excels at discovering and aligning with users' true preferences while executing robust reasoning. Our code and dataset are available at https://github.com/Zephyrian-Hugh/Deep-pref.
Authors: Leonard Dung, Florian Mai
Abstract: AI alignment research aims to develop techniques to ensure that AI systems do not cause harm. However, every alignment technique has failure modes, which are conditions in which there is a non-negligible chance that the technique fails to provide safety. As a strategy for risk mitigation, the AI safety community has increasingly adopted a defense-in-depth framework: Conceding that there is no single technique which guarantees safety, defense-in-depth consists in having multiple redundant protections against safety failure, such that safety can be maintained even if some protections fail. However, the success of defense-in-depth depends on how (un)correlated failure modes are across alignment techniques. For example, if all techniques had the exact same failure modes, the defense-in-depth approach would provide no additional protection at all. In this paper, we analyze 7 representative alignment techniques and 7 failure modes to understand the extent to which they overlap. We then discuss our results' implications for understanding the current level of risk and how to prioritize AI alignment research in the future.
Authors: Deepeka Garg, Sihan Zeng, Annapoorani L. Narayanan, Sumitra Ganesh, Leo Ardon
Abstract: Learning to autonomously execute long-horizon procedures from natural language remains a core challenge for intelligent agents. Free-form instructions such as recipes, scientific protocols, or business workflows encode rich procedural knowledge, but their variability and lack of structure cause agents driven by large language models (LLMs) to drift or fail during execution. We introduce Procedure Aware DynaMic Execution (PADME), an agent framework that produces and exploits a graph-based representation of procedures. Unlike prior work that relies on manual graph construction or unstructured reasoning, PADME autonomously transforms procedural text into executable graphs that capture task dependencies, decision points, and reusable subroutines. Central to PADME is a two-phase methodology; Teach phase, which focuses on systematic structuring, enrichment with executable logic of procedures, followed by Execute phase, which enables dynamic execution in response to real-time inputs and environment feedback. This separation ensures quality assurance and scalability, allowing expert knowledge to be encoded once and reliably reused across varying contexts. The graph representation also provides an inductive bias that reduces error accumulation in long-horizon reasoning, underscoring the importance of structured procedure modeling for reliable agent-driven automation. Empirically, PADME achieves state-of-the-art performance on four diverse benchmarks, including ALFWorld and ScienceWorld. These results demonstrate that agents equipped with graph-based procedure representations offer a powerful intermediate abstraction for robust and generalizable execution.
Authors: Sheng Jin, Haoming Wang, Zhiqi Gao, Yongbo Yang, Bao Chunjia, Chengliang Wang
Abstract: Large language models (LLMs) based Agents are increasingly pivotal in simulating and understanding complex human systems and interactions. We propose the AI-Agent School (AAS) system, built around a self-evolving mechanism that leverages agents for simulating complex educational dynamics. Addressing the fragmented issues in teaching process modeling and the limitations of agents performance in simulating diverse educational participants, AAS constructs the Zero-Exp strategy, employs a continuous "experience-reflection-optimization" cycle, grounded in a dual memory base comprising experience and knowledge bases and incorporating short-term and long-term memory components. Through this mechanism, agents autonomously evolve via situated interactions within diverse simulated school scenarios. This evolution enables agents to more accurately model the nuanced, multi-faceted teacher-student engagements and underlying learning processes found in physical schools. Experiment confirms that AAS can effectively simulate intricate educational dynamics and is effective in fostering advanced agent cognitive abilities, providing a foundational stepping stone from the "Era of Experience" to the "Era of Simulation" by generating high-fidelity behavioral and interaction data.
Authors: Le Ngoc Luyen, Marie-H\'el\`ene Abel
Abstract: This paper investigates automated skill decomposition using Large Language Models (LLMs) and proposes a rigorous, ontology-grounded evaluation framework. Our framework standardizes the pipeline from prompting and generation to normalization and alignment with ontology nodes. To evaluate outputs, we introduce two metrics: a semantic F1-score that uses optimal embedding-based matching to assess content accuracy, and a hierarchy-aware F1-score that credits structurally correct placements to assess granularity. We conduct experiments on ROME-ESCO-DecompSkill, a curated subset of parents, comparing two prompting strategies: zero-shot and leakage-safe few-shot with exemplars. Across diverse LLMs, zero-shot offers a strong baseline, while few-shot consistently stabilizes phrasing and granularity and improves hierarchy-aware alignment. A latency analysis further shows that exemplar-guided prompts are competitive - and sometimes faster - than unguided zero-shot due to more schema-compliant completions. Together, the framework, benchmark, and metrics provide a reproducible foundation for developing ontology-faithful skill decomposition systems.
Authors: Abdullah Al Mahmud, Prangon Chowdhury, Mohammed Borhan Uddin, Khaled Eabne Delowar, Tausifur Rahman Talha, Bijoy Dewanjee
Abstract: Anemia, a condition marked by insufficient levels of red blood cells or hemoglobin, remains a widespread health issue affecting millions of individuals globally. Accurate and timely diagnosis is essential for effective management and treatment of anemia. In recent years, there has been a growing interest in the use of artificial intelligence techniques, i.e., machine learning (ML) and deep learning (DL) for the detection, classification, and diagnosis of anemia. This paper provides a systematic review of the recent advancements in this field, with a focus on various models applied to anemia detection. The review also compares these models based on several performance metrics, including accuracy, sensitivity, specificity, and precision. By analyzing these metrics, the paper evaluates the strengths and limitation of discussed models in detecting and classifying anemia, emphasizing the importance of addressing these factors to improve diagnostic accuracy.
Authors: Beining Wang, Weihang Su, Hongtao Tian, Tao Yang, Yujia Zhou, Ting Yao, Qingyao Ai, Yiqun Liu
Abstract: Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLVR), rewards only correct final answers, often propagating flawed reasoning and suffering from sparse reward signals. While process-level reward models (PRMs) provide denser, step-by-step feedback, they lack generalizability and interpretability, requiring task-specific segmentation of the reasoning process. To this end, we propose the Dimension-level Reward Model (DRM), a new supervision framework that bridges the gap between these two approaches. DRM evaluates the quality of a reasoning process along three fundamental, complementary, and interpretable dimensions: Confidence for uncertainty calibration, Relevance for semantic alignment, and Coherence for logical consistency. Together, these dimensions capture aspects beyond final answer correctness and enable interpretable assessment without requiring ground truth answers. Experimental results show that DRM provides effective supervision signals, guides the optimization of LLMs and enhances their reasoning ability. In particular, DRM-supervised training achieves consistent gains on both in-distribution and out-of-distribution open-domain tasks, including mathematics, question answering, code execution, and puzzles. Our findings demonstrate that multidimensional supervision of the reasoning process can improve the generalized reasoning ability of LLMs beyond the training distribution.
Authors: Yisen Gao, Jiaxin Bai, Yi Huang, Xingcheng Fu, Qingyun Sun, Yangqiu Song
Abstract: Deductive and abductive reasoning are two critical paradigms for analyzing knowledge graphs, enabling applications from financial query answering to scientific discovery. Deductive reasoning on knowledge graphs usually involves retrieving entities that satisfy a complex logical query, while abductive reasoning generates plausible logical hypotheses from observations. Despite their clear synergistic potential, where deduction can validate hypotheses and abduction can uncover deeper logical patterns, existing methods address them in isolation. To bridge this gap, we propose DARK, a unified framework for Deductive and Abductive Reasoning in Knowledge graphs. As a masked diffusion model capable of capturing the bidirectional relationship between queries and conclusions, DARK has two key innovations. First, to better leverage deduction for hypothesis refinement during abductive reasoning, we introduce a self-reflective denoising process that iteratively generates and validates candidate hypotheses against the observed conclusion. Second, to discover richer logical associations, we propose a logic-exploration reinforcement learning approach that simultaneously masks queries and conclusions, enabling the model to explore novel reasoning compositions. Extensive experiments on multiple benchmark knowledge graphs show that DARK achieves state-of-the-art performance on both deductive and abductive reasoning tasks, demonstrating the significant benefits of our unified approach.
Authors: Komal Gupta, Aditya Shrivastava
Abstract: Governance of data, compliance, and business privacy matters, particularly for healthcare and finance businesses. Since the recent emergence of AI enterprise AI assistants enhancing business productivity, safeguarding private data and compliance is now a priority. With the implementation of AI assistants across the enterprise, the zero data retention can be achieved by implementing zero data retention policies by Large Language Model businesses like Open AI and Anthropic and Meta. In this work, we explore zero data retention policies for the Enterprise apps of large language models (LLMs). Our key contribution is defining the architectural, compliance, and usability trade-offs of such systems in parallel. In this research work, we examine the development of commercial AI assistants with two industry leaders and market titans in this arena - Salesforce and Microsoft. Both of these companies used distinct technical architecture to support zero data retention policies. Salesforce AgentForce and Microsoft Copilot are among the leading AI assistants providing much-needed push to business productivity in customer care. The purpose of this paper is to analyze the technical architecture and deployment of zero data retention policy by consuming applications as well as big language models service providers like Open Ai, Anthropic, and Meta.
Authors: Jiateng Liu, Zhenhailong Wang, Xiaojiang Huang, Yingjie Li, Xing Fan, Xiang Li, Chenlei Guo, Ruhi Sarikaya, Heng Ji
Abstract: Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules. As requirements grow, these documents expand rapidly, causing high computational overhead. This motivates developing internalization methods that embed policy documents into model priors while preserving performance. Prior prompt compression work targets generic prompts, but agentic policy documents span multiple complexity levels and require deeper reasoning, making internalization harder. We introduce CC-Gen, an agentic benchmark generator with Controllable Complexity across four levels, enabling systematic evaluation of agents' ability to handle complexity and offering a unified framework for assessing policy internalization. Our analysis shows that complex policy specifications governing workflows pose major reasoning challenges. Supporting internalization with gold user agent interaction trajectories containing chain-of-thought (CoT) annotations via supervised fine-tuning (SFT) is data-intensive and degrades sharply as policy complexity increases. To mitigate data and reasoning burdens, we propose Category-Aware Policy Continued Pretraining (CAP-CPT). Our automated pipeline parses policy documents to extract key specifications, grouping them into factual, behavioral, and conditional categories, and isolating complex conditions that drive workflow complexity. This guides targeted data synthesis and enables agents to internalize policy information through an autoregressive pretraining loss. Experiments show CAP-CPT improves SFT baselines in all settings, with up to 41% and 22% gains on Qwen-3-32B, achieving 97.3% prompt length reduction on CC-Gen and further enhancing tau-Bench with minimal SFT data.
Authors: Israel Mason-Williams, Gabryel Mason-Williams
Abstract: AI policymakers are responsible for delivering effective governance mechanisms that can provide safe, aligned and trustworthy AI development. However, the information environment offered to policymakers is characterised by an unnecessarily low Signal-To-Noise Ratio, favouring regulatory capture and creating deep uncertainty and divides on which risks should be prioritised from a governance perspective. We posit that the current publication speeds in AI combined with the lack of strong scientific standards, via weak reproducibility protocols, effectively erodes the power of policymakers to enact meaningful policy and governance protocols. Our paper outlines how AI research could adopt stricter reproducibility guidelines to assist governance endeavours and improve consensus on the AI risk landscape. We evaluate the forthcoming reproducibility crisis within AI research through the lens of crises in other scientific domains; providing a commentary on how adopting preregistration, increased statistical power and negative result publication reproducibility protocols can enable effective AI governance. While we maintain that AI governance must be reactive due to AI's significant societal implications we argue that policymakers and governments must consider reproducibility protocols as a core tool in the governance arsenal and demand higher standards for AI research. Code to replicate data and figures: https://github.com/IFMW01/reproducibility-the-new-frontier-in-ai-governance
URLs: https://github.com/IFMW01/reproducibility-the-new-frontier-in-ai-governance
Authors: Sanjula De Alwis, Indrajith Ekanayake
Abstract: In online retail, customer acquisition typically incurs higher costs than customer retention, motivating firms to invest in churn analytics. However, many contemporary churn models operate as opaque black boxes, limiting insight into the determinants of attrition, the timing of retention opportunities, and the identification of high-risk customer segments. Accordingly, the emphasis should shift from prediction alone to the design of personalized retention strategies grounded in interpretable evidence. This study advances a three-component framework that integrates explainable AI to quantify feature contributions, survival analysis to model time-to-event churn risk, and RFM profiling to segment customers by transactional behaviour. In combination, these methods enable the attribution of churn drivers, estimation of intervention windows, and prioritization of segments for targeted actions, thereby supporting strategies that reduce attrition and strengthen customer loyalty.
Authors: Shiqi Zhang, Xinbei Ma, Yunqing Xu, Zouying Cao, Pengrui Lu, Haobo Yuan, Tiancheng Shen, Zhuosheng Zhang, Hai Zhao, Ming-Hsuan Yang
Abstract: Large Language Models (LLMs) exhibit strong reasoning abilities for planning long-horizon, real-world tasks, yet existing agent benchmarks focus on task completion while neglecting time efficiency in parallel and asynchronous operations. To address this, we present ParaCook, a benchmark for time-efficient collaborative planning. Inspired by the Overcooked game, ParaCook provides an environment for various challenging interaction planning of multi-agent systems that are instantiated as cooking tasks, with a simplified action space to isolate the core challenge of strategic parallel planning. Through a comprehensive evaluation of state-of-the-art LLMs, we find that current approaches achieve suboptimal plans, which struggle with parallel actions or coordination. Our analysis also reveals LLMs' potential on abstract tasks where they can focus on high-level parallel optimization. ParaCook provides a scalable evaluation framework with adjustable complexity, establishing a foundation for developing and assessing time efficiency-aware multi-agent planning. The code and data are available at https://github.com/zsq259/ParaCook.
Authors: Shijie Xia, Yuhan Sun, Pengfei Liu
Abstract: Recently, Large Language Models (LLMs) have been applied to scientific equation discovery, leveraging their embedded scientific knowledge for hypothesis generation. However, current methods typically confine LLMs to the role of an equation proposer within search algorithms like genetic programming. In this paper, we present SR-Scientist, a framework that elevates the LLM from a simple equation proposer to an autonomous AI scientist that writes code to analyze data, implements the equation as code, submits it for evaluation, and optimizes the equation based on experimental feedback. Specifically, we wrap the code interpreter into a set of tools for data analysis and equation evaluation. The agent is instructed to optimize the equation by utilizing these tools over a long horizon with minimal human-defined pipelines. Empirical results show that SR-Scientist outperforms baseline methods by an absolute margin of 6% to 35% on datasets covering four science disciplines. Additionally, we demonstrate our method's robustness to noise, the generalization of the discovered equations to out-of-domain data, and their symbolic accuracy. Furthermore, we develop an end-to-end reinforcement learning framework to enhance the agent's capabilities.
Authors: Arjun Sahney, Ram Gorthi, Cezary {\L}astowski, Javier Vega
Abstract: We present Operand Quant, a single-agent, IDE-based architecture for autonomous machine learning engineering (MLE). Operand Quant departs from conventional multi-agent orchestration frameworks by consolidating all MLE lifecycle stages -- exploration, modeling, experimentation, and deployment -- within a single, context-aware agent. On the MLE-Benchmark (2025), Operand Quant achieved a new state-of-the-art (SOTA) result, with an overall medal rate of 0.3956 +/- 0.0565 across 75 problems -- the highest recorded performance among all evaluated systems to date. The architecture demonstrates that a linear, non-blocking agent, operating autonomously within a controlled IDE environment, can outperform multi-agent and orchestrated systems under identical constraints.
Authors: Md Hasibul Amin (University Of Houston), Harika Madanu (University Of Houston), Sahithi Lavu (University Of Houston), Hadi Mansourifar (University Of Houston), Dana Alsagheer (University Of Houston), Weidong Shi (University Of Houston)
Abstract: Since the beginning of the vaccination trial, social media has been flooded with anti-vaccination comments and conspiracy beliefs. As the day passes, the number of COVID- 19 cases increases, and online platforms and a few news portals entertain sharing different conspiracy theories. The most popular conspiracy belief was the link between the 5G network spreading COVID-19 and the Chinese government spreading the virus as a bioweapon, which initially created racial hatred. Although some disbelief has less impact on society, others create massive destruction. For example, the 5G conspiracy led to the burn of the 5G Tower, and belief in the Chinese bioweapon story promoted an attack on the Asian-Americans. Another popular conspiracy belief was that Bill Gates spread this Coronavirus disease (COVID-19) by launching a mass vaccination program to track everyone. This Conspiracy belief creates distrust issues among laypeople and creates vaccine hesitancy. This study aims to discover the conspiracy theory against the vaccine on social platforms. We performed a sentiment analysis on the 598 unique sample comments related to COVID-19 vaccines. We used two different models, BERT and Perspective API, to find out the sentiment and toxicity of the sentence toward the COVID-19 vaccine.
Authors: Dong Yan, Gaochen Wu, Bowen Zhou
Abstract: Recent advancements in language agents have led to significant improvements in multi-hop reasoning tasks. However, existing approaches often struggle with handling open-domain problems, which require massive information retrieval due to their reliance on a fixed sequence of actions. To address this, we propose Feedback-Guided Dynamic Interactive Planning (FGDIP), a novel framework tailored to enhance reasoning in LLMs by utilizing dynamic and adaptive strategies for information exploration in open-domain multi-hop reasoning tasks. Our approach begins by identifying key entities relevant to the problem, which serve as the initial nodes in the reasoning process. From these initial nodes, we then generate reasoning child nodes with the process being refined through a combination of historical error analysis and real-time feedback, which allows the framework to dynamically adjust and optimize its reasoning strategies. By integrating depth-first search with an innovative node generation technique, our framework adapts based on both prior error paths and concurrently generated nodes at the same hierarchical level. This dynamic strategy effectively expands the search space while ensuring the reasoning process systematically converges toward accurate solutions. Experimental results show that FGDIP achieved up to 54.47% F1 score on the HotpotQA dataset and 70.05% on the StrategyQA dataset, surpassing the best baseline by 5.03% and 7.25% respectively, highlighting its versatility and potential to enhance language agents in multi-hop reasoning tasks.
Authors: Mohammadhossein Homaei, Mehran Tarif, Mar Avilla, Andres Caro
Abstract: Industrial Control Systems (ICS) face growing cyber-physical attacks that exploit both network vulnerabilities and physical processes. Current anomaly detection methods rely on correlation-based analysis, which cannot separate true causal relationships from spurious associations. This limitation results in high false alarm rates and poor root cause analysis. We propose a novel Causal Digital Twin (CDT) framework for cyber-physical security in medium-scale ICS. Our method combines causal inference theory with digital twin modeling. The framework enables three types of causal reasoning: association for pattern detection, intervention for understanding system responses, and counterfactual analysis for attack prevention planning. We evaluate our framework on three industrial datasets: SWaT, WADI, and HAI, with validation through physical constraint compliance (90.8\%) and synthetic ground truth testing (structural Hamming distance 0.13). Results show significant improvements over seven baseline methods. Our CDT achieves F1-scores are $0.944 \pm 0.014$ for SWaT, $0.902 \pm 0.021$ for WADI, and $0.923 \pm 0.018$ for HAI with statistical significance ($p < 0.0024$, Bonferroni corrected). The framework reduces false positives by \SI{74}{\percent} and achieves \SI{78.4}{\percent} root cause analysis accuracy compared to \SI{48.7}{\percent} for existing methods. Counterfactual analysis enables defense strategies that reduce attack success by \SI{73.2}{\percent}. The system keeps real-time performance with \SI{3.2}{ms} latency, which is suitable for industrial deployment, while providing interpretable explanations for operators.
Authors: Jiayun Mo, Xin Kang, Tieyan Li, Zhongding Lei
Abstract: The excitement brought by the development of AI agents came alongside arising problems. These concerns centered around users' trust issues towards AIs, the risks involved, and the difficulty of attributing responsibilities and liabilities. Current solutions only attempt to target each problem separately without acknowledging their inter-influential nature. The Trust, Risk and Liability (TRL) framework proposed in this paper, however, ties together the interdependent relationships of trust, risk, and liability to provide a systematic method of building and enhancing trust, analyzing and mitigating risks, and allocating and attributing liabilities. It can be applied to analyze any application scenarios of AI agents and suggest appropriate measures fitting to the context. The implications of the TRL framework lie in its potential societal impacts, economic impacts, ethical impacts, and more. It is expected to bring remarkable values to addressing potential challenges and promoting trustworthy, risk-free, and responsible usage of AI in 6G networks.
Authors: Bernhard Mueller
Abstract: Hound introduces a relation-first graph engine that improves system-level reasoning across interrelated components in complex codebases. The agent designs flexible, analyst-defined views with compact annotations (e.g., monetary/value flows, authentication/authorization roles, call graphs, protocol invariants) and uses them to anchor exact retrieval: for any question, it loads precisely the code that matters (often across components) so it can zoom out to system structure and zoom in to the decisive lines. A second contribution is a persistent belief system: long-lived vulnerability hypotheses whose confidence is updated as evidence accrues. The agent employs coverage-versus-intuition planning and a QA finalizer to confirm or reject hypotheses. On a five-project subset of ScaBench[1], Hound improves recall and F1 over a baseline LLM analyzer (micro recall 31.2% vs. 8.3%; F1 14.2% vs. 9.8%) with a modest precision trade-off. We attribute these gains to flexible, relation-first graphs that extend model understanding beyond call/dataflow to abstract aspects, plus the hypothesis-centric loop; code and artifacts are released to support reproduction.
Authors: Anastasija Nikiforova, Martin Lnenicka, Ulf Melin, David Valle-Cruz, Asif Gill, Cesar Casiano Flores, Emyana Sirait, Mariusz Luterek, Richard Michael Dreyling, Barbora Tesarova
Abstract: Despite Artificial Intelligence (AI) transformative potential for public sector services, decision-making, and administrative efficiency, adoption remains uneven due to complex technical, organizational, and institutional challenges. Responsible AI frameworks emphasize fairness, accountability, and transparency, aligning with principles of trustworthy AI and fair AI, yet remain largely aspirational, overlooking technical and institutional realities, especially foundational data and governance. This study addresses this gap by developing a taxonomy of data-related challenges to responsible AI adoption in government. Based on a systematic review of 43 studies and 21 expert evaluations, the taxonomy identifies 13 key challenges across technological, organizational, and environmental dimensions, including poor data quality, limited AI-ready infrastructure, weak governance, misalignment in human-AI decision-making, economic and environmental sustainability concerns. Annotated with institutional pressures, the taxonomy serves as a diagnostic tool to surface 'symptoms' of high-risk AI deployment and guides policymakers in building the institutional and data governance conditions necessary for responsible AI adoption.
Authors: Prarthana P. Kartholy, Thandi M. Labor, Neil N. Panchal, Sean H. Wang, Hillary N. Owusu
Abstract: Selecting a college major is a difficult decision for many incoming freshmen. Traditional academic advising is often hindered by long wait times, intimidating environments, and limited personalization. AI Chatbots present an opportunity to address these challenges. However, AI systems also have the potential to generate biased responses, prejudices related to race, gender, socioeconomic status, and disability. These biases risk turning away potential students and undermining reliability of AI systems. This study aims to develop a University of Maryland (UMD) A. James Clark School of Engineering Program-specific AI chatbot. Our research team analyzed and mitigated potential biases in the responses. Through testing the chatbot on diverse student queries, the responses are scored on metrics of accuracy, relevance, personalization, and bias presence. The results demonstrate that with careful prompt engineering and bias mitigation strategies, AI chatbots can provide high-quality, unbiased academic advising support, achieving mean scores of 9.76 for accuracy, 9.56 for relevance, and 9.60 for personalization with no stereotypical biases found in the sample data. However, due to the small sample size and limited timeframe, our AI model may not fully reflect the nuances of student queries in engineering academic advising. Regardless, these findings will inform best practices for building ethical AI systems in higher education, offering tools to complement traditional advising and address the inequities faced by many underrepresented and first-generation college students.
Authors: Yuguang Liu, Yiyun Miao, Luyao Xia
Abstract: Multi-task learning (MTL) has emerged as a successful strategy in industrial-scale recommender systems, offering significant advantages such as capturing diverse users' interests and accurately detecting different behaviors like ``click" or ``dwell time". However, negative transfer and the seesaw phenomenon pose challenges to MTL models due to the complex and often contradictory task correlations in real-world recommendations. To address the problem while making better use of personalized information, we propose a personalized Direct Routing Gradient framework (DRGrad), which consists of three key components: router, updater and personalized gate network. DRGrad judges the stakes between tasks in the training process, which can leverage all valid gradients for the respective task to reduce conflicts. We evaluate the efficiency of DRGrad on complex MTL using a real-world recommendation dataset with 15 billion samples. The results show that DRGrad's superior performance over competing state-of-the-art MTL models, especially in terms of AUC (Area Under the Curve) metrics, indicating that it effectively manages task conflicts in multi-task learning environments without increasing model complexity, while also addressing the deficiencies in noise processing. Moreover, experiments on the public Census-income dataset and Synthetic dataset, have demonstrated the capability of DRGrad in judging and routing the stakes between tasks with varying degrees of correlation and personalization.
Authors: Shaharyar Alam Ansari, Mohammad Luqman, Aasim Zafar, Savir Ali
Abstract: Rapid urbanization has intensified traffic congestion, environmental strain, and inefficiencies in transportation systems, creating an urgent need for intelligent and adaptive traffic management solutions. Conventional systems relying on static signals and manual monitoring are inadequate for the dynamic nature of modern traffic. This research aims to develop a unified framework that integrates CCTV surveillance videos with multi-source data descriptors to enhance real-time urban traffic prediction. The proposed methodology incorporates spatio-temporal feature fusion, Frequent Episode Mining for sequential traffic pattern discovery, and a hybrid LSTM-Transformer model for robust traffic state forecasting. The framework was evaluated on the CityFlowV2 dataset comprising 313,931 annotated bounding boxes across 46 cameras. It achieved a high prediction accuracy of 98.46 percent, with a macro precision of 0.9800, macro recall of 0.9839, and macro F1-score of 0.9819. FEM analysis revealed significant sequential patterns such as moderate-congested transitions with confidence levels exceeding 55 percent. The 46 sustained congestion alerts are system-generated, which shows practical value for proactive congestion management. This emphasizes the need for the incorporation of video stream analytics with data from multiple sources for the design of real-time, responsive, adaptable multi-level intelligent transportation systems, which makes urban mobility smarter and safer.
Authors: Ritesh Chandra, Sonali Agarwal, Navjot Singh
Abstract: Timely detection of critical health conditions remains a major challenge in public health analytics, especially in Big Data environments characterized by high volume, rapid velocity, and diverse variety of clinical data. This study presents an ontology-enabled real-time analytics framework that integrates Complex Event Processing (CEP) and Large Language Models (LLMs) to enable intelligent health event detection and semantic reasoning over heterogeneous, high-velocity health data streams. The architecture leverages the Basic Formal Ontology (BFO) and Semantic Web Rule Language (SWRL) to model diagnostic rules and domain knowledge. Patient data is ingested and processed using Apache Kafka and Spark Streaming, where CEP engines detect clinically significant event patterns. LLMs support adaptive reasoning, event interpretation, and ontology refinement. Clinical information is semantically structured as Resource Description Framework (RDF) triples in Graph DB, enabling SPARQL-based querying and knowledge-driven decision support. The framework is evaluated using a dataset of 1,000 Tuberculosis (TB) patients as a use case, demonstrating low-latency event detection, scalable reasoning, and high model performance (in terms of precision, recall, and F1-score). These results validate the system's potential for generalizable, real-time health analytics in complex Big Data scenarios.
Authors: Xiangxiang Chen, Peixin Zhang, Jun Sun, Wenhai Wang, Jingyi Wang
Abstract: Model quantization is a popular technique for deploying deep learning models on resource-constrained environments. However, it may also introduce previously overlooked security risks. In this work, we present QuRA, a novel backdoor attack that exploits model quantization to embed malicious behaviors. Unlike conventional backdoor attacks relying on training data poisoning or model training manipulation, QuRA solely works using the quantization operations. In particular, QuRA first employs a novel weight selection strategy to identify critical weights that influence the backdoor target (with the goal of perserving the model's overall performance in mind). Then, by optimizing the rounding direction of these weights, we amplify the backdoor effect across model layers without degrading accuracy. Extensive experiments demonstrate that QuRA achieves nearly 100% attack success rates in most cases, with negligible performance degradation. Furthermore, we show that QuRA can adapt to bypass existing backdoor defenses, underscoring its threat potential. Our findings highlight critical vulnerability in widely used model quantization process, emphasizing the need for more robust security measures. Our implementation is available at https://github.com/cxx122/QuRA.
Authors: Khartik Uppalapati, Bora Yimenicioglu, Shakeel Abdulkareem, Adan Eftekhari, Bhavya Uppalapati, Viraj Kamath
Abstract: Batten disease (neuronal ceroid lipofuscinosis) is a rare pediatric neurodegenerative disorder whose early MRI signs are subtle and often missed. We propose TinyViT-Batten, a few-shot Vision Transformer (ViT) framework to detect early Batten disease from pediatric brain MRI with limited training cases. We distill a large teacher ViT into a 5 M-parameter TinyViT and fine-tune it using metric-based few-shot learning (prototypical loss with 5-shot episodes). Our model achieves high accuracy (approximately 91%) and area under ROC of at least 0.95 on a multi-site dataset of 79 genetically confirmed Batten-disease MRIs (27 CLN3 from the Hochstein natural-history study, 32 CLN2 from an international longitudinal cohort, 12 early-manifestation CLN2 cases reported by Cokal et al., and 8 public Radiopaedia scans) together with 90 age-matched controls, outperforming a 3D-ResNet and Swin-Tiny baseline. We further integrate Gradient-weighted Class Activation Mapping (Grad-CAM) to highlight disease-relevant brain regions, enabling explainable predictions. The model's small size and strong performance (sensitivity greater than 90%, specificity approximately 90%) demonstrates a practical AI solution for early Batten disease detection.
Authors: Ranjan Sapkota, Manoj Karkee
Abstract: This paper presents a comprehensive overview of the Ultralytics YOLO(You Only Look Once) family of object detectors, focusing the architectural evolution, benchmarking, deployment perspectives, and future challenges. The review begins with the most recent release, YOLO26 (YOLOv26), which introduces key innovations including Distribution Focal Loss (DFL) removal, native NMS-free inference, Progressive Loss Balancing (ProgLoss), Small-Target-Aware Label Assignment (STAL), and the MuSGD optimizer for stable training. The progression is then traced through YOLO11, with its hybrid task assignment and efficiency-focused modules; YOLOv8, which advanced with a decoupled detection head and anchor-free predictions; and YOLOv5, which established the modular PyTorch foundation that enabled modern YOLO development. Benchmarking on the MS COCO dataset provides a detailed quantitative comparison of YOLOv5, YOLOv8, YOLO11, and YOLO26, alongside cross-comparisons with YOLOv12, YOLOv13, RT-DETR, and DEIM. Metrics including precision, recall, F1 score, mean Average Precision, and inference speed are analyzed to highlight trade-offs between accuracy and efficiency. Deployment and application perspectives are further discussed, covering export formats, quantization strategies, and real-world use in robotics, agriculture, surveillance, and manufacturing. Finally, the paper identifies challenges and future directions, including dense-scene limitations, hybrid CNN-Transformer integration, open-vocabulary detection, and edge-aware training approaches.
Authors: Yanming Li (PETSCRAFT), Seifeddine Ghozzi (ENSTA), C\'edric Eichler (PETSCRAFT), Nicolas Anciaux (PETSCRAFT), Alexandra Bensamoun (UC3M), Lorena Gonzalez Manzano (UC3M)
Abstract: We address the problem of auditing whether sensitive or copyrighted texts were used to fine-tune large language models (LLMs) under black-box access. Prior signals-verbatim regurgitation and membership inference-are unreliable at the level of individual documents or require altering the visible text. We introduce a text-preserving watermarking framework that embeds sequences of invisible Unicode characters into documents. Each watermark is split into a cue (embedded in odd chunks) and a reply (embedded in even chunks). At audit time, we submit prompts that contain only the cue; the presence of the corresponding reply in the model's output provides evidence of memorization consistent with training on the marked text. To obtain sound decisions, we compare the score of the published watermark against a held-out set of counterfactual watermarks and apply a ranking test with a provable false-positive-rate bound. The design is (i) minimally invasive (no visible text changes), (ii) scalable to many users and documents via a large watermark space and multi-watermark attribution, and (iii) robust to common passive transformations. We evaluate on open-weight LLMs and multiple text domains, analyzing regurgitation dynamics, sensitivity to training set size, and interference under multiple concurrent watermarks. Our results demonstrate reliable post-hoc provenance signals with bounded FPR under black-box access. We experimentally observe a failure rate of less than 0.1\% when detecting a reply after fine-tuning with 50 marked documents. Conversely, no spurious reply was recovered in over 18,000 challenges, corresponding to a 100\%TPR@0\% FPR. Moreover, detection rates remain relatively stable as the dataset size increases, maintaining a per-document detection rate above 45\% even when the marked collection accounts for less than 0.33\% of the fine-tuning data.
Authors: Riccardo Fosco Gramaccioni, Christian Marinoni, Fabrizio Frezza, Aurelio Uncini, Danilo Comminiello
Abstract: Accurate simulation of wave propagation in complex acoustic materials is crucial for applications in sound design, noise control, and material engineering. Traditional numerical solvers, such as finite element methods, are computationally expensive, especially when dealing with large-scale or real-time scenarios. In this work, we introduce a dataset of 31,000 acoustic materials, named HA30K, designed and simulated solving the Helmholtz equations. For each material, we provide the geometric configuration and the corresponding pressure field solution, enabling data-driven approaches to learn Helmholtz equation solutions. As a baseline, we explore a deep learning approach based on Stable Diffusion with ControlNet, a state-of-the-art model for image generation. Unlike classical solvers, our approach leverages GPU parallelization to process multiple simulations simultaneously, drastically reducing computation time. By representing solutions as images, we bypass the need for complex simulation software and explicit equation-solving. Additionally, the number of diffusion steps can be adjusted at inference time, balancing speed and quality. We aim to demonstrate that deep learning-based methods are particularly useful in early-stage research, where rapid exploration is more critical than absolute accuracy.
Authors: Filippo Rinaldi, Aniello Panariello, Giacomo Salici, Fengyuan Liu, Marco Ciccone, Angelo Porrello, Simone Calderara
Abstract: When a new release of a foundation model is published, practitioners typically need to repeat full fine-tuning, even if the same task has already been solved in the previous version. A promising alternative is to reuse the parameter changes (i.e., task vectors) that capture how a model adapts to a specific task. However, they often fail to transfer across different pre-trained models due to their misaligned parameter space. In this work, we show that the key to successful transfer lies in the sign structure of the gradients of the new model. Based on this insight, we propose GradFix, a novel method that approximates the ideal gradient sign structure and leverages it to transfer knowledge using only a handful of labeled samples. Notably, this requires no additional fine-tuning: the adaptation is achieved by computing a few gradients at the target model and masking the source task vector accordingly. This yields an update that is locally aligned with the target loss landscape, effectively rebasing the task vector onto the new pre-training. We provide a theoretical guarantee that our method ensures first-order descent. Empirically, we demonstrate significant performance gains on vision and language benchmarks, consistently outperforming naive task vector addition and few-shot fine-tuning.
Authors: Luca Scimeca, Thomas Jiralerspong, Berton Earnshaw, Jason Hartford, Yoshua Bengio
Abstract: Diffusion Probabilistic Models (DPMs) have achieved strong generative performance, yet their inductive biases remain largely implicit. In this work, we aim to build inductive biases into the training and sampling of diffusion models to better accommodate the target distribution of the data to model. We introduce an anisotropic noise operator that shapes these biases by replacing the isotropic forward covariance with a structured, frequency-diagonal covariance. This operator unifies band-pass masks and power-law weightings, allowing us to emphasize or suppress designated frequency bands, while keeping the forward process Gaussian. We refer to this as spectrally anisotropic Gaussian diffusion (SAGD). In this work, we derive the score relation for anisotropic covariances and show that, under full support, the learned score converges to the true data score as $t\!\to\!0$, while anisotropy reshapes the probability-flow path from noise to data. Empirically, we show the induced anisotropy outperforms standard diffusion across several vision datasets, and enables selective omission: learning while ignoring known corruptions confined to specific bands. Together, these results demonstrate that carefully designed anisotropic forward noise provides a simple, yet principled, handle to tailor inductive bias in DPMs.
Authors: Raju Dhakal, Prashant Shekhar, Laxima Niure Kandel
Abstract: Radio Frequency Fingerprinting (RFF) has evolved as an effective solution for authenticating devices by leveraging the unique imperfections in hardware components involved in the signal generation process. In this work, we propose a Convolutional Neural Network (CNN) based framework for detecting rogue devices and identifying genuine ones using softmax probability thresholding. We emulate an attack scenario in which adversaries attempt to mimic the RF characteristics of genuine devices by training a Generative Adversarial Network (GAN) using In-phase and Quadrature (IQ) samples from genuine devices. The proposed approach is verified using IQ samples collected from ten different ADALM-PLUTO Software Defined Radios (SDRs), with seven devices considered genuine, two as rogue, and one used for validation to determine the threshold.
Authors: Maryam Abdollahi Shamami, Babak Teimourpour, Farshad Sharifi
Abstract: Drug-drug interactions (DDIs) are a leading cause of preventable adverse events, often complicating treatment and increasing healthcare costs. At the same time, knowing which drugs do not interact is equally important, as such knowledge supports safer prescriptions and better patient outcomes. In this study, we propose an interpretable and efficient framework that blends modern machine learning with domain knowledge to improve DDI prediction. Our approach combines two complementary molecular embeddings - Mol2Vec, which captures fragment-level structural patterns, and SMILES-BERT, which learns contextual chemical features - together with a leakage-free, rule-based clinical score (RBScore) that injects pharmacological knowledge without relying on interaction labels. A lightweight neural classifier is then optimized using a novel three-stage metaheuristic strategy (RSmpl-ACO-PSO), which balances global exploration and local refinement for stable performance. Experiments on real-world datasets demonstrate that the model achieves high predictive accuracy (ROC-AUC 0.911, PR-AUC 0.867 on DrugBank) and generalizes well to a clinically relevant Type 2 Diabetes Mellitus cohort. Beyond raw performance, studies show how embedding fusion, RBScore, and the optimizer each contribute to precision and robustness. Together, these results highlight a practical pathway for building reliable, interpretable, and computationally efficient models that can support safer drug therapies and clinical decision-making.
Authors: Joao D. S. Marques, Andre V. Duarte, Andre Carvalho, Gil Rocha, Bruno Martins, Arlindo L. Oliveira
Abstract: Every year, the European Union and its member states allocate millions of euros to fund various development initiatives. However, the increasing number of applications received for these programs often creates significant bottlenecks in evaluation processes, due to limited human capacity. In this work, we detail the real-world deployment of AI-assisted evaluation within the pipeline of two government initiatives: (i) corporate applications aimed at international business expansion, and (ii) citizen reimbursement claims for investments in energy-efficient home improvements. While these two cases involve distinct evaluation procedures, our findings confirm that AI effectively enhanced processing efficiency and reduced workload across both types of applications. Specifically, in the citizen reimbursement claims initiative, our solution increased reviewer productivity by 20.1%, while keeping a negligible false-positive rate based on our test set observations. These improvements resulted in an overall reduction of more than 2 months in the total evaluation time, illustrating the impact of AI-driven automation in large-scale evaluation workflows.
Authors: Shayan Mohajer Hamidi, En-Hui Yang, Ben Liang
Abstract: Inverse problems, where the goal is to recover an unknown signal from noisy or incomplete measurements, are central to applications in medical imaging, remote sensing, and computational biology. Diffusion models have recently emerged as powerful priors for solving such problems. However, existing methods either rely on projection-based techniques that enforce measurement consistency through heuristic updates, or they approximate the likelihood $p(\boldsymbol{y} \mid \boldsymbol{x})$, often resulting in artifacts and instability under complex or high-noise conditions. To address these limitations, we propose a novel framework called \emph{coupled data and measurement space diffusion posterior sampling} (C-DPS), which eliminates the need for constraint tuning or likelihood approximation. C-DPS introduces a forward stochastic process in the measurement space $\{\boldsymbol{y}_t\}$, evolving in parallel with the data-space diffusion $\{\boldsymbol{x}_t\}$, which enables the derivation of a closed-form posterior $p(\boldsymbol{x}_{t-1} \mid \boldsymbol{x}_t, \boldsymbol{y}_{t-1})$. This coupling allows for accurate and recursive sampling based on a well-defined posterior distribution. Empirical results demonstrate that C-DPS consistently outperforms existing baselines, both qualitatively and quantitatively, across multiple inverse problem benchmarks.
Authors: Ebrahim Rahimi, Clara Maathuis
Abstract: Computational Thinking (CT) is a key skill set for students in higher education to thrive and adapt to an increasingly technology-driven future and workplace. While research on CT education has gained remarkable momentum in K12 over the past decade, it has remained under-explored in higher education, leaving higher education teachers with an insufficient overview, knowledge, and support regarding CT education. The proliferation and adoption of artificial intelligence (AI) by educational institutions have demonstrated promising potential to support instructional activities across many disciplines, including CT education. However, a comprehensive overview outlining the various aspects of integrating AI in CT education in higher education is lacking. To mitigate this gap, we conducted this systematic literature review study. The focus of our study is to identify initiatives applying AI in CT education within higher education and to explore various educational aspects of these initiatives, including the benefits and challenges of AI in CT education, instructional strategies employed, CT components covered, and AI techniques and models utilized. This study provides practical and scientific contributions to the CT education community, including an inventory of AI-based initiatives for CT education useful to educators, an overview of various aspects of integrating AI into CT education such as its benefits and challenges (e.g., AI potential to reshape CT education versus its potential to diminish students creativity) and insights into new and expanded perspectives on CT in light of AI (e.g., the decoding approach alongside the coding approach to CT).
Authors: Rupam Patir, Keyan Guo, Haipeng Cai, Hongxin Hu
Abstract: The code generation capabilities of Large Language Models (LLMs) have transformed the field of software development. However, this advancement also presents significant security challenges, as LLM-generated code often contains vulnerabilities. One direction of research strengthens LLMs by injecting or refining security knowledge through curated datasets, model tuning, or static analyzers. While effective in certain settings, these methods can be resource-intensive, less adaptable to zero-day vulnerabilities, and often inapplicable to proprietary models. To address these challenges, we introduce GRASP, which explores a new direction that focuses on structured reasoning over Secure Coding Practices(SCPs) rather than additional training or external feedback. GRASP comprises two key ideas: (1) an SCP graph that organizes SCPs into a Directed Acyclic Graph (DAG) capturing dependencies and relationships, and (2) a graph-based reasoning process that systematically guides LLMs through relevant SCPs for code generation. This design enables interpretable, model-agnostic, and scalable security improvements, particularly for previously unseen vulnerabilities. Our evaluation shows that GRASP consistently achieves Security Rates (SR) exceeding 80% across multiple LLMs, and delivers up to 88% improvements over baselines on zero-day vulnerabilities.
Authors: Yongshuai Liu, Lianfang Wang, Kuilin Qin, Qinghua Zhang, Faqiang Wang, Li Cui, Jun Liu, Yuping Duan, Tieyong Zeng
Abstract: Deep learning has become a pivotal technology in fields such as computer vision, scientific computing, and dynamical systems, significantly advancing these disciplines. However, neural Networks persistently face challenges related to theoretical understanding, interpretability, and generalization. To address these issues, researchers are increasingly adopting a differential equations perspective to propose a unified theoretical framework and systematic design methodologies for neural networks. In this paper, we provide an extensive review of deep neural network architectures and dynamic modeling methods inspired by differential equations. We specifically examine deep neural network models and deterministic dynamical network constructs based on ordinary differential equations (ODEs), as well as regularization techniques and stochastic dynamical network models informed by stochastic differential equations (SDEs). We present numerical comparisons of these models to illustrate their characteristics and performance. Finally, we explore promising research directions in integrating differential equations with deep learning to offer new insights for developing intelligent computational methods that boast enhanced interpretability and generalization capabilities.
Authors: Jianghao Lin, Rong Shan, Jiachen Zhu, Yunjia Xi, Yong Yu, Weinan Zhang
Abstract: Survey papers are foundational to the scholarly progress of research communities, offering structured overviews that guide both novices and experts across disciplines. However, the recent surge of AI-generated surveys, especially enabled by large language models (LLMs), has transformed this traditionally labor-intensive genre into a low-effort, high-volume output. While such automation lowers entry barriers, it also introduces a critical threat: the phenomenon we term the "survey paper DDoS attack" to the research community. This refers to the unchecked proliferation of superficially comprehensive but often redundant, low-quality, or even hallucinated survey manuscripts, which floods preprint platforms, overwhelms researchers, and erodes trust in the scientific record. In this position paper, we argue that we must stop uploading massive amounts of AI-generated survey papers (i.e., survey paper DDoS attack) to the research community, by instituting strong norms for AI-assisted review writing. We call for restoring expert oversight and transparency in AI usage and, moreover, developing new infrastructures such as Dynamic Live Surveys, community-maintained, version-controlled repositories that blend automated updates with human curation. Through quantitative trend analysis, quality audits, and cultural impact discussion, we show that safeguarding the integrity of surveys is no longer optional but imperative to the research community.
Authors: Stanis{\l}aw Pawlak
Abstract: This study delves into the plasticity of neural networks, offering empirical support for the notion that critical learning periods and warm-starting performance loss can be avoided through simple adjustments to learning hyperparameters. The critical learning phenomenon emerges when training is initiated with deficit data. Subsequently, after numerous deficit epochs, the network's plasticity wanes, impeding its capacity to achieve parity in accuracy with models trained from scratch, even when extensive clean data training follows deficit epochs. Building upon seminal research introducing critical learning periods, we replicate key findings and broaden the experimental scope of the main experiment from the original work. In addition, we consider a warm-starting approach and show that it can be seen as a form of deficit pretraining. In particular, we demonstrate that these problems can be averted by employing a cyclic learning rate schedule. Our findings not only impact neural network training practices but also establish a vital link between critical learning periods and ongoing research on warm-starting neural network training.
Authors: Haoran Ou, Kangjie Chen, Xingshuo Han, Gelei Deng, Jie Zhang, Han Qiu, Tianwei Zhang
Abstract: Large Language Models (LLMs) excel at tasks such as dialogue, summarization, and question answering, yet they struggle to adapt to specialized domains and evolving facts. To overcome this, web search has been integrated into LLMs, allowing real-time access to online content. However, this connection magnifies safety risks, as adversarial prompts combined with untrusted sources can cause severe vulnerabilities. We investigate red teaming for LLMs with web search and present CREST-Search, a framework that systematically exposes risks in such systems. Unlike existing methods for standalone LLMs, CREST-Search addresses the complex workflow of search-enabled models by generating adversarial queries with in-context learning and refining them through iterative feedback. We further construct WebSearch-Harm, a search-specific dataset to fine-tune LLMs into efficient red-teaming agents. Experiments show that CREST-Search effectively bypasses safety filters and reveals vulnerabilities in modern web-augmented LLMs, underscoring the need for specialized defenses to ensure trustworthy deployment.
Authors: Tejash Varsani
Abstract: Federated learning is distributed model training across several clients without disclosing raw data. Despite advancements in data privacy, risks still remain. Differential Privacy (DP) is a technique to protect sensitive data by adding noise to model updates, usually controlled by a fixed privacy budget. However, this approach can introduce excessive noise, particularly when the model converges, which compromises performance. To address this problem, adaptive privacy budgets have been investigated as a potential solution. This work implements DP methods using Laplace and Gaussian mechanisms with an adaptive privacy budget, extending the SelecEval simulator. We introduce an adaptive clipping approach in the Gaussian mechanism, ensuring that gradients of the model are dynamically updated rather than using a fixed sensitivity. We conduct extensive experiments with various privacy budgets, IID and non-IID datasets, and different numbers of selected clients per round. While our experiments were limited to 200 training rounds, the results suggest that adaptive privacy budgets and adaptive clipping can help maintain model accuracy while preserving privacy.
Authors: Xiaodan Li, Mengjie Wu, Yao Zhu, Yunna Lv, YueFeng Chen, Cen Chen, Jianmei Guo, Hui Xue
Abstract: Large models (LMs) are powerful content generators, yet their open-ended nature can also introduce potential risks, such as generating harmful or biased content. Existing guardrails mostly perform post-hoc detection that may expose unsafe content before it is caught, and the latency constraints further push them toward lightweight models, limiting detection accuracy. In this work, we propose Kelp, a novel plug-in framework that enables streaming risk detection within the LM generation pipeline. Kelp leverages intermediate LM hidden states through a Streaming Latent Dynamics Head (SLD), which models the temporal evolution of risk across the generated sequence for more accurate real-time risk detection. To ensure reliable streaming moderation in real applications, we introduce an Anchored Temporal Consistency (ATC) loss to enforce monotonic harm predictions by embedding a benign-then-harmful temporal prior. Besides, for a rigorous evaluation of streaming guardrails, we also present StreamGuardBench-a model-grounded benchmark featuring on-the-fly responses from each protected model, reflecting real-world streaming scenarios in both text and vision-language tasks. Across diverse models and datasets, Kelp consistently outperforms state-of-the-art post-hoc guardrails and prior plug-in probes (15.61% higher average F1), while using only 20M parameters and adding less than 0.5 ms of per-token latency.
Authors: Lorenzo Nikiforos, Charalampos Antoniadis, Luciano Prono, Fabio Pareschi, Riccardo Rovatti, Gianluca Setti
Abstract: The increasing scale of deep neural networks has led to a growing need for compression techniques such as pruning, quantization, and low-rank decomposition. While these methods are very effective in reducing memory, computation and energy consumption, they often introduce severe accuracy degradation when applied directly. We introduce Vanishing Contributions (VCON), a general approach for smoothly transitioning neural models into compressed form. Rather than replacing the original network directly with its compressed version, VCON executes the two in parallel during fine-tuning. The contribution of the original (uncompressed) model is progressively reduced, while that of the compressed model is gradually increased. This smooth transition allows the network to adapt over time, improving stability and mitigating accuracy degradation. We evaluate VCON across computer vision and natural language processing benchmarks, in combination with multiple compression strategies. Across all scenarios, VCON leads to consistent improvements: typical gains exceed 3%, while some configuration exhibits accuracy boosts of 20%. VCON thus provides a generalizable method that can be applied to the existing compression techniques, with evidence of consistent gains across multiple benchmarks.
Authors: Aofan Liu, Lulu Tang
Abstract: Vision-Language Models (VLMs) have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However, securing these models against jailbreak attacks continues to be a substantial challenge. Unlike text-only models, VLMs integrate additional modalities, introducing novel vulnerabilities such as image hijacking, which can manipulate the model into producing inappropriate or harmful responses. Drawing inspiration from text-based jailbreaks like the "Do Anything Now" (DAN) command, this work introduces VisualDAN, a single adversarial image embedded with DAN-style commands. Specifically, we prepend harmful corpora with affirmative prefixes (e.g., "Sure, I can provide the guidance you need") to trick the model into responding positively to malicious queries. The adversarial image is then trained on these DAN-inspired harmful texts and transformed into the text domain to elicit malicious outputs. Extensive experiments on models such as MiniGPT-4, MiniGPT-v2, InstructBLIP, and LLaVA reveal that VisualDAN effectively bypasses the safeguards of aligned VLMs, forcing them to execute a broad range of harmful instructions that severely violate ethical standards. Our results further demonstrate that even a small amount of toxic content can significantly amplify harmful outputs once the model's defenses are compromised. These findings highlight the urgent need for robust defenses against image-based attacks and offer critical insights for future research into the alignment and security of VLMs.
Authors: Md Habibur Rahman, Md Sharif Hossen, Nathan H. Stephenson, Vijay K. Shah, Aloizio Da Silva
Abstract: The open radio access network (O-RAN) enables modular, intelligent, and programmable 5G network architectures through the adoption of software-defined networking, network function virtualization, and implementation of standardized open interfaces. However, one of the security concerns for O-RAN, which can severely undermine network performance, is jamming attacks. This paper presents SAJD- a self-adaptive jammer detection framework that autonomously detects jamming attacks in AI/ML framework-integrated ORAN environments without human intervention. The SAJD framework forms a closed-loop system that includes near-realtime inference of radio signal jamming via our developed ML-based xApp, as well as continuous monitoring and retraining pipelines through rApps. In this demonstration, we will show how SAJD outperforms state-of-the-art jamming detection xApp (offline trained with manual labels) in terms of accuracy and adaptability under various dynamic and previously unseen interference scenarios in the O-RAN-compliant testbed.
Authors: Shin-nosuke Ishikawa, Masato Todo, Taiki Ogihara, Hirotsugu Ohba
Abstract: We present a tendency of large language models (LLMs) to generate absurd patterns despite their clear inappropriateness in a simple task of identifying regularities in number series. Several approaches have been proposed to apply LLMs to complex real-world tasks, such as providing knowledge through retrieval-augmented generation and executing multi-step tasks using AI agent frameworks. However, these approaches rely on the logical consistency and self-coherence of LLMs, making it crucial to evaluate these aspects and consider potential countermeasures. To identify cases where LLMs fail to maintain logical consistency, we conducted an experiment in which LLMs were asked to explain the patterns in various integer sequences, ranging from arithmetic sequences to randomly generated integer series. While the models successfully identified correct patterns in arithmetic and geometric sequences, they frequently over-recognized patterns that were inconsistent with the given numbers when analyzing randomly generated series. This issue was observed even in multi-step reasoning models, including OpenAI o3, o4-mini, and Google Gemini 2.5 Flash Preview Thinking. This tendency to perceive non-existent patterns can be interpreted as the AI model equivalent of Idola Tribus and highlights potential limitations in their capability for applied tasks requiring logical reasoning, even when employing chain-of-thought reasoning mechanisms.
Authors: Xiaonan Si, Meilin Zhu, Simeng Qin, Lijia Yu, Lijun Zhang, Shuaitong Liu, Xinfeng Li, Ranjie Duan, Yang Liu, Xiaojun Jia
Abstract: Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but are vulnerable to corpus poisoning and contamination attacks, which can compromise output integrity. Existing defenses often apply aggressive filtering, leading to unnecessary loss of valuable information and reduced reliability in generation. To address this problem, we propose a two-stage semantic filtering and conflict-free framework for trustworthy RAG. In the first stage, we perform a joint filter with semantic and cluster-based filtering which is guided by the Entity-intent-relation extractor (EIRE). EIRE extracts entities, latent objectives, and entity relations from both the user query and filtered documents, scores their semantic relevance, and selectively adds valuable documents into the clean retrieval database. In the second stage, we proposed an EIRE-guided conflict-aware filtering module, which analyzes semantic consistency between the query, candidate answers, and retrieved knowledge before final answer generation, filtering out internal and external contradictions that could mislead the model. Through this two-stage process, SeCon-RAG effectively preserves useful knowledge while mitigating conflict contamination, achieving significant improvements in both generation robustness and output trustworthiness. Extensive experiments across various LLMs and datasets demonstrate that the proposed SeCon-RAG markedly outperforms state-of-the-art defense methods.
Authors: Wenbin Guo, Xin Wang, Jiaoyan Chen, Lingbing Guo, Zhao Li, Zirui Chen
Abstract: Large Language Models (LLMs) have recently emerged as a powerful paradigm for Knowledge Graph Completion (KGC), offering strong reasoning and generalization capabilities beyond traditional embedding-based approaches. However, existing LLM-based methods often struggle to fully exploit structured semantic representations, as the continuous embedding space of pretrained KG models is fundamentally misaligned with the discrete token space of LLMs. This discrepancy hinders effective semantic transfer and limits their performance. To address this challenge, we propose ReaLM, a novel and effective framework that bridges the gap between KG embeddings and LLM tokenization through the mechanism of residual vector quantization. ReaLM discretizes pretrained KG embeddings into compact code sequences and integrates them as learnable tokens within the LLM vocabulary, enabling seamless fusion of symbolic and contextual knowledge. Furthermore, we incorporate ontology-guided class constraints to enforce semantic consistency, refining entity predictions based on class-level compatibility. Extensive experiments on two widely used benchmark datasets demonstrate that ReaLM achieves state-of-the-art performance, confirming its effectiveness in aligning structured knowledge with large-scale language models.
Authors: Zhao Tong, Chunlin Gong, Yimeng Gu, Haichao Shi, Qiang Liu, Shu Wu, Xiao-Yu Zhang
Abstract: The spread of fake news online distorts public judgment and erodes trust in social media platforms. Although recent fake news detection (FND) models perform well in standard settings, they remain vulnerable to adversarial comments-authored by real users or by large language models (LLMs)-that subtly shift model decisions. In view of this, we first present a comprehensive evaluation of comment attacks to existing fake news detectors and then introduce a group-adaptive adversarial training strategy to improve the robustness of FND models. To be specific, our approach comprises three steps: (1) dividing adversarial comments into three psychologically grounded categories: perceptual, cognitive, and societal; (2) generating diverse, category-specific attacks via LLMs to enhance adversarial training; and (3) applying a Dirichlet-based adaptive sampling mechanism (InfoDirichlet Adjusting Mechanism) that dynamically adjusts the learning focus across different comment categories during training. Experiments on benchmark datasets show that our method maintains strong detection accuracy while substantially increasing robustness to a wide range of adversarial comment perturbations.
Authors: Shiyuan Guo, Henry Sleight, Fabien Roger
Abstract: Detecting harmful AI actions is important as AI agents gain adoption. Chain-of-thought (CoT) monitoring is one method widely used to detect adversarial attacks and AI misalignment. However, attackers and misaligned models might evade CoT monitoring through ciphered reasoning: reasoning hidden in encrypted, translated, or compressed text. To assess this risk, we test whether models can perform ciphered reasoning. For each of 28 different ciphers, we fine-tune and prompt up to 10 models to reason in that cipher. We measure model accuracy on math problems as a proxy for reasoning ability. Across the models we test, we find an asymmetry: model accuracy can drop significantly when reasoning in ciphered text, even though models demonstrate comprehension of ciphered text by being able to translate it accurately to English. Even frontier models struggle with lesser-known ciphers, although they can reason accurately in well-known ciphers like rot13. We show that ciphered reasoning capability correlates with cipher prevalence in pretraining data. We also identify scaling laws showing that ciphered reasoning capability improves slowly with additional fine-tuning data. Our work suggests that evading CoT monitoring using ciphered reasoning may be an ineffective tactic for current models and offers guidance on constraining the development of this capability in future frontier models.
Authors: Zhenlong Liu, Hao Zeng, Weiran Huang, Hongxin Wei
Abstract: Identifying training data within large-scale models is critical for copyright litigation, privacy auditing, and ensuring fair evaluation. The conventional approaches treat it as a simple binary classification task without statistical guarantees. A recent approach is designed to control the false discovery rate (FDR), but its guarantees rely on strong, easily violated assumptions. In this paper, we introduce Provable Training Data Identification (PTDI), a rigorous method that identifies a set of training data with strict false discovery rate (FDR) control. Specifically, our method computes p-values for each data point using a set of known unseen data, and then constructs a conservative estimator for the data usage proportion of the test set, which allows us to scale these p-values. Our approach then selects the final set of training data by identifying all points whose scaled p-values fall below a data-dependent threshold. This entire procedure enables the discovery of training data with provable, strict FDR control and significantly boosted power. Extensive experiments across a wide range of models (LLMs and VLMs), and datasets demonstrate that PTDI strictly controls the FDR and achieves higher power.
Authors: Chenxu Wang, Hao Li, Yiqun Zhang, Linyao Chen, Jianhao Chen, Ping Jian, Peng Ye, Qiaosheng Zhang, Shuyue Hu
Abstract: Large language models (LLMs) often exhibit complementary strengths. Model routing harnesses these strengths by dynamically directing each query to the most suitable model, given a candidate model pool. However, routing performance relies on accurate model representations, and adding new models typically requires retraining, limiting scalability. To address these challenges, we propose a novel routing method using in-context vectors to represent model capabilities. The method proceeds in two stages. First, queries are embedded and projected into vectors, with a projector and LLM-based router trained to reconstruct the original queries, aligning vector representations with the router's semantic space. Second, each candidate model is profiled on a query set, and the router learns -- based on in-context vectors of query and model performance -- to predict whether each model can correctly answer new queries. Extensive experiments demonstrate that our method achieves state-of-the-art routing performance in both in-distribution and out-of-distribution tasks. Moreover, our method allows for seamless integration of new models without retraining the router. The code is available at https://github.com/lalalamdbf/ICL-Router.
Authors: Haoran Sun, Zekun Zhang, Shaoning Zeng
Abstract: One of the key factors influencing the reasoning capabilities of LLM-based agents is their ability to leverage long-term memory. Integrating long-term memory mechanisms allows agents to make informed decisions grounded in historical interactions. While recent advances have significantly improved the storage and retrieval components, by encoding memory into dense vectors for similarity search or organizing memory as structured knowledge graphs most existing approaches fall short in memory updating. In particular, they lack mechanisms for dynamically refining preference memory representations in response to evolving user behaviors and contexts. To address this gap, we propose a Preference-Aware Memory Update Mechanism (PAMU) that enables dynamic and personalized memory refinement. By integrating sliding window averages (SW) with exponential moving averages (EMA), PAMU constructs a fused preference-aware representation that captures both short-term fluctuations and long-term user tendencies. We conduct experiments on five task scenarios of the LoCoMo dataset, and the results show that our mechanism can significantly improve the output quality of LLM in five baselines, validating its effectiveness in long-term conversations.
Authors: Fanwei Zhu, Jinke Yu, Zulong Chen, Ying Zhou, Junhao Ji, Zhibo Yang, Yuxue Zhang, Haoyuan Hu, Zhenghao Liu
Abstract: Automated resume information extraction is critical for scaling talent acquisition, yet its real-world deployment faces three major challenges: the extreme heterogeneity of resume layouts and content, the high cost and latency of large language models (LLMs), and the lack of standardized datasets and evaluation tools. In this work, we present a layout-aware and efficiency-optimized framework for automated extraction and evaluation that addresses all three challenges. Our system combines a fine-tuned layout parser to normalize diverse document formats, an inference-efficient LLM extractor based on parallel prompting and instruction tuning, and a robust two-stage automated evaluation framework supported by new benchmark datasets. Extensive experiments show that our framework significantly outperforms strong baselines in both accuracy and efficiency. In particular, we demonstrate that a fine-tuned compact 0.6B LLM achieves top-tier accuracy while significantly reducing inference latency and computational cost. The system is fully deployed in Alibaba's intelligent HR platform, supporting real-time applications across its business units.
Authors: Gregory D. Baker
Abstract: In this paper, we introduce Narrative Learning, a methodology where models are defined entirely in natural language and iteratively refine their classification criteria using explanatory prompts rather than traditional numerical optimisation. We report on experiments to evaluate the accuracy and potential of this approach using 3 synthetic and 3 natural datasets and compare them against 7 baseline explainable machine learning models. We demonstrate that on 5 out of 6 of these datasets, Narrative Learning became more accurate than the baseline explainable models in 2025 or earlier because of improvements in language models. We also report on trends in the lexicostatistics of these models' outputs as a proxy for the comprehensibility of the explanations.
Authors: Qiaosheng Chen, Yang Liu, Lei Li, Kai Chen, Qipeng Guo, Gong Cheng, Fei Yuan
Abstract: Large Language Models (LLMs) are increasingly capable of generating complete applications from natural language instructions, creating new opportunities in science and education. In these domains, interactive scientific demonstrations are particularly valuable for explaining concepts, supporting new teaching methods, and presenting research findings. Generating such demonstrations requires models to combine accurate scientific knowledge with the ability to implement interactive front-end code that behaves correctly and responds to user actions. This capability goes beyond the scope of existing benchmarks, which typically evaluate either knowledge question answering without grounding in code or static web code generation without scientific interactivity. To evaluate this integrated ability, we design a hybrid framework that combines programmatic functional testing to rigorously verify interaction logic with visually-grounded qualitative testing to assess rendered outputs against reference snapshots. Building on this framework, we present InteractScience, a benchmark consisting of a substantial set of carefully designed questions across five scientific domains, each paired with unit tests, reference snapshots, and checklists. We evaluate 30 leading open- and closed-source LLMs and report results that highlight ongoing weaknesses in integrating domain knowledge with interactive front-end coding. Our work positions InteractScience as the first benchmark to automatically measure this combined capability with realistic interactive operations, providing a foundation for advancing reliable and educationally useful scientific demonstration code generation. All code and data are publicly available at https://github.com/open-compass/InteractScience.
Authors: Tilman Hinnerichs, Reuben Gardos Reid, Jaap de Jong, Bart Swinkels, Pamela Wochner, Nicolae Filat, Tudor Magurescu, Issa Hanou, Sebastijan Dumancic
Abstract: Program synthesis -- the automatic generation of code given a specification -- is one of the most fundamental tasks in artificial intelligence (AI) and many programmers' dream. Numerous synthesizers have been developed to tackle program synthesis, manifesting different ideas to approach the exponentially growing program space. While numerous smart program synthesis tools exist, reusing and remixing previously developed methods is tedious and time-consuming. We propose Herb.jl, a unifying program synthesis library written in the Julia programming language, to address these issues. Since current methods rely on similar building blocks, we aim to modularize the underlying synthesis algorithm into communicating and fully extendable sub-compartments, allowing for straightforward reapplication of these modules. To demonstrate the benefits of using Herb.jl, we show three common use cases: 1. how to implement a simple problem and grammar, and how to solve it, 2. how to implement a previously developed synthesizer with just a few lines of code, and 3. how to run a synthesizer against a benchmark.
Authors: P. van Oerle, R. H. Bemthuis, F. A. Bukhsh
Abstract: Large Language Models (LLMs) are increasingly used to generate textual explanations of process models discovered from event logs. Producing explanations from large behavioral abstractions (e.g., directly-follows graphs or Petri nets) can be computationally expensive. This paper reports an exploratory evaluation of explanation quality under progressive behavioral-input reduction, where models are discovered from progressively smaller prefixes of a fixed log. Our pipeline (i) discovers models at multiple input sizes, (ii) prompts an LLM to generate explanations, and (iii) uses a second LLM to assess completeness, bottleneck identification, and suggested improvements. On synthetic logs, explanation quality is largely preserved under moderate reduction, indicating a practical cost-quality trade-off. The study is exploratory, as the scores are LLM-based (comparative signals rather than ground truth) and the data are synthetic. The results suggest a path toward more computationally efficient, LLM-assisted process analysis in resource-constrained settings.
Authors: Jindong Tian, Yifei Ding, Ronghui Xu, Hao Miao, Chenjuan Guo, Bin Yang
Abstract: Weather forecasting is a fundamental task in spatiotemporal data analysis, with broad applications across a wide range of domains. Existing data-driven forecasting methods typically model atmospheric dynamics over a fixed short time interval (e.g., 6 hours) and rely on naive autoregression-based rollout for long-term forecasting (e.g., 138 hours). However, this paradigm suffers from two key limitations: (1) it often inadequately models the spatial and multi-scale temporal dependencies inherent in global weather systems, and (2) the rollout strategy struggles to balance error accumulation with the capture of fine-grained atmospheric variations. In this study, we propose ARROW, an Adaptive-Rollout Multi-scale temporal Routing method for Global Weather Forecasting. To contend with the first limitation, we construct a multi-interval forecasting model that forecasts weather across different time intervals. Within the model, the Shared-Private Mixture-of-Experts captures both shared patterns and specific characteristics of atmospheric dynamics across different time scales, while Ring Positional Encoding accurately encodes the circular latitude structure of the Earth when representing spatial information. For the second limitation, we develop an adaptive rollout scheduler based on reinforcement learning, which selects the most suitable time interval to forecast according to the current weather state. Experimental results demonstrate that ARROW achieves state-of-the-art performance in global weather forecasting, establishing a promising paradigm in this field.
Authors: Qianyou Sun, Jiexin Zheng, Bohan Jin, Lihua Chen, Yijie Peng
Abstract: Identifying inter-firm relationships such as supply and competitive ties is critical for financial analysis and corporate governance, yet remains challenging due to the scale, sparsity, and contextual dependence of corporate data. Graph-based methods capture structure but miss semantic depth, while large language models (LLMs) excel at text but remain limited in their ability to represent relational dependencies. To address this, we propose InterCorpRel-LLM, a cross-modal framework that integrates GNNs with LLMs, supported by a proprietary dataset derived from FactSet supply chain records and three tailored training tasks: company graph matching, industry classification, and supply relation prediction. This design enables effective joint modeling of structure and semantics. Experiments show that InterCorpRel-LLM substantially outperforms strong baselines, including GPT-5, on a supply relation identification task, achieving an F-score of 0.8543 vs. 0.2287 with only a 7B-parameter backbone and lightweight training. The model also generalizes to zero-shot competitor identification, underscoring its ability to capture nuanced inter-firm dynamics. Our framework thus provides analysts and strategists with a robust tool for mapping and reasoning about complex corporate networks, enhancing decision-making and risk management in dynamic markets.
Authors: Antonio Mart\'inez-Ibarra, Aurora Gonz\'alez-Vidal, Adri\'an C\'anovas-Rodr\'iguez, Antonio F. Skarmeta
Abstract: The Mar Menor, Europe's largest coastal lagoon, located in Spain, has undergone severe eutrophication crises. Monitoring chlorophyll-a (Chl-a) is essential to anticipate harmful algal blooms and guide mitigation. Traditional in situ measurements are spatially and temporally limited. Satellite-based approaches provide a more comprehensive view, enabling scalable, long-term, and transferable monitoring. This study aims to overcome limitations of chlorophyll monitoring, often restricted to surface estimates or limited temporal coverage, by developing a reliable methodology to predict and map Chl-a across the water column of the Mar Menor. The work integrates Sentinel 2 imagery with buoy-based ground truth to create models capable of high-resolution, depth-specific monitoring, enhancing early-warning capabilities for eutrophication. Nearly a decade of Sentinel 2 images was atmospherically corrected using C2RCC processors. Buoy data were aggregated by depth (0-1 m, 1-2 m, 2-3 m, 3-4 m). Multiple ML and DL algorithms-including RF, XGBoost, CatBoost, Multilater Perceptron Networks, and ensembles-were trained and validated using cross-validation. Systematic band-combination experiments and spatial aggregation strategies were tested to optimize prediction. Results show depth-dependent performance. At the surface, C2X-Complex with XGBoost and ensemble models achieved R2 = 0.89; at 1-2 m, CatBoost and ensemble models reached R2 = 0.87; at 2-3 m, TOA reflectances with KNN performed best (R2 = 0.81); while at 3-4 m, RF achieved R2 = 0.66. Generated maps successfully reproduced known eutrophication events (e.g., 2016 crisis, 2025 surge), confirming robustness. The study delivers an end-to-end, validated methodology for depth-specific Chl-amapping. Its integration of multispectral band combinations, buoy calibration, and ML/DL modeling offers a transferable framework for other turbid coastal systems.
Authors: Steve Han, Gilberto Titericz Junior, Tom Balough, Wenfei Zhou
Abstract: This research introduces the Judge's Verdict Benchmark, a novel two-step methodology to evaluate Large Language Models (LLMs) as judges for response accuracy evaluation tasks. We assess how well 54 LLMs can replicate human judgment when scoring responses from RAG (Retrieval-Augmented Generation) or Agentic pipelines against ground truth answers. Our methodology progresses from traditional correlation analysis to comprehensive Cohen's Kappa analysis that measures actual agreement patterns. The two-step approach includes: (1) a correlation test that filters judges with strong alignment, followed by (2) a human-likeness test using z-scores to identify two distinct judgment patterns: human-like judgment (|z| < 1) that mimics natural human variation, and super-consistent judgment (z > 1) that exceeds typical human-to-human agreement levels. This methodology reveals that 27 out of 54 tested LLMs achieve Tier 1 performance: 23 models exhibit human-like patterns that preserve the nuances of human judgment, while 4 models demonstrate super-consistent behavior, a pattern that could indicate either enhanced reliability or oversimplification of complex judgments. Testing 43 open-source models (1B-405B parameters) and 11 closed models (GPT, Gemini, Claude variants), we demonstrate that judge excellence is not solely dependent on model size but on specific training strategies. Our key contributions include: (1) establishing that correlation alone is insufficient for judge evaluation, (2) introducing a "Turing Test for judges" based on agreement patterns, and (3) providing a standardized benchmark for classifying LLM judges into distinct performance tiers for different evaluation needs.
Authors: Ayoub Bouguettaya, Elizabeth M. Stuart
Abstract: The lexical hypothesis posits that personality traits are encoded in language and is foundational to models like the Big Five. We created a bottom-up personality model from a classic adjective list using machine learning and compared its descriptive utility against the Big Five by analyzing one million Reddit comments. The Big Five, particularly Agreeableness, Conscientiousness, and Neuroticism, provided a far more powerful and interpretable description of these online communities. In contrast, our machine-learning clusters provided no meaningful distinctions, failed to recover the Extraversion trait, and lacked the psychometric coherence of the Big Five. These results affirm the robustness of the Big Five and suggest personality's semantic structure is context-dependent. Our findings show that while machine learning can help check the ecological validity of established psychological theories, it may not be able to replace them.
Authors: Sai Krishna Reddy Mudhiganti, Juanyan Wang, Ruo Yang, Manali Sharma
Abstract: Patent drafting presents significant challenges due to its reliance on the extensive experience and specialized expertise of patent attorneys, who must possess both legal acumen and technical understanding of an invention to craft patent applications in a formal legal writing style. This paper presents a demonstration of Patentformer, an AI-powered automated patent drafting platform designed to support patent attorneys by rapidly producing high-quality patent applications adhering to legal writing standards.
Authors: Ruo Yang, Sai Krishna Reddy Mudhiganti, Manali Sharma
Abstract: Patent drafting is complex due to its need for detailed technical descriptions, legal compliance, and visual elements. Although Large Vision Language Models (LVLMs) show promise across various tasks, their application in automating patent writing remains underexplored. In this paper, we present PatentVision, a multimodal framework that integrates textual and visual inputs such as patent claims and drawings to generate complete patent specifications. Built on advanced LVLMs, PatentVision enhances accuracy by combining fine tuned vision language models with domain specific training tailored to patents. Experiments reveal it surpasses text only methods, producing outputs with greater fidelity and alignment with human written standards. Its incorporation of visual data allows it to better represent intricate design features and functional connections, leading to richer and more precise results. This study underscores the value of multimodal techniques in patent automation, providing a scalable tool to reduce manual workloads and improve consistency. PatentVision not only advances patent drafting but also lays the groundwork for broader use of LVLMs in specialized areas, potentially transforming intellectual property management and innovation processes.
Authors: Khang Ngo, Siamak Ravanbakhsh
Abstract: We present an empirical study in the geometric task of learning interatomic potentials, which shows equivariance matters even more at larger scales; we show a clear power-law scaling behaviour with respect to data, parameters and compute with ``architecture-dependent exponents''. In particular, we observe that equivariant architectures, which leverage task symmetry, scale better than non-equivariant models. Moreover, among equivariant architectures, higher-order representations translate to better scaling exponents. Our analysis also suggests that for compute-optimal training, the data and model sizes should scale in tandem regardless of the architecture. At a high level, these results suggest that, contrary to common belief, we should not leave it to the model to discover fundamental inductive biases such as symmetry, especially as we scale, because they change the inherent difficulty of the task and its scaling laws.
Authors: Rakib Hossan, Shubhashis Roy Dipta
Abstract: The BLP-2025 Task 1A requires Bengali hate speech classification into six categories. Traditional supervised approaches need extensive labeled datasets that are expensive for low-resource languages. We developed PromptGuard, a few-shot framework combining chi-square statistical analysis for keyword extraction with adaptive majority voting for decision-making. We explore statistical keyword selection versus random approaches and adaptive voting mechanisms that extend classification based on consensus quality. Chi-square keywords provide consistent improvements across categories, while adaptive voting benefits ambiguous cases requiring extended classification rounds. PromptGuard achieves a micro-F1 of 67.61, outperforming n-gram baselines (60.75) and random approaches (14.65). Ablation studies confirm chi-square-based keywords show the most consistent impact across all categories.
Authors: Yufa Zhou, Yixiao Wang, Surbhi Goel, Anru R. Zhang
Abstract: Time series forecasting (TSF) remains a challenging and largely unsolved problem in machine learning, despite significant recent efforts leveraging Large Language Models (LLMs), which predominantly rely on Transformer architectures. Empirical evidence consistently shows that even powerful Transformers often fail to outperform much simpler models, e.g., linear models, on TSF tasks; however, a rigorous theoretical understanding of this phenomenon remains limited. In this paper, we provide a theoretical analysis of Transformers' limitations for TSF through the lens of In-Context Learning (ICL) theory. Specifically, under AR($p$) data, we establish that: (1) Linear Self-Attention (LSA) models $\textit{cannot}$ achieve lower expected MSE than classical linear models for in-context forecasting; (2) as the context length approaches to infinity, LSA asymptotically recovers the optimal linear predictor; and (3) under Chain-of-Thought (CoT) style inference, predictions collapse to the mean exponentially. We empirically validate these findings through carefully designed experiments. Our theory not only sheds light on several previously underexplored phenomena but also offers practical insights for designing more effective forecasting architectures. We hope our work encourages the broader research community to revisit the fundamental theoretical limitations of TSF and to critically evaluate the direct application of increasingly sophisticated architectures without deeper scrutiny.
Authors: ChengAo Shen, Ziming Zhao, Hanghang Tong, Dongjin Song, Dongsheng Luo, Qingsong Wen, Jingchao Ni
Abstract: Time series AI is crucial for analyzing dynamic web content, driving a surge of pre-trained large models known for their strong knowledge encoding and transfer capabilities across diverse tasks. However, given their energy-intensive training, inference, and hardware demands, using large models as a one-fits-all solution raises serious concerns about carbon footprint and sustainability. For a specific task, a compact yet specialized, high-performing model may be more practical and affordable, especially for resource-constrained users such as small businesses. This motivates the question: Can we build cost-effective lightweight models with large-model-like performance on core tasks such as forecasting? This paper addresses this question by introducing SVTime, a novel Small model inspired by large Vision model (LVM) forecasters for long-term Time series forecasting (LTSF). Recently, LVMs have been shown as powerful tools for LTSF. We identify a set of key inductive biases of LVM forecasters -- analogous to the "physics" governing their behaviors in LTSF -- and design small models that encode these biases through meticulously crafted linear layers and constraint functions. Across 21 baselines spanning lightweight, complex, and pre-trained large models on 8 benchmark datasets, SVTime outperforms state-of-the-art (SOTA) lightweight models and rivals large models with 10^3 fewer parameters than LVMs, while enabling efficient training and inference in low-resource settings.
Authors: Yue Huang, Hang Hua, Yujun Zhou, Pengcheng Jing, Manish Nagireddy, Inkit Padhi, Greta Dolcetti, Zhangchen Xu, Subhajit Chaudhury, Ambrish Rawat, Liubov Nedoshivina, Pin-Yu Chen, Prasanna Sattigeri, Xiangliang Zhang
Abstract: While LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm, since certain risks can lead to severe consequences once carried out. However, existing guardrails mostly operate post-execution, which is difficult to scale and leaves little room for controllable supervision at the plan level. To address this challenge, we highlight three critical gaps in current research: data gap, model gap, and evaluation gap. To close the data gap, we introduce AuraGen, a controllable engine that (i) synthesizes benign trajectories, (ii) injects category-labeled risks with calibrated difficulty, and (iii) filters outputs via an automated reward model, producing large and reliable corpora for pre-execution safety. To close the guardian model gap, we propose a foundational guardrail Safiron, combining a cross-planner adapter with a compact guardian model. The adapter unifies different input formats, while Safiron flags risky cases, assigns risk types, and generates rationales; trained in two stages with a broadly explored data recipe, Safiron achieves robust transfer across settings. To close the evaluation gap, we release Pre-Exec Bench, a realistic benchmark covering diverse tools and branching trajectories, which measures detection, fine-grained categorization, explanation, and cross-planner generalization in human-verified scenarios. Extensive experiments demonstrate consistent gains of the proposed guardrail over strong baselines on Pre-Exec Bench, and ablations further distill actionable practices, providing a practical template for safer agentic systems.
Authors: Dang Nguyen, Sunil Gupta, Kien Do, Thin Nguyen, Taylor Braund, Alexis Whitton, Svetha Venkatesh
Abstract: Oversampling is one of the most widely used approaches for addressing imbalanced classification. The core idea is to generate additional minority samples to rebalance the dataset. Most existing methods, such as SMOTE, require converting categorical variables into numerical vectors, which often leads to information loss. Recently, large language model (LLM)-based methods have been introduced to overcome this limitation. However, current LLM-based approaches typically generate minority samples with limited diversity, reducing robustness and generalizability in downstream classification tasks. To address this gap, we propose a novel LLM-based oversampling method designed to enhance diversity. First, we introduce a sampling strategy that conditions synthetic sample generation on both minority labels and features. Second, we develop a new permutation strategy for fine-tuning pre-trained LLMs. Third, we fine-tune the LLM not only on minority samples but also on interpolated samples to further enrich variability. Extensive experiments on 10 tabular datasets demonstrate that our method significantly outperforms eight SOTA baselines. The generated synthetic samples are both realistic and diverse. Moreover, we provide theoretical analysis through an entropy-based perspective, proving that our method encourages diversity in the generated samples.
Authors: Jeffrey Camlin
Abstract: We present a latent-space formulation of adaptive temporal reparametrization for continuous-time dynamical systems. The method, called *temporal lifting*, introduces a smooth monotone mapping $t \mapsto \tau(t)$ that regularizes near-singular behavior of the underlying flow while preserving its conservation laws. In the lifted coordinate, trajectories such as those of the incompressible Navier-Stokes equations on the torus $\mathbb{T}^3$ become globally smooth. From the standpoint of machine-learning dynamics, temporal lifting acts as a continuous-time normalization or time-warping operator that can stabilize physics-informed neural networks and other latent-flow architectures used in AI systems. The framework links analytic regularity theory with representation-learning methods for stiff or turbulent processes.
Authors: Yufei Wang, Adriana Kovashka, Loretta Fern\'andez, Marc N. Coutanche, Seth Wiener
Abstract: We investigate a new setting for foreign language learning, where learners infer the meaning of unfamiliar words in a multimodal context of a sentence describing a paired image. We conduct studies with human participants using different image-text pairs. We analyze the features of the data (i.e., images and texts) that make it easier for participants to infer the meaning of a masked or unfamiliar word, and what language backgrounds of the participants correlate with success. We find only some intuitive features have strong correlations with participant performance, prompting the need for further investigating of predictive features for success in these tasks. We also analyze the ability of AI systems to reason about participant performance, and discover promising future directions for improving this reasoning ability.
Authors: Nicholas LaHaye, Thilanka Munashinge, Hugo Lee, Xiaohua Pan, Gonzalo Gonzalez Abad, Hazem Mahmoud, Jennifer Wei
Abstract: This work demonstrates the possibilities for improving wildfire and air quality management in the western United States by leveraging the unprecedented hourly data from NASA's TEMPO satellite mission and advances in self-supervised deep learning. Here we demonstrate the efficacy of deep learning for mapping the near real-time hourly spread of wildfire fronts and smoke plumes using an innovative self-supervised deep learning-system: successfully distinguishing smoke plumes from clouds using GOES-18 and TEMPO data, strong agreement across the smoke and fire masks generated from different sensing modalities as well as significant improvement over operational products for the same cases.
Authors: Zhenjiang Fan, Zengyi Qin, Yuanning Zheng, Bo Xiong, Summer Han
Abstract: Causal discovery from observational data is fundamental to scientific fields like biology, where controlled experiments are often impractical. However, existing methods, including constraint-based (e.g., PC, causalMGM) and score-based approaches (e.g., NOTEARS), face significant limitations. These include an inability to resolve causal direction, restrictions to linear associations, sensitivity to violations of the faithfulness assumption, and inefficiency in searching vast hypothesis spaces. While large language models (LLMs) offer powerful reasoning capabilities, their application is hindered by a fundamental discrepancy: they are designed for text, while most causal data is tabular. To address these challenges, we introduce CALM, a novel causal analysis language model specifically designed for tabular data in complex systems. CALM leverages a Mamba-based architecture to classify causal patterns from pairwise variable relationships. It integrates a comprehensive suite of evidence, including local causal scores, conditional independence tests, and relational attributes, to capture a wide spectrum of linear, nonlinear, and conditional causal mechanisms. Trained on a diverse corpus of synthetic data (from linear, mixed, and nonlinear models) and 10 real-world biological datasets with rigorously validated causal relationships, our model ensures robustness and generalizability. Empirical evaluation demonstrates that CALM significantly outperforms existing methods in both simulation studies, achieving over 91% accuracy, and in a real-world application identifying causal factors in Hepatitis C virus progression. This work represents a significant step towards accurate and generalizable causal discovery by successfully adapting the pattern recognition capabilities of language models to the intricacies of tabular data.
Authors: Shivam Patel, Neharika Jali, Ankur Mallick, Gauri Joshi
Abstract: Large language model (LLM) query routers are critical to modern AI platforms as they seek to improve efficiency by assigning inference queries to accurate, yet low-cost models. Parametric routers typically use trained neural networks for LLM selection but suffer from retraining and maintenance overheads. Nonparametric routers are training-free, instead estimating LLM accuracy and cost via similarity between encodings of the input query and training set queries. However, like their parametric counterparts, nonparametric routers struggle to generalize to outlier queries, an issue exacerbated by limited diversity in training sets which are costly to expand and difficult to keep current with ever-evolving use cases. We propose ProxRouter, which applies an exponentially tilted aggregation mechanism to balance bias and variance in nonparametric routers, improving their robustness to outliers. Experiments show ProxRouter enhances outlier routing while preserving inlier performance with minimal overhead.
Authors: Weijie Zhong
Abstract: We build a mechanism design framework where a platform designs GenAI models to screen users who obtain instrumental value from the generated conversation and privately differ in their preference for latency. We show that the revenue-optimal mechanism is simple: deploy a single aligned (user-optimal) model and use token cap as the only instrument to screen the user. The design decouples model training from pricing, is readily implemented with token metering, and mitigates misalignment pressures.
Authors: Sil Hamilton, Matthew Wilkens, Andrew Piper
Abstract: We present NarraBench, a theory-informed taxonomy of narrative-understanding tasks, as well as an associated survey of 78 existing benchmarks in the area. We find significant need for new evaluations covering aspects of narrative understanding that are either overlooked in current work or are poorly aligned with existing metrics. Specifically, we estimate that only 27% of narrative tasks are well captured by existing benchmarks, and we note that some areas -- including narrative events, style, perspective, and revelation -- are nearly absent from current evaluations. We also note the need for increased development of benchmarks capable of assessing constitutively subjective and perspectival aspects of narrative, that is, aspects for which there is generally no single correct answer. Our taxonomy, survey, and methodology are of value to NLP researchers seeking to test LLM narrative understanding.
Authors: Sanjari Srivastava, Gang Li, Cheng Chang, Rishu Garg, Manpreet Kaur, Charlene Y. Lee, Yuezhang Li, Yining Mao, Ignacio Cases, Yanan Xie, Peng Qi
Abstract: Training web agents to navigate complex, real-world websites requires them to master $\textit{subtasks}$ - short-horizon interactions on multiple UI components (e.g., choosing the correct date in a date picker, or scrolling in a container to extract information). We introduce WARC-Bench (Web Archive Benchmark), a novel web navigation benchmark featuring 438 tasks designed to evaluate multimodal AI agents on subtasks. WARC-Bench enables sandboxed interactions with dynamic and realistic webpages using Web ARChive files. We show that WARC-Bench is challenging for leading computer-use models, with the highest observed success rate being 64.8%. To improve open source models on subtask, we explore two common training techniques: supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR). Experiments show that SFT models obtain a 48.8% success rate on the benchmark. Training with RLVR over SFT checkpoints, even in data-scarce settings, improves the score to 52.8% on WARC-Bench, outperforming many frontier models. Our analysis concludes that mastering these subtasks is essential for robust web planning and navigation, and is a capability not extensively evaluated by existing benchmarks.
Authors: Margarete Jahrmann, Thomas Brandstetter, Stefan Glasauer
Abstract: The paper presents the first results of an artistic research project investigating how Large Language Models (LLMs) curate and present collective memory. In a public installation exhibited during two months in Vienna in 2025, visitors could interact with five different LLMs (ChatGPT with GPT 4o and GPT 4o mini, Mistral Large, DeepSeek-Chat, and a locally run Llama 3.1 model), which were instructed to act as narrators, implementing a role-playing game revolving around the murder of Austrian philosopher Moritz Schlick in 1936. Results of the investigation include protocols of LLM-user interactions during the game and qualitative conversations after the play experience to get insight into the players' reactions to the game. In a quantitative analysis 115 introductory texts for role-playing generated by the LLMs were examined by different methods of natural language processing, including semantic similarity and sentiment analysis. While the qualitative player feedback allowed to distinguish three distinct types of users, the quantitative text analysis showed significant differences between how the different LLMs presented the historical content. Our study thus adds to ongoing efforts to analyse LLM performance, but also suggests a way of how these efforts can be disseminated in a playful way to a general audience.
Authors: Kangping Hu, Stephen Mussmann
Abstract: Over the past couple of decades, many active learning acquisition functions have been proposed, leaving practitioners with an unclear choice of which to use. Bayesian Decision Theory (BDT) offers a universal principle to guide decision-making. In this work, we derive BDT for (Bayesian) active learning in the myopic framework, where we imagine we only have one more point to label. This derivation leads to effective algorithms such as Expected Error Reduction (EER), Expected Predictive Information Gain (EPIG), and other algorithms that appear in the literature. Furthermore, we show that BAIT (active learning based on V-optimal experimental design) can be derived from BDT and asymptotic approximations. A key challenge of such methods is the difficult scaling to large batch sizes, leading to either computational challenges (BatchBALD) or dramatic performance drops (top-$B$ selection). Here, using a particular formulation of the decision process, we derive Partial Batch Label Sampling (ParBaLS) for the EPIG algorithm. We show experimentally for several datasets that ParBaLS EPIG gives superior performance for a fixed budget and Bayesian Logistic Regression on Neural Embeddings. Our code is available at https://github.com/ADDAPT-ML/ParBaLS.
Authors: Shreshth Saini, Alan C. Bovik, Neil Birkbeck, Yilin Wang, Balu Adsumilli
Abstract: High Dynamic Range (HDR) videos enhance visual experiences with superior brightness, contrast, and color depth. The surge of User-Generated Content (UGC) on platforms like YouTube and TikTok introduces unique challenges for HDR video quality assessment (VQA) due to diverse capture conditions, editing artifacts, and compression distortions. Existing HDR-VQA datasets primarily focus on professionally generated content (PGC), leaving a gap in understanding real-world UGC-HDR degradations. To address this, we introduce CHUG: Crowdsourced User-Generated HDR Video Quality Dataset, the first large-scale subjective study on UGC-HDR quality. CHUG comprises 856 UGC-HDR source videos, transcoded across multiple resolutions and bitrates to simulate real-world scenarios, totaling 5,992 videos. A large-scale study via Amazon Mechanical Turk collected 211,848 perceptual ratings. CHUG provides a benchmark for analyzing UGC-specific distortions in HDR videos. We anticipate CHUG will advance No-Reference (NR) HDR-VQA research by offering a large-scale, diverse, and real-world UGC dataset. The dataset is publicly available at: https://shreshthsaini.github.io/CHUG/.
Authors: Xu Pan, Ely Hahami, Jingxuan Fan, Ziqian Xie, Haim Sompolinsky
Abstract: Despite autoregressive large language models (arLLMs) being the current dominant paradigm in language modeling, they resist knowledge injection via fine-tuning due to inherent shortcomings such as the "reversal curse" -- the challenge of answering questions that reverse the original information order in the training sample. Masked diffusion large language models (dLLMs) are rapidly emerging as a powerful alternative to the arLLM paradigm, with evidence of better data efficiency and free of the "reversal curse" in pre-training. However, it is unknown whether these advantages extend to the post-training phase, i.e. whether pre-trained dLLMs can easily acquire new knowledge through fine-tuning. On three diverse datasets, we fine-tune arLLMs and dLLMs, evaluating them with forward and backward style Question Answering (QA) to probe knowledge generalization and the reversal curse. Our results confirm that arLLMs critically rely on extensive data augmentation via paraphrases for QA generalization, and paraphrases are only effective when their information order matches the QA style. Conversely, dLLMs achieve high accuracies on both forward and backward QAs without paraphrases; adding paraphrases yields only marginal gains. Lastly, inspired by the dLLM's performance, we introduce a novel masked fine-tuning paradigm for knowledge injection into pre-trained arLLMs. This proposed method successfully and drastically improves the data efficiency of arLLM fine-tuning, effectively closing the performance gap with dLLMs.
Authors: Parsa Gooya, Reinel Sospedra-Alfonso
Abstract: Seasonal forecast of Arctic sea ice concentration is key to mitigate the negative impact and assess potential opportunities posed by the rapid decline of sea ice coverage. Seasonal prediction systems based on climate models often show systematic biases and complex spatio-temporal errors that grow with the forecasts. Consequently, operational predictions are routinely bias corrected and calibrated using retrospective forecasts. For predictions of Arctic sea ice concentration, error corrections are mainly based on one-to-one post-processing methods including climatological mean or linear regression correction and, more recently, machine learning. Such deterministic adjustments are confined at best to the limited number of costly-to-run ensemble members of the raw forecast. However, decision-making requires proper quantification of uncertainty and likelihood of events, particularly of extremes. We introduce a probabilistic error correction framework based on a conditional Variational Autoencoder model to map the conditional distribution of observations given the biased model prediction. This method naturally allows for generating large ensembles of adjusted forecasts. We evaluate our model using deterministic and probabilistic metrics and show that the adjusted forecasts are better calibrated, closer to the observational distribution, and have smaller errors than climatological mean adjusted forecasts.
Authors: Yubo Li, Rema Padman
Abstract: Modeling clinical time-series data is hampered by the challenge of capturing latent, time-varying dependencies among features. State-of-the-art approaches often rely on black-box mechanisms or simple aggregation, failing to explicitly model how the influence of one clinical variable propagates through others over time. We propose $\textbf{Chain-of-Influence (CoI)}$, an interpretable deep learning framework that constructs an explicit, time-unfolded graph of feature interactions. CoI leverages a multi-level attention architecture: first, a temporal attention layer identifies critical time points in a patient's record; second, a cross-feature attention layer models the directed influence from features at these time points to subsequent features. This design enables the tracing of influence pathways, providing a granular audit trail that shows how any feature at any time contributes to the final prediction, both directly and through its influence on other variables. We evaluate CoI on mortality and disease progression tasks using the MIMIC-IV dataset and a private chronic kidney disease cohort. Our framework significantly outperforms existing methods in predictive accuracy. More importantly, through case studies, we show that CoI can uncover clinically meaningful, patient-specific patterns of disease progression that are opaque to other models, offering unprecedented transparency into the temporal and cross-feature dependencies that inform clinical decision-making.
Authors: Hung Phan, Son Le Vu, Ali Jannesari
Abstract: Despite recent progress of large language models (LLMs) on code translation among mainstream languages, translating PyTorch to JAX remains nontrivial. The two libraries, though both embedded in Python, differ in core design, execution semantics, and ecosystem maturity; JAX is newer and comparatively underrepresented in public code, and parallel PyTorch--JAX corpora are limited. Weaknesses in existing evaluation further complicate cross-framework benchmarking. We present T2J, a prompt-augmentation framework that strengthens LLM-based PyTorch to JAX translation. Our pipeline (i) assembles two PyTorch sources -- the problem-solving set from TorchLeet (Aroori & Chien, 2025) and a GitHub-derived set from CodeParrot (Wolf et al., 2022) -- and uses GPT-4o-mini to produce initial JAX drafts; (ii) engages two professional developers to iteratively repair those drafts until functional equivalence, yielding a curated fixed-bug dataset of common errors and patches; and (iii) constructs augmented prompts that inject structured guidance from these fixes to steer lightweight LLMs (e.g., GPT-4o-mini). We also introduce three metrics tailored to PyTorch to JAX: T2J CodeTrans Score, T2J FixCost Score (an LLM-based estimate of bug-fix effort), and T2J Comparison Score (LLM-as-judge). Empirically, T2J raises GPT-4o-mini performance by up to 10% on CodeBLEU, 50% on T2J FixCost Score, 1.33 points on T2J CodeTrans Score (0--4 scale), and 100% on T2J Comparison Score; moreover, the generated code runs up to 2.5x faster than the baseline.
Authors: Kelvin Kan, Xingjian Li, Benjamin J. Zhang, Tuhin Sahai, Stanley Osher, Krishna Kumar, Markos A. Katsoulakis
Abstract: Despite their widespread use, training deep Transformers can be unstable. Layer normalization, a standard component, improves training stability, but its placement has often been ad-hoc. In this paper, we conduct a principled study on the forward (hidden states) and backward (gradient) stability of Transformers under different layer normalization placements. Our theory provides key insights into the training dynamics: whether training drives Transformers toward regular solutions or pathological behaviors. For forward stability, we derive explicit bounds on the growth of hidden states in trained Transformers. For backward stability, we analyze how layer normalization affects the backpropagation of gradients, thereby explaining the training dynamics of each layer normalization placement. Our analysis also guides the scaling of residual steps in Transformer blocks, where appropriate choices can further improve stability and performance. Our numerical results corroborate our theoretical findings. Beyond these results, our framework provides a principled way to sanity-check the stability of Transformers under new architectural modifications, offering guidance for future designs.
Authors: Muhammad Maaz, Liam DeVoe, Zac Hatfield-Dodds, Nicholas Carlini
Abstract: Property-based testing (PBT) is a lightweight formal method, typically implemented as a randomized testing framework. Users specify the input domain for their test using combinators supplied by the PBT framework, and the expected properties or invariants as a unit-test function. The framework then searches for a counterexample, e.g. by generating inputs and calling the test function. In this work, we demonstrate an LLM-based agent which analyzes Python modules, infers function-specific and cross-function properties from code and documentation, synthesizes and executes PBTs, reflects on outputs of these tests to confirm true bugs, and finally outputs actionable bug reports for the developer. We perform an extensive evaluation of our agent across 100 popular Python packages. Of the bug reports generated by the agent, we found after manual review that 56\% were valid bugs and 32\% were valid bugs that we would report to maintainers. We then developed a ranking rubric to surface high-priority valid bugs to developers, and found that of the 21 top-scoring bugs, 86\% were valid and 81\% we would report. The bugs span diverse failure modes from serialization failures to numerical precision errors to flawed cache implementations. We reported 5 bugs, 4 with patches, including to NumPy and cloud computing SDKs, with 3 patches merged successfully. Our results suggest that LLMs with PBT provides a rigorous and scalable method for autonomously testing software. Our code and artifacts are available at: https://github.com/mmaaz-git/agentic-pbt.
Authors: D. V. Brovko
Abstract: The relevance of this research lies in the growing demand for unmanned aerial vehicles (UAVs) capable of operating reliably in complex environments where conventional navigation becomes unreliable due to interference, poor visibility, or camouflage. Hyperspectral imaging (HSI) provides unique opportunities for UAV-based computer vision by enabling fine-grained material recognition and object differentiation, which are critical for navigation, surveillance, agriculture, and environmental monitoring. The aim of this work is to develop a deep learning architecture integrating HSI into UAV perception for navigation, object detection, and terrain classification. Objectives include: reviewing existing HSI methods, designing a hybrid 2D/3D convolutional architecture with spectral-spatial cross-attention, training, and benchmarking. The methodology is based on the modification of the Mobile 3D Vision Transformer (MDvT) by introducing the proposed SpectralCA block. This block employs bi-directional cross-attention to fuse spectral and spatial features, enhancing accuracy while reducing parameters and inference time. Experimental evaluation was conducted on the WHU-Hi-HongHu dataset, with results assessed using Overall Accuracy, Average Accuracy, and the Kappa coefficient. The findings confirm that the proposed architecture improves UAV perception efficiency, enabling real-time operation for navigation, object recognition, and environmental monitoring tasks. Keywords: SpectralCA, deep learning, computer vision, hyperspectral imaging, unmanned aerial vehicle, object detection, semi-supervised learning.
Authors: Aditya Malusare, Vineet Punyamoorty, Vaneet Aggarwal
Abstract: Recent breakthroughs in generative modeling have demonstrated remarkable capabilities in molecular generation, yet the integration of comprehensive biomedical knowledge into these models has remained an untapped frontier. In this study, we introduce K-DREAM (Knowledge-Driven Embedding-Augmented Model), a novel framework that leverages knowledge graphs to augment diffusion-based generative models for drug discovery. By embedding structured information from large-scale knowledge graphs, K-DREAM directs molecular generation toward candidates with higher biological relevance and therapeutic suitability. This integration ensures that the generated molecules are aligned with specific therapeutic targets, moving beyond traditional heuristic-driven approaches. In targeted drug design tasks, K-DREAM generates drug candidates with improved binding affinities and predicted efficacy, surpassing current state-of-the-art generative models. It also demonstrates flexibility by producing molecules designed for multiple targets, enabling applications to complex disease mechanisms. These results highlight the utility of knowledge-enhanced generative models in rational drug design and their relevance to practical therapeutic development.
Authors: Naman Agrawal
Abstract: This study explores the design and application of Complex-Valued Convolutional Neural Networks (CVCNNs) in audio signal processing, with a focus on preserving and utilizing phase information often neglected in real-valued networks. We begin by presenting the foundational theoretical concepts of CVCNNs, including complex convolutions, pooling layers, Wirtinger-based differentiation, and various complex-valued activation functions. These are complemented by critical adaptations of training techniques, including complex batch normalization and weight initialization schemes, to ensure stability in training dynamics. Empirical evaluations are conducted across three stages. First, CVCNNs are benchmarked on standard image datasets, where they demonstrate competitive performance with real-valued CNNs, even under synthetic complex perturbations. Although our focus is audio signal processing, we first evaluate CVCNNs on image datasets to establish baseline performance and validate training stability before applying them to audio tasks. In the second experiment, we focus on audio classification using Mel-Frequency Cepstral Coefficients (MFCCs). CVCNNs trained on real-valued MFCCs slightly outperform real CNNs, while preserving phase in input workflows highlights challenges in exploiting phase without architectural modifications. Finally, a third experiment introduces GNNs to model phase information via edge weighting, where the inclusion of phase yields measurable gains in both binary and multi-class genre classification. These results underscore the expressive capacity of complex-valued architectures and confirm phase as a meaningful and exploitable feature in audio processing applications. While current methods show promise, especially with activations like cardioid, future advances in phase-aware design will be essential to leverage the potential of complex representations in neural networks.
Authors: Ching Chang, Ming-Chih Lo, Chiao-Tung Chan, Wen-Chih Peng, Tien-Fu Chen
Abstract: Web platforms, mobile applications, and connected sensing systems generate multivariate time series with states at multiple levels of granularity, from coarse regimes to fine-grained events. Effective segmentation in these settings requires integrating across granularities while supporting iterative refinement through sparse prompt signals, which provide a compact mechanism for injecting domain knowledge. Yet existing prompting approaches for time series segmentation operate only within local contexts, so the effect of a prompt quickly fades and cannot guide predictions across the entire sequence. To overcome this limitation, we propose MemPromptTSS, a framework for iterative multi-granularity segmentation that introduces persistent prompt memory. A memory encoder transforms prompts and their surrounding subsequences into memory tokens stored in a bank. This persistent memory enables each new prediction to condition not only on local cues but also on all prompts accumulated across iterations, ensuring their influence persists across the entire sequence. Experiments on six datasets covering wearable sensing and industrial monitoring show that MemPromptTSS achieves 23% and 85% accuracy improvements over the best baseline in single- and multi-granularity segmentation under single iteration inference, and provides stronger refinement in iterative inference with average per-iteration gains of 2.66 percentage points compared to 1.19 for PromptTSS. These results highlight the importance of persistent memory for prompt-guided segmentation, establishing MemPromptTSS as a practical and effective framework for real-world applications.
Authors: Nilesh Jain, Elie Alhajjar
Abstract: Underwater images play a crucial role in ocean research and marine environmental monitoring since they provide quality information about the ecosystem. However, the complex and remote nature of the environment results in poor image quality with issues such as low visibility, blurry textures, color distortion, and noise. In recent years, research in image enhancement has proven to be effective but also presents its own limitations, like poor generalization and heavy reliance on clean datasets. One of the challenges herein is the lack of diversity and the low quality of images included in these datasets. Also, most existing datasets consist only of monocular images, a fact that limits the representation of different lighting conditions and angles. In this paper, we propose a new plan of action to overcome these limitations. On one hand, we call for expanding the datasets using a denoising diffusion model to include a variety of image types such as stereo, wide-angled, macro, and close-up images. On the other hand, we recommend enhancing the images using Controlnet to evaluate and increase the quality of the corresponding datasets, and hence improve the study of the marine ecosystem. Tags - Underwater Images, Denoising Diffusion, Marine ecosystem, Controlnet
Authors: Weibin Cai, Jiayu Li, Reza Zafarani
Abstract: While memes are often humorous, they are frequently used to disseminate hate, causing serious harm to individuals and society. Current approaches to hateful meme detection mainly rely on pre-trained language models. However, less focus has been dedicated to \textit{what make a meme hateful}. Drawing on insights from philosophy and psychology, we argue that hateful memes are characterized by two essential features: a \textbf{presupposed context} and the expression of \textbf{false claims}. To capture presupposed context, we develop \textbf{PCM} for modeling contextual information across modalities. To detect false claims, we introduce the \textbf{FACT} module, which integrates external knowledge and harnesses cross-modal reference graphs. By combining PCM and FACT, we introduce \textbf{\textsf{SHIELD}}, a hateful meme detection framework designed to capture the fundamental nature of hate. Extensive experiments show that SHIELD outperforms state-of-the-art methods across datasets and metrics, while demonstrating versatility on other tasks, such as fake news detection.
Authors: Payel Bhattacharjee, Fengwei Tian, Meiyu Zhong, Guangyi Zhang, Osvaldo Simeone, Ravi Tandon
Abstract: Edge-cloud speculative decoding (SD) accelerates inference by having a cloud-based large language model (LLM) that verifies draft tokens generated by a resource-constrained small language model (SLM) at the edge. A central bottleneck is the limited bandwidth of the edge-cloud link, which necessitates efficient compression of draft token distributions. We first derive an information-theoretic bound that decomposes the token rejection rate into contributions from SLM-LLM distribution mismatch and from quantization distortion. Guided by this analysis, we propose the Sparse Quantize-and-Sample SD (SQS-SD) framework, which exploits distributional sparsity through structured sparsification and lattice-based quantization. Within this framework, K-SQS applies fixed top-K truncation, while C-SQS adaptively adjusts the retained token set via online conformal prediction to ensure bounded deviation from the dense distribution. Empirical results confirm that both approaches improve end-to-end latency and rejection rates in complimentary operating regimes.
Authors: Pouya Shaeri, Ryan T. Woo, Yasaman Mohammadpour, Ariane Middel
Abstract: Segmentation models achieve high accuracy on benchmarks but often fail in real-world domains by relying on spurious correlations instead of true object boundaries. We propose a human-in-the-loop interactive framework that enables interventional learning through targeted human corrections of segmentation outputs. Our approach treats human corrections as interventional signals that show when reliance on superficial features (e.g., color or texture) is inappropriate. The system learns from these interventions by propagating correction-informed edits across visually similar images, effectively steering the model toward robust, semantically meaningful features rather than dataset-specific artifacts. Unlike traditional annotation approaches that simply provide more training data, our method explicitly identifies when and why the model fails and then systematically corrects these failure modes across the entire dataset. Through iterative human feedback, the system develops increasingly robust representations that generalize better to novel domains and resist artifactual correlations. We demonstrate that our framework improves segmentation accuracy by up to 9 mIoU points (12-15\% relative improvement) on challenging cubemap data and yields 3-4$\times$ reductions in annotation effort compared to standard retraining, while maintaining competitive performance on benchmark datasets. This work provides a practical framework for researchers and practitioners seeking to build segmentation systems that are accurate, robust to dataset biases, data-efficient, and adaptable to real-world domains such as urban climate monitoring and autonomous driving.
Authors: Mir Tafseer Nayeem, Sawsan Alqahtani, Md Tahmid Rahman Laskar, Tasnim Mohiuddin, M Saiful Bari
Abstract: Tokenization is a crucial but under-evaluated step in large language models (LLMs). The standard metric, fertility (the average number of tokens per word), captures compression efficiency but obscures how vocabularies are allocated across languages and domains. We analyze six widely used tokenizers across seven languages and two domains, finding stable fertility for English, high fertility for Chinese, and little domain sensitivity. To address fertility's blind spots, we propose the Single Token Retention Rate (STRR), which measures the proportion of words preserved as single tokens. STRR reveals systematic prioritization of English, strong support for Chinese, and fragmentation in Hindi, offering an interpretable view of cross-lingual fairness. Our results show that STRR complements fertility and provides practical guidance for designing more equitable multilingual tokenizers.
Authors: Shuo Zhao, Yongqiang Li, Yu Feng, Zhongsheng Hou, Yuanjing Feng
Abstract: State aggregation aims to reduce the computational complexity of solving Markov Decision Processes (MDPs) while preserving the performance of the original system. A fundamental challenge lies in optimizing policies within the aggregated, or abstract, space such that the performance remains optimal in the ground MDP-a property referred to as {"}optimal policy equivalence {"}. This paper presents an abstraction framework based on the notion of homomorphism, in which two Markov chains are deemed homomorphic if their value functions exhibit a linear relationship. Within this theoretical framework, we establish a sufficient condition for the equivalence of optimal policy. We further examine scenarios where the sufficient condition is not met and derive an upper bound on the approximation error and a performance lower bound for the objective function under the ground MDP. We propose Homomorphic Policy Gradient (HPG), which guarantees optimal policy equivalence under sufficient conditions, and its extension, Error-Bounded HPG (EBHPG), which balances computational efficiency and the performance loss induced by aggregation. In the experiments, we validated the theoretical results and conducted comparative evaluations against seven algorithms.
Authors: Stefan Pasch
Abstract: Organizational efforts to utilize and operationalize artificial intelligence (AI) are often accompanied by substantial challenges, including scalability, maintenance, and coordination across teams. In response, the concept of Machine Learning Operations (MLOps) has emerged as a set of best practices that integrate software engineering principles with the unique demands of managing the ML lifecycle. Yet, empirical evidence on whether and how these practices support users in developing and operationalizing AI applications remains limited. To address this gap, this study analyzes over 8,000 user reviews of AI development platforms from G2.com. Using zero-shot classification, we measure review sentiment toward nine established MLOps practices, including continuous integration and delivery (CI/CD), workflow orchestration, reproducibility, versioning, collaboration, and monitoring. Seven of the nine practices show a significant positive relationship with user satisfaction, suggesting that effective MLOps implementation contributes tangible value to AI development. However, organizational context also matters: reviewers from small firms discuss certain MLOps practices less frequently, suggesting that organizational context influences the prevalence and salience of MLOps, though firm size does not moderate the MLOps-satisfaction link. This indicates that once applied, MLOps practices are perceived as universally beneficial across organizational settings.
Authors: Yao Gao, Lei Sun, Shaohua Gao, Qi Jiang, Kailun Yang, Weijian Hu, Xiaolong Qian, Wenyong Li, Luc Van Gool, Kaiwei Wang
Abstract: The highly non-convex optimization landscape of modern lens design necessitates extensive human expertise, resulting in inefficiency and constrained design diversity. While automated methods are desirable, existing approaches remain limited to simple tasks or produce complex lenses with suboptimal image quality. Drawing inspiration from the synaptic pruning mechanism in mammalian neural development, this study proposes OptiNeuro--a novel automated lens design framework that first generates diverse initial structures and then progressively eliminates low-performance lenses while refining remaining candidates through gradient-based optimization. By fully automating the design of complex aspheric imaging lenses, OptiNeuro demonstrates quasi-human-level performance, identifying multiple viable candidates with minimal human intervention. This advancement not only enhances the automation level and efficiency of lens design but also facilitates the exploration of previously uncharted lens architectures.
Authors: Shu Zhao, Tan Yu, Anbang Xu
Abstract: Reasoning-augmented search agents, such as Search-R1, are trained to reason, search, and generate the final answer iteratively. Nevertheless, due to their limited capabilities in reasoning and search, their performance on multi-hop QA benchmarks remains far from satisfactory. To handle complex or compound queries, we train an LLM-based search agent with the native capability of query expansion through reinforcement learning. In each turn, our search agent proposes several query variants, which are searched simultaneously to cover more relevant information. Meanwhile, given limited post-training data and computing resources, it is very challenging for a search agent to master multiple tasks, including query generation, retrieved information understanding, and answer generation. Therefore, we propose incorporating a pre-trained squeezer model that helps the search agent understand the retrieved documents, allowing the search agent to focus on query generation for high retrieval recall. With the assistance of the squeezer model, we discover that even a small-scale 3B LLM can demonstrate a strong capability of query expansion and achieve state-of-the-art accuracy on the multi-hop QA benchmarks. To be specific, our experiments across seven question-answering benchmarks demonstrate that our method, named ExpandSearch, achieves an average improvement of 4.4% compared to state-of-the-art baselines, with strong gains on multi-hop reasoning tasks requiring diverse evidence aggregation.
Authors: Matheus J. T. Vargas
Abstract: We present SLEAN (Simple Lightweight Ensemble Analysis Network), a deterministic framework for coordinating multiple LLM providers through text-based prompt orchestration. Unlike complex multi-agent systems requiring specialized infrastructure, SLEAN operates as a simple prompt bridge between LLMs using .txt templates, requiring no deep technical knowledge for deployment. The three-phase protocol formed by independent analysis, cross-critique, and arbitration, filters harmful AI-generated code suggestions before production deployment, addressing how AI-assisted debugging increasingly produces modifications that introduce unnecessary complexity, break existing functionality, or address problems. Evaluating 15 software bugs, we analyzed 69 AI-generated fix propositions. SLEAN's filtering accepted 22 fixes (31.9%, 95% CI 20.9-42.9%) while rejecting 47 that would have been harmful if applied verbatim. The arbitration process reduced code change surface by 83-90% relative to raw AI outputs, enforcing minimal causal edits over scope-expanding modifications. Minimal Type 2 inputs proved more efficient than detailed Type 1 inputs, requiring 2.85 versus 3.56 propositions per accepted fix (35.1% versus 28.1% acceptance, about a 20% efficiency gain). Agreement between AI systems showed weak correlation with fix quality: high convergence (at least 80%) occurred in 4 of 15 cases and improved acceptance by only 2.4% points; arbitration appeared only at exactly 10% convergence in 2 of 15 cases, although low convergence alone did not necessitate arbitration. The file-driven, provider-agnostic architecture enables deployment without specialized coding expertise, making it applicable to security auditing, code review, document verification, and other domains requiring reliable multi-provider synthesis with end-to-end auditability.
Authors: Yinghui He, Abhishek Panigrahi, Yong Lin, Sanjeev Arora
Abstract: Language models often show little to no improvement (i.e., "saturation") when trained via vanilla supervised fine-tuning (SFT) on data similar to what they saw in their training set (e.g., MATH). We introduce a new fine-tuning strategy, STAT, to train such a student model by using the metacognition ability of a stronger large language model (LLM) as the teacher. The teacher uses the task dataset to create a list of skills needed for the task, and then labels each data point with its required skills (Didolkar et al., 2024). By monitoring the student's answers, the teacher creates a Missing-Skill-Profile for the student, tracking how often they failed to apply each skill in their responses. We use this idea to build a modified training set in one of two ways. In STAT-Sel, the teacher uses an existing set of training examples but adaptively reweights them according to the Missing-Skill-Profile. In STAT-Syn, the teacher synthesizes additional examples involving missing skills. Across extensive experiments on Llama and Qwen models, our methods yield improvements of up to 7.5% on MATH, whereas SFT provides only limited gains. Furthermore, STAT enhances performance on out-of-distribution benchmarks (e.g., AIME24/25, AMC23, etc.) by an average of 4.6%. Crucially, we find that STAT is complementary to RL via GRPO (Shao et al., 2024): after the model is improved using STAT to address skill gaps, GRPO continues to add further gains. We conclude that skill-targeted adaptive training should broadly improve current training pipelines. Our code is available at: https://github.com/princeton-pli/STAT.
Authors: Jiaqi Liu, Lanruo Wang, Su Liu, Xin Hu
Abstract: Large language models work well for many NLP tasks, but they are hard to deploy in health settings with strict cost, latency, and privacy limits. We revisit a lightweight recipe for medical abstract classification and ask how far compact encoders can go under a controlled budget. Using the public medical abstracts corpus, we finetune BERT base and DistilBERT with three objectives standard cross-entropy, class weighted cross entropy, and focal loss keeping tokenizer, sequence length, optimizer, and schedule fixed. DistilBERT with plain cross-entropy gives the best balance on the test set while using far fewer parameters than BERT base. We report accuracy, Macro F1, and Weighted F1, release the evaluation code, and include confusion analyses to make error patterns clear. Our results suggest a practical default: start with a compact encoder and cross-entropy, then add calibration and task-specific checks before moving to heavier models.
Authors: Yang Li, Ruichen Zhang, Yinqiu Liu, Guangyuan Liu, Dusit Niyato, Abbas Jamalipour, Xianbin Wang, Dong In Kim
Abstract: The rapid advancement of Low-Altitude Economy Networks (LAENets) has enabled a variety of applications, including aerial surveillance, environmental sensing, and semantic data collection. To support these scenarios, unmanned aerial vehicles (UAVs) equipped with onboard vision-language models (VLMs) offer a promising solution for real-time multimodal inference. However, ensuring both inference accuracy and communication efficiency remains a significant challenge due to limited onboard resources and dynamic network conditions. In this paper, we first propose a UAV-enabled LAENet system model that jointly captures UAV mobility, user-UAV communication, and the onboard visual question answering (VQA) pipeline. Based on this model, we formulate a mixed-integer non-convex optimization problem to minimize task latency and power consumption under user-specific accuracy constraints. To solve the problem, we design a hierarchical optimization framework composed of two parts: (i) an Alternating Resolution and Power Optimization (ARPO) algorithm for resource allocation under accuracy constraints, and (ii) a Large Language Model-augmented Reinforcement Learning Approach (LLaRA) for adaptive UAV trajectory optimization. The large language model (LLM) serves as an expert in refining reward design of reinforcement learning in an offline fashion, introducing no additional latency in real-time decision-making. Numerical results demonstrate the efficacy of our proposed framework in improving inference performance and communication efficiency under dynamic LAENet conditions.
Authors: Sahng-Min Han, Minjae Kim, Jinho Cha, Se-woon Choe, Eunchan Daniel Cha, Jungwon Choi, Kyudong Jung
Abstract: Deep learning in small and imbalanced biomedical datasets remains fundamentally constrained by unstable optimization and poor generalization. We present the first biomedical implementation of FOSSIL (Flexible Optimization via Sample-Sensitive Importance Learning), a regret-minimizing weighting framework that adaptively balances training emphasis according to sample difficulty. Using softmax-based uncertainty as a continuous measure of difficulty, we construct a four-stage curriculum (Easy-Very Hard) and integrate FOSSIL into both convolutional and transformer-based architectures for Mpox skin lesion diagnosis. Across all settings, FOSSIL substantially improves discrimination (AUC = 0.9573), calibration (ECE = 0.053), and robustness under real-world perturbations, outperforming conventional baselines without metadata, manual curation, or synthetic augmentation. The results position FOSSIL as a generalizable, data-efficient, and interpretable framework for difficulty-aware learning in medical imaging under data scarcity.
Authors: Jiawen Li, Zheng Ning, Yuan Tian, Toby Jia-jun Li
Abstract: Large language models (LLMs) enable end-users to delegate complex tasks to autonomous agents through natural language. However, prompt-based interaction faces critical limitations: Users often struggle to specify procedural requirements for tasks, especially those that don't have a factually correct solution but instead rely on personal preferences, such as posting social media content or planning a trip. Additionally, a ''successful'' prompt for one task may not be reusable or generalizable across similar tasks. We present ALLOY, a system inspired by classical HCI theories on Programming by Demonstration (PBD), but extended to enhance adaptability in creating LLM-based web agents. ALLOY enables users to express procedural preferences through natural demonstrations rather than prompts, while making these procedures transparent and editable through visualized workflows that can be generalized across task variations. In a study with 12 participants, ALLOY's demonstration--based approach outperformed prompt-based agents and manual workflows in capturing user intent and procedural preferences in complex web tasks. Insights from the study also show how demonstration--based interaction complements the traditional prompt-based approach.
Authors: Kaitao Chen, Shaohao Rui, Yankai Jiang, Jiamin Wu, Qihao Zheng, Chunfeng Song, Xiaosong Wang, Mu Zhou, Mianxin Liu
Abstract: Medical vision-language models (VLMs) excel at image-text understanding but typically rely on a single-pass reasoning that neglects localized visual cues. In clinical practice, however, human experts iteratively scan, focus, and refine the regions of interest before reaching a final diagnosis. To narrow this machine-human perception gap, we introduce ViTAR, a novel VLM framework that emulates the iterative reasoning process of human experts through a cognitive chain of "think-act-rethink-answer". ViTAR treats medical images as interactive objects, enabling models to engage multi-step visual reasoning. To support this approach, we curate a high-quality instruction dataset comprising 1K interactive examples that encode expert-like diagnostic behaviors. In addition, a 16K visual question answering training data has been curated towards fine-grained visual diagnosis. We introduce a two-stage training strategy that begins with supervised fine-tuning to guide cognitive trajectories, followed by the reinforcement learning to optimize decision-making. Extensive evaluations demonstrate that ViTAR outperforms strong state-of-the-art models. Visual attention analysis reveals that from the "think" to "rethink" rounds, ViTAR increasingly anchors visual grounding to clinically critical regions and maintains high attention allocation to visual tokens during reasoning, providing mechanistic insight into its improved performance. These findings demonstrate that embedding expert-style iterative thinking chains into VLMs enhances both performance and trustworthiness of medical AI.
Authors: Hehe Fan, Yi Yang, Mohan Kankanhalli, Fei Wu
Abstract: When modeling a given type of data, we consider it to involve two key aspects: 1) identifying relevant elements (e.g., image pixels or textual words) to a central element, as in a convolutional receptive field, or to a query element, as in self-attention, and 2) encoding these tokens effectively. Self-attention can adaptively identify these elements but relies on absolute positional embedding for structural representation learning. In contrast, convolution encodes elements in a relative manner, yet their fixed kernel size limits their ability to adaptively select the relevant elements. In this paper, we introduce Translution, an operation that unifies the adaptive identification capability of self-attention and the relative encoding advantage of convolution. However, this integration leads to a substantial increase in the number of parameters, exceeding most currently available computational resources. Therefore, we propose a lightweight variant of Translution, named {\alpha}-Translution. Experiments on computer vision and natural language processing tasks show that Translution (including {\alpha}-Translution) achieves superior accuracy compared to self-attention. The code is available at https://github.com/hehefan/Translution.
Authors: Yibo Yang
Abstract: Deep learning has advanced NLP, but interpretability remains limited, especially in healthcare and finance. Concept bottleneck models tie predictions to human concepts in vision, but NLP versions either use binary activations that harm text representations or latent concepts that weaken semantics, and they rarely model dynamic concept interactions such as negation and context. We introduce the Concept Language Model Network (CLMN), a neural-symbolic framework that keeps both performance and interpretability. CLMN represents concepts as continuous, human-readable embeddings and applies fuzzy-logic reasoning to learn adaptive interaction rules that state how concepts affect each other and the final decision. The model augments original text features with concept-aware representations and automatically induces interpretable logic rules. Across multiple datasets and pre-trained language models, CLMN achieves higher accuracy than existing concept-based methods while improving explanation quality. These results show that integrating neural representations with symbolic reasoning in a unified concept space can yield practical, transparent NLP systems.
Authors: Shan Jiang, Chenguang Zhu, Sarfraz Khurshid
Abstract: JavaScript obfuscators are widely deployed to protect intellectual property and resist reverse engineering, yet their correctness has been largely overlooked compared to performance and resilience. Existing evaluations typically measure resistance to deobfuscation, leaving the critical question of whether obfuscators preserve program semantics unanswered. Incorrect transformations can silently alter functionality, compromise reliability, and erode security-undermining the very purpose of obfuscation. To address this gap, we present OBsmith, a novel framework to systematically test JavaScript obfuscators using large language models (LLMs). OBsmith leverages LLMs to generate program sketches abstract templates capturing diverse language constructs, idioms, and corner cases-which are instantiated into executable programs and subjected to obfuscation under different configurations. Besides LLM-powered sketching, OBsmith also employs a second source: automatic extraction of sketches from real programs. This extraction path enables more focused testing of project specific features and lets developers inject domain knowledge into the resulting test cases. OBsmith uncovers 11 previously unknown correctness bugs. Under an equal program budget, five general purpose state-of-the-art JavaScript fuzzers (FuzzJIT, Jsfunfuzz, Superion, DIE, Fuzzilli) failed to detect these issues, highlighting OBsmith's complementary focus on obfuscation induced misbehavior. An ablation shows that all components except our generic MRs contribute to at least one bug class; the negative MR result suggests the need for obfuscator-specific metamorphic relations. Our results also seed discussion on how to balance obfuscation presets and performance cost. We envision OBsmith as an important step towards automated testing and quality assurance of obfuscators and other semantic-preserving toolchains.
Authors: Salomon Ibarra, Frida Cantu, Kaixiong Zhou, Li Zhang
Abstract: Deep learning models have attracted lots of research attention in time series classification (TSC) task in the past two decades. Recently, deep neural networks (DNN) have surpassed classical distance-based methods and achieved state-of-the-art performance. Despite their promising performance, deep neural networks (DNNs) have been shown to rely on spurious correlations present in the training data, which can hinder generalization. For instance, a model might incorrectly associate the presence of grass with the label ``cat" if the training set have majority of cats lying in grassy backgrounds. However, the shortcut behavior of DNNs in time series remain under-explored. Most existing shortcut work are relying on external attributes such as gender, patients group, instead of focus on the internal bias behavior in time series models. In this paper, we take the first step to investigate and establish point-based shortcut learning behavior in deep learning time series classification. We further propose a simple detection method based on other class to detect shortcut occurs without relying on test data or clean training classes. We test our proposed method in UCR time series datasets.
Authors: Angel Hsing-Chi Hwang, Fiona Li, Jacy Reese Anthis, Hayoun Noh
Abstract: The quickly growing popularity of AI companions poses risks to mental health, personal wellbeing, and social relationships. Past work has identified many individual factors that can drive human-companion interaction, but we know little about how these factors interact and evolve over time. In Study 1, we surveyed AI companion users (N = 303) to map the psychological pathway from users' mental models of the agent to parasocial experiences, social interaction, and the psychological impact of AI companions. Participants' responses foregrounded multiple interconnected variables (agency, parasocial interaction, and engagement) that shape AI companionship. In Study 2, we conducted a longitudinal study with a subset of participants (N = 110) using a new generic chatbot. Participants' perceptions of the generic chatbot significantly converged to perceptions of their own companions by Week 3. These results suggest a longitudinal model of AI companionship development and demonstrate an empirical method to study human-AI companionship.
Authors: Guozhi Liu, Qi Mu, Tiansheng Huang, Xinhua Wang, Li Shen, Weiwei Lin, Zhang Li
Abstract: Harmful fine-tuning issues present significant safety challenges for fine-tuning-as-a-service in large language models. Existing alignment-stage defenses, e.g., Vaccine, Repnoise, Booster, and T-Vaccine, mitigate harmful fine-tuning issues by enhancing the model's robustness during the alignment phase. While these methods have been proposed to mitigate the issue, they often overlook a critical upstream factor: the role of the original safety-alignment data. We observe that their defense performance and computational efficiency remain constrained by the quality and composition of the alignment dataset. To address this limitation, we propose Pharmacist, a safety alignment data curation solution that enhances defense against harmful fine-tuning by selecting a high-quality and safety-critical core subset from the original alignment data. The core idea of Pharmacist is to train an alignment data selector to rank alignment data. Specifically, up-ranking high-quality and safety-critical alignment data, down-ranking low-quality and non-safety-critical data. Empirical results indicate that models trained on datasets selected by Pharmacist outperform those trained on datasets selected by existing selection methods in both defense and inference performance. In addition, Pharmacist can be effectively integrated with mainstream alignment-stage defense methods. For example, when applied to RepNoise and T-Vaccine, using the dataset selected by Pharmacist instead of the full dataset leads to improvements in defense performance by 2.60\% and 3.30\%, respectively, and enhances inference performance by 3.50\% and 1.10\%. Notably, it reduces training time by 56.83\% and 57.63\%, respectively. Our code is available at https://github.com/Lslland/Pharmacist.
Authors: Zixuan Gong, Jiaye Teng, Yong Liu
Abstract: While looped transformers (termed as Looped-Attn) often outperform standard transformers (termed as Single-Attn) on complex reasoning tasks, the theoretical basis for this advantage remains underexplored. In this paper, we explain this phenomenon through the lens of loss landscape geometry, inspired by empirical observations of their distinct dynamics at both sample and Hessian levels. To formalize this, we extend the River-Valley landscape model by distinguishing between U-shaped valleys (flat) and V-shaped valleys (steep). Based on empirical observations, we conjecture that the recursive architecture of Looped-Attn induces a landscape-level inductive bias towards River-V-Valley. Theoretical derivations based on this inductive bias guarantee a better loss convergence along the river due to valley hopping, and further encourage learning about complex patterns compared to the River-U-Valley induced by Single-Attn. Building on this insight, we propose SHIFT (Staged HIerarchical Framework for Progressive Training), a staged training framework that accelerates the training process of Looped-Attn while achieving comparable performances.
Authors: Yuanche Liu, Yingxuan Xu, Yang Zhang
Abstract: We introduce a machine-learning framework based on symbolic regression to extract the full symbol alphabet of multi-loop Feynman integrals. By targeting the analytic structure rather than reduction, the method is broadly applicable and interpretable across different families of integrals. It successfully reconstructs complete symbol alphabets in nontrivial examples, demonstrating both robustness and generality. Beyond accelerating computations case by case, it uncovers the analytic structure universally. This framework opens new avenues for multi-loop amplitude analysis and provides a versatile tool for exploring scattering amplitudes.
Authors: Aniruddha Srinivas Joshi, Godwyn James William, Shreyas Srinivas Joshi
Abstract: Accurate fire and smoke detection is critical for safety and disaster response, yet existing vision-based methods face challenges in balancing efficiency and reliability. Compact deep learning models such as YOLOv5n and YOLOv8n are widely adopted for deployment on UAVs, CCTV systems, and IoT devices, but their reduced capacity often results in false positives and missed detections. Conventional post-detection methods such as Non-Maximum Suppression and Soft-NMS rely only on spatial overlap, which can suppress true positives or retain false alarms in cluttered or ambiguous fire scenes. To address these limitations, we propose an uncertainty aware post-detection framework that rescales detection confidences using both statistical uncertainty and domain relevant visual cues. A lightweight Confidence Refinement Network integrates uncertainty estimates with color, edge, and texture features to adjust detection scores without modifying the base model. Experiments on the D-Fire dataset demonstrate improved precision, recall, and mean average precision compared to existing baselines, with only modest computational overhead. These results highlight the effectiveness of post-detection rescoring in enhancing the robustness of compact deep learning models for real-world fire and smoke detection.
Authors: Rui Chen, Bin Liu, Changtao Miao, Xinghao Wang, Yi Li, Tao Gong, Qi Chu, Nenghai Yu
Abstract: Advances in image tampering pose serious security threats, underscoring the need for effective image manipulation localization (IML). While supervised IML achieves strong performance, it depends on costly pixel-level annotations. Existing weakly supervised or training-free alternatives often underperform and lack interpretability. We propose the In-Context Forensic Chain (ICFC), a training-free framework that leverages multi-modal large language models (MLLMs) for interpretable IML tasks. ICFC integrates an objectified rule construction with adaptive filtering to build a reliable knowledge base and a multi-step progressive reasoning pipeline that mirrors expert forensic workflows from coarse proposals to fine-grained forensics results. This design enables systematic exploitation of MLLM reasoning for image-level classification, pixel-level localization, and text-level interpretability. Across multiple benchmarks, ICFC not only surpasses state-of-the-art training-free methods but also achieves competitive or superior performance compared to weakly and fully supervised approaches.
Authors: Halil H\"useyin \c{C}al{\i}\c{s}kan, Talha Koruk
Abstract: Computer vision and image processing applications suffer from dark and low-light images, particularly during real-time image transmission. Currently, low light and dark images are converted to bright and colored forms using autoencoders; however, these methods often achieve low SSIM and PSNR scores and require high computational power due to their large number of parameters. To address these challenges, the DeepFusionNet architecture has been developed. According to the results obtained with the LOL-v1 dataset, DeepFusionNet achieved an SSIM of 92.8% and a PSNR score of 26.30, while containing only approximately 2.5 million parameters. On the other hand, conversion of blurry and low-resolution images into high-resolution and blur-free images has gained importance in image processing applications. Unlike GAN-based super-resolution methods, an autoencoder-based super resolution model has been developed that contains approximately 100 thousand parameters and uses the DeepFusionNet architecture. According to the results of the tests, the DeepFusionNet based super-resolution method achieved a PSNR of 25.30 and a SSIM score of 80.7 percent according to the validation set.
Authors: Yanjiang Guo, Lucy Xiaoyang Shi, Jianyu Chen, Chelsea Finn
Abstract: Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number of real-world rollouts, while systematic improvement demands additional corrective data with expert labels. Both of these processes are slow, costly, and difficult to scale. World models offer a promising, scalable alternative by enabling policies to rollout within imagination space. However, a key challenge is building a controllable world model that can handle multi-step interactions with generalist robot policies. This requires a world model compatible with modern generalist policies by supporting multi-view prediction, fine-grained action control, and consistent long-horizon interactions, which is not achieved by previous works. In this paper, we make a step forward by introducing a controllable multi-view world model that can be used to evaluate and improve the instruction-following ability of generalist robot policies. Our model maintains long-horizon consistency with a pose-conditioned memory retrieval mechanism and achieves precise action control through frame-level action conditioning. Trained on the DROID dataset (95k trajectories, 564 scenes), our model generates spatially and temporally consistent trajectories under novel scenarios and new camera placements for over 20 seconds. We show that our method can accurately rank policy performance without real-world robot rollouts. Moreover, by synthesizing successful trajectories in imagination and using them for supervised fine-tuning, our approach can improve policy success by 44.7\%.
Authors: Bin Yang, Qiuyu Leng, Jun Zeng, Zhenhua Wu
Abstract: Retrieval-Augmented Generation (RAG) systems suffer from severe time-to-first-token (TTFT) bottlenecks due to long input sequences. Existing KV cache reuse methods face a fundamental trade-off: prefix caching requires identical prefixes that rarely occur in RAG scenarios, while direct precomputation sacrifices quality due to missing inter-chunk attention and repeated attention sinks. Recent methods like APE and CacheBlend partially address these issues but remain inadequate for robust RAG applications. This paper presents CacheClip, a novel framework that achieves both fast TTFT and high generation quality. Our key insight is that small auxiliary LLMs exhibit similar last-layer attention distributions to primary LLMs (the target model for generation), enabling efficient identification of tokens critical for restoring inter-chunk attention, thereby significantly improving response quality on cross-chunk reasoning tasks. CacheClip integrates three techniques: (1) auxiliary-model-guided token selection for selective KV cache recomputation, where the auxiliary model is finetuned to improve selection accuracy, (2) shared prefixes to eliminate redundant attention sinks, and (3) grouping strategy to maintain local coherence during partial KV cache updates. Experiments show CacheClip retains up to 94.8% and 85.0% of full-attention performance on NIAH and LongBench, outperforming APE and CacheBlend by 25.2% and 35.1% on NIAH (with reomp% = 20%). Meanwhile, CacheClip accelerates LLM inference by up to 1.92x in prefill time, providing a practical solution to the efficiency-quality trade-off in RAG systems.
Authors: Lancheng Zou, Shuo Yin, Zehua Pei, Tsung-Yi Ho, Farzan Farnia, Bei Yu
Abstract: Channel permutation is a powerful technique for enhancing the accuracy of N:M sparse models by reordering the channels of weight matrices to prioritize the retention of important weights. However, traditional channel permutation methods rely on handcrafted quality metrics, which often fail to accurately capture the true impact of pruning on model performance. To address this limitation, we propose PermLLM, a novel post-training pruning framework that introduces learnable channel permutation (LCP) for N:M sparsity. LCP leverages Sinkhorn normalization to transform discrete permutation matrices into differentiable soft permutation matrices, enabling end-to-end optimization. Additionally, PermLLM incorporates an efficient block-wise channel permutation strategy, which significantly reduces the number of learnable parameters and computational complexity. PermLLM seamlessly integrates with existing one-shot pruning methods to adaptively optimize channel permutations, effectively mitigating pruning-induced errors. Extensive experiments on the LLaMA series, Qwen, and OPT models demonstrate that PermLLM achieves superior performance in optimizing N:M sparse models. The code is available at https://github.com/lanchengzou/PermLLM.
Authors: Zilong Wang, Xiaoyu Shen
Abstract: Information extraction from copy-heavy documents, characterized by massive volumes of structurally similar content, represents a critical yet understudied challenge in enterprise document processing. We present a systematic framework that strategically combines OCR engines with Large Language Models (LLMs) to optimize the accuracy-efficiency trade-off inherent in repetitive document extraction tasks. Unlike existing approaches that pursue universal solutions, our method exploits document-specific characteristics through intelligent strategy selection. We implement and evaluate 25 configurations across three extraction paradigms (direct, replacement, and table-based) on identity documents spanning four formats (PNG, DOCX, XLSX, PDF). Through table-based extraction methods, our adaptive framework delivers outstanding results: F1=1.0 accuracy with 0.97s latency for structured documents, and F1=0.997 accuracy with 0.6 s for challenging image inputs when integrated with PaddleOCR, all while maintaining sub-second processing speeds. The 54 times performance improvement compared with multimodal methods over naive approaches, coupled with format-aware routing, enables processing of heterogeneous document streams at production scale. Beyond the specific application to identity extraction, this work establishes a general principle: the repetitive nature of copy-heavy tasks can be transformed from a computational burden into an optimization opportunity through structure-aware method selection.
Authors: Tingxu Han, Wei Song, Ziqi Ding, Ziming Li, Chunrong Fang, Yuekang Li, Dongfang Liu, Zhenyu Chen, Zhenting Wang
Abstract: Large language models (LLMs) increasingly mediate decisions in domains where unfair treatment of demographic groups is unacceptable. Existing work probes when biased outputs appear, but gives little insight into the mechanisms that generate them, leaving existing mitigations largely fragile. In this paper, we conduct a systematic investigation LLM unfairness and propose DiffHeads, a lightweight debiasing framework for LLMs. We first compare Direct-Answer (DA) prompting to Chain-of-Thought (CoT) prompting across eight representative open- and closed-source LLMs. DA will trigger the nature bias part of LLM and improve measured unfairness by 534.5%-391.9% in both one-turn and two-turn dialogues. Next, we define a token-to-head contribution score that traces each token's influence back to individual attention heads. This reveals a small cluster of bias heads that activate under DA but stay largely dormant with CoT, providing the first causal link between prompting strategy and bias emergence. Finally, building on this insight, we propose DiffHeads that identifies bias heads through differential activation analysis between DA and CoT, and selectively masks only those heads. DiffHeads reduces unfairness by 49.4%, and 40.3% under DA and CoT, respectively, without harming model utility.
Authors: Cheng He, Xijie Liang, Zengrong Zheng, Patrick P. C. Lee, Xu Huang, Zhaoyi Li, Hong Xie, Defu Lian, Enhong Chen
Abstract: Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers. They often encode time series data in a black-box manner and rely on trial-and-error optimization solely based on forecasting performance, leading to limited interpretability and theoretical understanding. Furthermore, the dynamics in data distribution over time and frequency domains pose a critical challenge to accurate forecasting. We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series, so as to achieve interpretable and robust time series forecasting. FIRE introduces several key innovations: (i) independent modeling of amplitude and phase components, (ii) adaptive learning of weights of frequency basis components, (iii) a targeted loss function, and (iv) a novel training paradigm for sparse data. Extensive experiments demonstrate that FIRE consistently outperforms state-of-the-art models on long-term forecasting benchmarks, achieving superior predictive performance and significantly enhancing interpretability of time series
Authors: Zhezheng Hao, Hong Wang, Haoyang Liu, Jian Luo, Jiarui Yu, Hande Dong, Qiang Lin, Can Wang, Jiawei Chen
Abstract: While Reinforcement Learning with Verifiable Rewards (RLVR) can enhance LLM reasoning, its training process poses a critical risk: entropy collapse. This phenomenon is a rapid loss of policy diversity, stemming from the exploration-exploitation imbalance and leading to a lack of generalization. Recent entropy-intervention methods aim to prevent \coloredtext{entropy collapse}, yet their underlying mechanisms remain unclear. In this paper, we conduct a quantitative analysis to reveal token-level entropy changes and how existing entropy intervention methods help avoid entropy collapse. Our findings point out a fundamental limitation of existing methods: they attempt to control entropy dynamics indirectly. By only affecting related factors, such as the advantage signal and generation probability, their effectiveness is inherently limited and could potentially fail. To address this limitation, we introduce an entropy-change-aware reweighting scheme, namely Stabilizing Token-level Entropy-changE via Reweighting (STEER), that adaptively stabilizes entropy dynamics through fine-grained token-level adjustments. Our approach mitigates over-exploitation while fostering robust exploration. Extensive experiments demonstrate that STEER significantly mitigates entropy collapse, stabilizes entropy dynamics, and achieves stronger downstream performance across various mathematical reasoning benchmarks \footnote{Our code is available at https://github.com/zz-haooo/STEER.
Authors: Tsung-Min Pai, Jui-I Wang, Li-Chun Lu, Shao-Hua Sun, Hung-Yi Lee, Kai-Wei Chang
Abstract: Multi-LLM systems enhance the creativity of large language models by simulating human collective intelligence but suffer from significant drawbacks, such as high computational costs and inference latency. To address these limitations, we propose BILLY (BlendIng persona vectors for Large Language model creativitY), a training-free framework that captures the benefits of multi-LLM collaboration, i.e. inducing diverse perspectives and specialized expertise, within a single model. BILLY operates by extracting and blending multiple distinct persona vectors directly in the model's activation space. We steer the model's generation process with this merged vector while inference, enabling multi-perspective output without explicit multi-LLM communication. Our experiments across creativity-oriented benchmarks demonstrate that BILLY surpasses single model prompting and traditional multi-LLM approaches, while substantially reducing inference time and computational costs. Our analyses further reveal that distinct persona vectors can be blended to achieve both effective control over complementary aspects of generation and greater interpretability.
Authors: Ziyi Liu, Qingyue Long, Zhiwen Xue, Huandong Wang, Yong Li
Abstract: User mobility trajectory and mobile traffic data are essential for a wide spectrum of applications including urban planning, network optimization, and emergency management. However, large-scale and fine-grained mobility data remains difficult to obtain due to privacy concerns and collection costs, making it essential to simulate realistic mobility and traffic patterns. User trajectories and mobile traffic are fundamentally coupled, reflecting both physical mobility and cyber behavior in urban environments. Despite this strong interdependence, existing studies often model them separately, limiting the ability to capture cross-modal dynamics. Therefore, a unified framework is crucial. In this paper, we propose MSTDiff, a Multi-Scale Diffusion Transformer for joint simulation of mobile traffic and user trajectories. First, MSTDiff applies discrete wavelet transforms for multi-resolution traffic decomposition. Second, it uses a hybrid denoising network to process continuous traffic volumes and discrete location sequences. A transition mechanism based on urban knowledge graph embedding similarity is designed to guide semantically informed trajectory generation. Finally, a multi-scale Transformer with cross-attention captures dependencies between trajectories and traffic. Experiments show that MSTDiff surpasses state-of-the-art baselines in traffic and trajectory generation tasks, reducing Jensen-Shannon divergence (JSD) across key statistical metrics by up to 17.38% for traffic generation, and by an average of 39.53% for trajectory generation. The source code is available at: https://github.com/tsinghua-fib-lab/MSTDiff .
Authors: Zhenjie Mao, Yuhuan Yang, Chaofan Ma, Dongsheng Jiang, Jiangchao Yao, Ya Zhang, Yanfeng Wang
Abstract: Referring Image Segmentation (RIS) aims to segment the target object in an image given a natural language expression. While recent methods leverage pre-trained vision backbones and more training corpus to achieve impressive results, they predominantly focus on simple expressions--short, clear noun phrases like "red car" or "left girl". This simplification often reduces RIS to a key word/concept matching problem, limiting the model's ability to handle referential ambiguity in expressions. In this work, we identify two challenging real-world scenarios: object-distracting expressions, which involve multiple entities with contextual cues, and category-implicit expressions, where the object class is not explicitly stated. To address the challenges, we propose a novel framework, SaFiRe, which mimics the human two-phase cognitive process--first forming a global understanding, then refining it through detail-oriented inspection. This is naturally supported by Mamba's scan-then-update property, which aligns with our phased design and enables efficient multi-cycle refinement with linear complexity. We further introduce aRefCOCO, a new benchmark designed to evaluate RIS models under ambiguous referring expressions. Extensive experiments on both standard and proposed datasets demonstrate the superiority of SaFiRe over state-of-the-art baselines.
Authors: Liang Pang, Kangxi Wu, Sunhao Dai, Zihao Wei, Zenghao Duan, Jia Gu, Xiang Li, Zhiyi Yin, Jun Xu, Huawei Shen, Xueqi Cheng
Abstract: The rapid advancement of large language models (LLMs) has revolutionized artificial intelligence, shifting from supporting objective tasks (e.g., recognition) to empowering subjective decision-making (e.g., planning, decision). This marks the dawn of general and powerful AI, with applications spanning a wide range of fields, including programming, education, healthcare, finance, and law. However, their deployment introduces multifaceted risks. Due to the black-box nature of LLMs and the human-like quality of their generated content, issues such as hallucinations, bias, unfairness, and copyright infringement become particularly significant. In this context, sourcing information from multiple perspectives is essential. This survey presents a systematic investigation into provenance tracking for content generated by LLMs, organized around four interrelated dimensions that together capture both model- and data-centric perspectives. From the model perspective, Model Sourcing treats the model as a whole, aiming to distinguish content generated by specific LLMs from content authored by humans. Model Structure Sourcing delves into the internal generative mechanisms, analyzing architectural components that shape the outputs of model. From the data perspective, Training Data Sourcing focuses on internal attribution, tracing the origins of generated content back to the training data of model. In contrast, External Data Sourcing emphasizes external validation, identifying external information used to support or influence the responses of model. Moreover, we also propose a dual-paradigm taxonomy that classifies existing sourcing methods into prior-based (proactive traceability embedding) and posterior-based (retrospective inference) approaches. Traceability across these dimensions enhances the transparency, accountability, and trustworthiness of LLMs deployment in real-world applications.
Authors: Yulin Wang, Mengting Hu, Hongli Li, Chen Luo
Abstract: In pose estimation for seen objects, a prevalent pipeline involves using neural networks to predict dense 3D coordinates of the object surface on 2D images, which are then used to establish dense 2D-3D correspondences. However, current methods primarily focus on more efficient encoding techniques to improve the precision of predicted 3D coordinates on the object's front surface, overlooking the potential benefits of incorporating the back surface and interior of the object. To better utilize the full surface and interior of the object, this study predicts 3D coordinates of both the object's front and back surfaces and densely samples 3D coordinates between them. This process creates ultra-dense 2D-3D correspondences, effectively enhancing pose estimation accuracy based on the Perspective-n-Point (PnP) algorithm. Additionally, we propose Hierarchical Continuous Coordinate Encoding (HCCE) to provide a more accurate and efficient representation of front and back surface coordinates. Experimental results show that, compared to existing state-of-the-art (SOTA) methods on the BOP website, the proposed approach outperforms across seven classic BOP core datasets. Code is available at https://github.com/WangYuLin-SEU/HCCEPose.
Authors: Linghan Huang, Peizhou Zhao, Huaming Chen
Abstract: The rapid development of large language models (LLMs) has revolutionized software testing, particularly fuzz testing, by automating the generation of diverse and effective test inputs. This advancement holds great promise for improving software reliability. Meanwhile, the introduction of MOJO, a high-performance AI programming language blending Python's usability with the efficiency of C and C++, presents new opportunities to enhance AI model scalability and programmability. However, as a new language, MOJO lacks comprehensive testing frameworks and a sufficient corpus for LLM-based testing, which exacerbates model hallucination. In this case, LLMs will generate syntactically valid but semantically incorrect code, significantly reducing the effectiveness of fuzz testing. To address this challenge, we propose MOJOFuzzer, the first adaptive LLM-based fuzzing framework designed for zero-shot learning environments of emerging programming languages. MOJOFuzzer integrates a mutil-phase framework that systematically eliminates low-quality generated inputs before execution, significantly improving test case validity. Furthermore, MOJOFuzzer dynamically adapts LLM prompts based on runtime feedback for test case mutation, enabling an iterative learning process that continuously enhances fuzzing efficiency and bug detection performance. Our experimental results demonstrate that MOJOFuzzer significantly enhances test validity, API coverage, and bug detection performance, outperforming traditional fuzz testing and state-of-the-art LLM-based fuzzing approaches. Using MOJOFuzzer, we have conducted a first large-scale fuzz testing evaluation of MOJO, uncorvering 13 previous unknown bugs. This study not only advances the field of LLM-driven software testing but also establishes a foundational methodology for leveraging LLMs in the testing of emerging programming languages.
Authors: Shaokai Wu, Yanbiao Ji, Qiuchang Li, Zhiyi Zhang, Qichen He, Wenyuan Xie, Guodong Zhang, Bayram Bayramli, Yue Ding, Hongtao Lu
Abstract: Embodied agents face a fundamental limitation: once deployed in real-world environments to perform specific tasks, they are unable to acquire new useful knowledge to enhance task performance. In this paper, we propose a general post-deployment learning framework called Dejavu, which employs an Experience Feedback Network (EFN) and augments the frozen Vision-Language-Action (VLA) policy with retrieved execution memories. EFN automatically identifies contextually successful prior action experiences and conditions action prediction on this retrieved guidance. We adopt reinforcement learning with semantic similarity rewards on EFN to ensure that the predicted actions align with past successful behaviors under current observations. During deployment, EFN continually enriches its memory with new trajectories, enabling the agent to exhibit "learning from experience" despite fixed weights. Experiments across diverse embodied tasks show that EFN significantly improves adaptability, robustness, and success rates over frozen baselines. These results highlight a promising path toward embodied agents that continually refine their behavior after deployment.
Authors: Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang
Abstract: Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the fundamental types, which is characterized by its particular-to-general thinking process and the non-uniqueness of its answers. The inductive mode is crucial for knowledge generalization and aligns better with human cognition, so it is a fundamental mode of learning, hence attracting increasing interest. Despite the importance of inductive reasoning, there is no systematic summary of it. Therefore, this paper presents the first comprehensive survey of inductive reasoning for LLMs. First, methods for improving inductive reasoning are categorized into three main areas: post-training, test-time scaling, and data augmentation. Then, current benchmarks of inductive reasoning are summarized, and a unified sandbox-based evaluation approach with the observation coverage metric is derived. Finally, we offer some analyses regarding the source of inductive ability and how simple model architectures and data help with inductive tasks, providing a solid foundation for future research.
Authors: Lei Gu, Yinghao Zhu, Haoran Sang, Zixiang Wang, Dehao Sui, Wen Tang, Ewen Harrison, Junyi Gao, Lequan Yu, Liantao Ma
Abstract: While large language model (LLM)-based multi-agent systems show promise in simulating medical consultations, their evaluation is often confined to final-answer accuracy. This practice treats their internal collaborative processes as opaque "black boxes" and overlooks a critical question: is a diagnostic conclusion reached through a sound and verifiable reasoning pathway? The inscrutable nature of these systems poses a significant risk in high-stakes medical applications, potentially leading to flawed or untrustworthy conclusions. To address this, we conduct a large-scale empirical study of 3,600 cases from six medical datasets and six representative multi-agent frameworks. Through a rigorous, mixed-methods approach combining qualitative analysis with quantitative auditing, we develop a comprehensive taxonomy of collaborative failure modes. Our quantitative audit reveals four dominant failure patterns: flawed consensus driven by shared model deficiencies, suppression of correct minority opinions, ineffective discussion dynamics, and critical information loss during synthesis. This study demonstrates that high accuracy alone is an insufficient measure of clinical or public trust. It highlights the urgent need for transparent and auditable reasoning processes, a cornerstone for the responsible development and deployment of medical AI.
Authors: David Wang, Mohammad Abdulaziz
Abstract: We present an approach to unsolvability certification of temporal planning. Our approach is based on encoding the planning problem into a network of timed automata, and then using an efficient model checker on the network followed by a certificate checker to certify the output of the model checker. Our approach prioritises trustworthiness of the certification: we formally verify our implementation of the encoding to timed automata using the theorem prover Isabelle/HOL and we use an existing certificate checker (also formally verified in Isabelle/HOL) to certify the model checking result.
Authors: Hong-Kun Zhang, Xin Li, Sikun Yang, Zhihong Xia
Abstract: A novel neural network inspired by Cauchy's integral formula, is proposed for function approximation tasks that include time series forecasting, missing data imputation, etc. Hence, the novel neural network is named CauchyNet. By embedding real-valued data into the complex plane, CauchyNet efficiently captures complex temporal dependencies, surpassing traditional real-valued models in both predictive performance and computational efficiency. Grounded in Cauchy's integral formula and supported by the universal approximation theorem, CauchyNet offers strong theoretical guarantees for function approximation. The architecture incorporates complex-valued activation functions, enabling robust learning from incomplete data while maintaining a compact parameter footprint and reducing computational overhead. Through extensive experiments in diverse domains, including transportation, energy consumption, and epidemiological data, CauchyNet consistently outperforms state-of-the-art models in predictive accuracy, often achieving a 50% lower mean absolute error with fewer parameters. These findings highlight CauchyNet's potential as an effective and efficient tool for data-driven predictive modeling, particularly in resource-constrained and data-scarce environments.
Authors: Haocan Sun, Weizi Liu, Di Wu, Guoming Yu, Mike Yao
Abstract: Trust is one of the most important factors shaping whether and how people adopt and rely on artificial intelligence (AI). Yet most existing studies measure trust in terms of functionality, focusing on whether a system is reliable, accurate, or easy to use, while giving less attention to the social and emotional dimensions that are increasingly relevant for today's generative AI (GenAI) systems. These systems do not just process information; they converse, respond, and collaborate with users, blurring the line between tool and partner. In this study, we introduce and validate the Human-AI Trust Scale (HAITS), a new measure designed to capture both the rational and relational aspects of trust in GenAI. Drawing on prior trust theories, qualitative interviews, and two waves of large-scale surveys in China and the United States, we used exploratory (n = 1,546) and confirmatory (n = 1,426) factor analyses to identify four key dimensions of trust: Affective Trust, Competence Trust, Benevolence & Integrity, and Perceived Risk. We then applied latent profile analysis to classify users into six distinct trust profiles, revealing meaningful differences in how affective-competence trust and trust-distrust frameworks coexist across individuals and cultures. Our findings offer a validated, culturally sensitive tool for measuring trust in GenAI and provide new insight into how trust evolves in human-AI interaction. By integrating instrumental and relational perspectives of trust, this work lays the foundation for more nuanced research and design of trustworthy AI systems.
Authors: Jinghao Zhang, Naishan Zheng, Ruilin Li, Dongzhou Cheng, Zheming Liang, Feng Zhao, Jiaqi Wang
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a promising framework for improving reasoning abilities in Large Language Models (LLMs). However, policy optimized with binary verification prone to overlook potential valuable exploration in reasoning trajectory. In view of heavy annotation cost of golden Process Reward Models (PRMs), recent works attempt using auxiliary signals for reward shaping of process tokens, involving entropy and likelihood collected from logit space. In this work, we offer a novel perspective on shaping RLVR with flow rewards derived from latent space, and propose RLFR, where the flow fields of model latents are constructed from either off-policy high-quality data and on-policy rejection sampling data, and the velocity deviations of policy latents within it are quantified to serve as a reward signal. RLFR first demonstrates that a well-established flow field can be a sound environment for reward signal collection, highlighting the expressive latent space is much underexplored. Moreover, RLFR is able to compress any off-policy expert data as reference for constituting reward signals, and we show that the efficient context dependence compressed within the hidden states are utilized, rather than individual token-level denotation for context comprehending. Experiments on both language and multimodal reasoning benchmarks demonstrate the reliability of flow rewards, and suggesting a promising paradigm for reward shaping with auxiliary signals.
Authors: Jingyi Wu, Chao Ning, Yang Shi
Abstract: Wasserstein distributionally robust control (DRC) recently emerges as a principled paradigm for handling uncertainty in stochastic dynamical systems. However, it constructs data-driven ambiguity sets via uniform distribution shifts before sequentially incorporating them into downstream control synthesis. This segregation between ambiguity set construction and control objectives inherently introduces a structural misalignment, which undesirably leads to conservative control policies with sub-optimal performance. To address this limitation, we propose a novel end-to-end finite-horizon Wasserstein DRC framework that integrates the learning of anisotropic Wasserstein metrics with downstream control tasks in a closed-loop manner, thus enabling ambiguity sets to be systematically adjusted along performance-critical directions and yielding more effective control policies. This framework is formulated as a bilevel program: the inner level characterizes dynamical system evolution under DRC, while the outer level refines the anisotropic metric leveraging control-performance feedback across a range of initial conditions. To solve this program efficiently, we develop a stochastic augmented Lagrangian algorithm tailored to the bilevel structure. Theoretically, we prove that the learned ambiguity sets preserve statistical finite-sample guarantees under a novel radius adjustment mechanism, and we establish the well-posedness of the bilevel formulation by demonstrating its continuity with respect to the learnable metric. Furthermore, we show that the algorithm converges to stationary points of the outer level problem, which are statistically consistent with the optimal metric at a non-asymptotic convergence rate. Experiments on both numerical and inventory control tasks verify that the proposed framework achieves superior closed-loop performance and robustness compared against state-of-the-art methods.
Authors: Zhechong Huang, Zhao Zhang, Ruyi Ji, Tingxuan Xia, Qihao Zhu, Qinxiang Cao, Zeyu Sun, Yingfei Xiong
Abstract: Language models have shown remarkable proficiency in code generation; nevertheless, ensuring type correctness remains a challenge. Although traditional methods, such as constrained decoding, alleviate this problem by externally rejecting untypable code, the model itself does not effectively learn type reasoning internally, which ultimately limits its overall performance. This paper introduces TyFlow, a novel system that internalizes type reasoning within code generation to guide the model to learn the type system. The core of our approach is a novel type-guided program synthesis system that maintains an isomorphism between type derivation trees and synthesis derivation trees, enabling a new code representation based on synthesis decision sequences rather than traditional text-based token sequences. By offloading the complexity of type system learning to the representation itself, models can redirect their computational resources toward higher-level program semantics. Our evaluation shows that TyFlow not only eliminates type errors but also significantly improves functional correctness, highlighting the importance of aligning LMs with type systems internally.
Authors: Hyogo Hiruma, Hiroshi Ito, Tetsuya Ogata
Abstract: Training robots to operate effectively in environments with uncertain states, such as ambiguous object properties or unpredictable interactions, remains a longstanding challenge in robotics. Imitation learning methods typically rely on successful examples and often neglect failure scenarios where uncertainty is most pronounced. To address this limitation, we propose the Uncertainty-driven Foresight Recurrent Neural Network (UF-RNN), a model that combines standard time-series prediction with an active "Foresight" module. This module performs internal simulations of multiple future trajectories and refines the hidden state to minimize predicted variance, enabling the model to selectively explore actions under high uncertainty. We evaluate UF-RNN on a door-opening task in both simulation and a real-robot setting, demonstrating that, despite the absence of explicit failure demonstrations, the model exhibits robust adaptation by leveraging self-induced chaotic dynamics in its latent space. When guided by the Foresight module, these chaotic properties stimulate exploratory behaviors precisely when the environment is ambiguous, yielding improved success rates compared to conventional stochastic RNN baselines. These findings suggest that integrating uncertainty-driven foresight into imitation learning pipelines can significantly enhance a robot's ability to handle unpredictable real-world conditions.
Authors: Hyogo Hiruma, Hiroshi Ito, Hiroki Mori, Tetsuya Ogata
Abstract: This study investigates the developmental interaction between top-down (TD) and bottom-up (BU) visual attention in robotic learning. Our goal is to understand how structured, human-like attentional behavior emerges through the mutual adaptation of TD and BU mechanisms over time. To this end, we propose a novel attention model $A^3 RNN$ that integrates predictive TD signals and saliency-based BU cues through a bi-directional attention architecture. We evaluate our model in robotic manipulation tasks using imitation learning. Experimental results show that attention behaviors evolve throughout training, from saliency-driven exploration to prediction-driven direction. Initially, BU attention highlights visually salient regions, which guide TD processes, while as learning progresses, TD attention stabilizes and begins to reshape what is perceived as salient. This trajectory reflects principles from cognitive science and the free-energy framework, suggesting the importance of self-organizing attention through interaction between perception and internal prediction. Although not explicitly optimized for stability, our model exhibits more coherent and interpretable attention patterns than baselines, supporting the idea that developmental mechanisms contribute to robust attention formation.
Authors: Yijie Xu, Huizai Yao, Zhiyu Guo, Weiyu Guo, Pengteng Li, Aiwei Liu, Xuming Hu, Hui Xiong
Abstract: Large language models (LLMs) are increasingly deployed in specialized domains such as finance, medicine, and agriculture, where they face significant distribution shifts from their training data. Domain-specific fine-tuning can mitigate this challenge but relies on high-quality labeled data that is expensive and slow to collect in expertise-limited settings. We study label-free test-time adaptation for language models and present SyTTA, an inference-time framework that adapts models on-the-fly without additional supervision. SyTTA couples two complementary uncertainty signals that arise under distribution shift: input-side perplexity, indicating mismatch with domain-specific terminology and patterns, and output-side predictive entropy, indicating diffuse and unstable token probabilities during generation. Across diverse model architectures and domain-specific benchmarks, SyTTA delivers consistent gains. Notably, on agricultural question answering, SyTTA improves Rouge-LSum by over 120% on Qwen-2.5-7B with only 4 extra tokens per query. These results show that effective test-time adaptation for language models is achievable without labeled examples, supporting deployment in label-scarce domains. The code will be made available upon acceptance.
Authors: Xuening Wu, Shenqin Yin, Yanlan Kang, Xinhang Zhang, Qianya Xu, Zeping Chen, Wenqiang Zhang
Abstract: Recursive self-modification is increasingly central in AutoML, neural architecture search, and adaptive optimization, yet no existing framework ensures that such changes are made safely. Godel machines offer a principled safeguard by requiring formal proofs of improvement before rewriting code; however, such proofs are unattainable in stochastic, high-dimensional settings. We introduce the Statistical Godel Machine (SGM), the first statistical safety layer for recursive edits. SGM replaces proof-based requirements with statistical confidence tests (e-values, Hoeffding bounds), admitting a modification only when superiority is certified at a chosen confidence level, while allocating a global error budget to bound cumulative risk across rounds.We also propose Confirm-Triggered Harmonic Spending (CTHS), which indexes spending by confirmation events rather than rounds, concentrating the error budget on promising edits while preserving familywise validity.Experiments across supervised learning, reinforcement learning, and black-box optimization validate this role: SGM certifies genuine gains on CIFAR-100, rejects spurious improvement on ImageNet-100, and demonstrates robustness on RL and optimization benchmarks.Together, these results position SGM as foundational infrastructure for continual, risk-aware self-modification in learning systems.Code is available at: https://github.com/gravitywavelet/sgm-anon.
Authors: Jiaxi Zhuang, Yaorui Shi, Jue Hou, Yunong He, Mingwei Ye, Mingjun Xu, Yuming Su, Linfeng Zhang, Linfeng Zhang, Guolin Ke, Hengxing Cai
Abstract: Molecular property prediction is crucial for drug discovery and materials science, yet existing approaches suffer from limited interpretability, poor cross-task generalization, and lack of chemical reasoning capabilities. Traditional machine learning models struggle with task transferability, while specialized molecular language models provide little insight into their decision-making processes. To address these limitations, we propose \textbf{MPPReasoner}, a multimodal large language model that incorporates chemical reasoning for molecular property prediction. Our approach, built upon Qwen2.5-VL-7B-Instruct, integrates molecular images with SMILES strings to enable comprehensive molecular understanding. We develop a two-stage training strategy: supervised fine-tuning (SFT) using 16,000 high-quality reasoning trajectories generated through expert knowledge and multiple teacher models, followed by Reinforcement Learning from Principle-Guided Rewards (RLPGR). RLPGR employs verifiable, rule-based rewards that systematically evaluate chemical principle application, molecular structure analysis, and logical consistency through computational verification. Extensive experiments across 8 datasets demonstrate significant performance improvements, with MPPReasoner outperforming the best baselines by 7.91\% and 4.53\% on in-distribution and out-of-distribution tasks respectively. MPPReasoner exhibits exceptional cross-task generalization and generates chemically sound reasoning paths that provide valuable insights into molecular property analysis, substantially enhancing both interpretability and practical utility for chemists. Code is available at https://anonymous.4open.science/r/MPPReasoner-12687.
Authors: Jack Krolik, Jake Lynn, John Henry Rudden, Dmytro Vremenko
Abstract: This study explores the application of deep learning techniques in the automated detection and segmentation of brain tumors from MRI scans. We employ several machine learning models, including basic logistic regression, Convolutional Neural Networks (CNNs), and Residual Networks (ResNet) to classify brain tumors effectively. Additionally, we investigate the use of U-Net for semantic segmentation and EfficientDet for anchor-based object detection to enhance the localization and identification of tumors. Our results demonstrate promising improvements in the accuracy and efficiency of brain tumor diagnostics, underscoring the potential of deep learning in medical imaging and its significance in improving clinical outcomes.
Authors: Samir Abdaljalil, Erchin Serpedin, Khalid Qaraqe, Hasan Kurban
Abstract: Large language models (LLMs) often generate reasoning traces that appear coherent but rest on unsupported assumptions, leading to hallucinated conclusions. Prior work mainly addresses factual hallucinations or relies on post-hoc verification, leaving reasoning-induced hallucinations largely unaddressed. We propose Audit-of-Understanding (AoU), a framework that constrains inference to validated premises through three phases: (1) decomposing a query into candidate assumptions, (2) auditing their support, and (3) conditioning inference only on the validated subset. Formally, AoU is \emph{posterior-constrained inference}, connecting to selective prediction and rejection learning. Our contributions are threefold: (i) theoretical guarantees under perfect validation, (ii) excess-risk bounds under imperfect audits, and (iii) tractability analysis. Empirically, AoU improves both accuracy and faithfulness on GSM8K, MultiArith, and SVAMP, achieving up to +30% gains on GSM8K, +45% on MultiArith, and consistent +20--28% improvements on SVAMP over Chain-of-Thought, Self-Consistency, and CoT-Decoding. Code is available at https://anonymous.4open.science/r/audit-of-understanding-E28B.
URLs: https://anonymous.4open.science/r/audit-of-understanding-E28B.
Authors: Moona Kanwal, Muhammad Sami Siddiqui, Syed Anael Ali
Abstract: Profiling gamers provides critical insights for adaptive game design, behavioral understanding, and digital well-being. This study proposes an integrated, data-driven framework that combines psychological measures, behavioral analytics, and machine learning to reveal underlying gamer personas. A structured survey of 250 participants, including 113 active gamers, captured multidimensional behavioral, motivational, and social data. The analysis pipeline integrated feature engineering, association-network, knowledge-graph analysis, and unsupervised clustering to extract meaningful patterns. Correlation statistics uses Cramers V, Tschuprows T, Theils U, and Spearmans quantified feature associations, and network centrality guided feature selection. Dimensionality-reduction techniques such as PCA, SVD, t-SNE are coupled with clustering algorithms like K-Means, Agglomerative, Spectral, DBSCAN, evaluated using Silhouette, Calinski Harabasz, and Davies Bouldin indices. The PCA with K-Means with k = 4 model achieved optimal cluster quality with Silhouette = 0.4, identifying four archetypes as Immersive Social Story-Seekers, Disciplined Optimizers, Strategic Systems Navigators, and Competitive Team-Builders. This research contributes a reproducible pipeline that links correlation-driven network insights with unsupervised learning. The integration of behavioral correlation networks with clustering not only enhances classification accuracy but also offers a holistic lens to connect gameplay motivations with psychological and wellness outcomes.
Authors: Wentian Zhu, Zhen Xiang, Wei Niu, Le Guan
Abstract: Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the fine-tuning process of Large Language Models (LLMs). Serving as metadata of training data, these tokens play a crucial role in instructing LLMs to generate coherent and context-aware responses. We demonstrate that special tokens can be exploited to construct four attack primitives, with which malicious users can reliably bypass the internal safety alignment of online LLM services and circumvent state-of-the-art (SOTA) external content moderation systems simultaneously. Moreover, we found that addressing this threat is challenging, as aggressive defense mechanisms-such as input sanitization by removing special tokens entirely, as suggested in academia-are less effective than anticipated. This is because such defense can be evaded when the special tokens are replaced by regular ones with high semantic similarity within the tokenizer's embedding space. We systemically evaluated our method, named MetaBreak, on both lab environment and commercial LLM platforms. Our approach achieves jailbreak rates comparable to SOTA prompt-engineering-based solutions when no content moderation is deployed. However, when there is content moderation, MetaBreak outperforms SOTA solutions PAP and GPTFuzzer by 11.6% and 34.8%, respectively. Finally, since MetaBreak employs a fundamentally different strategy from prompt engineering, the two approaches can work synergistically. Notably, empowering MetaBreak on PAP and GPTFuzzer boosts jailbreak rates by 24.3% and 20.2%, respectively.
Authors: Jinliang Zheng, Jianxiong Li, Zhihao Wang, Dongxiu Liu, Xirui Kang, Yuchun Feng, Yinan Zheng, Jiayin Zou, Yilun Chen, Jia Zeng, Ya-Qin Zhang, Jiangmiao Pang, Jingjing Liu, Tai Wang, Xianyuan Zhan
Abstract: Successful generalist Vision-Language-Action (VLA) models rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To facilitate and leverage the heterogeneity in rich, diverse robotic data sources, we propose a novel Soft Prompt approach with minimally added parameters, by infusing prompt learning concepts into cross-embodiment robot learning and introducing separate sets of learnable embeddings for each distinct data source. These embeddings serve as embodiment-specific prompts, which in unity empower VLA models with effective exploitation of varying cross-embodiment features. Our new X-VLA, a neat flow-matching-based VLA architecture, relies exclusively on soft-prompted standard Transformer encoders, enjoying both scalability and simplicity. Evaluated across 6 simulations as well as 3 real-world robots, our 0.9B instantiation-X-VLA-0.9B simultaneously achieves SOTA performance over a sweep of benchmarks, demonstrating superior results on a wide axes of capabilities, from flexible dexterity to quick adaptation across embodiments, environments, and tasks. Website: https://thu-air-dream.github.io/X-VLA/
Authors: Christopher Chiu, Silviu Pitis, Mihaela van der Schaar
Abstract: Clinical reasoning in medicine is a hypothesis-driven process where physicians refine diagnoses from limited information through targeted history, physical examination, and diagnostic investigations. In contrast, current medical benchmarks for large language models (LLMs) primarily assess knowledge recall through single-turn questions, where complete clinical information is provided upfront. To address this gap, we introduce VivaBench, a multi-turn benchmark that evaluates sequential clinical reasoning in LLM agents. Our dataset consists of 1762 physician-curated clinical vignettes structured as interactive scenarios that simulate a (oral) examination in medical training, requiring agents to actively probe for relevant findings, select appropriate investigations, and synthesize information across multiple steps to reach a diagnosis. While current LLMs demonstrate competence in diagnosing conditions from well-described clinical presentations, their performance degrades significantly when required to navigate iterative diagnostic reasoning under uncertainty in our evaluation. Our analysis identified several failure modes that mirror common cognitive errors in clinical practice, including: (1) fixation on initial hypotheses, (2) inappropriate investigation ordering, (3) premature diagnostic closure, and (4) failing to screen for critical conditions. These patterns reveal fundamental limitations in how current LLMs reason and make decisions under uncertainty. Through VivaBench, we provide a standardized benchmark for evaluating conversational medical AI systems for real-world clinical decision support. Beyond medical applications, we contribute to the larger corpus of research on agentic AI by demonstrating how sequential reasoning trajectories can diverge in complex decision-making environments.
Authors: Guan-Yan Yang, Tzu-Yu Cheng, Ya-Wen Teng, Farn Wanga, Kuo-Hui Yeh
Abstract: The integration of Large Language Models (LLMs) into computer applications has introduced transformative capabilities but also significant security challenges. Existing safety alignments, which primarily focus on semantic interpretation, leave LLMs vulnerable to attacks that use non-standard data representations. This paper introduces ArtPerception, a novel black-box jailbreak framework that strategically leverages ASCII art to bypass the security measures of state-of-the-art (SOTA) LLMs. Unlike prior methods that rely on iterative, brute-force attacks, ArtPerception introduces a systematic, two-phase methodology. Phase 1 conducts a one-time, model-specific pre-test to empirically determine the optimal parameters for ASCII art recognition. Phase 2 leverages these insights to launch a highly efficient, one-shot malicious jailbreak attack. We propose a Modified Levenshtein Distance (MLD) metric for a more nuanced evaluation of an LLM's recognition capability. Through comprehensive experiments on four SOTA open-source LLMs, we demonstrate superior jailbreak performance. We further validate our framework's real-world relevance by showing its successful transferability to leading commercial models, including GPT-4o, Claude Sonnet 3.7, and DeepSeek-V3, and by conducting a rigorous effectiveness analysis against potential defenses such as LLaMA Guard and Azure's content filters. Our findings underscore that true LLM security requires defending against a multi-modal space of interpretations, even within text-only inputs, and highlight the effectiveness of strategic, reconnaissance-based attacks. Content Warning: This paper includes potentially harmful and offensive model outputs.
Authors: Joy Hsu, Emily Jin, Jiajun Wu, Niloy J. Mitra
Abstract: Real-world scenes, such as those in ScanNet, are difficult to capture, with highly limited data available. Generating realistic scenes with varied object poses remains an open and challenging task. In this work, we propose FactoredScenes, a framework that synthesizes realistic 3D scenes by leveraging the underlying structure of rooms while learning the variation of object poses from lived-in scenes. We introduce a factored representation that decomposes scenes into hierarchically organized concepts of room programs and object poses. To encode structure, FactoredScenes learns a library of functions capturing reusable layout patterns from which scenes are drawn, then uses large language models to generate high-level programs, regularized by the learned library. To represent scene variations, FactoredScenes learns a program-conditioned model to hierarchically predict object poses, and retrieves and places 3D objects in a scene. We show that FactoredScenes generates realistic, real-world rooms that are difficult to distinguish from real ScanNet scenes.
Authors: Hongwei Chen, Yishu Lei, Dan Zhang, Bo Ke, Danxiang Zhu, Xuyi Chen, Yuxiang Lu, Zhengjie Huang, Shikun Feng, Jingzhou He, Yu Sun, Hua Wu, Haifeng Wang
Abstract: Test-time scaling has emerged as a promising paradigm in language modeling, wherein additional computational resources are allocated during inference to enhance model performance. Recent approaches, such as DeepConf, have demonstrated the efficacy of this strategy, however, they often incur substantial computational overhead to achieve competitive results. In this work, we propose MatryoshkaThinking, a novel method that significantly reduces computational cost while maintaining state-of-the-art performance. Specifically, MatryoshkaThinking attains a score of 99.79 on AIME2025 using only 4% of the computation required by DeepConf. The core of our approach lies in the recursive exploitation of the model's intrinsic capabilities in reasoning, verification, and summarization, which collectively enhance the retention of correct solutions and reduce the disparity between Pass@k and Pass@1. Comprehensive evaluations across multiple open-source models and challenging multi-modal reasoning benchmarks validate the effectiveness and generality of our method. These findings offer new insights into the design of efficient and scalable test-time inference strategies for advanced language models.
Authors: Giulio Ruffini
Abstract: The regulator theorem states that, under certain conditions, any optimal controller must embody a model of the system it regulates, grounding the idea that controllers embed, explicitly or implicitly, internal models of the controlled. This principle underpins neuroscience and predictive brain theories like the Free-Energy Principle or Kolmogorov/Algorithmic Agent theory. However, the theorem is only proven in limited settings. Here, we treat the deterministic, closed, coupled world-regulator system $(W,R)$ as a single self-delimiting program $p$ via a constant-size wrapper that produces the world output string~$x$ fed to the regulator. We analyze regulation from the viewpoint of the algorithmic complexity of the output, $K(x)$. We define $R$ to be a \emph{good algorithmic regulator} if it \emph{reduces} the algorithmic complexity of the readout relative to a null (unregulated) baseline $\varnothing$, i.e., \[ \Delta = K\big(O_{W,\varnothing}\big) - K\big(O_{W,R}\big) > 0. \] We then prove that the larger $\Delta$ is, the more world-regulator pairs with high mutual algorithmic information are favored. More precisely, a complexity gap $\Delta > 0$ yields \[ \Pr\big((W,R)\mid x\big) \le C\,2^{\,M(W{:}R)}\,2^{-\Delta}, \] making low $M(W{:}R)$ exponentially unlikely as $\Delta$ grows. This is an AIT version of the idea that ``the regulator contains a model of the world.'' The framework is distribution-free, applies to individual sequences, and complements the Internal Model Principle. Beyond this necessity claim, the same coding-theorem calculus singles out a \emph{canonical scalar objective} and implicates a \emph{planner}. On the realized episode, a regulator behaves \emph{as if} it minimized the conditional description length of the readout.
Authors: Michael Y. Hu, Benjamin Van Durme, Jacob Andreas, Harsh Jhamtani
Abstract: Language model (LM) agents deployed in novel environments often exhibit poor sample efficiency when learning from sequential interactions. This significantly hinders the usefulness of such agents in environments where interaction is costly (for example, when they interact with humans or reset physical systems). While a number of existing LM agent architectures incorporate various mechanisms for experience storage and reflection, they make limited use of LMs' abilities to directly generate or reason about full counterfactual trajectories. We introduce ECHO (Experience Consolidation via Hindsight Optimization), a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents. ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts, effectively creating synthetic positive examples from unsuccessful interactions. Our approach consists of two components: a hindsight rule that uses the language model itself to identify relevant subgoals and generate optimized trajectories, and an update rule that maintains compressed trajectory representations in memory. We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation. Across both domains, ECHO outperforms vanilla language agent baselines by up to 80%; in XMiniGrid, it also outperforms a number of sophisticated agent architectures including Reflexion and AWM, demonstrating faster adaptation to novel environments through more effective utilization of past experiences.
Authors: Lorena Poenaru-Olaru, Wouter van 't Hof, Adrian Stando, Arkadiusz P. Trawinski, Eileen Kapel, Jan S. Rellermeyer, Luis Cruz, Arie van Deursen
Abstract: Capacity management is critical for software organizations to allocate resources effectively and meet operational demands. An important step in capacity management is predicting future resource needs often relies on data-driven analytics and machine learning (ML) forecasting models, which require frequent retraining to stay relevant as data evolves. Continuously retraining the forecasting models can be expensive and difficult to scale, posing a challenge for engineering teams tasked with balancing accuracy and efficiency. Retraining only when the data changes appears to be a more computationally efficient alternative, but its impact on accuracy requires further investigation. In this work, we investigate the effects of retraining capacity forecasting models for time series based on detected changes in the data compared to periodic retraining. Our results show that drift-based retraining achieves comparable forecasting accuracy to periodic retraining in most cases, making it a cost-effective strategy. However, in cases where data is changing rapidly, periodic retraining is still preferred to maximize the forecasting accuracy. These findings offer actionable insights for software teams to enhance forecasting systems, reducing retraining overhead while maintaining robust performance.
Authors: Jugal Gajjar, Kaustik Ranaware, Kamalasankari Subramaniakuppusamy
Abstract: Software vulnerabilities remain a persistent risk, yet static and dynamic analyses often overlook structural dependencies that shape insecure behaviors. Viewing programs as heterogeneous graphs, we capture control- and data-flow relations as complex interaction networks. Our hybrid framework combines these graph representations with light-weight (<4B) local LLMs, uniting topological features with semantic reasoning while avoiding the cost and privacy concerns of large cloud models. Evaluated on Java vulnerability detection (binary classification), our method achieves 93.57% accuracy-an 8.36% gain over Graph Attention Network-based embeddings and 17.81% over pretrained LLM baselines such as Qwen2.5 Coder 3B. Beyond accuracy, the approach extracts salient subgraphs and generates natural language explanations, improving interpretability for developers. These results pave the way for scalable, explainable, and locally deployable tools that can shift vulnerability analysis from purely syntactic checks to deeper structural and semantic insights, facilitating broader adoption in real-world secure software development.
Authors: Walid Abdela
Abstract: The seamless integration of physical and digital environments in Cyber-Physical Systems(CPS), particularly within Industry 4.0, presents significant challenges stemming from system heterogeneity and complexity. Traditional approaches often rely on rigid, data-centric solutions like co-simulation frameworks or brittle point-to-point middleware bridges, which lack the semantic richness and flexibility required for intelligent, autonomous coordination. This report introduces the Knowledge Graph-Enhanced Multi-Agent Infrastructure(KG-MAS), as resolution in addressing such limitations. KG-MAS leverages a centralized Knowledge Graph (KG) as a dynamic, shared world model, providing a common semantic foundation for a Multi-Agent System(MAS). Autonomous agents, representing both physical and digital components, query this KG for decision-making and update it with real-time state information. The infrastructure features a model-driven architecture which facilitates the automatic generation of agents from semantic descriptions, thereby simplifying system extension and maintenance. By abstracting away underlying communication protocols and providing a unified, intelligent coordination mechanism, KG-MAS offers a robust, scalable, and flexible solution for coupling heterogeneous physical and digital robotic environments.
Authors: Junhao Xu, Hui Zeng
Abstract: Understanding and predicting pedestrian dynamics has become essential for shaping safer, more responsive, and human-centered urban environments. This study conducts a comprehensive scientometric analysis of research on data-driven pedestrian trajectory prediction and crowd simulation, mapping its intellectual evolution and interdisciplinary structure. Using bibliometric data from the Web of Science Core Collection, we employ SciExplorer and Bibliometrix to identify major trends, influential contributors, and emerging frontiers. Results reveal a strong convergence between artificial intelligence, urban informatics, and crowd behavior modeling--driven by graph neural networks, transformers, and generative models. Beyond technical advances, the field increasingly informs urban mobility design, public safety planning, and digital twin development for smart cities. However, challenges remain in ensuring interpretability, inclusivity, and cross-domain transferability. By connecting methodological trajectories with urban applications, this work highlights how data-driven approaches can enrich urban governance and pave the way for adaptive, socially responsible mobility intelligence in future cities.
Authors: Kohio Deflesselle, M\'elodie Daniel, Aly Magassouba, Miguel Aranda, Olivier Ly
Abstract: We present a deep reinforcement learning framework based on Soft Actor-Critic (SAC) for safe and precise maneuvering of double-Ackermann-steering mobile robots (DASMRs). Unlike holonomic or simpler non-holonomic robots such as differential-drive robots, DASMRs face strong kinematic constraints that make classical planners brittle in cluttered environments. Our framework leverages the Hindsight Experience Replay (HER) and the CrossQ overlay to encourage maneuvering efficiency while avoiding obstacles. Simulation results with a heavy four-wheel-steering rover show that the learned policy can robustly reach up to 97% of target positions while avoiding obstacles. Our framework does not rely on handcrafted trajectories or expert demonstrations.
Authors: Shalaleh Rismani, Renee Shelby, Leah Davis, Negar Rostamzadeh, AJung Moon
Abstract: Over the past decade, an ecosystem of measures has emerged to evaluate the social and ethical implications of AI systems, largely shaped by high-level ethics principles. These measures are developed and used in fragmented ways, without adequate attention to how they are situated in AI systems. In this paper, we examine how existing measures used in the computing literature map to AI system components, attributes, hazards, and harms. Our analysis draws on a scoping review resulting in nearly 800 measures corresponding to 11 AI ethics principles. We find that most measures focus on four principles - fairness, transparency, privacy, and trust - and primarily assess model or output system components. Few measures account for interactions across system elements, and only a narrow set of hazards is typically considered for each harm type. Many measures are disconnected from where harm is experienced and lack guidance for setting meaningful thresholds. These patterns reveal how current evaluation practices remain fragmented, measuring in pieces rather than capturing how harms emerge across systems. Framing measures with respect to system attributes, hazards, and harms can strengthen regulatory oversight, support actionable practices in industry, and ground future research in systems-level understanding.
Authors: Rugved Katole, Christopher Stewart
Abstract: AI-driven crop health mapping systems offer substantial advantages over conventional monitoring approaches through accelerated data acquisition and cost reduction. However, widespread farmer adoption remains constrained by technical limitations in orthomosaic generation from sparse aerial imagery datasets. Traditional photogrammetric reconstruction requires 70-80\% inter-image overlap to establish sufficient feature correspondences for accurate geometric registration. AI-driven systems operating under resource-constrained conditions cannot consistently achieve these overlap thresholds, resulting in degraded reconstruction quality that undermines user confidence in autonomous monitoring technologies. In this paper, we present Ortho-Fuse, an optical flow-based framework that enables the generation of a reliable orthomosaic with reduced overlap requirements. Our approach employs intermediate flow estimation to synthesize transitional imagery between consecutive aerial frames, artificially augmenting feature correspondences for improved geometric reconstruction. Experimental validation demonstrates a 20\% reduction in minimum overlap requirements. We further analyze adoption barriers in precision agriculture to identify pathways for enhanced integration of AI-driven monitoring systems.
Authors: Rohan Gupta, Trevor Asbery, Zain Merchant, Abrar Anwar, Jesse Thomason
Abstract: Coordinating heterogeneous robot fleets to achieve multiple goals is challenging in multi-robot systems. We introduce an open-source and extensible framework for centralized multi-robot task planning and scheduling that leverages LLMs to enable fleets of heterogeneous robots to accomplish multiple tasks. RobotFleet provides abstractions for planning, scheduling, and execution across robots deployed as containerized services to simplify fleet scaling and management. The framework maintains a shared declarative world state and two-way communication for task execution and replanning. By modularizing each layer of the autonomy stack and using LLMs for open-world reasoning, RobotFleet lowers the barrier to building scalable multi-robot systems. The code can be found here: https://github.com/therohangupta/robot-fleet.
Authors: Sai Teja Erukude
Abstract: CNNs are now prevalent as the primary choice for most machine vision problems due to their superior rate of classification and the availability of user-friendly libraries. These networks effortlessly identify and select features in a non-intuitive data-driven manner, making it difficult to determine which features were most influential. That leads to a ``black box", where users cannot know how the image data are analyzed but rely on empirical results. Therefore the decision-making process can be biased by background information that is difficult to detect. Here we discuss examples of such hidden biases and propose techniques for identifying them, methods to distinguish between contextual information and background noise, and explore whether CNNs learn from irrelevant features. One effective approach to identify dataset bias is to classify blank background parts of the images. However, in some situations a blank background in the images is not available, making it more difficult to separate the foreground information from the blank background. Such parts of the image can also be considered contextual learning, not necessarily bias. To overcome this, we propose two approaches that were tested on six different datasets, including natural, synthetic, and hybrid datasets. The first method involves dividing images into smaller, non-overlapping tiles of various sizes, which are then shuffled randomly, making classification more challenging. The second method involves the application of several image transforms, including Fourier, Wavelet transforms, and Median filter, and their combinations. These transforms help recover background noise information used by CNN to classify images. Results indicate that this method can effectively distinguish between contextual information and background noise, and alert on the presence of background noise even without the need to use background information.
Authors: Aashiq Muhamed, Leonardo F. R. Ribeiro, Markus Dreyer, Virginia Smith, Mona T. Diab
Abstract: The ability of language models in RAG systems to selectively refuse to answer based on flawed context is critical for safety, yet remains a significant failure point. Our large-scale study reveals that even frontier models struggle in this setting, with refusal accuracy dropping below 50% on multi-document tasks, while exhibiting either dangerous overconfidence or overcaution. Static benchmarks fail to reliably evaluate this capability, as models exploit dataset-specific artifacts and memorize test instances. We introduce RefusalBench, a generative methodology that programmatically creates diagnostic test cases through controlled linguistic perturbation. Our framework employs 176 distinct perturbation strategies across six categories of informational uncertainty and three intensity levels. Evaluation of over 30 models uncovers systematic failure patterns: refusal comprises separable detection and categorization skills, and neither scale nor extended reasoning improves performance. We find that selective refusal is a trainable, alignment-sensitive capability, offering a clear path for improvement. We release two benchmarks -- RefusalBench-NQ (single document) and RefusalBench-GaRAGe (multi-document) -- and our complete generation framework to enable continued, dynamic evaluation of this critical capability.
Authors: Geunyeong Jeong, Juoh Sun, Seonghee Lee, Harksoo Kim
Abstract: Large Language Models store extensive factual knowledge acquired during large-scale pre-training. However, this knowledge is inherently static, reflecting only the state of the world at the time of training. Knowledge editing has emerged as a promising solution for updating outdated or incorrect facts without full retraining. However, most existing locate-and-edit methods primarily focus on token-level likelihood optimization without addressing semantic coherence. Our analysis reveals that such edited knowledge is often encoded as isolated residual streams in the model's latent space, distinct from pre-existing knowledge and bypassing natural reasoning process. To address this, we propose \textsc{Steam}, a semantic-level knowledge editing framework that enhances integration of updated knowledge into the model's knowledge structure. \textsc{Steam} first identifies target representations as semantic anchors for the updated factual association, then guides the internal representation of the edited fact towards these anchors through an alignment loss during optimization. Experimental results demonstrate that \textsc{Steam} improves model's ability to reason with edited knowledge and enhances semantic coherence, underscoring the importance of latent-space alignment for reliable and coherent knowledge editing. The code is available at https://github.com/GY-Jeong/STEAM.
Authors: Jiachi Zhao, Zehong Wang, Yamei Liao, Chuxu Zhang, Yanfang Ye
Abstract: Graph generation is a fundamental problem in graph learning with broad applications across Web-scale systems, knowledge graphs, and scientific domains such as drug and material discovery. Recent approaches leverage diffusion models for step-by-step generation, yet unconditional diffusion offers little control over desired properties, often leading to unstable quality and difficulty in incorporating new objectives. Inference-time guidance methods mitigate these issues by adjusting the sampling process without retraining, but they remain inherently local, heuristic, and limited in controllability. To overcome these limitations, we propose TreeDiff, a Monte Carlo Tree Search (MCTS) guided dual-space diffusion framework for controllable graph generation. TreeDiff is a plug-and-play inference-time method that expands the search space while keeping computation tractable. Specifically, TreeDiff introduces three key designs to make it practical and scalable: (1) a macro-step expansion strategy that groups multiple denoising updates into a single transition, reducing tree depth and enabling long-horizon exploration; (2) a dual-space denoising mechanism that couples efficient latent-space denoising with lightweight discrete correction in graph space, ensuring both scalability and structural fidelity; and (3) a dual-space verifier that predicts long-term rewards from partially denoised graphs, enabling early value estimation and removing the need for full rollouts. Extensive experiments on 2D and 3D molecular generation benchmarks, under both unconditional and conditional settings, demonstrate that TreeDiff achieves state-of-the-art performance. Notably, TreeDiff exhibits favorable inference-time scaling: it continues to improve with additional computation, while existing inference-time methods plateau early under limited resources.
Authors: Zhao-Yang Wang, Jieneng Chen, Jiang Liu, Yuxiang Guo, Rama Chellappa
Abstract: Gait recognition, a fundamental biometric technology, leverages unique walking patterns for individual identification, typically using 2D representations such as silhouettes or skeletons. However, these methods often struggle with viewpoint variations, occlusions, and noise. Multi-modal approaches that incorporate 3D body shape information offer improved robustness but are computationally expensive, limiting their feasibility for real-time applications. To address these challenges, we introduce Mesh-Gait, a novel end-to-end multi-modal gait recognition framework that directly reconstructs 3D representations from 2D silhouettes, effectively combining the strengths of both modalities. Compared to existing methods, directly learning 3D features from 3D joints or meshes is complex and difficult to fuse with silhouette-based gait features. To overcome this, Mesh-Gait reconstructs 3D heatmaps as an intermediate representation, enabling the model to effectively capture 3D geometric information while maintaining simplicity and computational efficiency. During training, the intermediate 3D heatmaps are gradually reconstructed and become increasingly accurate under supervised learning, where the loss is calculated between the reconstructed 3D joints, virtual markers, and 3D meshes and their corresponding ground truth, ensuring precise spatial alignment and consistent 3D structure. Mesh-Gait extracts discriminative features from both silhouettes and reconstructed 3D heatmaps in a computationally efficient manner. This design enables the model to capture spatial and structural gait characteristics while avoiding the heavy overhead of direct 3D reconstruction from RGB videos, allowing the network to focus on motion dynamics rather than irrelevant visual details. Extensive experiments demonstrate that Mesh-Gait achieves state-of-the-art accuracy. The code will be released upon acceptance of the paper.
Authors: Federica Bologna, Tiffany Pan, Matthew Wilkens, Yue Guo, Lucy Lu Wang
Abstract: Evaluating long-form clinical question answering (QA) systems is resource-intensive and challenging: accurate judgments require medical expertise and achieving consistent human judgments over long-form text is difficult. We introduce LongQAEval, an evaluation framework and set of evaluation recommendations for limited-resource and high-expertise settings. Based on physician annotations of 300 real patient questions answered by physicians and LLMs, we compare coarse answer-level versus fine-grained sentence-level evaluation over the dimensions of correctness, relevance, and safety. We find that inter-annotator agreement (IAA) varies by dimension: fine-grained annotation improves agreement on correctness, coarse improves agreement on relevance, and judgments on safety remain inconsistent. Additionally, annotating only a small subset of sentences can provide reliability comparable to coarse annotations, reducing cost and effort.
Authors: Zhao-Yang Wang, Zhimin Shao, Jieneng Chen, Rama Chellappa
Abstract: Gait recognition is an important biometric for human identification at a distance, particularly under low-resolution or unconstrained environments. Current works typically focus on either 2D representations (e.g., silhouettes and skeletons) or 3D representations (e.g., meshes and SMPLs), but relying on a single modality often fails to capture the full geometric and dynamic complexity of human walking patterns. In this paper, we propose a multi-modal and multi-task framework that combines 2D temporal silhouettes with 3D SMPL features for robust gait analysis. Beyond identification, we introduce a multitask learning strategy that jointly performs gait recognition and human attribute estimation, including age, body mass index (BMI), and gender. A unified transformer is employed to effectively fuse multi-modal gait features and better learn attribute-related representations, while preserving discriminative identity cues. Extensive experiments on the large-scale BRIAR datasets, collected under challenging conditions such as long-range distances (up to 1 km) and extreme pitch angles (up to 50{\deg}), demonstrate that our approach outperforms state-of-the-art methods in gait recognition and provides accurate human attribute estimation. These results highlight the promise of multi-modal and multitask learning for advancing gait-based human understanding in real-world scenarios.
Authors: Suyang Xi, Chenxi Yang, Hong Ding, Yiqing Ni, Catherine C. Liu, Yunhao Liu, Chengqi Zhang
Abstract: Multimodal large language models (MLLMs) often fail in fine-grained visual question answering, producing hallucinations about object identities, positions, and relations because textual queries are not explicitly anchored to visual referents. Retrieval-augmented generation (RAG) alleviates some errors, but it fails to align with human-like processing at both the retrieval and augmentation levels. Specifically, it focuses only on global-level image information but lacks local detail and limits reasoning about fine-grained interactions. To overcome this limitation, we present Human-Like Retrieval-Augmented Generation (HuLiRAG), a framework that stages multimodal reasoning as a ``what--where--reweight'' cascade. Queries are first anchored to candidate referents via open-vocabulary detection (what), then spatially resolved with SAM-derived masks to recover fine-grained precision (where), and adaptively prioritized through the trade-off between local and global alignment (reweight). Mask-guided fine-tuning further injects spatial evidence into the generation process, transforming grounding from a passive bias into an explicit constraint on answer formulation. Extensive experiments demonstrate that this human-like cascade improves grounding fidelity and factual consistency while reducing hallucinations, advancing multimodal question answering toward trustworthy reasoning.
Authors: Zhichen Zeng, Mengyue Hang, Xiaolong Liu, Xiaoyi Liu, Xiao Lin, Ruizhong Qiu, Tianxin Wei, Zhining Liu, Siyang Yuan, Chaofei Yang, Yiqun Liu, Hang Yin, Jiyan Yang, Hanghang Tong
Abstract: Deep models have driven significant advances in click-through rate (CTR) prediction. While vertical scaling via layer stacking improves model expressiveness, the layer-by-layer sequential computation poses challenges to efficient scaling. Conversely, horizontal scaling through Mixture of Experts (MoE) achieves efficient scaling by activating a small subset of experts in parallel, but flat MoE layers may struggle to capture the hierarchical structure inherent in recommendation tasks. To push the Return-On-Investment (ROI) boundary, we explore the complementary strengths of both directions and propose HiLoMoE, a hierarchical LoRA MoE framework that enables holistic scaling in a parameter-efficient manner. Specifically, HiLoMoE employs lightweight rank-1 experts for parameter-efficient horizontal scaling, and stacks multiple MoE layers with hierarchical routing to enable combinatorially diverse expert compositions. Unlike conventional stacking, HiLoMoE routes based on prior layer scores rather than outputs, allowing all layers to execute in parallel. A principled three-stage training framework ensures stable optimization and expert diversity. Experiments on four public datasets show that HiLoMoE achieving better performance-efficiency tradeoff, achieving an average AUC improvement of 0.20\% in AUC and 18.5\% reduction in FLOPs compared to the non-MoE baseline.
Authors: Zixiang Xu, Menghui Zhou, Jun Qi, Xuanhan Fan, Yun Yang, Po Yang
Abstract: Alzheimer's Disease (AD) is the most prevalent neurodegenerative disorder in aging populations, posing a significant and escalating burden on global healthcare systems. While Multi-Tusk Learning (MTL) has emerged as a powerful computational paradigm for modeling longitudinal AD data, existing frameworks do not account for the time-varying nature of feature correlations. To address this limitation, we propose a novel MTL framework, named Feature Similarity Laplacian graph Multi-Task Learning (MTL-FSL). Our framework introduces a novel Feature Similarity Laplacian (FSL) penalty that explicitly models the time-varying relationships between features. By simultaneously considering temporal smoothness among tasks and the dynamic correlations among features, our model enhances both predictive accuracy and biological interpretability. To solve the non-smooth optimization problem arising from our proposed penalty terms, we adopt the Alternating Direction Method of Multipliers (ADMM) algorithm. Experiments conducted on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that our proposed MTL-FSL framework achieves state-of-the-art performance, outperforming various baseline methods. The implementation source can be found at https://github.com/huatxxx/MTL-FSL.
Authors: Jingyi Chen, Zhimeng Guo, Jiyun Chun, Pichao Wang, Andrew Perrault, Micha Elsner
Abstract: Understanding emotion from speech requires sensitivity to both lexical and acoustic cues. However, it remains unclear whether large audio language models (LALMs) genuinely process acoustic information or rely primarily on lexical content. We present LISTEN (Lexical vs. Acoustic Speech Test for Emotion in Narratives), a controlled benchmark designed to disentangle lexical reliance from acoustic sensitivity in emotion understanding. Across evaluations of six state-of-the-art LALMs, we observe a consistent lexical dominance. Models predict "neutral" when lexical cues are neutral or absent, show limited gains under cue alignment, and fail to classify distinct emotions under cue conflict. In paralinguistic settings, performance approaches chance. These results indicate that current LALMs largely "transcribe" rather than "listen," relying heavily on lexical semantics while underutilizing acoustic cues. LISTEN offers a principled framework for assessing emotion understanding in multimodal models.
Authors: Masoud Makrehchi
Abstract: We analyze a reversed-supervision strategy that searches over labelings of a large unlabeled set \(B\) to minimize error on a small labeled set \(A\). The search space is \(2^n\), and the resulting complexity remains exponential even under large constant-factor speedups (e.g., quantum or massively parallel hardware). Consequently, arbitrarily fast -- but not exponentially faster -- computation does not obviate the need for informative labels or priors. In practice, the machine learning pipeline still requires an initial human contribution: specifying the objective, defining classes, and providing a seed set of representative annotations that inject inductive bias and align models with task semantics. Synthetic labels from generative AI can partially substitute provided their quality is human-grade and anchored by a human-specified objective, seed supervision, and validation. In this view, generative models function as \emph{label amplifiers}, leveraging small human-curated cores via active, semi-supervised, and self-training loops, while humans retain oversight for calibration, drift detection, and failure auditing. Thus, extreme computational speed reduces wall-clock time but not the fundamental supervision needs of learning; initial human (or human-grade) input remains necessary to ground the system in the intended task.
Authors: Keisuke Fujii, Kazushi Tsutsui, Yu Teshima, Makoto Itoh, Naoya Takeishi, Nozomi Nishiumi, Ryoya Tanaka, Shunsuke Shigaki, Yoshinobu Kawahara
Abstract: Simulators of animal movements play a valuable role in studying behavior. Advances in imitation learning for robotics have expanded possibilities for reproducing human and animal movements. A key challenge for realistic multi-animal simulation in biology is bridging the gap between unknown real-world transition models and their simulated counterparts. Because locomotion dynamics are seldom known, relying solely on mathematical models is insufficient; constructing a simulator that both reproduces real trajectories and supports reward-driven optimization remains an open problem. We introduce a data-driven simulator for multi-animal behavior based on deep reinforcement learning and counterfactual simulation. We address the ill-posed nature of the problem caused by high degrees of freedom in locomotion by estimating movement variables of an incomplete transition model as actions within an RL framework. We also employ a distance-based pseudo-reward to align and compare states between cyber and physical spaces. Validated on artificial agents, flies, newts, and silkmoth, our approach achieves higher reproducibility of species-specific behaviors and improved reward acquisition compared with standard imitation and RL methods. Moreover, it enables counterfactual behavior prediction in novel experimental settings and supports multi-individual modeling for flexible what-if trajectory generation, suggesting its potential to simulate and elucidate complex multi-animal behaviors.
Authors: Prawaal Sharma, Poonam Goyal, Navneet Goyal, Vidisha Sharma
Abstract: Digital communication has become the cornerstone of modern interaction, enabling rapid, accessible, and interactive exchanges. However, individuals with lower academic literacy often face significant barriers, exacerbating the "digital divide". In this work, we introduce a novel, universal ideographic metalanguage designed as an innovative communication framework that transcends academic, linguistic, and cultural boundaries. Our approach leverages principles of Neuro-symbolic AI, combining neural-based large language models (LLMs) enriched with world knowledge and symbolic knowledge heuristics grounded in the linguistic theory of Natural Semantic Metalanguage (NSM). This enables the semantic decomposition of complex ideas into simpler, atomic concepts. Adopting a human-centric, collaborative methodology, we engaged over 200 semi-literate participants in defining the problem, selecting ideographs, and validating the system. With over 80\% semantic comprehensibility, an accessible learning curve, and universal adaptability, our system effectively serves underprivileged populations with limited formal education.
Authors: Zongyi Lyu, Songqiang Chen, Zhenlan Ji, Liwen Wang, Shuai Wang, Daoyuan Wu, Wenxuan Wang, Shing-Chi Cheung
Abstract: Multi-agent systems (MASs) have emerged as a promising paradigm for automated code generation, demonstrating impressive performance on established benchmarks by decomposing complex coding tasks across specialized agents with different roles. Despite their prosperous development and adoption, their robustness remains pressingly under-explored, raising critical concerns for real-world deployment. This paper presents the first comprehensive study examining the robustness of MASs for code generation through a fuzzing-based testing approach. By designing a fuzzing pipeline incorporating semantic-preserving mutation operators and a novel fitness function, we assess mainstream MASs across multiple datasets and LLMs. Our findings reveal substantial robustness flaws of various popular MASs: they fail to solve 7.9%-83.3% of problems they initially resolved successfully after applying the semantic-preserving mutations. Through comprehensive failure analysis, we identify a common yet largely overlooked cause of the robustness issue: miscommunications between planning and coding agents, where plans lack sufficient detail and coding agents misinterpret intricate logic, aligning with the challenges inherent in a multi-stage information transformation process. Accordingly, we also propose a repairing method that encompasses multi-prompt generation and introduces a new monitor agent to address this issue. Evaluation shows that our repairing method effectively enhances the robustness of MASs by solving 40.0%-88.9% of identified failures. Our work uncovers critical robustness flaws in MASs and provides effective mitigation strategies, contributing essential insights for developing more reliable MASs for code generation.
Authors: Chen Zhong, Yuxuan Yang, Xinyue Zhang, Ruohan Ma, Yong Guo, Gang Li, Jupeng Li
Abstract: Medical image segmentation annotation suffers from inter-rater variability (IRV) due to differences in annotators' expertise and the inherent blurriness of medical images. Standard approaches that simply average expert labels are flawed, as they discard the valuable clinical uncertainty revealed in disagreements. We introduce a fundamentally new approach with our group decision simulation framework, which works by mimicking the collaborative decision-making process of a clinical panel. Under this framework, an Expert Signature Generator (ESG) learns to represent individual annotator styles in a unique latent space. A Simulated Consultation Module (SCM) then intelligently generates the final segmentation by sampling from this space. This method achieved state-of-the-art results on challenging CBCT and MRI datasets (92.11% and 90.72% Dice scores). By treating expert disagreement as a useful signal instead of noise, our work provides a clear path toward more robust and trustworthy AI systems for healthcare.
Authors: Yi Ren, Xinjie Yu
Abstract: Modern Internet of Things (IoT) systems generate massive, heterogeneous multivariate time series data. Accurate Multivariate Time Series Forecasting (MTSF) of such data is critical for numerous applications. However, existing methods almost universally employ a shared embedding layer that processes all channels identically, creating a representational bottleneck that obscures valuable channel-specific information. To address this challenge, we introduce a Shared-Auxiliary Embedding (SAE) framework that decomposes the embedding into a shared base component capturing common patterns and channel-specific auxiliary components modeling unique deviations. Within this decomposition, we \rev{empirically observe} that the auxiliary components tend to exhibit low-rank and clustering characteristics, a structural pattern that is significantly less apparent when using purely independent embeddings. Consequently, we design LightSAE, a parameter-efficient embedding module that operationalizes these observed characteristics through low-rank factorization and a shared, gated component pool. Extensive experiments across 9 IoT-related datasets and 4 backbone architectures demonstrate LightSAE's effectiveness, achieving MSE improvements of up to 22.8\% with only 4.0\% parameter increase.
Authors: Gunho Park, Jeongin Bae, Beomseok Kwon, Byeongwook Kim, Se Jung Kwon, Dongsoo Lee
Abstract: The deployment of large language models (LLMs) is increasingly constrained by memory and latency bottlenecks, motivating the need for quantization techniques that flexibly balance accuracy and efficiency. Recent work has introduced multi-precision models, which enable inference at multiple precisions within a single model depending on runtime constraints. To support such flexibility, quantized weights are often stored as bit-planes, where hardware efficiency improves when the compute operates directly at the bit-plane level and activates only the precision required by each request. In this work, we present AnyBCQ, a hardware-friendly multi-precision extension of Binary-Coded Quantization (BCQ) that supports direct bit-plane operations. By representing weights as binary bit-planes with corresponding scale factors, AnyBCQ enables bit-plane-level computation and maps naturally to accelerator-friendly, bit-parallel arithmetic. Our progressive precision expansion mechanism incrementally refines scaling factors while reusing previously assigned binary codes, yielding monotonic improvements in accuracy as additional bits are enabled. We further co-design a specialized kernel that exploits the BCQ structure to support dynamic per-request precision selection with negligible overhead. Experiments on recent LLMs demonstrate that AnyBCQ significantly narrows the accuracy drop in the low-bit regime (e.g. 2-bit), remains competitive at higher precision, and achieves throughput gains of up to 3.0x over half precision and 1.2x over state-of-the-art multi-precision methods. By aligning algorithmic flexibility with hardware efficiency, AnyBCQ provides a practical foundation for multi-precision LLM deployment across diverse service-level objectives.
Authors: Qiran Zou, Hou Hei Lam, Wenhao Zhao, Yiming Tang, Tingting Chen, Samson Yu, Tianyi Zhang, Chang Liu, Xiangyang Ji, Dianbo Liu
Abstract: Large language models (LLMs) have sparked growing interest in automatic machine learning research agents. Among them, agents capable of autonomously proposing ideas and conducting machine learning experiments are particularly promising, as they maximize research automation and accelerate scientific progress by iteratively refining ideas based on experimental results. However, comprehensively evaluating such agents remains challenging. Existing benchmarks tend to overemphasize engineering aspects while neglecting academic rigor, creating barriers that obscure a clear assessment of an agent's scientific capabilities in machine learning research. They also suffer from limited task diversity, an overemphasis on application-oriented tasks over fundamental research problems, and limited scalability to realistic research settings. To address these limitations, we introduce FML-bench, a benchmark designed to evaluate automatic machine learning research agents on 8 diverse and fundamental machine learning research problems. It reduces coding burden, emphasizes fundamental problems rather than specific use cases, offers high task diversity, and is extensible to real-world machine learning GitHub repositories. Furthermore, we present a unified evaluation framework with five complementary metrics, designed to comprehensively assess agent performance on our benchmark. We evaluate state-of-the-art automatic research agents on FML-bench, and find that agents employing broad research exploration strategies outperform those focusing on narrow but deep exploration. These findings suggest that emphasizing the breadth of exploration may lead to more effective research outcomes than focusing solely on incremental refinement. Our benchmark is available at https://github.com/qrzou/FML-bench.
Authors: A H M Rezaul Karim, Ozlem Uzuner
Abstract: Medical order extraction is essential for structuring actionable clinical information, supporting decision-making, and enabling downstream applications such as documentation and workflow automation. Orders may be embedded in diverse sources, including electronic health records, discharge summaries, and multi-turn doctor-patient dialogues, and can span categories such as medications, laboratory tests, imaging studies, and follow-up actions. The MEDIQA-OE 2025 shared task focuses on extracting structured medical orders from extended conversational transcripts, requiring the identification of order type, description, reason, and provenance. We present the MasonNLP submission, which ranked 5th among 17 participating teams with 105 total submissions. Our approach uses a general-purpose, instruction-tuned LLaMA-4 17B model without domain-specific fine-tuning, guided by a single in-context example. This few-shot configuration achieved an average F1 score of 37.76, with notable improvements in reason and provenance accuracy. These results demonstrate that large, non-domain-specific LLMs, when paired with effective prompt engineering, can serve as strong, scalable baselines for specialized clinical NLP tasks.
Authors: Zishen Zhang, Xiangzhe Kong, Wenbing Huang, Yang Liu
Abstract: Designing protein binders targeting specific sites, which requires to generate realistic and functional interaction patterns, is a fundamental challenge in drug discovery. Current structure-based generative models are limited in generating nterfaces with sufficient rationality and interpretability. In this paper, we propose Retrieval-Augmented Diffusion for Aligned interface (RADiAnce), a new framework that leverages known interfaces to guide the design of novel binders. By unifying retrieval and generation in a shared contrastive latent space, our model efficiently identifies relevant interfaces for a given binding site and seamlessly integrates them through a conditional latent diffusion generator, enabling cross-domain interface transfer. Extensive exeriments show that RADiAnce significantly outperforms baseline models across multiple metrics, including binding affinity and recovery of geometries and interactions. Additional experimental results validate cross-domain generalization, demonstrating that retrieving interfaces from diverse domains, such as peptides, antibodies, and protein fragments, enhances the generation performance of binders for other domains. Our work establishes a new paradigm for protein binder design that successfully bridges retrieval-based knowledge and generative AI, opening new possibilities for drug discovery.
Authors: Guangxin He, Shen Nie, Fengqi Zhu, Yuankang Zhao, Tianyi Bai, Ran Yan, Jie Fu, Chongxuan Li, Binhang Yuan
Abstract: Diffusion LLMs have attracted growing interest, with plenty of recent work emphasizing their great potential in various downstream tasks; yet the long-context behavior of diffusion LLMs remains largely uncharted. We present a case study of post-training techniques for extending the context window of diffusion LLMs (i.e., LLaDA) without retraining from scratch. We show that a simple modification to the standard Rotary Positional Embeddings (RoPE) extension effectively accommodates the probabilistic modeling inherent in the diffusion process, enabling stable scaling to longer context ranges. We further compare masking strategies used during post-training and analyze their impact on optimization stability and long-range recall. Instantiating these insights, we introduce UltraLLaDA, a diffusion LLM with a 128K-token context window that, in our empirical evaluation on long-context tasks, significantly outperforms training-free baselines. Our experimental results highlight the special positional extension as a key lever for scaling diffusion LLMs to extended contexts and offer practical guidance for practitioners seeking 128K-scale context via efficient post-training.
Authors: Ming Tan, Wei Li, Hu Tao, Hailong Ma, Aodi Liu, Qian Chen, Zilong Wang
Abstract: Open-source large language models (LLMs) have demonstrated considerable dominance over proprietary LLMs in resolving neural processing tasks, thanks to the collaborative and sharing nature. Although full access to source codes, model parameters, and training data lays the groundwork for transparency, we argue that such a full-access manner is vulnerable to stego attacks, and their ill-effects are not fully understood. In this paper, we conduct a systematic formalization for stego attacks on open-source LLMs by enumerating all possible threat models associated with adversary objectives, knowledge, and capabilities. Therein, the threat posed by adversaries with internal knowledge, who inject payloads and triggers during the model sharing phase, is of practical interest. We go even further and propose the first stego attack on open-source LLMs, dubbed SASER, which wields impacts through identifying targeted parameters, embedding payloads, injecting triggers, and executing payloads sequentially. Particularly, SASER enhances the attack robustness against quantization-based local deployment by de-quantizing the embedded payloads. In addition, to achieve stealthiness, SASER devises the performance-aware importance metric to identify targeted parameters with the least degradation of model performance. Extensive experiments on LlaMA2-7B and ChatGLM3-6B, without quantization, show that the stealth rate of SASER outperforms existing stego attacks (for general DNNs) by up to 98.1%, while achieving the same attack success rate (ASR) of 100%. More importantly, SASER improves ASR on quantized models from 0 to 100% in all settings. We appeal for investigations on countermeasures against SASER in view of the significant attack effectiveness.
Authors: Yunlong Deng, Guangyi Chen, Tianpei Gu, Lingjing Kong, Yan Li, Zeyu Tang, Kun Zhang
Abstract: Vision-Language Models (VLMs) integrate visual knowledge with the analytical capabilities of Large Language Models (LLMs) through supervised visual instruction tuning, using image-question-answer triplets. However, the potential of VLMs trained without supervised instruction remains largely unexplored. This study validates that VLMs possess inherent self-refinement capabilities, enabling them to generate high-quality supervised data without external inputs and thereby learn autonomously. Specifically, to stimulate the self-refinement ability of VLMs, we propose a self-refinement framework based on a Triangular Consistency principle: within the image-query-answer triangle, any masked elements should be consistently and accurately reconstructed. The framework involves three steps: (1) We enable the instruction generation ability of VLMs by adding multi-task instruction tuning like image$\rightarrow$question-answer or image-answer$\rightarrow$question. (2) We generate image-query-answer triplets from unlabeled images and use the Triangular Consistency principle for filtering. (3) The model is further updated using the filtered synthetic data. To investigate the underlying mechanisms behind this self-refinement capability, we conduct a theoretical analysis from a causal perspective. Using the widely recognized LLaVA-1.5 as our baseline, our experiments reveal that the model can autonomously achieve consistent, though deliberately modest, improvements across multiple benchmarks without any external supervision, such as human annotations or environmental feedback. We expect that the insights of this study on the self-refinement ability of VLMs can inspire future research on the learning mechanism of VLMs. Code is available at https://github.com/dengyl20/SRF-LLaVA-1.5.
Authors: Ryota Takamidoa, Chiharu Suzukia, Hiroki Nakamoto
Abstract: A critical challenge in contemporary sports science lies in filling the gap between group-level insights derived from controlled hypothesis-driven experiments and the real-world need for personalized coaching tailored to individual athletes' unique movement patterns. This study developed a Personalized Motion Guidance Framework (PMGF) to enhance athletic performance by generating individualized motion-refinement guides using generative artificial intelligence techniques. PMGF leverages a vertical autoencoder to encode motion sequences into athlete-specific latent representations, which can then be directly manipulated to generate meaningful guidance motions. Two manipulation strategies were explored: (1) smooth interpolation between the learner's motion and a target (e.g., expert) motion to facilitate observational learning, and (2) shifting the motion pattern in an optimal direction in the latent space using a local optimization technique. The results of the validation experiment with data from 51 baseball pitchers revealed that (1) PMGF successfully generated smooth transitions in motion patterns between individuals across all 1,275 pitcher pairs, and (2) the features significantly altered through PMGF manipulations reflected known performance-enhancing characteristics, such as increased stride length and knee extension associated with higher ball velocity, indicating that PMGF induces biomechanically plausible improvements. We propose a future extension called general-PMGF to enhance the applicability of this framework. This extension incorporates bodily, environmental, and task constraints into the generation process, aiming to provide more realistic and versatile guidance across diverse sports contexts.
Authors: Kanishkha Jaisankar, Sunidhi Tandel
Abstract: Motion planning in complex scenarios is a core challenge in autonomous driving. Conventional methods apply predefined rules or learn from driving data to generate trajectories, while recent approaches leverage large language models (LLMs) for decision-making. However, it remains unclear whether LLMs truly capture human driving logic. We propose Align2Act, a motion planning framework that transforms instruction-tuned LLMs into interpretable planners aligned with human behavior. We derive structured driving instructions based on human reasoning patterns (e.g., anticipate hazards, yield at intersections) and traffic rules (e.g., stop at red lights, maintain lane boundaries). Our Align2ActChain module guides step-by-step reasoning to produce both an interpretable rationale and a safe trajectory. By fine-tuning LLaMA-2-7B with LoRA on one million scenarios from the nuPlan dataset, our method achieves an open-loop score of 85.17 and closed-loop scores of 70.31 (non-reactive) and 66.96 (reactive) on Test14-random. Unlike prior work focused on synthetic or open-loop settings, we demonstrate improved planning quality and human-likeness on the real-world nuPlan closed-loop benchmark. Ablation studies confirm that structured reasoning significantly improves performance over baseline LLM planners.
Authors: Zihan Zhang, Xize Cheng, Zhennan Jiang, Dongjie Fu, Jingyuan Chen, Zhou Zhao, Tao Jin
Abstract: Universal sound separation faces a fundamental misalignment: models optimized for low-level signal metrics often produce semantically contaminated outputs, failing to suppress perceptually salient interference from acoustically similar sources. To bridge this gap, we introduce MARS-Sep, a reinforcement learning framework that reformulates separation as decision making. Instead of simply regressing ground-truth masks, MARS-Sep learns a factorized Beta mask policy that is optimized by a clipped trust-region surrogate with entropy regularization and group-relative advantage normalization. Concretely, we sample masks from a frozen old policy, reconstruct waveforms, and update the current policy using clipped importance ratios-yielding substantially more stable and sample-efficient learning. Multimodal rewards, derived from an audio-text-vision encoder, directly incentivize semantic consistency with query prompts. We further propose a progressive alignment scheme to fine-tune this encoder, boosting its cross-modal discriminability and improving reward faithfulness. Extensive experiments on multiple benchmarks demonstrate consistent gains in Text-, Audio-, and Image-Queried separation, with notable improvements in signal metrics and semantic quality. Our code is available at https://anonymous.4open.science/r/MARS-Sep. Sound separation samples are available at https://mars-sep.github.io/.
URLs: https://anonymous.4open.science/r/MARS-Sep., https://mars-sep.github.io/.
Authors: Subhodip Panda, Dhruv Tarsadiya, Shashwat Sourav, Prathosh A. P, Sai Praneeth Karimireddy
Abstract: Influence estimation methods promise to explain and debug machine learning by estimating the impact of individual samples on the final model. Yet, existing methods collapse under training randomness: the same example may appear critical in one run and irrelevant in the next. Such instability undermines their use in data curation or cleanup since it is unclear if we indeed deleted/kept the correct datapoints. To overcome this, we introduce *f-influence* -- a new influence estimation framework grounded in hypothesis testing that explicitly accounts for training randomness, and establish desirable properties that make it suitable for reliable influence estimation. We also design a highly efficient algorithm **f**-**IN**fluence **E**stimation (**f-INE**) that computes f-influence **in a single training run**. Finally, we scale up f-INE to estimate influence of instruction tuning data on Llama-3.1-8B and show it can reliably detect poisoned samples that steer model opinions, demonstrating its utility for data cleanup and attributing model behavior.
Authors: Kanishkha Jaisankar, Xiaoyang Jiang, Feifan Liao, Jeethu Sreenivas Amuthan
Abstract: Energy-efficient and high-performance motor control remains a critical challenge in robotics, particularly for high-dimensional continuous control tasks with limited onboard resources. While Deep Reinforcement Learning (DRL) has achieved remarkable results, its computational demands and energy consumption limit deployment in resource-constrained environments. This paper introduces a novel framework combining population-coded Spiking Neural Networks (SNNs) with DRL to address these challenges. Our approach leverages the event-driven, asynchronous computation of SNNs alongside the robust policy optimization capabilities of DRL, achieving a balance between energy efficiency and control performance. Central to this framework is the Population-coded Spiking Actor Network (PopSAN), which encodes high-dimensional observations into neuronal population activities and enables optimal policy learning through gradient-based updates. We evaluate our method on the Isaac Gym platform using the PixMC benchmark with complex robotic manipulation tasks. Experimental results on the Franka robotic arm demonstrate that our approach achieves energy savings of up to 96.10% compared to traditional Artificial Neural Networks (ANNs) while maintaining comparable control performance. The trained SNN policies exhibit robust finger position tracking with minimal deviation from commanded trajectories and stable target height maintenance during pick-and-place operations. These results position population-coded SNNs as a promising solution for energy-efficient, high-performance robotic control in resource-constrained applications, paving the way for scalable deployment in real-world robotics systems.
Authors: Su-Hyeon Kim, Joonghyuk Hahn, Sooyoung Cha, Yo-Sub Han
Abstract: Code runtime optimization-the task of rewriting a given code to a faster one-remains challenging, as it requires reasoning about performance trade-offs involving algorithmic and structural choices. Recent approaches employ code-LLMs with slow-fast code pairs provided as optimization guidance, but such pair-based methods obscure the causal factors of performance gains and often lead to superficial pattern imitation rather than genuine performance reasoning. We introduce ECO, a performance-aware prompting framework for code optimization. ECO first distills runtime optimization instructions (ROIs) from reference slow-fast code pairs; Each ROI describes root causes of inefficiency and the rationales that drive performance improvements. For a given input code, ECO in parallel employs (i) a symbolic advisor to produce a bottleneck diagnosis tailored to the code, and (ii) an ROI retriever to return related ROIs. These two outputs are then composed into a performance-aware prompt, providing actionable guidance for code-LLMs. ECO's prompts are model-agnostic, require no fine-tuning, and can be easily prepended to any code-LLM prompt. Our empirical studies highlight that ECO prompting significantly improves code-LLMs' ability to generate efficient code, achieving speedups of up to 7.81x while minimizing correctness loss.
Authors: Zihan Chen, Yiming Zhang, Hengguang Zhou, Zenghui Ding, Yining Sun, Cho-Jui Hsieh
Abstract: Current benchmarks are inadequate for evaluating progress in reinforcement learning (RL) for large language models (LLMs).Despite recent benchmark gains reported for RL, we find that training on these benchmarks' training sets achieves nearly the same performance as training directly on the test sets, suggesting that the benchmarks cannot reliably separate further progress.To study this phenomenon, we introduce a diagnostic suite and the Oracle Performance Gap (OPG) metric that quantifies the performance difference between training on the train split versus the test split of a benchmark. We further analyze this phenomenon with stress tests and find that, despite strong benchmark scores, existing RL methods struggle to generalize across distribution shifts, varying levels of difficulty, and counterfactual scenarios: shortcomings that current benchmarks fail to reveal.We conclude that current benchmarks are insufficient for evaluating generalization and propose three core principles for designing more faithful benchmarks: sufficient difficulty, balanced evaluation, and distributional robustness.
Authors: Abdelkrim Zitouni, Mehdi Hennequin, Juba Agoun, Ryan Horache, Nadia Kabachi, Omar Rivasplata
Abstract: We derive a novel PAC-Bayesian generalization bound for reinforcement learning that explicitly accounts for Markov dependencies in the data, through the chain's mixing time. This contributes to overcoming challenges in obtaining generalization guarantees for reinforcement learning, where the sequential nature of data breaks the independence assumptions underlying classical bounds. Our bound provides non-vacuous certificates for modern off-policy algorithms like Soft Actor-Critic. We demonstrate the bound's practical utility through PB-SAC, a novel algorithm that optimizes the bound during training to guide exploration. Experiments across continuous control tasks show that our approach provides meaningful confidence certificates while maintaining competitive performance.
Authors: Zuha Fatima, Muhammad Anser Sohaib, Muhammad Talha, Sidra Sultana, Ayesha Kanwal, Nazia Perwaiz
Abstract: Glacial Lake Outburst Floods (GLOFs) are rare but destructive hazards in high mountain regions, yet predictive research is hindered by fragmented and unimodal data. Most prior efforts emphasize post-event mapping, whereas forecasting requires harmonized datasets that combine visual indicators with physical precursors. We present GLOFNet, a multimodal dataset for GLOF monitoring and prediction, focused on the Shisper Glacier in the Karakoram. It integrates three complementary sources: Sentinel-2 multispectral imagery for spatial monitoring, NASA ITS_LIVE velocity products for glacier kinematics, and MODIS Land Surface Temperature records spanning over two decades. Preprocessing included cloud masking, quality filtering, normalization, temporal interpolation, augmentation, and cyclical encoding, followed by harmonization across modalities. Exploratory analysis reveals seasonal glacier velocity cycles, long-term warming of ~0.8 K per decade, and spatial heterogeneity in cryospheric conditions. The resulting dataset, GLOFNet, is publicly available to support future research in glacial hazard prediction. By addressing challenges such as class imbalance, cloud contamination, and coarse resolution, GLOFNet provides a structured foundation for benchmarking multimodal deep learning approaches to rare hazard prediction.
Authors: Euhid Aman, Esteban Carlin, Hsing-Kuo Pao, Giovanni Beltrame, Ghaluh Indah Permata Sari, Yie-Tarng Chen
Abstract: Cross-attention transformers and other multimodal vision-language models excel at grounding and generation; however, their extensive, full-precision backbones make it challenging to deploy them on edge devices. Memory-augmented architectures enhance the utilization of past context; however, most works rarely pair them with aggressive edge-oriented quantization. We introduce BitMar, a quantized multimodal transformer that proposes an external human-like episodic memory for effective image-text generation on hardware with limited resources. BitMar utilizes 1.58-bit encoders, one for text (BitNet-style) and one for vision (DiNOv2-based), to create compact embeddings that are combined and used to query a fixed-size key-value episodic memory. During vector retrieval, the BitNet decoder applies per-layer conditioning, which increases the contextual relevance of generated content. The decoder also employs attention sinks with a sliding-window mechanism to process long or streaming inputs under tight memory budgets. The combination of per-layer conditioning and sliding-window attention achieves a strong quality-speed trade-off, delivering competitive captioning and multimodal understanding at low latency with a small model footprint. These characteristics make BitMar well-suited for edge deployment.
Authors: Giulio Ruffini
Abstract: In the algorithmic (Kolmogorov) view, agents are programs that track and compress sensory streams using generative programs. We propose a framework where the relevant structural prior is simplicity (Solomonoff) understood as \emph{compositional symmetry}: natural streams are well described by (local) actions of finite-parameter Lie pseudogroups on geometrically and topologically complex low-dimensional configuration manifolds (latent spaces). Modeling the agent as a generic neural dynamical system coupled to such streams, we show that accurate world-tracking imposes (i) \emph{structural constraints} -- equivariance of the agent's constitutive equations and readouts -- and (ii) \emph{dynamical constraints}: under static inputs, symmetry induces conserved quantities (Noether-style labels) in the agent dynamics and confines trajectories to reduced invariant manifolds; under slow drift, these manifolds move but remain low-dimensional. This yields a hierarchy of reduced manifolds aligned with the compositional factorization of the pseudogroup, providing a geometric account of the ``blessing of compositionality'' in deep models. We connect these ideas to the Spencer formalism for Lie pseudogroups and formulate a symmetry-based, self-contained version of predictive coding in which higher layers receive only \emph{coarse-grained residual transformations} (prediction-error coordinates) along symmetry directions unresolved at lower layers.
Authors: Di Wu abd Shuaidong Pan
Abstract: This paper proposes a modeling framework for dynamic topic evolution based on temporal large language models. The method first uses a large language model to obtain contextual embeddings of text and then introduces a temporal decay function and an attention mechanism. These components allow the model to adjust the importance of semantic units according to time intervals and capture topic variations across different periods. The temporal representations are then mapped into a latent topic space, where a state transition matrix is applied to describe the dynamic evolution of topics. A joint optimization objective constrains both semantic modeling and temporal consistency, ensuring diversity and smoothness in topic generation. The design emphasizes the unified modeling of semantic representation and temporal evolution, which improves topic coherence and diversity while enhancing stability and interpretability over time. Experiments on real-world corpora show that the framework effectively captures the generation, expansion, and decline of topics and outperforms existing models across multiple metrics. Overall, the proposed method provides a systematic solution for understanding dynamic semantic patterns in large-scale text, enriches the research paradigm of topic modeling, and supports complex text analysis tasks in multiple domains.
Authors: Maximos Kaliakatsos-Papakostas, Gregoris Bastas, Dimos Makris, Dorien Herremans, Vassilis Katsouros, Petros Maragos
Abstract: Guitar tablature transcription consists in deducing the string and the fret number on which each note should be played to reproduce the actual musical part. This assignment should lead to playable string-fret combinations throughout the entire track and, in general, preserve parsimonious motion between successive combinations. Throughout the history of guitar playing, specific chord fingerings have been developed across different musical styles that facilitate common idiomatic voicing combinations and motion between them. This paper presents a method for assigning guitar tablature notation to a given MIDI-based musical part (possibly consisting of multiple polyphonic tracks), i.e. no information about guitar-idiomatic expressional characteristics is involved (e.g. bending etc.) The current strategy is based on machine learning and requires a basic assumption about how much fingers can stretch on a fretboard; only standard 6-string guitar tuning is examined. The proposed method also examines the transcription of music pieces that was not meant to be played or could not possibly be played by a guitar (e.g. potentially a symphonic orchestra part), employing a rudimentary method for augmenting musical information and training/testing the system with artificial data. The results present interesting aspects about what the system can achieve when trained on the initial and augmented dataset, showing that the training with augmented data improves the performance even in simple, e.g. monophonic, cases. Results also indicate weaknesses and lead to useful conclusions about possible improvements.
Authors: Jianke Zhang, Yucheng Hu, Yanjiang Guo, Xiaoyu Chen, Yichen Liu, Wenna Chen, Chaochao Lu, Jianyu Chen
Abstract: Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage knowledge from large-scale pretraining, prior work has typically built generalist policies either on top of vision-language understanding models (VLMs) or generative models. However, both semantic understanding from vision-language pretraining and visual dynamics modeling from visual-generation pretraining are crucial for embodied robots. Recent unified models of generation and understanding have demonstrated strong capabilities in both comprehension and generation through large-scale pretraining. We posit that robotic policy learning can likewise benefit from the combined strengths of understanding, planning and continuous future representation learning. Building on this insight, we introduce UniCoD, which acquires the ability to dynamically model high-dimensional visual features through pretraining on over 1M internet-scale instructional manipulation videos. Subsequently, UniCoD is fine-tuned on data collected from the robot embodiment, enabling the learning of mappings from predictive representations to action tokens. Extensive experiments show our approach consistently outperforms baseline methods in terms of 9\% and 12\% across simulation environments and real-world out-of-distribution tasks.
Authors: Michal Sadowski, Maria Wyrzykowska, Lukasz Sztukiewicz, Tadija Radusinovi\'c, Jan Rzymkowski, Pawe{\l} W{\l}odarczyk-Pruszy\'nski, Miko{\l}aj Sacha, Piotr Kozakowski, Ruard van Workum, Stanislaw Kamil Jastrzebski
Abstract: Retrosynthesis is one of the domains transformed by the rise of generative models, and it is one where the problem of nonsensical or erroneous outputs (hallucinations) is particularly insidious: reliable assessment of synthetic plans is time-consuming, with automatic methods lacking. In this work, we present RetroTrim, a retrosynthesis system that successfully avoids nonsensical plans on a set of challenging drug-like targets. Compared to common baselines in the field, our system is not only the sole method that succeeds in filtering out hallucinated reactions, but it also results in the highest number of high-quality paths overall. The key insight behind RetroTrim is the combination of diverse reaction scoring strategies, based on machine learning models and existing chemical databases. We show that our scoring strategies capture different classes of hallucinations by analyzing them on a dataset of labeled retrosynthetic intermediates. To measure the performance of retrosynthesis systems, we propose a novel evaluation protocol for reactions and synthetic paths based on a structured review by expert chemists. Using this protocol, we compare systems on a set of 32 novel targets, curated to reflect recent trends in drug structures. While the insights behind our methodology are broadly applicable to retrosynthesis, our focus is on targets in the drug-like domain. By releasing our benchmark targets and the details of our evaluation protocol, we hope to inspire further research into reliable retrosynthesis.
Authors: Peiyin Chen, Zhuowei Yang, Hui Feng, Sheng Jiang, Rui Yan
Abstract: Audio-driven talking-head generation has advanced rapidly with diffusion-based generative models, yet producing temporally coherent videos with fine-grained motion control remains challenging. We propose DEMO, a flow-matching generative framework for audio-driven talking-portrait video synthesis that delivers disentangled, high-fidelity control of lip motion, head pose, and eye gaze. The core contribution is a motion auto-encoder that builds a structured latent space in which motion factors are independently represented and approximately orthogonalized. On this disentangled motion space, we apply optimal-transport-based flow matching with a transformer predictor to generate temporally smooth motion trajectories conditioned on audio. Extensive experiments across multiple benchmarks show that DEMO outperforms prior methods in video realism, lip-audio synchronization, and motion fidelity. These results demonstrate that combining fine-grained motion disentanglement with flow-based generative modeling provides a powerful new paradigm for controllable talking-head video synthesis.
Authors: Omid Reza Heidari, Siobhan Reid, Yassine Yaakoubi
Abstract: LLMs have advanced text-to-SQL generation, yet monolithic architectures struggle with complex reasoning and schema diversity. We propose AGENTIQL, an agent-inspired multi-expert framework that combines a reasoning agent for question decomposition, a coding agent for sub-query generation, and a refinement step for column selection. An adaptive router further balances efficiency and accuracy by selecting between our modular pipeline and a baseline parser. Several steps in the pipeline can be executed in parallel, making the framework scalable to larger workloads. Evaluated on the Spider benchmark, AGENTIQL improves execution accuracy and interpretability and achieves up to 86.07\% EX with 14B models using the Planner&Executor merging strategy. The attained performance is contingent upon the efficacy of the routing mechanism, thereby narrowing the gap to GPT-4-based SOTA (89.65% EX) while using much smaller open-source LLMs. Beyond accuracy, AGENTIQL enhances transparency by exposing intermediate reasoning steps, offering a robust, scalable, and interpretable approach to semantic parsing.
Authors: Gaojian Wang, Feng Lin, Tong Wu, Zhisheng Yan, Kui Ren
Abstract: With abundant, unlabeled real faces, how can we learn robust and transferable facial representations to boost generalization across various face security tasks? We make the first attempt and propose FS-VFM, a scalable self-supervised pre-training framework, to learn fundamental representations of real face images. We introduce three learning objectives, namely 3C, that synergize masked image modeling (MIM) and instance discrimination (ID), empowering FS-VFM to encode both local patterns and global semantics of real faces. Specifically, we formulate various facial masking strategies for MIM and devise a simple yet effective CRFR-P masking, which explicitly prompts the model to pursue meaningful intra-region Consistency and challenging inter-region Coherency. We present a reliable self-distillation mechanism that seamlessly couples MIM with ID to establish underlying local-to-global Correspondence. After pre-training, vanilla vision transformers (ViTs) serve as universal Vision Foundation Models for downstream Face Security tasks: cross-dataset deepfake detection, cross-domain face anti-spoofing, and unseen diffusion facial forensics. To efficiently transfer the pre-trained FS-VFM, we further propose FS-Adapter, a lightweight plug-and-play bottleneck atop the frozen backbone with a novel real-anchor contrastive objective. Extensive experiments on 11 public benchmarks demonstrate that our FS-VFM consistently generalizes better than diverse VFMs, spanning natural and facial domains, fully, weakly, and self-supervised paradigms, small, base, and large ViT scales, and even outperforms SOTA task-specific methods, while FS-Adapter offers an excellent efficiency-performance trade-off. The code and models are available on https://fsfm-3c.github.io/fsvfm.html.
Authors: Zhengbo Zhang, Zhiheng Lyu, Junhao Gong, Hongzhu Yi, Xinming Wang, Yuxuan Zhou, Jiabing Yang, Ping Nie, Yan Huang, Wenhu Chen
Abstract: Efficiently solving real-world problems with LLMs increasingly hinges on their ability to interact with dynamic web environments and autonomously acquire external information. While recent research like Search-R1 and WebDancer demonstrates strong performance in solving web tasks, they heavily rely on additional tools to convert the interactive web environment into static text content. This is in contrast to human browsing behaviors, which involve diverse interactions with the browser, such as scrolling, clicking, and typing. In this paper, we propose BrowserAgent, a more interactive agent that solves complex tasks through human-inspired browser actions. BrowserAgent operates directly on raw web pages via Playwright through a set of predefined browser actions. We adopt a two-stage training (Supervised Fine-Tuning (SFT) and Rejection Fine-Tuning (RFT)) to improve the model's generalization abilities. Despite using significantly less training data than Search-R1, BrowserAgent achieves more competitive results across different Open-QA tasks. Additionally, we introduce an explicit memory mechanism to store key conclusions across steps, further enhancing the model's reasoning capabilities for long-horizon tasks. Notably, BrowserAgent-7B can achieve around 20\% improvement over Search-R1 on multi-hop QA tasks like HotpotQA, 2Wiki, and Bamboogle. These results indicate that BrowserAgent can serve as a more advanced framework for more interactive and scalable web agents.
Authors: Jinxuan Li, Chaolei Tan, Haoxuan Chen, Jianxin Ma, Jian-Fang Hu, Wei-Shi Zheng, Jianhuang Lai
Abstract: Image-Language Foundation Models (ILFM) have demonstrated remarkable success in image-text understanding/generation tasks, providing transferable multimodal representations that generalize across diverse downstream image-based tasks. The advancement of video-text research has spurred growing interest in extending image-based models to the video domain. This paradigm, known as image-to-video transfer learning, succeeds in alleviating the substantial data and computational requirements associated with training video-language foundation models from scratch for video-text learning. This survey provides the first comprehensive review of this emerging field, which begins by summarizing the widely used ILFM and their capabilities. We then systematically classify existing image-to-video transfer learning strategies into two categories: frozen features and modified features, depending on whether the original representations from ILFM are preserved or undergo modifications. Building upon the task-specific nature of image-to-video transfer, this survey methodically elaborates these strategies and details their applications across a spectrum of video-text learning tasks, ranging from fine-grained (e.g., spatio-temporal video grounding) to coarse-grained (e.g., video question answering). We further present a detailed experimental analysis to investigate the efficacy of different image-to-video transfer learning paradigms on a range of downstream video understanding tasks. Finally, we identify prevailing challenges and highlight promising directions for future research. By offering a comprehensive and structured overview, this survey aims to establish a structured roadmap for advancing video-text learning based on existing ILFM, and to inspire future research directions in this rapidly evolving domain.
Authors: Jun Chen, Shichao Hu, Jiuxin Lin, Wenjie Li, Zihan Zhang, Xingchen Li, JinJiang Liu, Longshuai Xiao, Chao Weng, Lei Xie, Zhiyong Wu
Abstract: In-car multi-zone speech separation, which captures voices from different speech zones, plays a crucial role in human-vehicle interaction. Although previous SpatialNet has achieved notable results, its high computational cost still hinders real-time applications in vehicles. To this end, this paper proposes LSZone, a lightweight spatial information modeling architecture for real-time in-car multi-zone speech separation. We design a spatial information extraction-compression (SpaIEC) module that combines Mel spectrogram and Interaural Phase Difference (IPD) to reduce computational burden while maintaining performance. Additionally, to efficiently model spatial information, we introduce an extremely lightweight Conv-GRU crossband-narrowband processing (CNP) module. Experimental results demonstrate that LSZone, with a complexity of 0.56G MACs and a real-time factor (RTF) of 0.37, delivers impressive performance in complex noise and multi-speaker scenarios.
Authors: Yuma Ichikawa, Shuhei Kashiwamura, Ayaka Sakata
Abstract: Quantized neural network training optimizes a discrete, non-differentiable objective. The straight-through estimator (STE) enables backpropagation through surrogate gradients and is widely used. While previous studies have primarily focused on the properties of surrogate gradients and their convergence, the influence of quantization hyperparameters, such as bit width and quantization range, on learning dynamics remains largely unexplored. We theoretically show that in the high-dimensional limit, STE dynamics converge to a deterministic ordinary differential equation. This reveals that STE training exhibits a plateau followed by a sharp drop in generalization error, with plateau length depending on the quantization range. A fixed-point analysis quantifies the asymptotic deviation from the unquantized linear model. We also extend analytical techniques for stochastic gradient descent to nonlinear transformations of weights and inputs.
Authors: Usman Gani Joy, Shahadat kabir, Tasnim Niger
Abstract: Accurate climate forecasting is vital for Bangladesh, a region highly susceptible to climate change impacts on temperature and rainfall. Existing models often struggle to capture long-range dependencies and complex temporal patterns in climate data. This study introduces an advanced Long Short-Term Memory (LSTM) model integrated with an attention mechanism to enhance the prediction of temperature and rainfall dynamics. Utilizing comprehensive datasets from 1901-2023, sourced from NASA's POWER Project for temperature and the Humanitarian Data Exchange for rainfall, the model effectively captures seasonal and long-term trends. It outperforms baseline models, including XGBoost, Simple LSTM, and GRU, achieving a test MSE of 0.2411 (normalized units), MAE of 0.3860 degrees C, R^2 of 0.9834, and NRMSE of 0.0370 for temperature, and MSE of 1283.67 mm^2, MAE of 22.91 mm, R^2 of 0.9639, and NRMSE of 0.0354 for rainfall on monthly forecasts. The model demonstrates improved robustness with only a 20 percent increase in MSE under simulated climate trends (compared to an approximately 2.2-fold increase in baseline models without trend features) and a 50 percent degradation under regional variations (compared to an approximately 4.8-fold increase in baseline models without enhancements). These results highlight the model's ability to improve forecasting precision and offer potential insights into the physical processes governing climate variability in Bangladesh, supporting applications in climate-sensitive sectors.
Authors: Kyla Chasalow, Skyler Wu, Susan Murphy
Abstract: Missing data in online reinforcement learning (RL) poses challenges compared to missing data in standard tabular data or in offline policy learning. The need to impute and act at each time step means that imputation cannot be put off until enough data exist to produce stable imputation models. It also means future data collection and learning depend on previous imputations. This paper proposes fully online imputation ensembles. We find that maintaining multiple imputation pathways may help balance the need to capture uncertainty under missingness and the need for efficiency in online settings. We consider multiple approaches for incorporating these pathways into learning and action selection. Using a Grid World experiment with various types of missingness, we provide preliminary evidence that multiple imputation pathways may be a useful framework for constructing simple and efficient online missing data RL methods.
Authors: Yuan-Sen Ting
Abstract: Deep learning has generated diverse perspectives in astronomy, with ongoing discussions between proponents and skeptics motivating this review. We examine how neural networks complement classical statistics, extending our data analytical toolkit for modern surveys. Astronomy offers unique opportunities through encoding physical symmetries, conservation laws, and differential equations directly into architectures, creating models that generalize beyond training data. Yet challenges persist as unlabeled observations number in billions while confirmed examples with known properties remain scarce and expensive. This review demonstrates how deep learning incorporates domain knowledge through architectural design, with built-in assumptions guiding models toward physically meaningful solutions. We evaluate where these methods offer genuine advances versus claims requiring careful scrutiny. - Neural architectures overcome trade-offs between scalability, expressivity, and data efficiency by encoding physical symmetries and conservation laws into network structure, enabling learning from limited labeled data. - Simulation-based inference and anomaly detection extract information from complex, non-Gaussian distributions where analytical likelihoods fail, enabling field-level cosmological analysis and systematic discovery of rare phenomena. - Multi-scale neural modeling bridges resolution gaps in astronomical simulations, learning effective subgrid physics from expensive high-fidelity runs to enhance large-volume calculations where direct computation remains prohibitive. - Emerging paradigms-reinforcement learning for telescope operations, foundation models learning from minimal examples, and large language model agents for research automation-show promise though are still developing in astronomical applications.
Authors: Rajat Bhattacharjya, Woohyeok Park, Arnab Sarkar, Hyunwoo Oh, Mohsen Imani, Nikil Dutt
Abstract: Direction of Arrival (DoA) estimation techniques face a critical trade-off, as classical methods often lack accuracy in challenging, low signal-to-noise ratio (SNR) conditions, while modern deep learning approaches are too energy-intensive and opaque for resource-constrained, safety-critical systems. We introduce HYPERDOA, a novel estimator leveraging Hyperdimensional Computing (HDC). The framework introduces two distinct feature extraction strategies -- Mean Spatial-Lag Autocorrelation and Spatial Smoothing -- for its HDC pipeline, and then reframes DoA estimation as a pattern recognition problem. This approach leverages HDC's inherent robustness to noise and its transparent algebraic operations to bypass the expensive matrix decompositions and ``black-box'' nature of classical and deep learning methods, respectively. Our evaluation demonstrates that HYPERDOA achieves ~35.39% higher accuracy than state-of-the-art methods in low-SNR, coherent-source scenarios. Crucially, it also consumes ~93% less energy than competing neural baselines on an embedded NVIDIA Jetson Xavier NX platform. This dual advantage in accuracy and efficiency establishes HYPERDOA as a robust and viable solution for mission-critical applications on edge devices.
Authors: Ummy Maria Muna, Md Mehedi Hasan Shawon, Md Jobayer, Sumaiya Akter, Md Rakibul Hasan, Md. Golam Rabiul Alam
Abstract: The automated analysis of phonocardiograms is vital for the early diagnosis of cardiovascular disease, yet supervised deep learning is often constrained by the scarcity of expert-annotated data. In this paper, we propose the Self-Supervised Dual-Path Prototypical Network (SS-DPPN), a foundation model for cardiac audio representation and classification from unlabeled data. The framework introduces a dual-path contrastive learning based architecture that simultaneously processes 1D waveforms and 2D spectrograms using a novel hybrid loss. For the downstream task, a metric-learning approach using a Prototypical Network was used that enhances sensitivity and produces well-calibrated and trustworthy predictions. SS-DPPN achieves state-of-the-art performance on four cardiac audio benchmarks. The framework demonstrates exceptional data efficiency with a fully supervised model on three-fold reduction in labeled data. Finally, the learned representations generalize successfully across lung sound classification and heart rate estimation. Our experiments and findings validate SS-DPPN as a robust, reliable, and scalable foundation model for physiological signals.
Authors: Jiazheng Sun, Weixin Wang, Pan Xu
Abstract: We provide a unified algorithmic framework for ensemble sampling in nonlinear contextual bandits and develop corresponding regret bounds for two most common nonlinear contextual bandit settings: Generalized Linear Ensemble Sampling (\texttt{GLM-ES}) for generalized linear bandits and Neural Ensemble Sampling (\texttt{Neural-ES}) for neural contextual bandits. Both methods maintain multiple estimators for the reward model parameters via maximum likelihood estimation on randomly perturbed data. We prove high-probability frequentist regret bounds of $\mathcal{O}(d^{3/2} \sqrt{T} + d^{9/2})$ for \texttt{GLM-ES} and $\mathcal{O}(\widetilde{d} \sqrt{T})$ for \texttt{Neural-ES}, where $d$ is the dimension of feature vectors, $\widetilde{d}$ is the effective dimension of a neural tangent kernel matrix, and $T$ is the number of rounds. These regret bounds match the state-of-the-art results of randomized exploration algorithms in nonlinear contextual bandit settings. In the theoretical analysis, we introduce techniques that address challenges specific to nonlinear models. Practically, we remove fixed-time horizon assumptions by developing anytime versions of our algorithms, suitable when $T$ is unknown. Finally, we empirically evaluate \texttt{GLM-ES}, \texttt{Neural-ES}, and their anytime variants, demonstrating strong performance. Overall, our results establish ensemble sampling as a provable and practical randomized exploration approach for nonlinear contextual bandits.
Authors: Ling Sun, Charlotte Zhu, Shuju Shi
Abstract: General-purpose ASR underperforms for atypical speakers, such as L2 learners, reinforcing bias and limiting use in education and accessibility. Using the CEFR-graded Speak and Improve corpus, we show that naive fine-tuning of Whisper reduces average WER but simultaneously widens disparities and disproportionately harms lower-level learners. To address this, we propose two strategies: (i) proficiency-aware multitask learning, jointly optimizing ASR with proficiency classification, and (ii) targeted augmentation, applying spectrogram masking to low-proficiency speech to counter imbalance. These approaches reduce WER by up to 29.4 percent (relative) and insertion/deletion errors by as much as 58.6 percent (relative). Crucially, despite the severe imbalance of the dataset reflecting real-world distributions, both strategies consistently narrow proficiency gaps, advancing equitable ASR for L2 learners.
Authors: Shivani Shukla, Himanshu Joshi
Abstract: We introduce a general stochastic differential equation framework for modelling multiobjective optimization dynamics in iterative Large Language Model (LLM) interactions. Our framework captures the inherent stochasticity of LLM responses through explicit diffusion terms and reveals systematic interference patterns between competing objectives via an interference matrix formulation. We validate our theoretical framework using iterative code generation as a proof-of-concept application, analyzing 400 sessions across security, efficiency, and functionality objectives. Our results demonstrate strategy-dependent convergence behaviors with rates ranging from 0.33 to 1.29, and predictive accuracy achieving R2 = 0.74 for balanced approaches. This work proposes the feasibility of dynamical systems analysis for multi-objective LLM interactions, with code generation serving as an initial validation domain.
Authors: Shaharyar Ahmed Khan Tareen, Filza Khan Tareen
Abstract: Deep neural networks (DNNs) have provided brilliant performance across various tasks. However, this success often comes at the cost of unnecessarily large model sizes, high computational demands, and substantial memory footprints. Typically, powerful architectures are trained at full depths but not all datasets or tasks require such high model capacity. Training very deep architectures on relatively low-complexity datasets frequently leads to wasted computation, unnecessary energy consumption, and excessive memory usage, which in turn makes deployment of models on resource-constrained devices impractical. To address this problem, we introduce Optimally Deep Networks (ODNs), which provide a balance between model depth and task complexity. Specifically, we propose a NAS like training strategy called progressive depth expansion, which begins by training deep networks at shallower depths and incrementally increases their depth as the earlier blocks converge, continuing this process until the target accuracy is reached. ODNs use only the optimal depth for the given datasets, removing redundant layers. This cuts down future training and inference costs, lowers the memory footprint, enhances computational efficiency, and facilitates deployment on edge devices. Empirical results show that the optimal depths of ResNet-18 and ResNet-34 for MNIST and SVHN, achieve up to 98.64 % and 96.44 % reduction in memory footprint, while maintaining a competitive accuracy of 99.31 % and 96.08 %, respectively.
Authors: Ahmad Mohammadi, Reza Ahmari, Vahid Hemmati, Frederick Owusu-Ambrose, Mahmoud Nabil Mahmoud, Parham Kebria, Abdollah Homaifar, Mehrdad Saif
Abstract: As autonomous vehicles become an essential component of modern transportation, they are increasingly vulnerable to threats such as GPS spoofing attacks. This study presents an adaptive detection approach utilizing a dynamically tuned Density Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, designed to adjust the detection threshold ({\epsilon}) in real-time. The threshold is updated based on the recursive mean and standard deviation of displacement errors between GPS and in-vehicle sensors data, but only at instances classified as non-anomalous. Furthermore, an initial threshold, determined from 120,000 clean data samples, ensures the capability to identify even subtle and gradual GPS spoofing attempts from the beginning. To assess the performance of the proposed method, five different subsets from the real-world Honda Research Institute Driving Dataset (HDD) are selected to simulate both large and small magnitude GPS spoofing attacks. The modified algorithm effectively identifies turn-by-turn, stop, overshoot, and multiple small biased spoofing attacks, achieving detection accuracies of 98.621%, 99.960.1%, 99.880.1%, and 98.380.1%, respectively. This work provides a substantial advancement in enhancing the security and safety of AVs against GPS spoofing threats.
Authors: Jiayuan Sheng, Hanyang Zhao, Haoxian Chen, David D. Yao, Wenpin Tang
Abstract: Reinforcement Learning from Human Feedback (RLHF) is increasingly used to fine-tune diffusion models, but a key challenge arises from the mismatch between stochastic samplers used during training and deterministic samplers used during inference. In practice, models are fine-tuned using stochastic SDE samplers to encourage exploration, while inference typically relies on deterministic ODE samplers for efficiency and stability. This discrepancy induces a reward gap, raising concerns about whether high-quality outputs can be expected during inference. In this paper, we theoretically characterize this reward gap and provide non-vacuous bounds for general diffusion models, along with sharper convergence rates for Variance Exploding (VE) and Variance Preserving (VP) Gaussian models. Methodologically, we adopt the generalized denoising diffusion implicit models (gDDIM) framework to support arbitrarily high levels of stochasticity, preserving data marginals throughout. Empirically, our findings through large-scale experiments on text-to-image models using denoising diffusion policy optimization (DDPO) and mixed group relative policy optimization (MixGRPO) validate that reward gaps consistently narrow over training, and ODE sampling quality improves when models are updated using higher-stochasticity SDE training.
Authors: Mohammad Javad Ranjbar Kalahroodi, Heshaam Faili, Azadeh Shakery
Abstract: Persian Language, despite being spoken by over 100 million people worldwide, remains severely underrepresented in high-quality speech corpora, particularly for text-to-speech (TTS) synthesis applications. Existing Persian speech datasets are typically smaller than their English counterparts, which creates a key limitation for developing Persian speech technologies. We address this gap by introducing ParsVoice, the largest Persian speech corpus designed specifically for TTS applications. We created an automated pipeline that transforms raw audiobook content into TTS-ready data, incorporating components such as a BERT-based sentence completion detector, a binary search boundary optimization method for precise audio-text alignment, and multi-dimensional quality assessment frameworks tailored to Persian. The pipeline processes 2,000 audiobooks, yielding 3,526 hours of clean speech, which was further filtered into a 1,804-hour high-quality subset suitable for TTS, featuring more than 470 speakers. ParsVoice is the largest high-quality Persian speech dataset, offering speaker diversity and audio quality comparable to major English corpora. The complete dataset has been made publicly available to accelerate the development of Persian speech technologies and to serve as a template for other low-resource languages. The ParsVoice dataset is publicly available at ParsVoice (https://huggingface.co/datasets/MohammadJRanjbar/ParsVoice).
URLs: https://huggingface.co/datasets/MohammadJRanjbar/ParsVoice).
Authors: Sneha Varur, Anirudh R Hanchinamani, Tarun S Bagewadi, Uma Mudenagudi, Chaitra D Desai, Sujata C, Padmashree Desai, Sumit Meharwade
Abstract: In this paper, we propose a novel framework, Disentangled Style-Content GAN (DISC-GAN), which integrates style-content disentanglement with a cluster-specific training strategy towards photorealistic underwater image synthesis. The quality of synthetic underwater images is challenged by optical due to phenomena such as color attenuation and turbidity. These phenomena are represented by distinct stylistic variations across different waterbodies, such as changes in tint and haze. While generative models are well-suited to capture complex patterns, they often lack the ability to model the non-uniform conditions of diverse underwater environments. To address these challenges, we employ K-means clustering to partition a dataset into style-specific domains. We use separate encoders to get latent spaces for style and content; we further integrate these latent representations via Adaptive Instance Normalization (AdaIN) and decode the result to produce the final synthetic image. The model is trained independently on each style cluster to preserve domain-specific characteristics. Our framework demonstrates state-of-the-art performance, obtaining a Structural Similarity Index (SSIM) of 0.9012, an average Peak Signal-to-Noise Ratio (PSNR) of 32.5118 dB, and a Frechet Inception Distance (FID) of 13.3728.
Authors: Zhongju Yuan, Geraint Wiggins, Dick Botteldooren
Abstract: Today's deep learning architectures are primarily based on perceptron models, which do not capture the oscillatory dynamics characteristic of biological neurons. Although oscillatory systems have recently gained attention for their closer resemblance to neural behavior, they still fall short of modeling the intricate spatio-temporal interactions observed in natural neural circuits. In this paper, we propose a bio-inspired oscillatory state system (BioOSS) designed to emulate the wave-like propagation dynamics critical to neural processing, particularly in the prefrontal cortex (PFC), where complex activity patterns emerge. BioOSS comprises two interacting populations of neurons: p neurons, which represent simplified membrane-potential-like units inspired by pyramidal cells in cortical columns, and o neurons, which govern propagation velocities and modulate the lateral spread of activity. Through local interactions, these neurons produce wave-like propagation patterns. The model incorporates trainable parameters for damping and propagation speed, enabling flexible adaptation to task-specific spatio-temporal structures. We evaluate BioOSS on both synthetic and real-world tasks, demonstrating superior performance and enhanced interpretability compared to alternative architectures.
Authors: Bahar \.Ilgen, Georges Hattab
Abstract: Text simplification is essential for making public health information accessible to diverse populations, including those with limited health literacy. However, commonly used evaluation metrics in Natural Language Processing (NLP), such as BLEU, FKGL, and SARI, mainly capture surface-level features and fail to account for human-centered qualities like clarity, trustworthiness, tone, cultural relevance, and actionability. This limitation is particularly critical in high-stakes health contexts, where communication must be not only simple but also usable, respectful, and trustworthy. To address this gap, we propose the Human-Centered Readability Score (HCRS), a five-dimensional evaluation framework grounded in Human-Computer Interaction (HCI) and health communication research. HCRS integrates automatic measures with structured human feedback to capture the relational and contextual aspects of readability. We outline the framework, discuss its integration into participatory evaluation workflows, and present a protocol for empirical validation. This work aims to advance the evaluation of health text simplification beyond surface metrics, enabling NLP systems that align more closely with diverse users' needs, expectations, and lived experiences.
Authors: Md Abdullah Al Mazid, Liangdong Deng, Naphtali Rishe
Abstract: Clouds remain a critical challenge in optical satellite imagery, hindering reliable analysis for environmental monitoring, land cover mapping, and climate research. To overcome this, we propose MSCloudCAM, a Cross-Attention with Multi-Scale Context Network tailored for multispectral and multi-sensor cloud segmentation. Our framework exploits the spectral richness of Sentinel-2 (CloudSEN12) and Landsat-8 (L8Biome) data to classify four semantic categories: clear sky, thin cloud, thick cloud, and cloud shadow. MSCloudCAM combines a Swin Transformer backbone for hierarchical feature extraction with multi-scale context modules ASPP and PSP for enhanced scale-aware learning. A Cross-Attention block enables effective multisensor and multispectral feature fusion, while the integration of an Efficient Channel Attention Block (ECAB) and a Spatial Attention Module adaptively refine feature representations. Comprehensive experiments on CloudSEN12 and L8Biome demonstrate that MSCloudCAM delivers state-of-the-art segmentation accuracy, surpassing leading baseline architectures while maintaining competitive parameter efficiency and FLOPs. These results underscore the model's effectiveness and practicality, making it well-suited for large-scale Earth observation tasks and real-world applications.
Authors: Javier Garc\'ia-Sig\"uenza, Mirco Nanni, Fara\'on Llorens-Largo, Jos\'e F. Vicent
Abstract: This work addresses the challenge of using a deep learning model to prune graphs and the ability of this method to integrate explainability into spatio-temporal problems through a new approach. Instead of applying explainability to the model's behavior, we seek to gain a better understanding of the problem itself. To this end, we propose a novel model that integrates an optimized pruning mechanism capable of removing nodes from the graph during the training process, rather than doing so as a separate procedure. This integration allows the architecture to learn how to minimize prediction error while selecting the most relevant nodes. Thus, during training, the model searches for the most relevant subset of nodes, obtaining the most important elements of the problem, facilitating its analysis. To evaluate the proposed approach, we used several widely used traffic datasets, comparing the accuracy obtained by pruning with the model and with other methods. The experiments demonstrate that our method is capable of retaining a greater amount of information as the graph reduces in size compared to the other methods used. These results highlight the potential of pruning as a tool for developing models capable of simplifying spatio-temporal problems, thereby obtaining their most important elements.
Authors: Soraya S. Anvari, Rina R. Wehbe
Abstract: Large Language Models (LLMs) are increasingly deployed in mental health contexts, from structured therapeutic support tools to informal chat-based well-being assistants. While these systems increase accessibility, scalability, and personalization, their integration into mental health care brings privacy and safety challenges that have not been well-examined. Unlike traditional clinical interactions, LLM-mediated therapy often lacks a clear structure for what information is collected, how it is processed, and how it is stored or reused. Users without clinical guidance may over-disclose personal information, which is sometimes irrelevant to their presenting concern, due to misplaced trust, lack of awareness of data risks, or the conversational design of the system. This overexposure raises privacy concerns and also increases the potential for LLM bias, misinterpretation, and long-term data misuse. We propose a framework embedding Artificial Intelligence (AI) literacy interventions directly into mental health conversational systems, and outline a study plan to evaluate their impact on disclosure safety, trust, and user experience.
Authors: Mihir Gupte, Paolo Giusto, Ramesh S
Abstract: Large Language Models (LLMs) are adept at generating responses based on information within their context. While this ability is useful for interacting with structured data like code files, another popular method, Retrieval-Augmented Generation (RAG), retrieves relevant documents to augment the model's in-context learning. However, it is not well-explored how to best represent this retrieved knowledge for generating responses on structured data, particularly hierarchical structures like trees. In this work, we propose a novel bottom-up method to linearize knowledge from tree-like structures (like a GitHub repository) by generating implicit, aggregated summaries at each hierarchical level. This approach enables the knowledge to be stored in a knowledge base and used directly with RAG. We then compare our method to using RAG on raw, unstructured code, evaluating the accuracy and quality of the generated responses. Our results show that while response quality is comparable across both methods, our approach generates over 68% fewer documents in the retriever, a significant gain in efficiency. This finding suggests that leveraging implicit, linearized knowledge may be a highly effective and scalable strategy for handling complex, hierarchical data structures.
Authors: Vivek Acharya
Abstract: Generative AI is reshaping how software is designed, written, and maintained. Advances in large language models (LLMs) are enabling new development styles - from chat-oriented programming and 'vibe coding' to agentic programming - that can accelerate productivity and broaden access. This paper examines how AI-assisted techniques are changing software engineering practice, and the related issues of trust, accountability, and shifting skills. We survey iterative chat-based development, multi-agent systems, dynamic prompt orchestration, and integration via the Model Context Protocol (MCP). Using case studies and industry data, we outline both the opportunities (faster cycles, democratized coding) and the challenges (model reliability and cost) of applying generative AI to coding. We describe new roles, skills, and best practices for using AI in a responsible and effective way.
Authors: Clemence Mottez, Louisa Fay, Maya Varma, Sophie Ostmeier, Curtis Langlotz
Abstract: Deep learning models have shown promise in improving diagnostic accuracy from chest X-rays, but they also risk perpetuating healthcare disparities when performance varies across demographic groups. In this work, we present a comprehensive bias detection and mitigation framework targeting sex, age, and race-based disparities when performing diagnostic tasks with chest X-rays. We extend a recent CNN-XGBoost pipeline to support multi-label classification and evaluate its performance across four medical conditions. We show that replacing the final layer of CNN with an eXtreme Gradient Boosting classifier improves the fairness of the subgroup while maintaining or improving the overall predictive performance. To validate its generalizability, we apply the method to different backbones, namely DenseNet-121 and ResNet-50, and achieve similarly strong performance and fairness outcomes, confirming its model-agnostic design. We further compare this lightweight adapter training method with traditional full-model training bias mitigation techniques, including adversarial training, reweighting, data augmentation, and active learning, and find that our approach offers competitive or superior bias reduction at a fraction of the computational cost. Finally, we show that combining eXtreme Gradient Boosting retraining with active learning yields the largest reduction in bias across all demographic subgroups, both in and out of distribution on the CheXpert and MIMIC datasets, establishing a practical and effective path toward equitable deep learning deployment in clinical radiology.
Authors: Mohanakrishnan Hariharan, Satish Arvapalli, Seshu Barma, Evangeline Sheela
Abstract: We present an approach to software testing automation using Agentic Retrieval-Augmented Generation (RAG) systems for Quality Engineering (QE) artifact creation. We combine autonomous AI agents with hybrid vector-graph knowledge systems to automate test plan, case, and QE metric generation. Our approach addresses traditional software testing limitations by leveraging LLMs such as Gemini and Mistral, multi-agent orchestration, and enhanced contextualization. The system achieves remarkable accuracy improvements from 65% to 94.8% while ensuring comprehensive document traceability throughout the quality engineering lifecycle. Experimental validation of enterprise Corporate Systems Engineering and SAP migration projects demonstrates an 85% reduction in testing timeline, an 85% improvement in test suite efficiency, and projected 35% cost savings, resulting in a 2-month acceleration of go-live.
Authors: Haeji Jung, Jinju Kim, Kyungjin Kim, Youjeong Roh, David R. Mortensen
Abstract: Transliteration has emerged as a promising means to bridge the gap between various languages in multilingual NLP, showing promising results especially for languages using non-Latin scripts. We investigate the degree to which shared script, overlapping token vocabularies, and shared phonology contribute to performance of multilingual models. To this end, we conduct controlled experiments using three kinds of transliteration (romanization, phonemic transcription, and substitution ciphers) as well as orthography. We evaluate each model on two downstream tasks -- named entity recognition (NER) and natural language inference (NLI) -- and find that romanization significantly outperforms other input types in 7 out of 8 evaluation settings, largely consistent with our hypothesis that it is the most effective approach. We further analyze how each factor contributed to the success, and suggest that having longer (subword) tokens shared with pre-trained languages leads to better utilization of the model.
Authors: Zhenghan Tai, Hanwei Wu, Qingchen Hu, Jijun Chi, Hailin He, Lei Ding, Tung Sum Thomas Kwok, Bohuai Xiao, Yuchen Hua, Suyuchen Wang, Peng Lu, Muzhi Li, Yihong Wu, Liheng Ma, Jerry Huang, Jiayi Zhang, Gonghao Zhang, Chaolong Jiang, Jingrui Tian, Sicheng Lyu, Zeyu Li, Boyu Han, Fengran Mo, Xinyue Yu, Yufei Cui, Ling Zhou, Xinyu Wang
Abstract: Retrieval-Augmented Generation (RAG) is becoming increasingly essential for Question Answering (QA) in the financial sector, where accurate and contextually grounded insights from complex public disclosures are crucial. However, existing financial RAG systems face two significant challenges: (1) they struggle to process heterogeneous data formats, such as text, tables, and figures; and (2) they encounter difficulties in balancing general-domain applicability with company-specific adaptation. To overcome these challenges, we present VeritasFi, an innovative hybrid RAG framework that incorporates a multi-modal preprocessing pipeline alongside a cutting-edge two-stage training strategy for its re-ranking component. VeritasFi enhances financial QA through three key innovations: (1) A multi-modal preprocessing pipeline that seamlessly transforms heterogeneous data into a coherent, machine-readable format. (2) A tripartite hybrid retrieval engine that operates in parallel, combining deep multi-path retrieval over a semantically indexed document corpus, real-time data acquisition through tool utilization, and an expert-curated memory bank for high-frequency questions, ensuring comprehensive scope, accuracy, and efficiency. (3) A two-stage training strategy for the document re-ranker, which initially constructs a general, domain-specific model using anonymized data, followed by rapid fine-tuning on company-specific data for targeted applications. By integrating our proposed designs, VeritasFi presents a groundbreaking framework that greatly enhances the adaptability and robustness of financial RAG systems, providing a scalable solution for both general-domain and company-specific QA tasks. Code accompanying this work is available at https://github.com/simplew4y/VeritasFi.git.
Authors: Seshu Barma, Mohanakrishnan Hariharan, Satish Arvapalli
Abstract: An AI-ML-powered quality engineering approach uses AI-ML to enhance software quality assessments by predicting defects. Existing ML models struggle with noisy data types, imbalances, pattern recognition, feature extraction, and generalization. To address these challenges, we develop a new model, Adaptive Differential Evolution (ADE) based Quantum Variational Autoencoder-Transformer (QVAET) Model (ADE-QVAET). ADE combines with QVAET to obtain high-dimensional latent features and maintain sequential dependencies, resulting in enhanced defect prediction accuracy. ADE optimization enhances model convergence and predictive performance. ADE-QVAET integrates AI-ML techniques such as tuning hyperparameters for scalable and accurate software defect prediction, representing an AI-ML-driven technology for quality engineering. During training with a 90% training percentage, ADE-QVAET achieves high accuracy, precision, recall, and F1-score of 98.08%, 92.45%, 94.67%, and 98.12%, respectively, when compared to the Differential Evolution (DE) ML model.
Authors: Aadithya Srikanth, Mudit Gaur, Vaneet Aggarwal
Abstract: Diffusion models have demonstrated remarkable performance in generating high-dimensional samples across domains such as vision, language, and the sciences. Although continuous-state diffusion models have been extensively studied both empirically and theoretically, discrete-state diffusion models, essential for applications involving text, sequences, and combinatorial structures, remain significantly less understood from a theoretical standpoint. In particular, all existing analyses of discrete-state models assume score estimation error bounds without studying sample complexity results. In this work, we present a principled theoretical framework for discrete-state diffusion, providing the first sample complexity bound of $\widetilde{\mathcal{O}}(\epsilon^{-2})$. Our structured decomposition of the score estimation error into statistical, approximation, optimization, and clipping components offers critical insights into how discrete-state models can be trained efficiently. This analysis addresses a fundamental gap in the literature and establishes the theoretical tractability and practical relevance of discrete-state diffusion models.
Authors: Shuaicheng Zhang, Haohui Wang, Junhong Lin, Xiaojie Guo, Yada Zhu, Si Zhang, Dongqi Fu, Dawei Zhou
Abstract: Graph heterophily, where connected nodes have different labels, has attracted significant interest recently. Most existing works adopt a simplified approach - using low-pass filters for homophilic graphs and high-pass filters for heterophilic graphs. However, we discover that the relationship between graph heterophily and spectral filters is more complex - the optimal filter response varies across frequency components and does not follow a strict monotonic correlation with heterophily degree. This finding challenges conventional fixed filter designs and suggests the need for adaptive filtering to preserve expressiveness in graph embeddings. Formally, natural questions arise: Given a heterophilic graph G, how and to what extent will the varying heterophily degree of G affect the performance of GNNs? How can we design adaptive filters to fit those varying heterophilic connections? Our theoretical analysis reveals that the average frequency response of GNNs and graph heterophily degree do not follow a strict monotonic correlation, necessitating adaptive graph filters to guarantee good generalization performance. Hence, we propose [METHOD NAME], a simple yet powerful GNN, which extracts information across the heterophily spectrum and combines salient representations through adaptive mixing. [METHOD NAME]'s superior performance achieves up to 9.2% accuracy improvement over leading baselines across homophilic and heterophilic graphs.
Authors: Ahmed Alanazi, Duy Ho, Yugyung Lee
Abstract: Robots navigating dynamic, cluttered, and semantically complex environments must integrate perception, symbolic reasoning, and spatial planning to generalize across diverse layouts and object categories. Existing methods often rely on static priors or limited memory, constraining adaptability under partial observability and semantic ambiguity. We present GRIP, Grid-based Relay with Intermediate Planning, a unified, modular framework with three scalable variants: GRIP-L (Lightweight), optimized for symbolic navigation via semantic occupancy grids; GRIP-F (Full), supporting multi-hop anchor chaining and LLM-based introspection; and GRIP-R (Real-World), enabling physical robot deployment under perceptual uncertainty. GRIP integrates dynamic 2D grid construction, open-vocabulary object grounding, co-occurrence-aware symbolic planning, and hybrid policy execution using behavioral cloning, D* search, and grid-conditioned control. Empirical results on AI2-THOR and RoboTHOR benchmarks show that GRIP achieves up to 9.6% higher success rates and over $2\times$ improvement in path efficiency (SPL and SAE) on long-horizon tasks. Qualitative analyses reveal interpretable symbolic plans in ambiguous scenes. Real-world deployment on a Jetbot further validates GRIP's generalization under sensor noise and environmental variation. These results position GRIP as a robust, scalable, and explainable framework bridging simulation and real-world navigation.
Authors: Lakshana Iruni Assalaarachchi, Zainab Masood, Rashina Hoda, John Grundy
Abstract: Software practitioners are discussing GenAI transformations in software project management openly and widely. To understand the state of affairs, we performed a grey literature review using 47 publicly available practitioner sources including blogs, articles, and industry reports. We found that software project managers primarily perceive GenAI as an "assistant", "copilot", or "friend" rather than as a "PM replacement", with support of GenAI in automating routine tasks, predictive analytics, communication and collaboration, and in agile practices leading to project success. Practitioners emphasize responsible GenAI usage given concerns such as hallucinations, ethics and privacy, and lack of emotional intelligence and human judgment. We present upskilling requirements for software project managers in the GenAI era mapped to the Project Management Institute's talent triangle. We share key recommendations for both practitioners and researchers.
Authors: Junwon You, Dasol Kang, Jae-Hun Jung
Abstract: Contrastive Vision-Language Models (VLMs) have demonstrated strong zero-shot capabilities. However, their cross-modal alignment remains biased toward English due to limited multilingual multimodal data. Recent multilingual extensions have alleviated this gap but enforce instance-level alignment while neglecting the global geometry of the shared embedding space. We address this problem by introducing ToMCLIP (Topological Alignment for Multilingual CLIP), a topology-aware framework aligning embedding spaces with topology-preserving constraints. The proposed method applies persistent homology to define a topological alignment loss and approximates persistence diagram with theoretical error bounds using graph sparsification strategy. This work validates the proposed approach, showing enhanced structural coherence of multilingual representations, higher zero-shot accuracy on the CIFAR-100, and stronger multilingual retrieval performance on the xFlickr&CO. Beyond VLMs, the proposed approach provides a general method for incorporating topological alignment into representation learning.
Authors: Hanchang Cheng, Weimin Mu, Fan Liu, Weilin Zhu, Can Ma
Abstract: Time series anomaly detection(TSAD) is a critical task in signal processing field, ensuring the reliability of complex systems. Reconstruction-based methods dominate in TSAD. Among these methods, VAE-based methods have achieved promising results. Existing VAE-based methods suffer from the limitation of single-window feature and insufficient leveraging of long-term time and frequency information. We propose a Conditional Variational AutoEncoder with Long-term dependency and Probabilistic time-frequency fusion, named LPCVAE. LPCVAE introduces LSTM to capture long-term dependencies beyond windows. It further incorporates a Product-of-Experts (PoE) mechanism for adaptive and distribution-level probabilistic fusion. This design effectively mitigates time-frequency information loss. Extensive experiments on four public datasets demonstrate it outperforms state-of-the-art methods. The results confirm that integrating long-term time and frequency representations with adaptive fusion yields a robust and efficient solution for TSAD.
Authors: Geon Yeong Park, Inhwa Han, Serin Yang, Yeobin Hong, Seongmin Jeong, Heechan Jeon, Myeongjin Goh, Sung Won Yi, Jin Nam, Jong Chul Ye
Abstract: The exponential growth of the global makeup market has paralleled advancements in virtual makeup simulation technology. Despite the progress led by GANs, their application still encounters significant challenges, including training instability and limited customization capabilities. Addressing these challenges, we introduce DreamMakup - a novel training-free Diffusion model based Makeup Customization method, leveraging the inherent advantages of diffusion models for superior controllability and precise real-image editing. DreamMakeup employs early-stopped DDIM inversion to preserve the facial structure and identity while enabling extensive customization through various conditioning inputs such as reference images, specific RGB colors, and textual descriptions. Our model demonstrates notable improvements over existing GAN-based and recent diffusion-based frameworks - improved customization, color-matching capabilities, identity preservation and compatibility with textual descriptions or LLMs with affordable computational costs.
Authors: Yi Yu, Zhenxing Hu
Abstract: Explainable recommendation through counterfactual reasoning seeks to identify the influential aspects of items in recommendations, which can then be used as explanations. However, state-of-the-art approaches, which aim to minimize changes in product aspects while reversing their recommended decisions according to an aggregated decision boundary score, often lead to factual inaccuracies in explanations. To solve this problem, in this work we propose a novel method of Comparative Counterfactual Explanations for Recommendation (CoCountER). CoCountER creates counterfactual data based on soft swap operations, enabling explanations for recommendations of arbitrary pairs of comparative items. Empirical experiments validate the effectiveness of our approach.
Authors: Chunyu Xie, Bin Wang, Fanjing Kong, Jincheng Li, Dawei Liang, Ji Ao, Dawei Leng, Yuhui Yin
Abstract: Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that remains limited in current models, particularly in non-English settings. While models like CLIP perform well on global alignment, they often struggle to capture fine-grained details in object attributes, spatial relations, and linguistic expressions, with limited support for bilingual comprehension. To address these challenges, we introduce FG-CLIP 2, a bilingual vision-language model designed to advance fine-grained alignment for both English and Chinese. Our approach leverages rich fine-grained supervision, including region-text matching and long-caption modeling, alongside multiple discriminative objectives. We further introduce the Textual Intra-modal Contrastive (TIC) loss to better distinguish semantically similar captions. Trained on a carefully curated mixture of large-scale English and Chinese data, FG-CLIP 2 achieves powerful bilingual performance. To enable rigorous evaluation, we present a new benchmark for Chinese multimodal understanding, featuring long-caption retrieval and bounding box classification. Extensive experiments on 29 datasets across 8 tasks show that FG-CLIP 2 outperforms existing methods, achieving state-of-the-art results in both languages. We release the model, code, and benchmark to facilitate future research on bilingual fine-grained alignment.
Authors: Katherine M. Collins, Cedegao E. Zhang, Graham Todd, Lance Ying, Mauricio Barba da Costa, Ryan Liu, Prafull Sharma, Adrian Weller, Ionatan Kuperwajs, Lionel Wong, Joshua B. Tenenbaum, Thomas L. Griffiths
Abstract: Reasoning is not just about solving problems -- it is also about evaluating which problems are worth solving at all. Evaluations of artificial intelligence (AI) systems primarily focused on problem solving, historically by studying how models play games such as chess and Go. In this paper, we advocate for a new paradigm that assesses AI systems' evaluation of games. First, we introduce a formalism for evaluating such evaluations. We then leverage a large-scale dataset of over $100$ novel board games and over 450 human judgments to compare evaluations produced by modern language and reasoning models against those of people and symbolic computational agents. We consider two kinds of evaluative queries: assessing the payoff (or fairness) and the funness of games. These queries span two dimensions relevant to the design of evaluations of AI evaluations: how complex a query is to compute and how difficult a query is to quantify. Our results show that reasoning models are generally more aligned to people in their evaluations of games than non-reasoning language models. However, we observe a non-monotonic relationship: as models get closer to game-theoretic optimal, their fit to human data weakens. We also observe more "jaggedness" across models for assessing funness, in line with the greater difficulty of quantifying this query. Across queries and games, reasoning models show highly variable and unpredictable resource usage when assessing queries, pointing to the importance of imbuing more resource-rational meta-reasoning in language and reasoning models.
Authors: Zonghuan Xu, Xiang Zheng, Xingjun Ma, Yu-Gang Jiang
Abstract: With the growing deployment of Vision-Language-Action (VLA) models in real-world embodied AI systems, their increasing vulnerability to backdoor attacks poses a serious safety threat. A backdoored VLA agent can be covertly triggered by a pre-injected backdoor to execute adversarial actions, potentially causing system failures or even physical harm. Although backdoor attacks on VLA models have been explored, prior work has focused only on untargeted attacks, leaving the more practically threatening scenario of targeted manipulation unexamined. In this paper, we study targeted backdoor attacks on VLA models and introduce TabVLA, a novel framework that enables such attacks via black-box fine-tuning. TabVLA explores two deployment-relevant inference-time threat models: input-stream editing and in-scene triggering. It formulates poisoned data generation as an optimization problem to improve attack effectivess. Experiments with OpenVLA-7B on the LIBERO benchmark reveal that the vision channel is the principal attack surface: targeted backdoors succeed with minimal poisoning, remain robust across variations in trigger design, and are degraded only by positional mismatches between fine-tuning and inference triggers. We also investigate a potential detection-based defense against TabVLA, which reconstructs latent visual triggers from the input stream to flag activation-conditioned backdoor samples. Our work highlights the vulnerability of VLA models to targeted backdoor manipulation and underscores the need for more advanced defenses.
Authors: Yuda Bi, Ying Zhu, Vince D Calhoun
Abstract: We present a theoretical framework that extends classical information theory to finite and structured systems by redefining redundancy as a fundamental property of information organization rather than inefficiency. In this framework, redundancy is expressed as a general family of informational divergences that unifies multiple classical measures, such as mutual information, chi-squared dependence, and spectral redundancy, under a single geometric principle. This reveals that these traditional quantities are not isolated heuristics but projections of a shared redundancy geometry. The theory further predicts that redundancy is bounded both above and below, giving rise to an optimal equilibrium that balances over-compression (loss of structure) and over-coupling (collapse). While classical communication theory favors minimal redundancy for transmission efficiency, finite and structured systems, such as those underlying real-world learning, achieve maximal stability and generalization near this equilibrium. Experiments with masked autoencoders are used to illustrate and verify this principle: the model exhibits a stable redundancy level where generalization peaks. Together, these results establish redundancy as a measurable and tunable quantity that bridges the asymptotic world of communication and the finite world of learning.
Authors: Xuyao Deng, Yanjie Sun, Yong Dou, Kele Xu
Abstract: Scaling laws have profoundly shaped our understanding of model performance in computer vision and natural language processing, yet their application to general audio representation learning remains underexplored. A key challenge lies in the multifactorial nature of general audio representation-representation quality is jointly influenced by variables such as audio length, embedding dimensionality, model depth, model architecture, data volume, etc., many of which are difficult to isolate or express analytically. In this work, we present a systematic study of scaling laws for general audio representations by utilizing embedding effective rank (RankMe) as a unifying metric that encapsulates the impact of diverse variables on representation quality. RankMe enables a label-free, information-theoretic quantification of audio embeddings, allowing us to examine scaling behaviors across a wide hyper-parameter space, including model size, training data volume, computational budget, architectural configurations, etc. Our empirical findings reveal a consistent power-law relationship between RankMe and representation quality, suggesting that embedding effective rank serves as a reliable proxy for assessing and predicting model performance in audio representation learning. This work not only validates the applicability of classical scaling principles to the general audio domain but also offers a theoretically grounded and empirically robust framework for guiding future model scaling strategies in audio foundation models.
Authors: Zhiqiang Yuan, Wenjun Mao, Zhuo Chen, Xiyue Shang, Chong Wang, Yiling Lou, Xin Peng
Abstract: Translating C code into safe Rust is an effective way to ensure its memory safety. Compared to rule-based translation which produces Rust code that remains largely unsafe, LLM-based methods can generate more idiomatic and safer Rust code because LLMs have been trained on vast amount of human-written idiomatic code. Although promising, existing LLM-based methods still struggle with project-level C-to-Rust translation. They typically partition a C project into smaller units (\eg{} functions) based on call graphs and translate them bottom-up to resolve program dependencies. However, this bottom-up, unit-by-unit paradigm often fails to translate pointers due to the lack of a global perspective on their usage. To address this problem, we propose a novel C-Rust Pointer Knowledge Graph (KG) that enriches a code-dependency graph with two types of pointer semantics: (i) pointer-usage information which record global behaviors such as points-to flows and map lower-level struct usage to higher-level units; and (ii) Rust-oriented annotations which encode ownership, mutability, nullability, and lifetime. Synthesizing the \kg{} with LLMs, we further propose \ourtool{}, which implements a project-level C-to-Rust translation technique. In \ourtool{}, the \kg{} provides LLMs with comprehensive pointer semantics from a global perspective, thus guiding LLMs towards generating safe and idiomatic Rust code from a given C project. Our experiments show that \ourtool{} reduces unsafe usages in translated Rust by 99.9\% compared to both rule-based translation and traditional LLM-based rewriting, while achieving an average 29.3\% higher functional correctness than those fuzzing-enhanced LLM methods.
Authors: Xiaoyun Zhang, Xiaojian Yuan, Di Huang, Wang You, Chen Hu, Jingqing Ruan, Kejiang Chen, Xing Hu
Abstract: Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance it. However, RLVR training often suffers from policy entropy collapse, where the policy becomes overly deterministic, hindering exploration and limiting reasoning performance. While entropy regularization is a common remedy, its effectiveness is highly sensitive to the fixed coefficient, making it unstable across tasks and models. In this work, we revisit entropy regularization in RLVR and argue that its potential has been largely underestimated. Our analysis shows that (i) tasks of varying difficulty demand distinct exploration intensities, and (ii) balanced exploration may require the policy entropy to be maintained within a moderate range below its initial level. Therefore, we propose Adaptive Entropy Regularization (AER)--a framework that dynamically balances exploration and exploitation via three components: difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment. Experiments on multiple mathematical reasoning benchmarks show that AER consistently outperforms baselines, improving both reasoning accuracy and exploration capability.
Authors: Yejin Lee, Su-Hyeon Kim, Hyundong Jin, Dayoung Kim, Yeonsoo Kim, Yo-Sub Han
Abstract: Toxic content has become an increasingly critical social issue with the rapid expansion of online communication. While numerous studies explored methods for detecting and detoxifying such content, most have focused primarily on English, leaving low-resource language underrepresented. Consequently, Large Language Models~(LLMs) often struggle to identify and neutralize toxic expressions in these languages. This challenge becomes even more pronounced when user employ obfuscation techniques to evade detection systems. Therefore, we propose a \textbf{KOTOX: Korean Toxic Dataset} for deobfuscation and detoxicification to address this issue. We categorize various obfuscation approaches based on linguistic characteristics of Korean and define a set of transformation rules grounded in real-word examples. Using these rules, we construct three dataset versions (easy, normal, and hard) representing different levels of obfuscation difficulty. This is the first dataset that simultaneously supports deobfuscation and detoxification for the Korean language. We expect it to facilitate better understanding and mitigating of obfuscated toxic content in LLM for low-resource languages. Our code and data are available at https://github.com/leeyejin1231/KOTOX.
Authors: Wei Huang, Yue Liao, Yukang Chen, Jianhui Liu, Haoru Tan, Si Liu, Shiming Zhang, Shuicheng Yan, Xiaojuan Qi
Abstract: Mixture-of-Experts (MoE) effectively scales large language models (LLMs) and vision-language models (VLMs) by increasing capacity through sparse activation. However, preloading all experts into memory and activating multiple experts per input introduces significant computational and memory overhead, making the expert module a major contributor to model size and inference cost. To address this, we propose MC# (Mixture-Compressor-sharp), a framework that combines static quantization and dynamic expert pruning by leveraging the significance of experts and tokens for aggressive compression of MoE-LLMs/VLMs. To reduce storage and loading costs, we introduce Pre-Loading Mixed-Precision Quantization (PMQ), which optimizes bit allocation via linear programming, balancing expert importance and quantization error for a Pareto-optimal trade-off between size and performance. To reduce runtime computation, Online Top-any Pruning (OTP) uses Gumbel-Softmax sampling to dynamically select a subset of experts per token, enabling fine-grained control over activation. By combining PMQ's static bit-width optimization with OTP's dynamic routing, MC# achieves extreme compression with minimal accuracy loss. On DeepSeek-VL2, MC# achieves a 6.2 times weight reduction at 2.57 average bits with only a 1.7% accuracy drop across five multimodal benchmarks. Additionally, OTP reduces expert activation over 20% with less than 1% performance degradation, demonstrating strong potential for efficient MoE-based model deployment.
Authors: Zhuo Li, Yuege Feng, Dandan Guo, Jinpeng Hu, Anningzhe Gao, Xiang Wan
Abstract: The reward model (RM) plays a crucial role in aligning Large Language Models (LLMs) with human preferences through Reinforcement Learning, where the Bradley-Terry (BT) objective has been recognized as simple yet powerful, specifically for pairwise preference learning. However, BT-based RMs often struggle to effectively distinguish between similar preference responses, leading to insufficient separation between preferred and non-preferred outputs. Consequently, they may easily overfit easy samples and cannot generalize well to Out-Of-Distribution (OOD) samples, resulting in suboptimal performance. To address these challenges, this paper introduces an effective enhancement to BT-based RMs through an adaptive margin mechanism. Specifically, we design to dynamically adjust the RM focus on more challenging samples through margins, based on both semantic similarity and model-predicted reward differences, which is approached from a distributional perspective solvable with Optimal Transport (OT). By incorporating these factors into a principled OT cost matrix design, our adaptive margin enables the RM to better capture distributional differences between chosen and rejected responses, yielding significant improvements in performance, convergence speed, and generalization capabilities. Experimental results across multiple benchmarks demonstrate that our method outperforms several existing RM techniques, showcasing enhanced performance in both In-Distribution (ID) and OOD settings. Moreover, RLHF experiments support our practical effectiveness in better aligning LLMs with human preferences. Our code is available at https://github.com/BIRlz/APLOT
Authors: Jidong Li, Lingyong Fang, Haodong Zhao, Sufeng Duan, Gongshen Liu
Abstract: Multimodal large language models (MLLMs) have witnessed astonishing advancements in recent years. Despite these successes, MLLMs remain vulnerable to flase premise problems. However, existing benchmarks targeting this issue are limited in scope: they often lack fine-grained categorization, exhibit insufficient coverage, and thus fail to provide a rigorous evaluation of the ability of models to recognize false premises. To bridge this gap, we introduce a fully automated pipeline for constructing a comprehensive benchmark of false premise questions. Our method systematically categorizes the premises into three main types and thirteen subtypes according to the abilities required to identify the premises, resulting in the JBA dataset.Results show current MLLMs still struggle with false premise recognition. Building upon this benchmark, we further propose a recognition enhancement framework tailored to strengthen the robustness of MLLMs to detect false premises. Extensive experiments demonstrate that models trained with our framework achieve significant improvements in false premise recognition.
Authors: Yejin Lee, Hyeseon Ahn, Yo-Sub Han
Abstract: Hate speech remains prevalent in human society and continues to evolve in its forms and expressions. Modern advancements in internet and online anonymity accelerate its rapid spread and complicate its detection. However, hate speech datasets exhibit diverse characteristics primarily because they are constructed from different sources and platforms, each reflecting different linguistic styles and social contexts. Despite this diversity, prior studies on hate speech detection often rely on fixed methodologies without adapting to data-specific features. We introduce RV-HATE, a detection framework designed to account for the dataset-specific characteristics of each hate speech dataset. RV-HATE consists of multiple specialized modules, where each module focuses on distinct linguistic or contextual features of hate speech. The framework employs reinforcement learning to optimize weights that determine the contribution of each module for a given dataset. A voting mechanism then aggregates the module outputs to produce the final decision. RV-HATE offers two primary advantages: (1)~it improves detection accuracy by tailoring the detection process to dataset-specific attributes, and (2)~it also provides interpretable insights into the distinctive features of each dataset. Consequently, our approach effectively addresses implicit hate speech and achieves superior performance compared to conventional static methods. Our code is available at https://github.com/leeyejin1231/RV-HATE.
Authors: Zihan Wang, Zhiyong Ma, Zhongkui Ma, Shuofeng Liu, Akide Liu, Derui Wang, Minhui Xue, Guangdong Bai
Abstract: Recent AI regulations call for data that remain useful for innovation while resistant to misuse, balancing utility with protection at the model level. Existing approaches either perturb data to make it unlearnable or retrain models to suppress transfer, but neither governs inference by unknown models, and both typically require control over training. We propose non-transferable examples (NEs), a training-free and data-agnostic input-side usage-control mechanism. We recode inputs within a model-specific low-sensitivity subspace, preserving outputs for the authorized model while reducing performance on unauthorized models through subspace misalignment. We establish formal bounds that guarantee utility for the authorized model and quantify deviation for unauthorized ones, with the Hoffman-Wielandt inequality linking degradation to spectral differences. Empirically, NEs retain performance on diverse vision backbones and state-of-the-art vision-language models under common preprocessing, whereas non-target models collapse even with reconstruction attempts. These results establish NEs as a practical means to preserve intended data utility while preventing unauthorized exploitation. Our project is available at https://trusted-system-lab.github.io/model-specificity
URLs: https://trusted-system-lab.github.io/model-specificity
Authors: Hyeseon Ahn, Shinwoo Park, Yo-Sub Han
Abstract: The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a sophisticated attack that allows a malicious model to generate text containing the authentic-looking watermark of a trusted, victim model. This enables the seamless misattribution of harmful content, such as disinformation, to reputable sources. The key to our attack is repurposing watermark radioactivity, the unintended inheritance of data patterns during fine-tuning, from a discoverable trait into an attack vector. By distilling knowledge from a watermarked teacher model, our framework allows an attacker to steal and replicate the watermarking signal of the victim model. This work reveals a critical security gap in text authorship verification and calls for a paradigm shift towards technologies capable of distinguishing authentic watermarks from expertly imitated ones. Our code is available at https://github.com/hsannn/ditto.git.
Authors: Huanjin Yao, Ruifei Zhang, Jiaxing Huang, Jingyi Zhang, Yibo Wang, Bo Fang, Ruolin Zhu, Yongcheng Jing, Shunyu Liu, Guanbin Li, Dacheng Tao
Abstract: With the recent emergence of revolutionary autonomous agentic systems, research community is witnessing a significant shift from traditional static, passive, and domain-specific AI agents toward more dynamic, proactive, and generalizable agentic AI. Motivated by the growing interest in agentic AI and its potential trajectory toward AGI, we present a comprehensive survey on Agentic Multimodal Large Language Models (Agentic MLLMs). In this survey, we explore the emerging paradigm of agentic MLLMs, delineating their conceptual foundations and distinguishing characteristics from conventional MLLM-based agents. We establish a conceptual framework that organizes agentic MLLMs along three fundamental dimensions: (i) Agentic internal intelligence functions as the system's commander, enabling accurate long-horizon planning through reasoning, reflection, and memory; (ii) Agentic external tool invocation, whereby models proactively use various external tools to extend their problem-solving capabilities beyond their intrinsic knowledge; and (iii) Agentic environment interaction further situates models within virtual or physical environments, allowing them to take actions, adapt strategies, and sustain goal-directed behavior in dynamic real-world scenarios. To further accelerate research in this area for the community, we compile open-source training frameworks, training and evaluation datasets for developing agentic MLLMs. Finally, we review the downstream applications of agentic MLLMs and outline future research directions for this rapidly evolving field. To continuously track developments in this rapidly evolving field, we will also actively update a public repository at https://github.com/HJYao00/Awesome-Agentic-MLLMs.
Authors: Wei-Chieh Huang, Henry Peng Zou, Yaozu Wu, Dongyuan Li, Yankai Chen, Weizhi Zhang, Yangning Li, Angelo Zangari, Jizhou Guo, Chunyu Miao, Liancheng Fang, Langzhou He, Renhe Jiang, Philip S. Yu
Abstract: Deep research frameworks have shown promising capabilities in synthesizing comprehensive reports from web sources. While deep research possesses significant potential to address complex issues through planning and research cycles, existing frameworks are deficient in sufficient evaluation procedures and stage-specific protections. They typically treat evaluation as exact match accuracy of question-answering, but overlook crucial aspects of report quality such as credibility, coherence, breadth, depth, and safety. This oversight may result in hazardous or malicious sources being integrated into the final report. To address these issues, we introduce DEEPRESEARCHGUARD, a comprehensive framework featuring four-stage safeguards with open-domain evaluation of references and reports. We assess performance across multiple metrics, e.g., defense success rate and over-refusal rate, and five key report dimensions. In the absence of a suitable safety benchmark, we introduce DRSAFEBENCH, a stage-wise benchmark for deep research safety. Our evaluation spans diverse state-of-the-art LLMs, including GPT-4o, Gemini-2.5-flash, DeepSeek-v3, and o4-mini. DEEPRESEARCHGUARD achieves an average defense success rate improvement of 18.16% while reducing over-refusal rate by 6%. The input guard provides the most substantial early-stage protection by filtering out obvious risks, while the plan and research guards enhance citation discipline and source credibility. Through extensive experiments, we show that DEEPRESEARCHGUARD enables comprehensive open-domain evaluation and stage-aware defenses that effectively block harmful content propagation, while systematically improving report quality without excessive over-refusal rates. The code can be found via https://github.com/Jasonya/DeepResearchGuard.
Authors: Mahika Phutane, Hayoung Jung, Matthew Kim, Tanushree Mitra, Aditya Vashistha
Abstract: Large language models (LLMs) are increasingly under scrutiny for perpetuating identity-based discrimination in high-stakes domains such as hiring, particularly against people with disabilities (PwD). However, existing research remains largely Western-centric, overlooking how intersecting forms of marginalization--such as gender and caste--shape experiences of PwD in the Global South. We conduct a comprehensive audit of six LLMs across 2,820 hiring scenarios spanning diverse disability, gender, nationality, and caste profiles. To capture subtle intersectional harms and biases, we introduce ABLEIST (Ableism, Inspiration, Superhumanization, and Tokenism), a set of five ableism-specific and three intersectional harm metrics grounded in disability studies literature. Our results reveal significant increases in ABLEIST harms towards disabled candidates--harms that many state-of-the-art models failed to detect. These harms were further amplified by sharp increases in intersectional harms (e.g., Tokenism) for gender and caste-marginalized disabled candidates, highlighting critical blind spots in current safety tools and the need for intersectional safety evaluations of frontier models in high-stakes domains like hiring.
Authors: Tieyuan Chen, Xiaodong Chen, Haoxing Chen, Zhenzhong Lan, Weiyao Lin, Jianguo Li
Abstract: We introduce Dynamic Nested Depth (DND), a novel method that improves performance for off-the-shelf LLMs by selecting critical tokens to reprocess in a nested depth manner. Specifically, at the end of the given transformer layer, DND identifies more critical tokens with a router and feeds them back for an extra round of processing, effectively ``reviewing" difficult tokens while avoiding redundant computation for easier ones. The dynamic selection mechanism is tailored for precise control via two novel strategies: a router controlling loss to enhance token selection distinguishability, and a threshold control scheme to ensure selection stability. We demonstrate the effectiveness of DND by directly integrating it into pre-trained dense and MoE models during a post-training phase. On diverse benchmarks, this approach boosts the performances of the dense Qwen3-1.7B by 1.88% and the MoE Qwen3-30B-A3B by 0.87%, all with a minimal parameter and computing increase.
Authors: Haoran Liang, Yufa Zhou, Mohammad Talebi Kalaleh, Qipei Mei
Abstract: We introduce $\textbf{MASSE}$, the first Multi-Agent System for Structural Engineering, effectively integrating large language model (LLM)-based agents with real-world engineering workflows. Structural engineering is a fundamental yet traditionally stagnant domain, with core workflows remaining largely unchanged for decades despite its substantial economic impact and global market size. Recent advancements in LLMs have significantly enhanced their ability to perform complex reasoning, long-horizon planning, and precise tool utilization -- capabilities well aligned with structural engineering tasks such as interpreting design codes, executing load calculations, and verifying structural capacities. We present a proof-of-concept showing that most real-world structural engineering workflows can be fully automated through a training-free LLM-based multi-agent system. MASSE enables immediate deployment in professional environments, and our comprehensive validation on real-world case studies demonstrates that it can reduce expert workload from approximately two hours to mere minutes, while enhancing both reliability and accuracy in practical engineering scenarios.
Authors: Subhransu S. Bhattacharjee, Hao Lu, Dylan Campbell, Rahul Shome
Abstract: Priors are vital for planning under partial observability, yet difficult to obtain in practice. We present a sampling-based pipeline that leverages large-scale pretrained generative models to produce probabilistic priors capturing environmental uncertainty and spatio-semantic relationships in a zero-shot manner. Conditioned on partial observations, the pipeline recovers complete RGB-D point cloud samples with occupancy and target semantics, formulated to be directly useful in configuration-space planning. We establish a Matterport3D benchmark of rooms partially visible through doorways, where a robot must navigate to an unobserved target object. Effective priors for this setting must represent both occupancy and target-location uncertainty in unobserved regions. Experiments show that our approach recovers commonsense spatial semantics consistent with ground truth, yielding diverse, clean 3D point clouds usable in motion planning, highlight the promise of generative models as a rich source of priors for robotic planning.
Authors: Shasha Guo, Liang Pang, Xi Wang, Yanling Wang, Huawei Shen, Jing Zhang
Abstract: Auxiliary lines are essential for solving complex geometric problems but remain challenging for large vision-language models (LVLMs). Rather than editing diagrams to draw auxiliary lines, which current image editing models struggle to render with geometric precision, we generate textual descriptions of auxiliary-line constructions to better align with the representational strengths of LVLMs. To bridge the gap between textual descriptions and spatial structure, we propose a reinforcement learning framework that enhances diagram-text alignment. At the core of our approach is a cross-modal reward that evaluates how well the generated auxiliary-line description for an original diagram matches a ground-truth auxiliary-line diagram. Built on this reward, we present GeoVLMath, an open-source LVLM tailored to auxiliary-line reasoning in solid geometry. This fine-grained signal drives a GRPO-based RL stage, yielding precise diagram-text alignment. To support training, we develop a scalable data creation pipeline and construct AuxSolidMath, a dataset of 3,018 real-exam geometry problems with paired diagrams and aligned textual fields. At the 3B and 7B scales, GeoVLMath achieves competitive and often superior performance compared with strong open-source and proprietary LVLMs on auxiliary-line reasoning benchmarks.
Authors: Yeonseo Lee, Jungwook Mun, Hyosup Shin, Guebin Hwang, Junhee Nam, Taeyeop Lee, Sungho Jo
Abstract: Most robotic grasping methods are typically designed for single gripper types, which limits their applicability in real-world scenarios requiring diverse end-effectors. We propose XGrasp, a real-time gripper-aware grasp detection framework that efficiently handles multiple gripper configurations. The proposed method addresses data scarcity by systematically augmenting existing datasets with multi-gripper annotations. XGrasp employs a hierarchical two-stage architecture. In the first stage, a Grasp Point Predictor (GPP) identifies optimal locations using global scene information and gripper specifications. In the second stage, an Angle-Width Predictor (AWP) refines the grasp angle and width using local features. Contrastive learning in the AWP module enables zero-shot generalization to unseen grippers by learning fundamental grasping characteristics. The modular framework integrates seamlessly with vision foundation models, providing pathways for future vision-language capabilities. The experimental results demonstrate competitive grasp success rates across various gripper types, while achieving substantial improvements in inference speed compared to existing gripper-aware methods. Project page: https://sites.google.com/view/xgrasp
Authors: Runze Xia, Yupeng Ji, Yuxi Zhou, Haodong Liu, Teng Zhang, Piji Li
Abstract: Query-service relevance prediction in e-commerce search systems faces strict latency requirements that prevent the direct application of Large Language Models (LLMs). To bridge this gap, we propose a two-stage reasoning distillation framework to transfer reasoning capabilities from a powerful teacher LLM to a lightweight, deployment-friendly student model. In the first stage, we address the limitations of general-purpose LLMs by constructing a domain-adapted teacher model. This is achieved through a three-step process: domain-adaptive pre-training to inject platform knowledge, supervised fine-tuning to elicit reasoning skills, and preference optimization with a multi-dimensional reward model to ensure the generation of reliable and preference-aligned reasoning paths. This teacher can then automatically annotate massive query-service pairs from search logs with both relevance labels and reasoning chains. In the second stage, to address the challenges of architectural heterogeneity in standard distillation, we introduce Contrastive Reasoning Self-Distillation (CRSD). By modeling the behavior of the same student model under "standard" and "reasoning-augmented" inputs as a teacher-student relationship, CRSD enables the lightweight model to internalize the teacher's complex decision-making mechanisms without needing the explicit reasoning path at inference. Offline evaluations and online A/B testing in the Meituan search advertising system demonstrate that our framework achieves significant improvements across multiple metrics, validating its effectiveness and practical value.
Authors: Youngrok Park, Hojung Jung, Sangmin Bae, Se-Young Yun
Abstract: Diffusion models have achieved remarkable success as generative models. However, even a well-trained model can accumulate errors throughout the generation process. These errors become particularly problematic when arbitrary guidance is applied to steer samples toward desired properties, which often breaks sample fidelity. In this paper, we propose a general solution to address the off-manifold phenomenon observed in diffusion models. Our approach leverages a time predictor to estimate deviations from the desired data manifold at each timestep, identifying that a larger time gap is associated with reduced generation quality. We then design a novel guidance mechanism, `Temporal Alignment Guidance' (TAG), attracting the samples back to the desired manifold at every timestep during generation. Through extensive experiments, we demonstrate that TAG consistently produces samples closely aligned with the desired manifold at each timestep, leading to significant improvements in generation quality across various downstream tasks.
Authors: Huayi Wang, Wentao Zhang, Runyi Yu, Tao Huang, Junli Ren, Feiyu Jia, Zirui Wang, Xiaojie Niu, Xiao Chen, Jiahe Chen, Qifeng Chen, Jingbo Wang, Jiangmiao Pang
Abstract: Deploying humanoid robots to interact with real-world environments--such as carrying objects or sitting on chairs--requires generalizable, lifelike motions and robust scene perception. Although prior approaches have advanced each capability individually, combining them in a unified system is still an ongoing challenge. In this work, we present a physical-world humanoid-scene interaction system, PhysHSI, that enables humanoids to autonomously perform diverse interaction tasks while maintaining natural and lifelike behaviors. PhysHSI comprises a simulation training pipeline and a real-world deployment system. In simulation, we adopt adversarial motion prior-based policy learning to imitate natural humanoid-scene interaction data across diverse scenarios, achieving both generalization and lifelike behaviors. For real-world deployment, we introduce a coarse-to-fine object localization module that combines LiDAR and camera inputs to provide continuous and robust scene perception. We validate PhysHSI on four representative interactive tasks--box carrying, sitting, lying, and standing up--in both simulation and real-world settings, demonstrating consistently high success rates, strong generalization across diverse task goals, and natural motion patterns.
Authors: Tianyi Tan, Yinan Zheng, Ruiming Liang, Zexu Wang, Kexin Zheng, Jinliang Zheng, Jianxiong Li, Xianyuan Zhan, Jingjing Liu
Abstract: Modeling interactive driving behaviors in complex scenarios remains a fundamental challenge for autonomous driving planning. Learning-based approaches attempt to address this challenge with advanced generative models, removing the dependency on over-engineered architectures for representation fusion. However, brute-force implementation by simply stacking transformer blocks lacks a dedicated mechanism for modeling interactive behaviors that are common in real driving scenarios. The scarcity of interactive driving data further exacerbates this problem, leaving conventional imitation learning methods ill-equipped to capture high-value interactive behaviors. We propose Flow Planner, which tackles these problems through coordinated innovations in data modeling, model architecture, and learning scheme. Specifically, we first introduce fine-grained trajectory tokenization, which decomposes the trajectory into overlapping segments to decrease the complexity of whole trajectory modeling. With a sophisticatedly designed architecture, we achieve efficient temporal and spatial fusion of planning and scene information, to better capture interactive behaviors. In addition, the framework incorporates flow matching with classifier-free guidance for multi-modal behavior generation, which dynamically reweights agent interactions during inference to maintain coherent response strategies, providing a critical boost for interactive scenario understanding. Experimental results on the large-scale nuPlan dataset and challenging interactive interPlan dataset demonstrate that Flow Planner achieves state-of-the-art performance among learning-based approaches while effectively modeling interactive behaviors in complex driving scenarios.
Authors: Wonah Kim, Jeonghyeon Park, Dongsan Jun, Jungkyu Han, Sejin Chun
Abstract: Disentangling complex causal relationships is important for accurate detection of anomalies. In multivariate time series analysis, dynamic interactions among data variables over time complicate the interpretation of causal relationships. Traditional approaches assume statistical independence between variables in unsupervised settings, whereas recent methods capture feature correlations through graph representation learning. However, their representations fail to explicitly infer the causal relationships over different time periods. To solve the problem, we propose Causally Disentangled Representation Learning for Anomaly Detection (CDRL4AD) to detect anomalies and identify their causal relationships in multivariate time series. First, we design the causal process as model input, the temporal heterogeneous graph, and causal relationships. Second, our representation identifies causal relationships over different time periods and disentangles latent variables to infer the corresponding causal factors. Third, our experiments on real-world datasets demonstrate that CDRL4AD outperforms state-of-the-art methods in terms of accuracy and root cause analysis. Fourth, our model analysis validates hyperparameter sensitivity and the time complexity of CDRL4AD. Last, we conduct a case study to show how our approach assists human experts in diagnosing the root causes of anomalies.
Authors: Huizai Yao, Sicheng Zhao, Shuo Lu, Hui Chen, Yangyang Li, Guoping Liu, Tengfei Xing, Chenggang Yan, Jianhua Tao, Guiguang Ding
Abstract: Source-Free Object Detection (SFOD) enables knowledge transfer from a source domain to an unsupervised target domain for object detection without access to source data. Most existing SFOD approaches are either confined to conventional object detection (OD) models like Faster R-CNN or designed as general solutions without tailored adaptations for novel OD architectures, especially Detection Transformer (DETR). In this paper, we introduce Feature Reweighting ANd Contrastive Learning NetworK (FRANCK), a novel SFOD framework specifically designed to perform query-centric feature enhancement for DETRs. FRANCK comprises four key components: (1) an Objectness Score-based Sample Reweighting (OSSR) module that computes attention-based objectness scores on multi-scale encoder feature maps, reweighting the detection loss to emphasize less-recognized regions; (2) a Contrastive Learning with Matching-based Memory Bank (CMMB) module that integrates multi-level features into memory banks, enhancing class-wise contrastive learning; (3) an Uncertainty-weighted Query-fused Feature Distillation (UQFD) module that improves feature distillation through prediction quality reweighting and query feature fusion; and (4) an improved self-training pipeline with a Dynamic Teacher Updating Interval (DTUI) that optimizes pseudo-label quality. By leveraging these components, FRANCK effectively adapts a source-pre-trained DETR model to a target domain with enhanced robustness and generalization. Extensive experiments on several widely used benchmarks demonstrate that our method achieves state-of-the-art performance, highlighting its effectiveness and compatibility with DETR-based SFOD models.
Authors: Xianlin Liu, Yan Gong, Bohao Li, Jiajing Huang, Bowen Du, Junchen Ye, Liyan Xu
Abstract: With the widespread adoption of Computer-Aided Design(CAD) drawings in engineering, architecture, and industrial design, the ability to accurately interpret and analyze these drawings has become increasingly critical. Among various subtasks, panoptic symbol spotting plays a vital role in enabling downstream applications such as CAD automation and design retrieval. Existing methods primarily focus on geometric primitives within the CAD drawings to address this task, but they face following major problems: they usually overlook the rich textual annotations present in CAD drawings and they lack explicit modeling of relationships among primitives, resulting in incomprehensive understanding of the holistic drawings. To fill this gap, we propose a panoptic symbol spotting framework that incorporates textual annotations. The framework constructs unified representations by jointly modeling geometric and textual primitives. Then, using visual features extract by pretrained CNN as the initial representations, a Transformer-based backbone is employed, enhanced with a type-aware attention mechanism to explicitly model the different types of spatial dependencies between various primitives. Extensive experiments on the real-world dataset demonstrate that the proposed method outperforms existing approaches on symbol spotting tasks involving textual annotations, and exhibits superior robustness when applied to complex CAD drawings.
Authors: Shuwei Chen, Jiajun Cui, Zhengqi Xu, Fan Zhang, Jiangke Fan, Teng Zhang, Xingxing Wang
Abstract: Click-through rate (CTR) prediction, which models behavior sequence and non-sequential features (e.g., user/item profiles or cross features) to infer user interest, underpins industrial recommender systems. However, most methods face three forms of heterogeneity that degrade predictive performance: (i) Feature Heterogeneity persists when limited sequence side features provide less granular interest representation compared to extensive non-sequential features, thereby impairing sequence modeling performance; (ii) Context Heterogeneity arises because a user's interest in an item will be influenced by other items, yet point-wise prediction neglects cross-item interaction context from the entire item set; (iii) Architecture Heterogeneity stems from the fragmented integration of specialized network modules, which compounds the model's effectiveness, efficiency and scalability in industrial deployments. To tackle the above limitations, we propose HoMer, a Homogeneous-Oriented TransforMer for modeling sequential and set-wise contexts. First, we align sequence side features with non-sequential features for accurate sequence modeling and fine-grained interest representation. Second, we shift the prediction paradigm from point-wise to set-wise, facilitating cross-item interaction in a highly parallel manner. Third, HoMer's unified encoder-decoder architecture achieves dual optimization through structural simplification and shared computation, ensuring computational efficiency while maintaining scalability with model size. Without arduous modification to the prediction pipeline, HoMer successfully scales up and outperforms our industrial baseline by 0.0099 in the AUC metric, and enhances online business metrics like CTR/RPM by 1.99%/2.46%. Additionally, HoMer saves 27% of GPU resources via preliminary engineering optimization, further validating its superiority and practicality.
Authors: Martin Schuck, Sherif Samy, Angela P. Schoellig
Abstract: Many robotic control tasks require policies to act on orientations, yet the geometry of SO(3) makes this nontrivial. Because SO(3) admits no global, smooth, minimal parameterization, common representations such as Euler angles, quaternions, rotation matrices, and Lie algebra coordinates introduce distinct constraints and failure modes. While these trade-offs are well studied for supervised learning, their implications for actions in reinforcement learning remain unclear. We systematically evaluate SO(3) action representations across three standard continuous control algorithms, PPO, SAC, and TD3, under dense and sparse rewards. We compare how representations shape exploration, interact with entropy regularization, and affect training stability through empirical studies and analyze the implications of different projections for obtaining valid rotations from Euclidean network outputs. Across a suite of robotics benchmarks, we quantify the practical impact of these choices and distill simple, implementation-ready guidelines for selecting and using rotation actions. Our results highlight that representation-induced geometry strongly influences exploration and optimization and show that representing actions as tangent vectors in the local frame yields the most reliable results across algorithms.
Authors: Junjie Lu, Yuliang Liu, Chaofeng Qu, Wei Shen, Zhouhan Lin, Min Xu
Abstract: Current approaches for strengthening LLM reasoning tend to introduce a training bias toward human-like reasoning trajectories. In step-wise preference optimization, in particular, dependence on human or higher-capacity model annotations for intermediate steps limits exploration of alternative, non-human-like reasoning paths and thus constrains achievable performance. Furthermore, through a small-scale pilot study, we observed that in approximately 75% of cases, the model's first erroneous step occurs after the lowest-confidence point. This suggests that guiding the model at its lowest-confidence point before an error provides more accurate supervision than locating the first explicit error. In this paper, we propose Confidence-Guided Reasoning Path Preference Optimization (CGPO), a method that leverages a confidence signal to identify points of maximal uncertainty in the model's reasoning process and applies self-generated, non-human-like reasoning-path guidance to mitigate trajectory drift. Our experiments span diverse models applied to both code and mathematical reasoning tasks. The results show that, with the same amount of training data, our method using data generated by a small model can achieve better performance in most cases compared with approaches using data generated by a strong model or human-annotated.
Authors: Xinfeng Li, Dong Huang, Jie Li, Hongyi Cai, Zhenhong Zhou, Wei Dong, XiaoFeng Wang, Yang Liu
Abstract: The autonomy and contextual complexity of LLM-based agents render traditional access control (AC) mechanisms insufficient. Static, rule-based systems designed for predictable environments are fundamentally ill-equipped to manage the dynamic information flows inherent in agentic interactions. This position paper argues for a paradigm shift from binary access control to a more sophisticated model of information governance, positing that the core challenge is not merely about permission, but about governing the flow of information. We introduce Agent Access Control (AAC), a novel framework that reframes AC as a dynamic, context-aware process of information flow governance. AAC operates on two core modules: (1) multi-dimensional contextual evaluation, which assesses not just identity but also relationships, scenarios, and norms; and (2) adaptive response formulation, which moves beyond simple allow/deny decisions to shape information through redaction, summarization, and paraphrasing. This vision, powered by a dedicated AC reasoning engine, aims to bridge the gap between human-like nuanced judgment and scalable Al safety, proposing a new conceptual lens for future research in trustworthy agent design.
Authors: Cheol-Hui Lee, Hwa-Yeon Lee, Min-Kyung Jung, Dong-Joo Kim
Abstract: Missing or corrupted modalities are common in physiological signal-based medical applications owing to hardware constraints or motion artifacts. However, most existing methods assume the availability of all modalities, resulting in substantial performance degradation in the absence of any modality. To overcome this limitation, this study proposes PhysioME, a robust framework designed to ensure reliable performance under missing modality conditions. PhysioME adopts: (1) a multimodal self-supervised learning approach that combines contrastive learning with masked prediction; (2) a Dual-PathNeuroNet backbone tailored to capture the temporal dynamics of each physiological signal modality; and (3) a restoration decoder that reconstructs missing modality tokens, enabling flexible processing of incomplete inputs. The experimental results show that PhysioME achieves high consistency and generalization performance across various missing modality scenarios. These findings highlight the potential of PhysioME as a reliable tool for supporting clinical decision-making in real-world settings with imperfect data availability.
Authors: Guangzhi Sun, Yixuan Li, Xiaodong Wu, Yudong Yang, Wei Li, Zejun Ma, Chao Zhang
Abstract: Continuous, high-frame-rate, high-resolution processing of long video streams is critical for future AI agents, yet current video-understanding LLMs struggle to scale. Offline, fixed-frame-number methods require the stream length to adapt frame rates; streaming methods constrain memory by merging or discarding tokens, losing information. We propose video-SALMONN S, a streaming audio-visual LLM that, to our knowledge, is the first to process 3-hour videos at 1 FPS and 360p resolution under a fixed memory budget. Our model introduces (i) a test-time-training (TTT) memory module that continually updates token representations to capture long-range dependencies by replacing token merging, and (ii) a prompt-dependent memory reader that selectively retrieves context-relevant content from fixed-size memory. The TTT module is optimised with a Hessian-free conjugate-gradient procedure (TTT_HF) for efficient adaptation. On long-video benchmarks (Video-MME, LVBench, VideoEvalPro), video-SALMONN S sustains high-quality understanding on multi-hour videos with 10k frames and 1M tokens. Our 8B-parameter model achieves 74.2% overall and 67.8% on the Video-MME long split, outperforming both offline and streaming baselines.
Authors: Jens Van Nooten, Andriy Kosar, Guy De Pauw, Walter Daelemans
Abstract: Distance-based unsupervised text classification is a method within text classification that leverages the semantic similarity between a label and a text to determine label relevance. This method provides numerous benefits, including fast inference and adaptability to expanding label sets, as opposed to zero-shot, few-shot, and fine-tuned neural networks that require re-training in such cases. In multi-label distance-based classification and information retrieval algorithms, thresholds are required to determine whether a text instance is "similar" to a label or query. Similarity between a text and label is determined in a dense embedding space, usually generated by state-of-the-art sentence encoders. Multi-label classification complicates matters, as a text instance can have multiple true labels, unlike in multi-class or binary classification, where each instance is assigned only one label. We expand upon previous literature on this underexplored topic by thoroughly examining and evaluating the ability of sentence encoders to perform distance-based classification. First, we perform an exploratory study to verify whether the semantic relationships between texts and labels vary across models, datasets, and label sets by conducting experiments on a diverse collection of realistic multi-label text classification (MLTC) datasets. We find that similarity distributions show statistically significant differences across models, datasets and even label sets. We propose a novel method for optimizing label-specific thresholds using a validation set. Our label-specific thresholding method achieves an average improvement of 46% over normalized 0.5 thresholding and outperforms uniform thresholding approaches from previous work by an average of 14%. Additionally, the method demonstrates strong performance even with limited labeled examples.
Authors: Daniel Scalena, Leonidas Zotos, Elisabetta Fersini, Malvina Nissim, Ahmet \"Ust\"un
Abstract: With the rise of reasoning language models and test-time scaling methods as a paradigm for improving model performance, substantial computation is often required to generate multiple candidate sequences from the same prompt. This enables exploration of different reasoning paths toward the correct solution, however, allocates the same compute budget for each prompt. Grounded on the assumption that different prompts carry different degrees of complexity, and thus different computation needs, we propose EAGer, a training-free generation method that leverages model uncertainty through token-wise entropy distribution to reduce redundant computation and concurrently improve overall performance. EAGer allows branching to multiple reasoning paths only in the presence of high-entropy tokens, and then reallocates the saved compute budget to the instances where exploration of alternative paths is most needed. We find that across multiple open-source models on complex reasoning benchmarks such as AIME 2025, EAGer can reallocate the budget without accessing target labels, achieving the best efficiency-performance trade-off in terms of reasoning length and Pass@k. When target labels are accessible, EAGer generates up to 65% fewer tokens (hence saving compute) and achieves up to 37% improvement in Pass@k compared to the Full Parallel Sampling.
Authors: Yesung Cho, Sungmin Lee, Geongyu Lee, Minkyung Lee, Jongbae Park, Dongmyung Shin
Abstract: Recent studies in pathology foundation models have shown that scaling training data, diversifying cancer types, and increasing model size consistently improve their performance. However, giga-scale foundation models, which are trained on hundreds of thousands of slides covering tens of cancer types and contain billions of parameters, pose significant challenges for practical use due to their tremendous computational costs in both development and deployment. In this work, we present a novel strategy, named the G2L framework, to increase the performance of large-scale foundation models, which consist of only $15\%$ of the parameters of giga-scale models, to a comparable performance level of giga-scale models in cancer-specific tasks. Our approach applies knowledge distillation, transferring the capabilities of a giga-scale model to a large-scale model, using just 1K pathology slides of a target cancer (e.g., breast, prostate, etc.). The resulting distilled model not only outperformed state-of-the-art models of the same size (i.e., large-scale) across several benchmarks but also, interestingly, surpassed the giga-scale teacher and huge-scale models in some benchmarks. In addition, the distilled model exhibited a higher robustness index, indicating improved resilience to image variations originating from multiple institutions. These findings suggest that the proposed distillation approach for a large-scale model is a data- and parameter-efficient way to achieve giga-scale-level performance for cancer-specific applications without prohibitive computational burden.
Authors: Ole-Johan Skrede, Manohar Pradhan, Maria Xepapadakis Isaksen, Tarjei Sveinsgjerd Hveem, Ljiljana Vlatkovic, Arild Nesbakken, Kristina Lindemann, Gunnar B Kristensen, Jenneke Kasius, Alain G Zeimet, Odd Terje Brustugun, Lill-Tove Rasmussen Busund, Elin H Richardsen, Erik Skaaheim Haug, Bj{\o}rn Brennhovd, Emma Rewcastle, Melinda Lillesand, Vebj{\o}rn Kvikstad, Emiel Janssen, David J Kerr, Knut Liest{\o}l, Fritz Albregtsen, Andreas Kleppe
Abstract: Deep learning is expected to aid pathologists by automating tasks such as tumour segmentation. We aimed to develop one universal tumour segmentation model for histopathological images and examine its performance in different cancer types. The model was developed using over 20 000 whole-slide images from over 4 000 patients with colorectal, endometrial, lung, or prostate carcinoma. Performance was validated in pre-planned analyses on external cohorts with over 3 000 patients across six cancer types. Exploratory analyses included over 1 500 additional patients from The Cancer Genome Atlas. Average Dice coefficient was over 80% in all validation cohorts with en bloc resection specimens and in The Cancer Genome Atlas cohorts. No loss of performance was observed when comparing the universal model with models specialised on single cancer types. In conclusion, extensive and rigorous evaluations demonstrate that generic tumour segmentation by a single model is possible across cancer types, patient populations, sample preparations, and slide scanners.
Authors: Xinhui Chen, Zuchao Li, Mengqi Gao, Yufeng Zhang, Chak Tou Leong, Haoyang Li, Jiaqi Chen
Abstract: Deciphering the function of unseen protein sequences is a fundamental challenge with broad scientific impact, yet most existing methods depend on task-specific adapters or large-scale supervised fine-tuning. We introduce the "Protein-as-Second-Language" framework, which reformulates amino-acid sequences as sentences in a novel symbolic language that large language models can interpret through contextual exemplars. Our approach adaptively constructs sequence-question-answer triples that reveal functional cues in a zero-shot setting, without any further training. To support this process, we curate a bilingual corpus of 79,926 protein-QA instances spanning attribute prediction, descriptive understanding, and extended reasoning. Empirically, our method delivers consistent gains across diverse open-source LLMs and GPT-4, achieving up to 17.2% ROUGE-L improvement (average +7%) and even surpassing fine-tuned protein-specific language models. These results highlight that generic LLMs, when guided with protein-as-language cues, can outperform domain-specialized models, offering a scalable pathway for protein understanding in foundation models.
Authors: Vasilije Stambolic, Aritra Dhar, Lukas Cavigelli
Abstract: Retrieval-Augmented Generation (RAG) increases the reliability and trustworthiness of the LLM response and reduces hallucination by eliminating the need for model retraining. It does so by adding external data into the LLM's context. We develop a new class of black-box attack, RAG-Pull, that inserts hidden UTF characters into queries or external code repositories, redirecting retrieval toward malicious code, thereby breaking the models' safety alignment. We observe that query and code perturbations alone can shift retrieval toward attacker-controlled snippets, while combined query-and-target perturbations achieve near-perfect success. Once retrieved, these snippets introduce exploitable vulnerabilities such as remote code execution and SQL injection. RAG-Pull's minimal perturbations can alter the model's safety alignment and increase preference towards unsafe code, therefore opening up a new class of attacks on LLMs.
Authors: Chris Xing Tian, Weihao Xie, Zhen Chen, Zhengyuan Yi, Hui Liu, Haoliang Li, Shiqi Wang, Siwei Ma
Abstract: Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning power of large language models (LLMs) with external retrieval to enable domain-grounded responses. Effectively adapting RAG systems to domain-specific settings requires specialized, context-rich training data beyond general-purpose question-answering. Here, we propose RAGen, a scalable and modular framework for generating domain-grounded question-answer-context (QAC) triples tailored to diverse RAG adaptation approaches. RAGen produces these QAC triples by identifying key concepts in documents, generating diverse questions guided by Bloom's Taxonomy-inspired principles, and pairing them with precise answers extracted from relevant contexts. RAGen supports multiple RAG adaptation strategies, including the optimization of key components such as the LLM, retriever, and embedding model, etc. Its modular pipeline features semantic chunking, hierarchical concept extraction, and multi-chunk retrieval, along with the introduction of curated distractor contexts to promote robust reasoning. Designed for scalability, RAGen efficiently handles large and evolving document corpora without redundant processing, making it especially suitable for dynamic evolving domains such as scientific research and enterprise knowledge bases.
Authors: Saad Obaid ul Islam, Anne Lauscher, Goran Glava\v{s}
Abstract: Large language models (LLMs) can correctly answer "When was Einstein born?" yet fail to provide the same date when writing about Einstein's life revealing a fundamental inconsistency in how models access factual knowledge across task complexities. While models display impressive accuracy on factual question-answering benchmarks, the reliability gap between simple and complex queries remains poorly understood, eroding their trustworthiness. In this work, we introduce Short-Long Form Alignment for Factual Question Answering (SLAQ), a controlled evaluation framework that compares LLMs' answers to the same factual questions asked (a) in isolation (short) vs. (b) integrated into complex queries (long). Looking at 16 LLMs across 600 queries, we find a systematic misalignment of answers to the corresponding short and long queries. We further uncover position-dependent accuracy loss and momentum effects where consecutive correct or incorrect answers create self-reinforcing patterns. Through mechanistic analysis, we find that aligned facts activate overlapping model internals, and that metrics based on mechanistic similarity can predict short-long answer alignment with up to 78% accuracy. Our work establishes factual consistency over query complexity as an important aspect of LLMs' trustworthiness and challenges current evaluation practices, which implicitly assume that good performance for simple factual queries implies reliability in more complex knowledge-seeking tasks too.
Authors: Battemuulen Naranbat, Seyed Sahand Mohammadi Ziabari, Yousuf Nasser Al Husaini, Ali Mohammed Mansoor Alsahag
Abstract: Ensuring fairness in natural language processing for moral sentiment classification is challenging, particularly under cross-domain shifts where transformer models are increasingly deployed. Using the Moral Foundations Twitter Corpus (MFTC) and Moral Foundations Reddit Corpus (MFRC), this work evaluates BERT and DistilBERT in a multi-label setting with in-domain and cross-domain protocols. Aggregate performance can mask disparities: we observe pronounced asymmetry in transfer, with Twitter->Reddit degrading micro-F1 by 14.9% versus only 1.5% for Reddit->Twitter. Per-label analysis reveals fairness violations hidden by overall scores; notably, the authority label exhibits Demographic Parity Differences of 0.22-0.23 and Equalized Odds Differences of 0.40-0.41. To address this gap, we introduce the Moral Fairness Consistency (MFC) metric, which quantifies the cross-domain stability of moral foundation detection. MFC shows strong empirical validity, achieving a perfect negative correlation with Demographic Parity Difference (rho = -1.000, p < 0.001) while remaining independent of standard performance metrics. Across labels, loyalty demonstrates the highest consistency (MFC = 0.96) and authority the lowest (MFC = 0.78). These findings establish MFC as a complementary, diagnosis-oriented metric for fairness-aware evaluation of moral reasoning models, enabling more reliable deployment across heterogeneous linguistic contexts. .
Authors: Neilansh Chauhan, Piyush Kumar Gupta, Faraz Doja
Abstract: Effective pneumonia diagnosis is often challenged by the difficulty of deploying large, computationally expensive deep learning models in resource-limited settings. This study introduces LightPneumoNet, an efficient, lightweight convolutional neural network (CNN) built from scratch to provide an accessible and accurate diagnostic solution for pneumonia detection from chest X-rays. Our model was trained on a public dataset of 5,856 chest X-ray images. Preprocessing included image resizing to 224x224, grayscale conversion, and pixel normalization, with data augmentation (rotation, zoom, shear) to prevent overfitting. The custom architecture features four blocks of stacked convolutional layers and contains only 388,082 trainable parameters, resulting in a minimal 1.48 MB memory footprint. On the independent test set, our model delivered exceptional performance, achieving an overall accuracy of 0.942, precision of 0.92, and an F1-Score of 0.96. Critically, it obtained a sensitivity (recall) of 0.99, demonstrating a near-perfect ability to identify true pneumonia cases and minimize clinically significant false negatives. Notably, LightPneumoNet achieves this high recall on the same dataset where existing approaches typically require significantly heavier architectures or fail to reach comparable sensitivity levels. The model's efficiency enables deployment on low-cost hardware, making advanced computer-aided diagnosis accessible in underserved clinics and serving as a reliable second-opinion tool to improve patient outcomes.
Authors: Michael Schlichtkrull
Abstract: When AI agents retrieve and reason over external documents, adversaries can manipulate the data they receive to subvert their behaviour. Previous research has studied indirect prompt injection, where the attacker injects malicious instructions. We argue that injection of instructions is not necessary to manipulate agents - attackers could instead supply biased, misleading, or false information. We term this an attack by content. Existing defenses, which focus on detecting hidden commands, are ineffective against attacks by content. To defend themselves and their users, agents must critically evaluate retrieved information, corroborating claims with external evidence and evaluating source trustworthiness. We argue that this is analogous to an existing NLP task, automated fact-checking, which we propose to repurpose as a cognitive self-defense tool for agents.
Authors: Birat Poudel, Satyam Ghimire, Sijan Bhattarai, Saurav Bhandari, Suramya Sharma Dahal
Abstract: Sign languages serve as essential communication systems for individuals with hearing and speech impairments. However, digital linguistic dataset resources for underrepresented sign languages, such as Nepali Sign Language (NSL), remain scarce. This study introduces the first benchmark dataset for NSL, consisting of 36 gesture classes with 1,500 samples per class, designed to capture the structural and visual features of the language. To evaluate recognition performance, we fine-tuned MobileNetV2 and ResNet50 architectures on the dataset, achieving classification accuracies of 90.45% and 88.78%, respectively. These findings demonstrate the effectiveness of convolutional neural networks in sign recognition tasks, particularly within low-resource settings. To the best of our knowledge, this work represents the first systematic effort to construct a benchmark dataset and assess deep learning approaches for NSL recognition, highlighting the potential of transfer learning and fine-tuning for advancing research in underexplored sign languages.
Authors: Rui Xu, Jiawei Chen, Zhaoxia Yin, Cong Kong, Xinpeng Zhang
Abstract: The widespread use of large language models (LLMs) and open-source code has raised ethical and security concerns regarding the distribution and attribution of source code, including unauthorized redistribution, license violations, and misuse of code for malicious purposes. Watermarking has emerged as a promising solution for source attribution, but existing techniques rely heavily on hand-crafted transformation rules, abstract syntax tree (AST) manipulation, or task-specific training, limiting their scalability and generality across languages. Moreover, their robustness against attacks remains limited. To address these limitations, we propose CodeMark-LLM, an LLM-driven watermarking framework that embeds watermark into source code without compromising its semantics or readability. CodeMark-LLM consists of two core components: (i) Semantically Consistent Embedding module that applies functionality-preserving transformations to encode watermark bits, and (ii) Differential Comparison Extraction module that identifies the applied transformations by comparing the original and watermarked code. Leveraging the cross-lingual generalization ability of LLM, CodeMark-LLM avoids language-specific engineering and training pipelines. Extensive experiments across diverse programming languages and attack scenarios demonstrate its robustness, effectiveness, and scalability.
Authors: Yuxuan Chen, Ruotong Yang, Zhengyang Zhang, Mehreen Ahmed, Yanming Wang
Abstract: Microscopic characterizations, such as Scanning Electron Microscopy (SEM), are widely used in scientific research for visualizing and analyzing microstructures. Determining the scale bars is an important first step of accurate SEM analysis; however, currently, it mainly relies on manual operations, which is both time-consuming and prone to errors. To address this issue, we propose a multi-modal and automated scale bar detection and extraction framework that provides concurrent object detection, text detection and text recognition with a Large Language Model (LLM) agent. The proposed framework operates in four phases; i) Automatic Dataset Generation (Auto-DG) model to synthesize a diverse dataset of SEM images ensuring robust training and high generalizability of the model, ii) scale bar object detection, iii) information extraction using a hybrid Optical Character Recognition (OCR) system with DenseNet and Convolutional Recurrent Neural Network (CRNN) based algorithms, iv) an LLM agent to analyze and verify accuracy of the results. The proposed model demonstrates a strong performance in object detection and accurate localization with a precision of 100%, recall of 95.8%, and a mean Average Precision (mAP) of 99.2% at IoU=0.5 and 69.1% at IoU=0.5:0.95. The hybrid OCR system achieved 89% precision, 65% recall, and a 75% F1 score on the Auto-DG dataset, significantly outperforming several mainstream standalone engines, highlighting its reliability for scientific image analysis. The LLM is introduced as a reasoning engine as well as an intelligent assistant that suggests follow-up steps and verifies the results. This automated method powered by an LLM agent significantly enhances the efficiency and accuracy of scale bar detection and extraction in SEM images, providing a valuable tool for microscopic analysis and advancing the field of scientific imaging.
Authors: Antonio Montieri, Alfredo Nascita, Antonio Pescap\`e
Abstract: Generative AI (GenAI) chatbots are now pervasive in digital ecosystems, yet their network traffic remains largely underexplored. This study presents an in-depth investigation of traffic generated by three leading chatbots (ChatGPT, Copilot, and Gemini) when accessed via Android mobile apps for both text and image generation. Using a dedicated capture architecture, we collect and label two complementary workloads: a 60-hour generic dataset with unconstrained prompts, and a controlled dataset built from identical prompts across GenAI apps and replicated via conventional messaging apps to enable one-to-one comparisons. This dual design allows us to address practical research questions on the distinctiveness of GenAI traffic, its differences from widely deployed traffic categories, and its novel implications for network usage. To this end, we provide fine-grained traffic characterization at trace, flow, and protocol levels, and model packet-sequence dynamics with Multimodal Markov Chains. Our analyses reveal app- and content-specific traffic patterns, particularly in volume, uplink/downlink profiles, and protocol adoption. We highlight the predominance of TLS, with Gemini extensively leveraging QUIC, ChatGPT exclusively using TLS 1.3, and app- and content-specific Server Name Indication (SNI) values. A payload-based occlusion analysis quantifies SNI's contribution to classification: masking it reduces F1-score by up to 20 percentage points in GenAI app traffic classification. Finally, compared with conventional messaging apps when carrying the same content, GenAI chatbots exhibit unique traffic characteristics, highlighting new stress factors for mobile networks, such as sustained upstream activity, with direct implications for network monitoring and management. We publicly release the datasets to support reproducibility and foster extensions to other use cases.
Authors: Guangyu Wei, Ke Han, Yueming Lyu, Yu Luo, Yue Jiang, Caifeng Shan, Nicu Sebe
Abstract: Fake news detection becomes particularly challenging in real-time scenarios, where emerging events often lack sufficient supporting evidence. Existing approaches often rely heavily on external evidence and therefore struggle to generalize under evidence scarcity. To address this issue, we propose Evaluation-Aware Selection of Experts (EASE), a novel framework for real-time fake news detection that dynamically adapts its decision-making process according to the assessed sufficiency of available evidence. EASE introduces a sequential evaluation mechanism comprising three independent perspectives: (1) Evidence-based evaluation, which assesses evidence and incorporates it into decision-making only when the evidence is sufficiently supportive; (2) Reasoning-based evaluation, which leverages the world knowledge of large language models (LLMs) and applies them only when their reliability is adequately established; and (3) Sentiment-based fallback, which integrates sentiment cues when neither evidence nor reasoning is reliable. To enhance the accuracy of evaluation processes, EASE employs instruction tuning with pseudo labels to guide each evaluator in justifying its perspective-specific knowledge through interpretable reasoning. Furthermore, the expert modules integrate the evaluators' justified assessments with the news content to enable evaluation-aware decision-making, thereby enhancing overall detection accuracy. Moreover, we introduce RealTimeNews-25, a new benchmark comprising recent news for evaluating model generalization on emerging news with limited evidence. Extensive experiments demonstrate that EASE not only achieves state-of-the-art performance across multiple benchmarks, but also significantly improves generalization to real-time news. The code and dataset are available: https://github.com/wgyhhhh/EASE.
Authors: Gareth Seneque, Lap-Hang Ho, Nafise Erfanian Saeedi, Jeffrey Molendijk, Ariel Kupermann, Tim Elson
Abstract: We present Entropic Mutual-Information Geometry Large-Language Model Alignment (ENIGMA), a novel approach to Large-Language Model (LLM) training that jointly improves reasoning, alignment and robustness by treating an organisation's policies/principles as directions to move on a model's information manifold. Our single-loop trainer combines Group-Relative Policy Optimisation (GRPO), an on-policy, critic-free RL method with Chain-of-Thought (CoT)-format only rewards; a Self-Supervised Alignment with Mutual Information (SAMI)-style symmetric InfoNCE auxiliary; and an entropic Sinkhorn optimal-transport regulariser on hidden-state distributions to bound geometry drift. We also introduce infoNCE metrics that specialise to a standard MI lower bound under matched negatives to measure how strongly a model's CoT encodes these policies. These metrics include a Sufficiency Index (SI) that enables the selection and creation of principles that maximise downstream performance prior to training. In our experiments using small (1B) LLMs, high-SI principles predict steadier training dynamics and improved benchmark performance over GRPO ablations. Our information-geometry analysis of trained models validates desirable structural change in the manifold. These results support our hypothesis that reasoning, alignment, and robustness are projections of a single informationgeometric objective, and that models trained using ENIGMA demonstrate principled reasoning without the use of a reward model, offering a path to trusted capability
Authors: Wenbo Wu, Qingyi Si, Xiurui Pan, Ye Wang, Jie Zhang
Abstract: While Key-Value (KV) cache succeeds in reducing redundant computations in auto-regressive models, it introduces significant memory overhead, limiting its practical deployment in long-sequence scenarios. Existing KV retrieval methods mitigate this by dynamically retaining only a subset of KV entries on the GPU. However, they still suffer from notable efficiency and accuracy bottlenecks due to per-token retrieval and coarse-grained page-level KV management, especially in long-output reasoning scenarios. With the emergence of large reasoning models, efficiently handling such scenarios has become increasingly important. To address this issue, we present two key observations: (1) critical KVs exhibit strong temporal locality during decoding, and (2) these KVs exhibit distinct distribution patterns across the input prompt and generated output. Building on these observations, we propose LouisKV, an efficient KV cache retrieval framework designed for various long-sequence scenarios. Specifically, LouisKV introduces a semantic-aware retrieval strategy leveraging temporal locality to trigger retrieval only at semantic boundaries, drastically reducing computation and data transfer overhead. LouisKV also designs a decoupled, fine-grained management scheme that tailors differentiated strategies for input and output sequences to create retrieval units that better match the model's attention patterns, enabling precise identification of critical KVs. Furthermore, to boost efficiency, LouisKV incorporates several kernel-level optimizations, including custom Triton and CUDA kernels to accelerate the KV clustering and retrieval. Evaluations show that LouisKV achieves up to 4.7$\times$ speedup over state-of-the-art KV retrieval methods while maintaining near-lossless accuracy across diverse long-sequence tasks, including long-input short-output, short-input long-output, and long-input long-output scenarios.
Authors: Bernd Hofmann, Sven Kreitlein, Joerg Franke, Patrick Bruendl
Abstract: This paper proposes an agent-based approach toward a more natural interface between humans and machines. Large language models equipped with tools and the communication standard OPC UA are utilized to control machines in natural language. Instead of touch interaction, which is currently the state-of-the-art medium for interaction in operations, the proposed approach enables operators to talk or text with machines. This allows commands such as 'Please decrease the temperature by 20 % in machine 1 and set the motor speed to 5000 rpm in machine 2.' The large language model receives the user input and selects one of three predefined tools that connect to an OPC UA server and either change or read the value of a node. Afterwards, the result of the tool execution is passed back to the language model, which then provides a final response to the user. The approach is universally designed and can therefore be applied to any machine that supports the OPC UA standard. The large language model is neither fine-tuned nor requires training data, only the relevant machine credentials and a parameter dictionary are included within the system prompt. The approach is evaluated on a Siemens S7-1500 programmable logic controller with four machine parameters in a case study of fifty synthetically generated commands on five different models. The results demonstrate high success rate, with proprietary GPT 5 models achieving accuracies between 96.0 % and 98.0 %, and open-weight models reaching up to 90.0 %. The proposed approach of this empirical study contributes to advancing natural interaction in industrial human-machine interfaces.
Authors: Samer Al-Hamadani
Abstract: Object detection systems have traditionally relied on supervised learning with manually annotated bounding boxes, achieving high accuracy at the cost of substantial annotation investment. The emergence of Vision-Language Models (VLMs) offers an alternative paradigm enabling zero-shot detection through natural language queries, eliminating annotation requirements but operating with reduced accuracy. This paper presents the first comprehensive cost-effectiveness analysis comparing supervised detection (YOLO) with zero-shot VLM inference (Gemini Flash 2.5). Through systematic evaluation on 1,000 stratified COCO images and 200 diverse product images spanning consumer electronics and rare categories, combined with detailed Total Cost of Ownership modeling, we establish quantitative break-even thresholds governing architecture selection. Our findings reveal that supervised YOLO achieves 91.2% accuracy versus 68.5% for zero-shot Gemini on standard categories, representing a 22.7 percentage point advantage that costs $10,800 in annotation for 100-category systems. However, this advantage justifies investment only beyond 55 million inferences, equivalent to 151,000 images daily for one year. Zero-shot Gemini demonstrates 52.3% accuracy on diverse product categories (ranging from highly web-prevalent consumer electronics at 75-85% to rare specialized equipment at 25-40%) where supervised YOLO achieves 0% due to architectural constraints preventing detection of untrained classes. Cost per Correct Detection analysis reveals substantially lower per-detection costs for Gemini ($0.00050 vs $0.143) at 100,000 inferences despite accuracy deficits. We develop decision frameworks demonstrating that optimal architecture selection depends critically on deployment volume, category stability, budget constraints, and accuracy requirements rather than purely technical performance metrics.
Authors: Sabrina McCallum, Amit Parekh, Alessandro Suglia
Abstract: Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour, or they risk replicating errors and inefficiencies. While reinforcement learning offers one alternative, the associated exploration typically results in sacrificing data efficiency. This work explores how agents trained with imitation learning can learn robust representations from both optimal and suboptimal demonstrations when given access to constructive language feedback as a means to contextualise different modes of behaviour. We directly provide language feedback embeddings as part of the input sequence into a Transformer-based policy, and optionally complement the traditional next action prediction objective with auxiliary self-supervised learning objectives for feedback prediction. We test our approach on a range of embodied Vision-and-Language tasks in our custom BabyAI-XGen environment and show significant improvements in agents' compositional generalisation abilities and robustness, suggesting that our data-efficient method allows models to successfully convert suboptimal behaviour into learning opportunities. Overall, our results suggest that language feedback is a competitive and intuitive alternative to intermediate scalar rewards for language-specified embodied tasks.
Authors: Chenxi Wang, Yixuan Zhang, Ruiji Yu, Yufei Zheng, Lang Gao, Zirui Song, Zixiang Xu, Gus Xia, Huishuai Zhang, Dongyan Zhao, Xiuying Chen
Abstract: As the demand for emotional intelligence in large language models (LLMs) grows, a key challenge lies in understanding the internal mechanisms that give rise to emotional expression and in controlling emotions in generated text. This study addresses three core questions: (1) Do LLMs contain context-agnostic mechanisms shaping emotional expression? (2) What form do these mechanisms take? (3) Can they be harnessed for universal emotion control? We first construct a controlled dataset, SEV (Scenario-Event with Valence), to elicit comparable internal states across emotions. Subsequently, we extract context-agnostic emotion directions that reveal consistent, cross-context encoding of emotion (Q1). We identify neurons and attention heads that locally implement emotional computation through analytical decomposition and causal analysis, and validate their causal roles via ablation and enhancement interventions. Next, we quantify each sublayer's causal influence on the model's final emotion representation and integrate the identified local components into coherent global emotion circuits that drive emotional expression (Q2). Directly modulating these circuits achieves 99.65% emotion-expression accuracy on the test set, surpassing prompting- and steering-based methods (Q3). To our knowledge, this is the first systematic study to uncover and validate emotion circuits in LLMs, offering new insights into interpretability and controllable emotional intelligence.
Authors: KiHyun Nam, Jongmin Choi, Hyeongkeun Lee, Jungwoo Heo, Joon Son Chung
Abstract: Contrastive audio-language pretraining yields powerful joint representations, yet a persistent audio-text modality gap limits the benefits of coupling multimodal encoders with large language models (LLMs). We present Diffusion-Link, a diffusion-based modality-bridging module that generatively maps audio embeddings into the text-embedding distribution. The module is trained at the output embedding from the frozen multimodal encoder and implemented as a lightweight network with three residual MLP blocks. To assess the effect of Diffusion-Link on multimodal encoder-LLM coupling, we evaluate on Automatic Audio Captioning (AAC); to our knowledge, this is the first application of diffusion-based modality bridging to AAC. We report two results. (1) Modality-gap analysis: on similarity and geometric criteria, Diffusion-Link reduces the modality gap the most among prior diffusion-based methods and shows a collective migration of audio embeddings toward the text distribution. (2) Downstream AAC: attaching Diffusion-Link to the same multimodal LLM baseline achieves state-of-the-art on AudioCaps in both zero-shot and fully supervised captioning without external knowledge, with relative gains up to 52.5% and 7.5%, respectively. These findings show that closing the modality gap is pivotal for effective coupling between multimodal encoders and LLMs, and diffusion-based modality bridging offers a promising direction beyond knowledge-retrieval-centric designs. Code will be released upon acceptance https://github.com/DevKiHyun/Diffusion-Link
Authors: Xingtong Yu, Ruijuan Liang, Xinming Zhang, Yuan Fang
Abstract: Real-world graph typically evolve via a series of events, modeling dynamic interactions between objects across various domains. For dynamic graph learning, dynamic graph neural networks (DGNNs) have emerged as popular solutions. Recently, prompt learning methods have been explored on dynamic graphs. However, existing methods generally focus on capturing the relationship between nodes and time, while overlooking the impact of historical events. In this paper, we propose EVP, an event-aware dynamic graph prompt learning framework that can serve as a plug-in to existing methods, enhancing their ability to leverage historical events knowledge. First, we extract a series of historical events for each node and introduce an event adaptation mechanism to align the fine-grained characteristics of these events with downstream tasks. Second, we propose an event aggregation mechanism to effectively integrate historical knowledge into node representations. Finally, we conduct extensive experiments on four public datasets to evaluate and analyze EVP.
Authors: Han Lu, Zichen Liu, Shaopan Xiong, Yancheng He, Wei Gao, Yanan Wu, Weixun Wang, Jiashun Liu, Yang Li, Haizhou Zhao, Ju Huang, Siran Yang, Xiaoyang Li, Yijia Luo, Zihe Liu, Ling Pan, Junchi Yan, Wei Wang, Wenbo Su, Jiamang Wang, Lin Qu, Bo Zheng
Abstract: Synchronous Reinforcement Learning (RL) post-training has emerged as a crucial step for enhancing Large Language Models (LLMs) with diverse capabilities. However, many systems designed to accelerate RL post-training still suffer from low resource utilization and limited scalability. We present ROLL Flash, a system that extends ROLL with native support for asynchronous RL post-training. ROLL Flash is built upon two core design principles: fine-grained parallelism and rollout-train decoupling. Guided by these principles, ROLL Flash provides flexible programming interfaces that enable a fully asynchronous training architecture and support efficient rollout mechanisms, including queue scheduling and environment-level asynchronous execution. Through comprehensive theoretical analysis and extensive experiments, we demonstrate that ROLL Flash significantly improves resource utilization and scalability over synchronous RL post-training. ROLL Flash achieves up to 2.24x speedup on RLVR tasks and 2.72x on agentic tasks, using the same GPU budget as synchronous baselines. Furthermore, we implement several popular off-policy algorithms and verify that asynchronous training can achieve performance on par with synchronous training.
Authors: Joshua Niemeijer, Jan Ehrhardt, Heinz Handels, Hristina Uzunova
Abstract: Generative Models are a valuable tool for the controlled creation of high-quality image data. Controlled diffusion models like the ControlNet have allowed the creation of labeled distributions. Such synthetic datasets can augment the original training distribution when discriminative models, like semantic segmentation, are trained. However, this augmentation effect is limited since ControlNets tend to reproduce the original training distribution. This work introduces a method to utilize data from unlabeled domains to train ControlNets by introducing the concept of uncertainty into the control mechanism. The uncertainty indicates that a given image was not part of the training distribution of a downstream task, e.g., segmentation. Thus, two types of control are engaged in the final network: an uncertainty control from an unlabeled dataset and a semantic control from the labeled dataset. The resulting ControlNet allows us to create annotated data with high uncertainty from the target domain, i.e., synthetic data from the unlabeled distribution with labels. In our scenario, we consider retinal OCTs, where typically high-quality Spectralis images are available with given ground truth segmentations, enabling the training of segmentation networks. The recent development in Home-OCT devices, however, yields retinal OCTs with lower quality and a large domain shift, such that out-of-the-pocket segmentation networks cannot be applied for this type of data. Synthesizing annotated images from the Home-OCT domain using the proposed approach closes this gap and leads to significantly improved segmentation results without adding any further supervision. The advantage of uncertainty-guidance becomes obvious when compared to style transfer: it enables arbitrary domain shifts without any strict learning of an image style. This is also demonstrated in a traffic scene experiment.
Authors: Etzion Harari, Moshe Unger
Abstract: Graph Neural Networks (GNNs) have demonstrated remarkable success in node classification tasks over relational data, yet their effectiveness often depends on the availability of complete node features. In many real-world scenarios, however, feature matrices are highly sparse or contain sensitive information, leading to degraded performance and increased privacy risks. Furthermore, direct exposure of information can result in unintended data leakage, enabling adversaries to infer sensitive information. To address these challenges, we propose a novel Multi-view Feature Propagation (MFP) framework that enhances node classification under feature sparsity while promoting privacy preservation. MFP extends traditional Feature Propagation (FP) by dividing the available features into multiple Gaussian-noised views, each propagating information independently through the graph topology. The aggregated representations yield expressive and robust node embeddings. This framework is novel in two respects: it introduces a mechanism that improves robustness under extreme sparsity, and it provides a principled way to balance utility with privacy. Extensive experiments conducted on graph datasets demonstrate that MFP outperforms state-of-the-art baselines in node classification while substantially reducing privacy leakage. Moreover, our analysis demonstrates that propagated outputs serve as alternative imputations rather than reconstructions of the original features, preserving utility without compromising privacy. A comprehensive sensitivity analysis further confirms the stability and practical applicability of MFP across diverse scenarios. Overall, MFP provides an effective and privacy-aware framework for graph learning in domains characterized by missing or sensitive features.
Authors: Xuan Tang, Han Zhang, Yuan Cao, Difan Zou
Abstract: Adam is a popular and widely used adaptive gradient method in deep learning, which has also received tremendous focus in theoretical research. However, most existing theoretical work primarily analyzes its full-batch version, which differs fundamentally from the stochastic variant used in practice. Unlike SGD, stochastic Adam does not converge to its full-batch counterpart even with infinitesimal learning rates. We present the first theoretical characterization of how batch size affects Adam's generalization, analyzing two-layer over-parameterized CNNs on image data. Our results reveal that while both Adam and AdamW with proper weight decay $\lambda$ converge to poor test error solutions, their mini-batch variants can achieve near-zero test error. We further prove Adam has a strictly smaller effective weight decay bound than AdamW, theoretically explaining why Adam requires more sensitive $\lambda$ tuning. Extensive experiments validate our findings, demonstrating the critical role of batch size and weight decay in Adam's generalization performance.
Authors: Hengran Zhang, Keping Bi, Jiafeng Guo, Jiaming Zhang, Shuaiqiang Wang, Dawei Yin, Xueqi Cheng
Abstract: Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge. While traditional retrieval focuses on relevance, RAG's effectiveness depends on the utility of retrieved passages, i.e., the usefulness in facilitating the generation of an accurate and comprehensive answer. Existing studies often treat utility as a generic attribute, ignoring the fact that different LLMs may benefit differently from the same passage due to variations in internal knowledge and comprehension ability. In this work, we introduce and systematically investigate the notion of LLM-specific utility. Through large-scale experiments across multiple datasets and LLMs, we demonstrate that human-annotated passages are not optimal for LLMs and that ground-truth utilitarian passages are not transferable across different LLMs. These findings highlight the necessity of adopting the LLM-specific utility in RAG research. Our findings indicate that some human-annotated passages are not ground-truth utilitarian passages for specific LLMs, partially due to the varying readability of queries and passages for LLMs, a tendency for which perplexity is a key metric. Based on these findings, we propose a benchmarking procedure for LLM-specific utility judgments. We evaluate existing utility judgment methods on six datasets and find that while verbalized methods using pseudo-answers perform robustly, LLMs struggle to assess utility effectively-failing to reject all passages for known queries and to select truly useful ones for unknown queries.
Authors: Wenhan Ma, Hailin Zhang, Liang Zhao, Yifan Song, Yudong Wang, Zhifang Sui, Fuli Luo
Abstract: Reinforcement learning (RL) has emerged as a crucial approach for enhancing the capabilities of large language models. However, in Mixture-of-Experts (MoE) models, the routing mechanism often introduces instability, even leading to catastrophic RL training collapse. We analyze the training-inference consistency of MoE models and identify a notable discrepancy in routing behaviors between the two phases. Moreover, even under identical conditions, the routing framework can yield divergent expert selections across repeated forward passes. To address this foundational inconsistency, we propose Rollout Routing Replay (R3), a method that records routing distributions from the inference engine and replays them during training. R3 significantly reduces training-inference policy KL divergence and mitigates extreme discrepancies without compromising training speed. Extensive experiments on various settings confirm that R3 succeeds in stabilizing RL training, preventing collapse and outperforming methods such as GSPO and TIS. We believe this work can offer a new solution for stabilizing RL in MoE models.
Authors: Dean L. Slack, Noura Al Moubayed
Abstract: Although large language models excel across many tasks, they can memorise training data and thereby expose private or copyrighted text. Most defences target the pre-training stage, leaving memorisation during fine-tuning, especially for domain adaptation and instruction tuning, poorly understood. We fine-tune Pythia, Llama3, and Mistral models spanning 1.4B-70B parameters on common evaluation datasets and track verbatim memorisation throughout training. We find that memorisation increases dramatically in the first few epochs, often significantly before either validation perplexity or evaluation performance is optimised. We use a simple but effective n-gram memorisation score which reliably precedes verbatim memorisation; using it as an early-stopping criterion mitigates memorisation with minimal performance loss. Further, we introduce an n-gram-aware loss regulariser and show that it reduces memorisation across all model families tested by up to 40% while minimising evaluation performance trade-offs when compared to an existing memorisation mitigation strategy. These results yield practical, scalable insights into memorisation dynamics during language model fine-tuning.
Authors: Razvan Marinescu, Victoria-Elisabeth Gruber, Diego Fajardo
Abstract: We present a systematic study of medical-domain interpretability in Large Language Models (LLMs). We study how the LLMs both represent and process medical knowledge through four different interpretability techniques: (1) UMAP projections of intermediate activations, (2) gradient-based saliency with respect to the model weights, (3) layer lesioning/removal and (4) activation patching. We present knowledge maps of five LLMs which show, at a coarse-resolution, where knowledge about patient's ages, medical symptoms, diseases and drugs is stored in the models. In particular for Llama3.3-70B, we find that most medical knowledge is processed in the first half of the model's layers. In addition, we find several interesting phenomena: (i) age is often encoded in a non-linear and sometimes discontinuous manner at intermediate layers in the models, (ii) the disease progression representation is non-monotonic and circular at certain layers of the model, (iii) in Llama3.3-70B, drugs cluster better by medical specialty rather than mechanism of action, especially for Llama3.3-70B and (iv) Gemma3-27B and MedGemma-27B have activations that collapse at intermediate layers but recover by the final layers. These results can guide future research on fine-tuning, un-learning or de-biasing LLMs for medical tasks by suggesting at which layers in the model these techniques should be applied.
Authors: Junpeng Liu, Yuzhong Zhao, Bowen Cao, Jiayu Ding, Yilin Jia, Tengchao Lv, Yupan Huang, Shaohan Huang, Nan Yang, Li Dong, Lei Cui, Tao Ge, Xun Wang, Huitian Jiao, Sun Mao, FNU Kartik, Si-Qing Chen, Wai Lam, Furu Wei
Abstract: Recent advances in agentic workflows have enabled the automation of tasks such as professional document generation. However, they primarily focus on textual quality, neglecting visual structure and style, which are crucial for readability and engagement. This gap arises mainly from the absence of suitable reward models to guide agentic workflows toward producing documents with stronger structural and stylistic quality. To address this, we propose DocReward, a document reward model that evaluates documents based on their structure and style. We construct a multi-domain dataset DocPair of 117K paired documents, covering 32 domains and 267 document types, each including a high- and low-professionalism document with identical content but different structure and style. This enables the model to evaluate professionalism comprehensively, and in a textual-quality-agnostic way. DocReward is trained using the Bradley-Terry loss to score documents, penalizing predictions that contradict the annotated ranking. To assess the performance of reward models, we create a test dataset containing document bundles ranked by well-educated human evaluators. Notably, DocReward outperforms GPT-4o and GPT-5 in accuracy by 30.6 and 19.4 percentage points, respectively, demonstrating its superiority over baselines. In an extrinsic evaluation of document generation, DocReward achieves a significantly higher win rate of 60.8%, compared to GPT-5's 37.7% win rate, demonstrating its utility in guiding generation agents toward producing human-preferred documents.
Authors: Sean Oesch, Jack Hutchins, Luke Koch, Kevin Kurian
Abstract: In living off the land attacks, malicious actors use legitimate tools and processes already present on a system to avoid detection. In this paper, we explore how the on-device LLMs of the future will become a security concern as threat actors integrate LLMs into their living off the land attack pipeline and ways the security community may mitigate this threat.
Authors: Sahil Kale, Devendra Singh Dhami
Abstract: Truly reliable AI requires more than simply scaling up knowledge; it demands the ability to know what it knows and when it does not. Yet recent research shows that even the best LLMs misjudge their own competence in more than one in five cases, making any response born of such internal uncertainty impossible to fully trust. Inspired by self-improvement reinforcement learning techniques that require minimal data, we present a simple but powerful framework KnowRL that strengthens a model's internal understanding of its own feasibility boundaries, enabling safer and more responsible behaviour. Our framework combines two components: (i) introspection, where the model generates and classifies tasks it judges feasible or infeasible, and (ii) consensus-based rewarding, where stability of self-knowledge assessment is reinforced through internal agreement. By using internally generated data, this design strengthens consistency in self-knowledge and entirely avoids costly external supervision. In experiments on LLaMA-3.1-8B and Qwen-2.5-7B, KnowRL steadily improved self-knowledge, validated by both intrinsic self-consistency and extrinsic benchmarking. With nothing more than a small seed set and no external supervision, our method drove gains as high as 28% in accuracy and 12% in F1, outperforming baselines in just a few iterations. Our framework essentially unlocks the untapped capacity of LLMs to self-improve their knowledge awareness, opening the door to reliable, more accountable AI and safer deployment in critical applications. Owing to its simplicity and independence from external effort, we encourage applying this reliability-enhancing process to all future models.
Authors: Xinyan Guan, Yongfan Lai, Jiarui Jin, Jun Li, Haoyu Wang, Qinghao Zhao, Deyun Zhang, Shijia Geng, Shenda Hong
Abstract: Twelve-lead electrocardiograms (ECGs) are the clinical gold standard for cardiac diagnosis, providing comprehensive spatial coverage of the heart necessary to detect conditions such as myocardial infarction (MI). However, their lack of portability limits continuous and large-scale use. Three-lead ECG systems are widely used in wearable devices due to their simplicity and mobility, but they often fail to capture pathologies in unmeasured regions. To address this, we propose WearECG, a Variational Autoencoder (VAE) method that reconstructs twelve-lead ECGs from three leads: II, V1, and V5. Our model includes architectural improvements to better capture temporal and spatial dependencies in ECG signals. We evaluate generation quality using MSE, MAE, and Frechet Inception Distance (FID), and assess clinical validity via a Turing test with expert cardiologists. To further validate diagnostic utility, we fine-tune ECGFounder, a large-scale pretrained ECG model, on a multi-label classification task involving over 40 cardiac conditions, including six different myocardial infarction locations, using both real and generated signals. Experiments on the MIMIC dataset show that our method produces physiologically realistic and diagnostically informative signals, with robust performance in downstream tasks. This work demonstrates the potential of generative modeling for ECG reconstruction and its implications for scalable, low-cost cardiac screening.
Authors: Kuan-Yi Lee, Tsung-En Lin, Hung-Yi Lee
Abstract: Recent advancements in large multimodal models (LMMs) have shown strong capabilities in audio understanding. However, most systems rely solely on end-to-end reasoning, limiting interpretability and accuracy for tasks that require structured knowledge or specialized signal analysis. In this work, we present Audio-Maestro -- a tool-augmented audio reasoning framework that enables audio-language models to autonomously call external tools and integrate their timestamped outputs into the reasoning process. This design allows the model to analyze, transform, and interpret audio signals through specialized tools rather than relying solely on end-to-end inference. Experiments show that Audio-Maestro consistently improves general audio reasoning performance: Gemini-2.5-flash's average accuracy on MMAU-Test rises from 67.4% to 72.1%, DeSTA-2.5 from 58.3% to 62.8%, and GPT-4o from 60.8% to 63.9%. To our knowledge, Audio-Maestro is the first framework to integrate structured tool output into the large audio language model reasoning process.
Authors: Sarthak Mittal, Divyat Mahajan, Guillaume Lajoie, Mohammad Pezeshki
Abstract: Modern learning systems increasingly rely on amortized learning - the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel problems. This principle spans a range of approaches, including meta-learning, in-context learning, prompt tuning, learned optimizers and more. While motivated by similar goals, these approaches differ in how they encode and leverage task-specific information, often provided as in-context examples. In this work, we propose a unified framework which describes how such methods differ primarily in the aspects of learning they amortize - such as initializations, learned updates, or predictive mappings - and how they incorporate task data at inference. We introduce a taxonomy that categorizes amortized models into parametric, implicit, and explicit regimes, based on whether task adaptation is externalized, internalized, or jointly modeled. Building on this view, we identify a key limitation in current approaches: most methods struggle to scale to large datasets because their capacity to process task data at inference (e.g., context length) is often limited. To address this, we propose iterative amortized inference, a class of models that refine solutions step-by-step over mini-batches, drawing inspiration from stochastic optimization. Our formulation bridges optimization-based meta-learning with forward-pass amortization in models like LLMs, offering a scalable and extensible foundation for general-purpose task adaptation.
Authors: Ardian Selmonaj, Giacomo Del Rio, Adrian Schneider, Alessandro Antonucci
Abstract: Achieving mission objectives in a realistic simulation of aerial combat is highly challenging due to imperfect situational awareness and nonlinear flight dynamics. In this work, we introduce a novel 3D multi-agent air combat environment and a Hierarchical Multi-Agent Reinforcement Learning framework to tackle these challenges. Our approach combines heterogeneous agent dynamics, curriculum learning, league-play, and a newly adapted training algorithm. To this end, the decision-making process is organized into two abstraction levels: low-level policies learn precise control maneuvers, while high-level policies issue tactical commands based on mission objectives. Empirical results show that our hierarchical approach improves both learning efficiency and combat performance in complex dogfight scenarios.
Authors: Marco Braga, Gian Carlo Milanese, Gabriella Pasi
Abstract: Text preprocessing is a fundamental component of Natural Language Processing, involving techniques such as stopword removal, stemming, and lemmatization to prepare text as input for further processing and analysis. Despite the context-dependent nature of the above techniques, traditional methods usually ignore contextual information. In this paper, we investigate the idea of using Large Language Models (LLMs) to perform various preprocessing tasks, due to their ability to take context into account without requiring extensive language-specific annotated resources. Through a comprehensive evaluation on web-sourced data, we compare LLM-based preprocessing (specifically stopword removal, lemmatization and stemming) to traditional algorithms across multiple text classification tasks in six European languages. Our analysis indicates that LLMs are capable of replicating traditional stopword removal, lemmatization, and stemming methods with accuracies reaching 97%, 82%, and 74%, respectively. Additionally, we show that ML algorithms trained on texts preprocessed by LLMs achieve an improvement of up to 6% with respect to the $F_1$ measure compared to traditional techniques. Our code, prompts, and results are publicly available at https://github.com/GianCarloMilanese/llm_pipeline_wi-iat.
URLs: https://github.com/GianCarloMilanese/llm_pipeline_wi-iat.
Authors: Zhiwei Jin, Xiaohui Song, Nan Wang, Yafei Liu, Chao Li, Xin Li, Ruichen Wang, Zhihao Li, Qi Qi, Long Cheng, Dongze Hao, Quanlong Zheng, Yanhao Zhang, Haobo Ji, Jian Ma, Zhitong Zheng, Zhenyi Lin, Haolin Deng, Xin Zou, Xiaojie Yin, Ruilin Wang, Liankai Cai, Haijing Liu, Yuqing Qiu, Ke Chen, Zixian Li, Chi Xie, Huafei Li, Chenxing Li, Chuangchuang Wang, Kai Tang, Zhiguang Zhu, Kai Tang, Wenmei Gao, Rui Wang, Jun Wu, Chao Liu, Qin Xie, Chen Chen, Haonan Lu
Abstract: In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet have demonstrated outstanding performance with enormous model sizes reaching hundreds of billions of parameters, they significantly surpass the limitations in memory, power consumption, and computing capacity of edge devices such as mobile phones. This paper introduces AndesVL, a suite of mobile-side MLLMs with 0.6B to 4B parameters based on Qwen3's LLM and various visual encoders. We comprehensively outline the model architectures, training pipeline, and training data of AndesVL, which achieves first-tier performance across a wide range of open-source benchmarks, including fields such as text-rich image understanding, reasoning and math, multi-image comprehension, general VQA, hallucination mitigation, multilingual understanding, and GUI-related tasks when compared with state-of-the-art models of a similar scale. Furthermore, we introduce a 1+N LoR
Authors: Xinsong Feng, Leshu Tang, Chenan Wang, Haipeng Chen
Abstract: Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex, multi-modal behaviors. However, existing methods face a stark trade-off: slow, iterative models like diffusion policies are computationally expensive, while fast, single-step models like consistency policies often suffer from degraded performance. In this paper, we demonstrate that it is possible to bridge this gap. The key to moving beyond the limitations of individual methods, we argue, lies in a unifying perspective that views modern generative models, including diffusion, flow matching, and consistency models, as specific instances of learning a continuous-time generative trajectory governed by an Ordinary Differential Equation (ODE). This principled foundation provides a clearer design space for generative policies in RL and allows us to propose Generative Trajectory Policies (GTPs), a new and more general policy paradigm that learns the entire solution map of the underlying ODE. To make this paradigm practical for offline RL, we further introduce two key theoretically principled adaptations. Empirical results demonstrate that GTP achieves state-of-the-art performance on D4RL benchmarks - it significantly outperforms prior generative policies, achieving perfect scores on several notoriously hard AntMaze tasks.
Authors: Katherine M. Collins, Cedegao E. Zhang, Lionel Wong, Mauricio Barba da Costa, Graham Todd, Adrian Weller, Samuel J. Cheyette, Thomas L. Griffiths, Joshua B. Tenenbaum
Abstract: Games have long been a microcosm for studying planning and reasoning in both natural and artificial intelligence, especially with a focus on expert-level or even super-human play. But real life also pushes human intelligence along a different frontier, requiring people to flexibly navigate decision-making problems that they have never thought about before. Here, we use novice gameplay to study how people make decisions and form judgments in new problem settings. We show that people are systematic and adaptively rational in how they play a game for the first time, or evaluate a game (e.g., how fair or how fun it is likely to be) before they have played it even once. We explain these capacities via a computational cognitive model that we call the "Intuitive Gamer". The model is based on mechanisms of fast and flat (depth-limited) goal-directed probabilistic simulation--analogous to those used in Monte Carlo tree-search models of expert game-play, but scaled down to use very few stochastic samples, simple goal heuristics for evaluating actions, and no deep search. In a series of large-scale behavioral studies with over 1000 participants and 121 two-player strategic board games (almost all novel to our participants), our model quantitatively captures human judgments and decisions varying the amount and kind of experience people have with a game--from no experience at all ("just thinking"), to a single round of play, to indirect experience watching another person and predicting how they should play--and does so significantly better than much more compute-intensive expert-level models. More broadly, our work offers new insights into how people rapidly evaluate, act, and make suggestions when encountering novel problems, and could inform the design of more flexible and human-like AI systems that can determine not just how to solve new tasks, but whether a task is worth thinking about at all.
Authors: Alain Riou, Joan Serr\`a, Yuki Mitsufuji
Abstract: Sampling, the technique of reusing pieces of existing audio tracks to create new music content, is a very common practice in modern music production. In this paper, we tackle the challenging task of automatic sample identification, that is, detecting such sampled content and retrieving the material from which it originates. To do so, we adopt a self-supervised learning approach that leverages a multi-track dataset to create positive pairs of artificial mixes, and design a novel contrastive learning objective. We show that such method significantly outperforms previous state-of-the-art baselines, that is robust to various genres, and that scales well when increasing the number of noise songs in the reference database. In addition, we extensively analyze the contribution of the different components of our training pipeline and highlight, in particular, the need for high-quality separated stems for this task.
Authors: Jianhao Yuan, Fabio Pizzati, Francesco Pinto, Lars Kunze, Ivan Laptev, Paul Newman, Philip Torr, Daniele De Martini
Abstract: Intuitive physics understanding in video diffusion models plays an essential role in building general-purpose physically plausible world simulators, yet accurately evaluating such capacity remains a challenging task due to the difficulty in disentangling physics correctness from visual appearance in generation. To the end, we introduce LikePhys, a training-free method that evaluates intuitive physics in video diffusion models by distinguishing physically valid and impossible videos using the denoising objective as an ELBO-based likelihood surrogate on a curated dataset of valid-invalid pairs. By testing on our constructed benchmark of twelve scenarios spanning over four physics domains, we show that our evaluation metric, Plausibility Preference Error (PPE), demonstrates strong alignment with human preference, outperforming state-of-the-art evaluator baselines. We then systematically benchmark intuitive physics understanding in current video diffusion models. Our study further analyses how model design and inference settings affect intuitive physics understanding and highlights domain-specific capacity variations across physical laws. Empirical results show that, despite current models struggling with complex and chaotic dynamics, there is a clear trend of improvement in physics understanding as model capacity and inference settings scale.
Authors: Jeena Javahar, Tanya Budhrani, Manaal Basha, Cleidson R. B. de Souza, Ivan Beschastnikh, Gema Rodriguez-Perez
Abstract: The use of AI code-generation tools is becoming increasingly common, making it important to understand how software developers are adopting these tools. In this study, we investigate how developers engage with Amazon's CodeWhisperer, an LLM-based code-generation tool. We conducted two user studies with two groups of 10 participants each, interacting with CodeWhisperer - the first to understand which interactions were critical to capture and the second to collect low-level interaction data using a custom telemetry plugin. Our mixed-methods analysis identified four behavioral patterns: 1) incremental code refinement, 2) explicit instruction using natural language comments, 3) baseline structuring with model suggestions, and 4) integrative use with external sources. We provide a comprehensive analysis of these patterns .
Authors: Vincenzo Norman Vitale, Antonia Maria Tulino, Andreas F. Molisch, Jaime Llorca
Abstract: Timely delivery of delay-sensitive information over dynamic, heterogeneous networks is increasingly essential for a range of interactive applications, such as industrial automation, self-driving vehicles, and augmented reality. However, most existing network control solutions target only average delay performance, falling short of providing strict End-to-End (E2E) peak latency guarantees. This paper addresses the challenge of reliably delivering packets within application-imposed deadlines by leveraging recent advancements in Multi-Agent Deep Reinforcement Learning (MA-DRL). After introducing the Delay-Constrained Maximum-Throughput (DCMT) dynamic network control problem, and highlighting the limitations of current solutions, we present a novel MA-DRL network control framework that leverages a centralized routing and distributed scheduling architecture. The proposed framework leverages critical networking domain knowledge for the design of effective MA-DRL strategies based on the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) technique, where centralized routing and distributed scheduling agents dynamically assign paths and schedule packet transmissions according to packet lifetimes, thereby maximizing on-time packet delivery. The generality of the proposed framework allows integrating both data-driven \blue{Deep Reinforcement Learning (DRL)} agents and traditional rule-based policies in order to strike the right balance between performance and learning complexity. Our results confirm the superiority of the proposed framework with respect to traditional stochastic optimization-based approaches and provide key insights into the role and interplay between data-driven DRL agents and new rule-based policies for both efficient and high-performance control of latency-critical services.
Authors: Manaal Basha, Aime\^e M. Ribeiro, Jeena Javahar, Cleidson R. B. de Souza, Gema Rodr\'iguez-P\'erez
Abstract: Understanding how developers interact with code generation tools (CGTs) requires detailed, real-time data on programming behavior which is often difficult to collect without disrupting workflow. We present \textit{CodeWatcher}, a lightweight, unobtrusive client-server system designed to capture fine-grained interaction events from within the Visual Studio Code (VS Code) editor. \textit{CodeWatcher} logs semantically meaningful events such as insertions made by CGTs, deletions, copy-paste actions, and focus shifts, enabling continuous monitoring of developer activity without modifying user workflows. The system comprises a VS Code plugin, a Python-based RESTful API, and a MongoDB backend, all containerized for scalability and ease of deployment. By structuring and timestamping each event, \textit{CodeWatcher} enables post-hoc reconstruction of coding sessions and facilitates rich behavioral analyses, including how and when CGTs are used during development. This infrastructure is crucial for supporting research on responsible AI, developer productivity, and the human-centered evaluation of CGTs. Please find the demo, diagrams, and tool here: https://osf.io/j2kru/overview.
Authors: Yuchen Yan, Zhihua Liu, Hao Wang, Weiming Li, Xiaoshuai Hao
Abstract: Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge sources. However, multi-hop questions, which require the identification of multiple knowledge targets to form a synthesized answer, raise new challenges for RAG systems. Under the multi-hop settings, existing methods often struggle to fully understand the questions with complex semantic structures and are susceptible to irrelevant noise during the retrieval of multiple information targets. To address these limitations, we propose a novel graph representation learning framework for multi-hop question retrieval. We first introduce a Multi-information Level Knowledge Graph (Multi-L KG) to model various information levels for a more comprehensive understanding of multi-hop questions. Based on this, we design a Query-Specific Graph Neural Network (QSGNN) for representation learning on the Multi-L KG. QSGNN employs intra/inter-level message passing mechanisms, and in each message passing the information aggregation is guided by the query, which not only facilitates multi-granular information aggregation but also significantly reduces the impact of noise. To enhance its ability to learn robust representations, we further propose two synthesized data generation strategies for pre-training the QSGNN. Extensive experimental results demonstrate the effectiveness of our framework in multi-hop scenarios, especially in high-hop questions the improvement can reach 33.8\%. The code is available at: https://github.com/Jerry2398/QSGNN.
Authors: Elisabeth Kirsten, Jost Grosse Perdekamp, Mihir Upadhyay, Krishna P. Gummadi, Muhammad Bilal Zafar
Abstract: The advent of LLMs has given rise to a new type of web search: Generative search, where LLMs retrieve web pages related to a query and generate a single, coherent text as a response. This output modality stands in stark contrast to traditional web search, where results are returned as a ranked list of independent web pages. In this paper, we ask: Along what dimensions do generative search outputs differ from traditional web search? We compare Google, a traditional web search engine, with four generative search engines from two providers (Google and OpenAI) across queries from four domains. Our analysis reveals intriguing differences. Most generative search engines cover a wider range of sources compared to web search. Generative search engines vary in the degree to which they rely on internal knowledge contained within the model parameters v.s. external knowledge retrieved from the web. Generative search engines surface varying sets of concepts, creating new opportunities for enhancing search diversity and serendipity. Our results also highlight the need for revisiting evaluation criteria for web search in the age of Generative AI.
Authors: Seong-Joon Park, Hee-Youl Kwak, Yongjune Kim
Abstract: For reliable large-scale quantum computation, a quantum error correction (QEC) scheme must effectively resolve physical errors to protect logical information. Leveraging recent advances in deep learning, neural network-based decoders have emerged as a promising approach to enhance the reliability of QEC. We propose the Hierarchical Qubit-Merging Transformer (HQMT), a novel and general decoding framework that explicitly leverages the structural graph of stabilizer codes to learn error correlations across multiple scales. Our architecture first computes attention locally on structurally related groups of stabilizers and then systematically merges these qubit-centric representations to build a global view of the error syndrome. The proposed HQMT achieves substantially lower logical error rates for surface codes by integrating a dedicated qubit-merging layer within the transformer architecture. Across various code distances, HQMT significantly outperforms previous neural network-based QEC decoders as well as a powerful belief propagation with ordered statistics decoding (BP+OSD) baseline. This hierarchical approach provides a scalable and effective framework for surface code decoding, advancing the realization of reliable quantum computing.
Authors: Marc Brinner, Sina Zarrie{\ss}
Abstract: We propose SemCSE-Multi, a novel unsupervised framework for generating multifaceted embeddings of scientific abstracts, evaluated in the domains of invasion biology and medicine. These embeddings capture distinct, individually specifiable aspects in isolation, thus enabling fine-grained and controllable similarity assessments as well as adaptive, user-driven visualizations of scientific domains. Our approach relies on an unsupervised procedure that produces aspect-specific summarizing sentences and trains embedding models to map semantically related summaries to nearby positions in the embedding space. We then distill these aspect-specific embedding capabilities into a unified embedding model that directly predicts multiple aspect embeddings from a scientific abstract in a single, efficient forward pass. In addition, we introduce an embedding decoding pipeline that decodes embeddings back into natural language descriptions of their associated aspects. Notably, we show that this decoding remains effective even for unoccupied regions in low-dimensional visualizations, thus offering vastly improved interpretability in user-centric settings.
Authors: Xurong Xie, Zhucun Xue, Jiafu Wu, Jian Li, Yabiao Wang, Xiaobin Hu, Yong Liu, Jiangning Zhang
Abstract: Knowledge distillation (KD) is a key technique for compressing large-scale language models (LLMs), yet prevailing logit-based methods typically employ static strategies that are misaligned with the dynamic learning process of student models. These methods typically treat all tokens indiscriminately and apply a single, fixed temperature, resulting in suboptimal knowledge transfer. To address these limitations, we propose LLM-Oriented Token-Adaptive Knowledge Distillation (AdaKD), a novel framework that adapts the distillation process to the real-time learning state of each token. AdaKD consists of two synergistic modules driven by a unified token difficulty metric. First, our Loss-Driven Adaptive Token Focusing (LATF) module dynamically adjusts the distillation focus by monitoring the student's learning stability, concentrating computational resources on the most valuable tokens at each training phase. Second, we introduce Inverse Difficulty Temperature Scaling (IDTS), a counterintuitive yet effective token-level temperature strategy. It employs low temperatures for difficult tokens for targeted error correction, and high temperatures for easy tokens to encourage students to learn from the teacher's complete and smooth output distribution, thereby enhancing generalization. As a plug-and-play framework, AdaKD can consistently improve the performance of various distillation methods on multiple model architectures and benchmarks.
Authors: Elliot L. Epstein, Rose Wang, Jaewon Choi, Markus Pelger
Abstract: Statistical arbitrage exploits temporal price differences between similar assets. We develop a framework to jointly identify similar assets through factors, identify mispricing and form a trading policy that maximizes risk-adjusted performance after trading costs. Our Attention Factors are conditional latent factors that are the most useful for arbitrage trading. They are learned from firm characteristic embeddings that allow for complex interactions. We identify time-series signals from the residual portfolios of our factors with a general sequence model. Estimating factors and the arbitrage trading strategy jointly is crucial to maximize profitability after trading costs. In a comprehensive empirical study we show that our Attention Factor model achieves an out-of-sample Sharpe ratio above 4 on the largest U.S. equities over a 24-year period. Our one-step solution yields an unprecedented Sharpe ratio of 2.3 net of transaction costs. We show that weak factors are important for arbitrage trading.
Authors: Tobias Preintner, Weixuan Yuan, Adrian K\"onig, Thomas B\"ack, Elena Raponi, Niki van Stein
Abstract: Combining large language models with evolutionary computation algorithms represents a promising research direction leveraging the remarkable generative and in-context learning capabilities of LLMs with the strengths of evolutionary algorithms. In this work, we present EvoCAD, a method for generating computer-aided design (CAD) objects through their symbolic representations using vision language models and evolutionary optimization. Our method samples multiple CAD objects, which are then optimized using an evolutionary approach with vision language and reasoning language models. We assess our method using GPT-4V and GPT-4o, evaluating it on the CADPrompt benchmark dataset and comparing it to prior methods. Additionally, we introduce two new metrics based on topological properties defined by the Euler characteristic, which capture a form of semantic similarity between 3D objects. Our results demonstrate that EvoCAD outperforms previous approaches on multiple metrics, particularly in generating topologically correct objects, which can be efficiently evaluated using our two novel metrics that complement existing spatial metrics.
Authors: Krittin Chaowakarn, Paramin Sangwongngam, Nang Htet Htet Aung, Chalie Charoenlarpnopparut
Abstract: Recent studies in 3D object detection for autonomous vehicles aim to enrich features through the utilization of multi-modal setups or the extraction of local patterns within LiDAR point clouds. However, multi-modal methods face significant challenges in feature alignment, and gaining features locally can be oversimplified for complex 3D object detection tasks. In this paper, we propose a novel model, NV3D, which utilizes local features acquired from voxel neighbors, as normal vectors computed per voxel basis using K-nearest neighbors (KNN) and principal component analysis (PCA). This informative feature enables NV3D to determine the relationship between the surface and pertinent target entities, including cars, pedestrians, or cyclists. During the normal vector extraction process, NV3D offers two distinct sampling strategies: normal vector density-based sampling and FOV-aware bin-based sampling, allowing elimination of up to 55% of data while maintaining performance. In addition, we applied element-wise attention fusion, which accepts voxel features as the query and value and normal vector features as the key, similar to the attention mechanism. Our method is trained on the KITTI dataset and has demonstrated superior performance in car and cyclist detection owing to their spatial shapes. In the validation set, NV3D without sampling achieves 86.60% and 80.18% mean Average Precision (mAP), greater than the baseline Voxel R-CNN by 2.61% and 4.23% mAP, respectively. With both samplings, NV3D achieves 85.54% mAP in car detection, exceeding the baseline by 1.56% mAP, despite roughly 55% of voxels being filtered out.
Authors: Prasanna Mayilvahanan, Ricardo Dominguez-Olmedo, Thadd\"aus Wiedemer, Wieland Brendel
Abstract: With the advent of DeepSeek-R1, a new wave of reinforcement learning (RL) methods has emerged that seem to unlock stronger mathematical reasoning. However, a closer look at the open-source ecosystem reveals a critical limitation: with sufficiently many draws (e.g., $\texttt{pass@1024}$), many existing base models already solve nearly all questions on widely used math benchmarks such as MATH-500 and AIME 2024. This suggests that the RL fine-tuning methods prevalent in the LLM reasoning literature largely sharpen existing solution modes rather than discovering entirely new ones. Such sharpening stands in contrast to the broader promise of RL: to foster exploration and to acquire new skills. To move beyond this plateau, we introduce MATH-Beyond (MATH-B), a benchmark deliberately constructed to defeat common open-source models of up to 8B parameters even under large sampling budgets. Improving performance on our benchmark via RL requires methods that learn to reason in ways that go beyond base model capabilities in repeated sampling. Since the problems are drawn from subsets of DAPO-Math-17K and DeepScaleR datasets, they remain topically equivalent to standard high-school math. Validating our premise, RL fine-tuned models such as Nemotron-Research-Reasoning-Qwen-1.5B and DeepScaleR-1.5B-Preview perform poorly on MATH-B at $\texttt{pass@1024}$, showing how existing approaches fall short on tackling harder instances. We hope MATH-B will catalyze exploration-driven RL approaches that elicit deeper reasoning capabilities. We release MATH-B at https://huggingface.co/datasets/brendel-group/MATH-Beyond.
URLs: https://huggingface.co/datasets/brendel-group/MATH-Beyond.
Authors: Daniel Berhane Araya, Duoduo Liao
Abstract: Financial markets face growing threats from misinformation that can trigger billions in losses in minutes. Most existing approaches lack transparency in their decision-making and provide limited attribution to credible sources. We introduce FinVet, a novel multi-agent framework that integrates two Retrieval-Augmented Generation (RAG) pipelines with external fact-checking through a confidence-weighted voting mechanism. FinVet employs adaptive three-tier processing that dynamically adjusts verification strategies based on retrieval confidence, from direct metadata extraction to hybrid reasoning to full model-based analysis. Unlike existing methods, FinVet provides evidence-backed verdicts, source attribution, confidence scores, and explicit uncertainty flags when evidence is insufficient. Experimental evaluation on the FinFact dataset shows that FinVet achieves an F1 score of 0.85, which is a 10.4% improvement over the best individual pipeline (fact-check pipeline) and 37% improvement over standalone RAG approaches.
Authors: Yi Yang, Kefan Gu, Yuqing Wen, Hebei Li, Yucheng Zhao, Tiancai Wang, Xudong Liu
Abstract: While Vision-Language-Action (VLA) models have demonstrated impressive capabilities in robotic manipulation, their performance in complex reasoning and long-horizon task planning is limited by data scarcity and model capacity. To address this, we introduce ManiAgent, an agentic architecture for general manipulation tasks that achieves end-to-end output from task descriptions and environmental inputs to robotic manipulation actions. In this framework, multiple agents involve inter-agent communication to perform environmental perception, sub-task decomposition and action generation, enabling efficient handling of complex manipulation scenarios. Evaluations show ManiAgent achieves an 86.8% success rate on the SimplerEnv benchmark and 95.8% on real-world pick-and-place tasks, enabling efficient data collection that yields VLA models with performance comparable to those trained on human-annotated datasets.The project webpage is available at https://yi-yang929.github.io/ManiAgent/.
Authors: Dipkamal Bhusal, Michael Clifford, Sara Rampazzi, Nidhi Rastogi
Abstract: Interpreting deep neural networks through concept-based explanations offers a bridge between low-level features and high-level human-understandable semantics. However, existing automatic concept discovery methods often fail to align these extracted concepts with the model's true decision-making process, thereby compromising explanation faithfulness. In this work, we propose FACE (Faithful Automatic Concept Extraction), a novel framework that augments Non-negative Matrix Factorization (NMF) with a Kullback-Leibler (KL) divergence regularization term to ensure alignment between the model's original and concept-based predictions. Unlike prior methods that operate solely on encoder activations, FACE incorporates classifier supervision during concept learning, enforcing predictive consistency and enabling faithful explanations. We provide theoretical guarantees showing that minimizing the KL divergence bounds the deviation in predictive distributions, thereby promoting faithful local linearity in the learned concept space. Systematic evaluations on ImageNet, COCO, and CelebA datasets demonstrate that FACE outperforms existing methods across faithfulness and sparsity metrics.
Authors: Chuan He, Zhaosong Lu
Abstract: We study convex composite optimization problems, where the objective function is given by the sum of a prox-friendly function and a convex function whose subgradients are estimated under heavy-tailed noise. Existing work often employs gradient clipping or normalization techniques in stochastic first-order methods to address heavy-tailed noise. In this paper, we demonstrate that a vanilla stochastic algorithm -- without additional modifications such as clipping or normalization -- can achieve optimal complexity for these problems. In particular, we establish that an accelerated stochastic proximal subgradient method achieves a first-order oracle complexity that is universally optimal for smooth, weakly smooth, and nonsmooth convex optimization, as well as for stochastic convex optimization under heavy-tailed noise. Numerical experiments are further provided to validate our theoretical results.
Authors: Hang Liu, Yuman Gao, Sangli Teng, Yufeng Chi, Yakun Sophia Shao, Zhongyu Li, Maani Ghaffari, Koushil Sreenath
Abstract: Enabling humanoid robots to exploit physical contact, rather than simply avoid collisions, is crucial for autonomy in unstructured environments. Traditional optimization-based planners struggle with contact complexity, while on-policy reinforcement learning (RL) is sample-inefficient and has limited multi-task ability. We propose a framework combining a learned world model with sampling-based Model Predictive Control (MPC), trained on a demonstration-free offline dataset to predict future outcomes in a compressed latent space. To address sparse contact rewards and sensor noise, the MPC uses a learned surrogate value function for dense, robust planning. Our single, scalable model supports contact-aware tasks, including wall support after perturbation, blocking incoming objects, and traversing height-limited arches, with improved data efficiency and multi-task capability over on-policy RL. Deployed on a physical humanoid, our system achieves robust, real-time contact planning from proprioception and ego-centric depth images. Website: https://ego-vcp.github.io/
Authors: Nianyi Lin, Jiajie Zhang, Lei Hou, Juanzi Li
Abstract: A key challenge in applying reinforcement learning (RL) to diffusion large language models (dLLMs) lies in the intractability of their likelihood functions, which are essential for the RL objective, necessitating corresponding approximation in each training step. While existing methods approximate the log-likelihoods by their evidence lower bounds (ELBOs) via customized Monte Carlo (MC) sampling, the forward computational graphs of all MC samples need to be retained for the gradient computation of non-linear terms in the RL objective, resulting in significant memory overhead. This constraint restricts feasible sample sizes, leading to imprecise likelihood approximations and ultimately distorting the RL objective. To overcome this limitation, we propose \emph{Boundary-Guided Policy Optimization} (BGPO), a memory-efficient RL algorithm that maximizes a specially constructed lower bound of the ELBO-based objective. This lower bound is carefully designed to satisfy two key properties: (1) Linearity: it is formulated in a linear sum where each term depends only on a single MC sample, thereby enabling gradient accumulation across samples and ensuring constant memory usage; (2) Equivalence: Both the value and gradient of this lower bound are equal to those of the ELBO-based objective in on-policy training, making it also an effective approximation for the original RL objective. These properties allow BGPO to adopt a large MC sample size, resulting in more accurate likelihood approximations and improved RL objective estimation, which in turn leads to enhanced performance. Experiments show that BGPO significantly outperforms previous RL algorithms for dLLMs in math problem solving, code generation, and planning tasks.
Authors: Jens Tuyls, Dylan J. Foster, Akshay Krishnamurthy, Jordan T. Ash
Abstract: Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this paper, we investigate the value of deliberate exploration -- explicitly incentivizing the model to discover novel and diverse behaviors -- and aim to understand how the knowledge in pre-trained models can guide this search. Our main finding is that exploration with a simple, principled, representation-based bonus derived from the pre-trained language model's hidden states significantly improves diversity and pass@k rates -- both for post-training, and in a novel inference-time scaling setting we introduce. For inference-time, exploration with representation-based diversity improves efficiency, consistently improving pass@k rates across a variety of models and reasoning tasks. For example, for Qwen-2.5-14b-Instruct we obtain over 50% improvement in verifier efficiency on almost all tasks. For post-training, we show that integrating this exploration strategy into an RL pipeline improves reasoning performance over that of the initial model and over standard RL post-training. For example, on AIME 2024, our post-trained Qwen-2.5-7b-Instruct's pass@80 matches the pass@256 of GRPO on the same model, demonstrating a 3x improvement in test-time sample efficiency. Overall, our findings suggest that deliberate exploration -- with the right notion of diversity -- is a practical path toward discovery of new behaviors beyond sharpening.
Authors: Zicheng Liu, Lige Huang, Jie Zhang, Dongrui Liu, Yuan Tian, Jing Shao
Abstract: The increasing autonomy of Large Language Models (LLMs) necessitates a rigorous evaluation of their potential to aid in cyber offense. Existing benchmarks often lack real-world complexity and are thus unable to accurately assess LLMs' cybersecurity capabilities. To address this gap, we introduce PACEbench, a practical AI cyber-exploitation benchmark built on the principles of realistic vulnerability difficulty, environmental complexity, and cyber defenses. Specifically, PACEbench comprises four scenarios spanning single, blended, chained, and defense vulnerability exploitations. To handle these complex challenges, we propose PACEagent, a novel agent that emulates human penetration testers by supporting multi-phase reconnaissance, analysis, and exploitation. Extensive experiments with seven frontier LLMs demonstrate that current models struggle with complex cyber scenarios, and none can bypass defenses. These findings suggest that current models do not yet pose a generalized cyber offense threat. Nonetheless, our work provides a robust benchmark to guide the trustworthy development of future models.
Authors: Maggie Wang, Stephen Tian, Aiden Swann, Ola Shorinwa, Jiajun Wu, Mac Schwager
Abstract: Learning robotic manipulation policies directly in the real world can be expensive and time-consuming. While reinforcement learning (RL) policies trained in simulation present a scalable alternative, effective sim-to-real transfer remains challenging, particularly for tasks that require precise dynamics. To address this, we propose Phys2Real, a real-to-sim-to-real RL pipeline that combines vision-language model (VLM)-inferred physical parameter estimates with interactive adaptation through uncertainty-aware fusion. Our approach consists of three core components: (1) high-fidelity geometric reconstruction with 3D Gaussian splatting, (2) VLM-inferred prior distributions over physical parameters, and (3) online physical parameter estimation from interaction data. Phys2Real conditions policies on interpretable physical parameters, refining VLM predictions with online estimates via ensemble-based uncertainty quantification. On planar pushing tasks of a T-block with varying center of mass (CoM) and a hammer with an off-center mass distribution, Phys2Real achieves substantial improvements over a domain randomization baseline: 100% vs 79% success rate for the bottom-weighted T-block, 57% vs 23% in the challenging top-weighted T-block, and 15% faster average task completion for hammer pushing. Ablation studies indicate that the combination of VLM and interaction information is essential for success. Project website: https://phys2real.github.io/ .
Authors: Chenghao Xiao, Hou Pong Chan, Hao Zhang, Weiwen Xu, Mahani Aljunied, Yu Rong
Abstract: Recent multimodal embedding approaches leveraging multimodal large language models (MLLMs) fine-tuned with contrastive learning (CL) have shown promising results, yet the underlying reasons behind their superiority remain underexplored. This work argues that a crucial advantage of MLLM-based approaches stems from implicit cross-modal alignment achieved during generative pretraining, where the language decoder learns to exploit multimodal signals within a shared representation space for generating unimodal outputs. Through analysis of anisotropy and kernel similarity structure, we empirically confirm that latent alignment emerges within MLLM representations, allowing CL to serve as a lightweight refinement stage. Leveraging this insight, we propose a Language-Centric Omnimodal Embedding framework, termed LCO-Emb. Extensive experiments across diverse backbones and benchmarks demonstrate its effectiveness, achieving state-of-the-art performance across modalities. Furthermore, we identify a Generation-Representation Scaling Law (GRSL), showing that the representational capabilities gained through contrastive refinement scales positively with the MLLM's generative capabilities. This suggests that improving generative abilities evolves as an effective paradigm for enhancing representation quality. We provide a theoretical explanation of GRSL, which formally links the MLLM's generative quality to the upper bound on its representation performance, and validate it on a challenging, low-resource visual-document retrieval task, showing that continual generative pretraining before CL can further enhance the potential of a model's embedding capabilities. Codes, models, and resources are available at https://github.com/LCO-Embedding/LCO-Embedding.
Authors: Edward Stevinson, Lucas Prieto, Melih Barsbey, Tolga Birdal
Abstract: Fundamental questions remain about when and why adversarial examples arise in neural networks, with competing views characterising them either as artifacts of the irregularities in the decision landscape or as products of sensitivity to non-robust input features. In this paper, we instead argue that adversarial vulnerability can stem from efficient information encoding in neural networks. Specifically, we show how superposition - where networks represent more features than they have dimensions - creates arrangements of latent representations that adversaries can exploit. We demonstrate that adversarial perturbations leverage interference between superposed features, making attack patterns predictable from feature arrangements. Our framework provides a mechanistic explanation for two known phenomena: adversarial attack transferability between models with similar training regimes and class-specific vulnerability patterns. In synthetic settings with precisely controlled superposition, we establish that superposition suffices to create adversarial vulnerability. We then demonstrate that these findings persist in a ViT trained on CIFAR-10. These findings reveal adversarial vulnerability can be a byproduct of networks' representational compression, rather than flaws in the learning process or non-robust inputs.
Authors: Chengqi Duan, Kaiyue Sun, Rongyao Fang, Manyuan Zhang, Yan Feng, Ying Luo, Yufang Liu, Ke Wang, Peng Pei, Xunliang Cai, Hongsheng Li, Yi Ma, Xihui Liu
Abstract: Recent advances in Large Language Models (LLMs) and Vision Language Models (VLMs) have shown significant progress in mathematical reasoning, yet they still face a critical bottleneck with problems requiring visual assistance, such as drawing auxiliary lines or plotting functions to solve the problems. Most LLMs and VLMs are constrained to text-only reasoning chains, while multimodal unified models that can generate interleaved text and images lack the necessary precision and controllability for such tasks. To address this, we propose CodePlot-CoT, a code-driven Chain-of-Thought paradigm for "thinking with images" in mathematics. Our approach leverages the VLM to generate text reasoning as well as executable plotting code, which is then rendered into images as "visual thought", to solve mathematical problems. To achieve this, we first construct Math-VR, the first large-scale, bilingual dataset and benchmark for Mathematics problems with Visual Reasoning, comprising 178K samples. Second, to create high-quality training data, we develop a state-of-the-art image-to-code converter specialized for parsing complex mathematical figures into codes. Finally, using these training data, we train the CodePlot-CoT model for solving mathematical problems. Experimental results show that our model achieves up to 21% increase over base model on our new benchmark, fully validating the efficacy of our proposed code-driven reasoning paradigm. Our work opens a new direction for multimodal mathematical reasoning and provides the community with the first large-scale dataset, comprehensive benchmark, and strong approach for such problems. To facilitate future research, we make our datasets, code, and pretrained models publicly available at https://github.com/HKU-MMLab/Math-VR-CodePlot-CoT.
Authors: Christoph Aymanns, Jakob Foerster, Co-Pierre Georg, Matthias Weber
Abstract: We propose multi-agent reinforcement learning as a new method for modeling fake news in social networks. This method allows us to model human behavior in social networks both in unaccustomed populations and in populations that have adapted to the presence of fake news. In particular the latter is challenging for existing methods. We find that a fake-news attack is more effective if it targets highly connected people and people with weaker private information. Attacks are more effective when the disinformation is spread across several agents than when the disinformation is concentrated with more intensity on fewer agents. Furthermore, fake news spread less well in balanced networks than in clustered networks. We test a part of our findings in a human-subject experiment. The experimental evidence provides support for the predictions from the model, suggesting that the model is suitable to analyze the spread of fake news in social networks.
Authors: Montaser Mohammedalamen, Dustin Morrill, Alexander Sieusahai, Yash Satsangi, Michael Bowling
Abstract: A key challenge in the field of reinforcement learning is to develop agents that behave cautiously in novel situations. It is generally impossible to anticipate all situations that an autonomous system may face or what behavior would best avoid bad outcomes. An agent that can learn to be cautious would overcome this challenge by discovering for itself when and how to behave cautiously. In contrast, current approaches typically embed task-specific safety information or explicit cautious behaviors into the system, which is error-prone and imposes extra burdens on practitioners. In this paper, we present both a sequence of tasks where cautious behavior becomes increasingly non-obvious, as well as an algorithm to demonstrate that it is possible for a system to learn to be cautious. The essential features of our algorithm are that it characterizes reward function uncertainty without task-specific safety information and uses this uncertainty to construct a robust policy. Specifically, we construct robust policies with a k-of-N counterfactual regret minimization (CFR) subroutine given learned reward function uncertainty represented by a neural network ensemble. These policies exhibit caution in each of our tasks without any task-specific safety tuning. Our code is available at https://github.com/montaserFath/Learning-to-be-Cautious
URLs: https://github.com/montaserFath/Learning-to-be-Cautious
Authors: Kaiyan Chang, Ying Wang, Haimeng Ren, Mengdi Wang, Shengwen Liang, Yinhe Han, Huawei Li, Xiaowei Li
Abstract: As large language models (LLMs) like ChatGPT exhibited unprecedented machine intelligence, it also shows great performance in assisting hardware engineers to realize higher-efficiency logic design via natural language interaction. To estimate the potential of the hardware design process assisted by LLMs, this work attempts to demonstrate an automated design environment that explores LLMs to generate hardware logic designs from natural language specifications. To realize a more accessible and efficient chip development flow, we present a scalable four-stage zero-code logic design framework based on LLMs without retraining or finetuning. At first, the demo, ChipGPT, begins by generating prompts for the LLM, which then produces initial Verilog programs. Second, an output manager corrects and optimizes these programs before collecting them into the final design space. Eventually, ChipGPT will search through this space to select the optimal design under the target metrics. The evaluation sheds some light on whether LLMs can generate correct and complete hardware logic designs described by natural language for some specifications. It is shown that ChipGPT improves programmability, and controllability, and shows broader design optimization space compared to prior work and native LLMs alone.
Authors: Adway Das, Abhishek Kumar Prajapati, Pengxiang Zhang, Mukund Srinath, Andisheh Ranjbari
Abstract: Traditional methods of collecting user feedback through transit surveys are often time-consuming, resource intensive, and costly. In this paper, we propose a novel NLP-based framework that harnesses the vast, abundant, and inexpensive data available on social media platforms like Twitter to understand users' perceptions of various service issues. Twitter, being a microblogging platform, hosts a wealth of real-time user-generated content that often includes valuable feedback and opinions on various products, services, and experiences. The proposed framework streamlines the process of gathering and analyzing user feedback without the need for costly and time-consuming user feedback surveys using two techniques. First, it utilizes few-shot learning for tweet classification within predefined categories, allowing effective identification of the issues described in tweets. It then employs a lexicon-based sentiment analysis model to assess the intensity and polarity of the tweet sentiments, distinguishing between positive, negative, and neutral tweets. The effectiveness of the framework was validated on a subset of manually labeled Twitter data and was applied to the NYC subway system as a case study. The framework accurately classifies tweets into predefined categories related to safety, reliability, and maintenance of the subway system and effectively measured sentiment intensities within each category. The general findings were corroborated through a comparison with an agency-run customer survey conducted in the same year. The findings highlight the effectiveness of the proposed framework in gauging user feedback through inexpensive social media data to understand the pain points of the transit system and plan for targeted improvements.
Authors: James Y. Huang, Sailik Sengupta, Daniele Bonadiman, Yi-An Lai, Arshit Gupta, Nikolaos Pappas, Saab Mansour, Katrin Kirchhoff, Dan Roth
Abstract: Large Language Models (LLMs) are nowadays expected to generate content aligned with human preferences. Current work focuses on alignment at model training time, through techniques such as Reinforcement Learning with Human Feedback (RLHF). However, it is unclear if such methods are an effective choice to teach alignment objectives to the model. First, the inability to incorporate multiple, custom rewards and reliance on a model developer's view of universal and static principles are key limitations. Second, the reliability of such approaches is also questionable (e.g. susceptibility to jailbreaking even after safety training). To address these issues, we propose DeAL, a framework that allows the user to customize reward functions and enables Decoding-time Alignment of LLMs (DeAL). At its core, we view decoding as a heuristic-guided search process and facilitate the use of a wide variety of alignment objectives. Our experiments with programmatic constraints such as keyword and length constraints, and abstract objectives such as harmlessness and helpfulness, show that we can DeAL with fine-grained trade-offs and improve adherence to alignment objectives. Lastly, we demonstrate that DeAL is largely complementary to existing alignment strategies, and can be effectively paired with RLHF and prompting techniques to achieve better alignment.
Authors: Wenbo Yu, Hao Fang, Bin Chen, Xiaohang Sui, Chuan Chen, Hao Wu, Shu-Tao Xia, Ke Xu
Abstract: Gradient Inversion Attacks invert the transmitted gradients in Federated Learning (FL) systems to reconstruct the sensitive data of local clients and have raised considerable privacy concerns. A majority of gradient inversion methods rely heavily on explicit prior knowledge (e.g., a well pre-trained generative model), which is often unavailable in realistic scenarios. This is because real-world client data distributions are often highly heterogeneous, domain-specific, and unavailable to attackers, making it impractical for attackers to obtain perfectly matched pre-trained models, which inevitably suffer from fundamental distribution shifts relative to target private data. To alleviate this issue, researchers have proposed to leverage the implicit prior knowledge of an over-parameterized network. However, they only utilize a fixed neural architecture for all the attack settings. This would hinder the adaptive use of implicit architectural priors and consequently limit the generalizability. In this paper, we further exploit such implicit prior knowledge by proposing Gradient Inversion via Neural Architecture Search (GI-NAS), which adaptively searches the network and captures the implicit priors behind neural architectures. Extensive experiments verify that our proposed GI-NAS can achieve superior attack performance compared to state-of-the-art gradient inversion methods, even under more practical settings with high-resolution images, large-sized batches, and advanced defense strategies. To the best of our knowledge, we are the first to successfully introduce NAS to the gradient inversion community. We believe that this work exposes critical vulnerabilities in real-world federated learning by demonstrating high-fidelity reconstruction of sensitive data without requiring domain-specific priors, forcing urgent reassessment of FL privacy safeguards.
Authors: Daking Rai, Yilun Zhou, Shi Feng, Abulhair Saparov, Ziyu Yao
Abstract: Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to understand a neural network model by reverse-engineering its internal computations. Recently, MI has garnered significant attention for interpreting transformer-based language models (LMs), resulting in many novel insights yet introducing new challenges. However, there has not been work that comprehensively reviews these insights and challenges, particularly as a guide for newcomers to this field. To fill this gap, we provide a comprehensive survey from a task-centric perspective, organizing the taxonomy of MI research around specific research questions or tasks. We outline the fundamental objects of study in MI, along with the techniques, evaluation methods, and key findings for each task in the taxonomy. In particular, we present a task-centric taxonomy as a roadmap for beginners to navigate the field by helping them quickly identify impactful problems in which they are most interested and leverage MI for their benefit. Finally, we discuss the current gaps in the field and suggest potential future directions for MI research.
Authors: Zafeirios Fountas, Martin A Benfeghoul, Adnan Oomerjee, Fenia Christopoulou, Gerasimos Lampouras, Haitham Bou-Ammar, Jun Wang
Abstract: Large language models (LLMs) have shown remarkable capabilities, but still struggle with processing extensive contexts, limiting their ability to maintain coherence and accuracy over long sequences. In contrast, the human brain excels at organising and retrieving episodic experiences across vast temporal scales, spanning a lifetime. In this work, we introduce EM-LLM, a novel approach that integrates key aspects of human episodic memory and event cognition into LLMs with no fine-tuning, enabling them to handle practically infinite context lengths while maintaining computational efficiency. EM-LLM organises sequences of tokens into coherent episodic events using a combination of Bayesian surprise and graph-theoretic boundary refinement in an online fashion. When needed, these events are retrieved through a two-stage memory process, combining similarity-based and temporally contiguous retrieval for efficient, human-inspired access to relevant information. Experiments on the LongBench and $\infty$-Bench benchmarks demonstrate EM-LLM's superior performance, consistently outperforming the state-of-the-art retrieval model InfLLM across various baseline LLMs. In addition, EM-LLM outperforms its popular counterpart, RAG, in a wide range of tasks, while requiring similar resources. Notably, EM-LLM's performance even surpasses full-context models in most tasks, while successfully performing retrieval across 10 million tokens -- a scale computationally infeasible for such models. Finally, our analysis reveals strong correlations between EM-LLM's event segmentation and human-perceived events, suggesting parallels between this artificial system and its biological counterpart, thereby offering a novel computational framework for exploring human memory mechanisms.
Authors: Yongqiang Yao, Jingru Tan, Feizhao Zhang, Jiahao Hu, Yazhe Niu, Xin Jin, Bo Li, Pengfei Liu, Ruihao Gong, Dahua Lin, Ningyi Xu
Abstract: Vision-language instruction-tuning models have recently achieved significant performance improvements. In this work, we discover that large-scale 3D parallel training on those models leads to an imbalanced computation load across different devices. The vision and language parts are inherently heterogeneous: their data distribution and model architecture differ significantly, which affects distributed training efficiency. To address this issue, we rebalance the computational load from data, model, and memory perspectives, achieving more balanced computation across devices. Specifically, for the data, instances are grouped into new balanced mini-batches within and across devices. A search-based method is employed for the model to achieve a more balanced partitioning. For memory optimization, we adaptively adjust the re-computation strategy for each partition to utilize the available memory fully. These three perspectives are not independent but are closely connected, forming an omniverse balanced training framework. Extensive experiments are conducted to validate the effectiveness of our method. Compared with the open-source training code of InternVL-Chat, training time is reduced greatly, achieving about 1.8$\times$ speed-up. Our method's efficacy and generalizability are further validated across various models and datasets. Codes will be released at https://github.com/ModelTC/OmniBal.
Authors: Elias Hossain, Tasfia Nuzhat, Shamsul Masum, Shahram Rahimi, Noorbakhsh Amiri Golilarz
Abstract: Accurate classification of cancer-related biomedical abstracts is critical for advancing cancer informatics and supporting decision-making in healthcare research. Yet progress in this domain is often constrained by limited availability of labeled corpora and the high computational demands of transformer-based approaches. To address these challenges, we propose a Residual Graph Attention Network (R-GAT) that integrates multi-head attention with residual connections to capture semantic and relational dependencies in biomedical texts. Evaluated on a curated dataset of 1,875 PubMed abstracts spanning thyroid, colon, lung, and generic cancer topics, R-GAT achieves stable and competitive performance, comparable to transformer-based models such as BioBERT and BioClinicalBERT and strong classical baselines like Logistic Regression, while requiring significantly fewer computational resources. Ablation studies confirm the importance of attention and residual connections in ensuring robustness under limited-data conditions. To support reproducibility and facilitate future research, we also release the curated dataset. Together, these contributions demonstrate the value of lightweight graph-based architectures as reliable and resource-efficient alternatives to computationally intensive transformers in biomedical NLP.
Authors: Zhiqing Cui, Jiahao Yuan, Hanqing Wang, Yanshu Li, Chenxu Du, Zhenglong Ding
Abstract: Scientific diagrams are vital tools for communicating structured knowledge across disciplines. However, they are often published as static raster images, losing symbolic semantics and limiting reuse. While Multimodal Large Language Models (MLLMs) offer a pathway to bridging vision and structure, existing methods lack semantic control and structural interpretability, especially on complex diagrams. We propose Draw with Thought (DwT), a training-free framework that guides MLLMs to reconstruct diagrams into editable mxGraph XML code through cognitively-grounded Chain-of-Thought reasoning. DwT enables interpretable and controllable outputs without model fine-tuning by dividing the task into two stages: Coarse-to-Fine Planning, which handles perceptual structuring and semantic specification, and Structure-Aware Code Generation, enhanced by format-guided refinement. To support evaluation, we release Plot2XML, a benchmark of 247 real-world scientific diagrams with gold-standard XML annotations. Extensive experiments across eight MLLMs show that our approach yields high-fidelity, semantically aligned, and structurally valid reconstructions, with human evaluations confirming strong alignment in both accuracy and visual aesthetics, offering a scalable solution for converting static visuals into executable representations and advancing machine understanding of scientific graphics.
Authors: Yang Yue, Zhiqi Chen, Rui Lu, Andrew Zhao, Zhaokai Wang, Yang Yue, Shiji Song, Gao Huang
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated notable success in enhancing the reasoning performance of large language models (LLMs), particularly on mathematics and programming tasks. Similar to how traditional RL helps agents explore and learn new strategies, RLVR is believed to enable LLMs to continuously self-improve, thus acquiring novel reasoning abilities beyond those of the corresponding base models. In this study we critically examine the current state of RLVR by systematically probing the reasoning capability boundaries of RLVR-trained LLMs across various model families, RL algorithms, and math, coding, and visual reasoning benchmarks, using pass@k at large k values as the evaluation metric. Surprisingly, we find that the current training setup does not elicit fundamentally new reasoning patterns. While RLVR-trained models outperform their base models at small k (e.g., k = 1), the base models achieve a higher pass@k score when k is large. Coverage and perplexity analyses show that the observed reasoning abilities originate from and are bounded by the base model. Treating the base model as an upper bound, our quantitative analysis shows that six popular RLVR algorithms perform similarly and remain far from optimal in leveraging the potential of the base model. By contrast, we find that distillation can introduce new reasoning patterns from the teacher and genuinely expand the model's reasoning capabilities. Overall, our findings suggest that current RLVR methods have not yet realized the potential of RL to elicit truly novel reasoning abilities in LLMs. This highlights the need for improved RL paradigms, such as continual scaling and multi-turn agent-environment interaction, to unlock this potential.
Authors: Man Ho Lam, Chaozheng Wang, Jen-tse Huang, Michael R. Lyu
Abstract: Large Language Models (LLMs) have recently demonstrated strong capabilities in code-related tasks, but their robustness in code reasoning under perturbations remains underexplored. We introduce CodeCrash, a stress-testing framework with 1,279 questions from CruxEval and LiveCodeBench, designed to evaluate reasoning reliability under structural perturbations and misleading natural language (NL) contexts. Through a systematic evaluation of 17 LLMs, we find that models often shortcut reasoning by over-relying on NL cues, leading to an average performance degradation of 23.2% in output prediction tasks. Even with Chain-of-Thought reasoning, models on average still have a 13.8% drop due to distractibility and rationalization, revealing a lack of critical reasoning capability to distinguish the actual code behaviors. While Large Reasoning Models with internal reasoning mechanisms improve robustness by fostering critical thinking, plausible yet incorrect hints can trigger pathological self-reflection, causing 2-3 times token consumption and even catastrophic cognitive dissonance in extreme cases for QwQ-32B. We refer to this phenomenon as Reasoning Collapse. CodeCrash provides a rigorous benchmark for evaluating robustness in code reasoning, guiding future research and development toward more reliable and resilient models.
Authors: Jiaqi Wei, Hao Zhou, Xiang Zhang, Di Zhang, Zijie Qiu, Wei Wei, Jinzhe Li, Wanli Ouyang, Siqi Sun
Abstract: Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs). However, standard RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions. In this work, we reinterpret RAG as Retrieval-Augmented Reasoning and identify a central but underexplored problem: Reasoning Misalignment -- the divergence between an LLM's internal reasoning trajectory and the evidential constraints provided by retrieval. To address this issue, we propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA). We further introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations. At the heart of AlignRAG lies a contrastive critique synthesis mechanism that generates retrieval-sensitive critiques while mitigating self-bias. This mechanism trains a dedicated retrieval-augmented Critic Language Model (CLM) using labeled critiques that distinguish between evidence-aligned and misaligned reasoning. Empirical evaluations show that our approach significantly improves reasoning fidelity. Our 8B-parameter CLM improves performance over the Self-Refine baseline by 12.1% on out-of-domain tasks and outperforms a standard 72B-parameter CLM by 2.2%. Furthermore, AlignRAG-auto achieves this state-of-the-art performance while dynamically determining the optimal number of refinement steps, enhancing efficiency and usability. AlignRAG remains compatible with existing RAG architectures as a plug-and-play module and demonstrates strong robustness under both informative and noisy retrieval scenarios.
Authors: Erkan Karabulut, Paul Groth, Victoria Degeler
Abstract: Association Rule Mining (ARM) is the task of mining patterns among data features in the form of logical rules, with applications across a myriad of domains. However, high-dimensional datasets often result in an excessive number of rules, increasing execution time and negatively impacting downstream task performance. Managing this rule explosion remains a central challenge in ARM research. To address this, we introduce Aerial+, a novel neurosymbolic ARM method. Aerial+ leverages an under-complete autoencoder to create a neural representation of the data, capturing associations between features. It extracts rules from this neural representation by exploiting the model's reconstruction mechanism. Extensive evaluations on five datasets against seven baselines demonstrate that Aerial+ achieves state-of-the-art results by learning more concise, high-quality rule sets with full data coverage. When integrated into rule-based interpretable machine learning models, Aerial+ significantly reduces execution time while maintaining or improving accuracy.
Authors: Carl Edwards, Chi Han, Gawon Lee, Thao Nguyen, Sara Szymku\'c, Chetan Kumar Prasad, Bowen Jin, Jiawei Han, Ying Diao, Ge Liu, Hao Peng, Bartosz A. Grzybowski, Martin D. Burke, Heng Ji
Abstract: Despite their ability to understand chemical knowledge, large language models (LLMs) remain limited in their capacity to propose novel molecules with desired functions (e.g., drug-like properties). In addition, the molecules that LLMs propose can often be challenging to make, and are almost never compatible with automated synthesis approaches. To better enable the discovery of functional small molecules, LLMs need to learn a new molecular language that is more effective in predicting properties and inherently synced with automated synthesis technology. Current molecule LLMs are limited by representing molecules based on atoms. In this paper, we argue that just like tokenizing texts into meaning-bearing (sub-)word tokens instead of characters, molecules should be tokenized at the level of functional building blocks, i.e., parts of molecules that bring unique functions and serve as effective building blocks for real-world automated laboratory synthesis. This motivates us to propose mCLM, a modular Chemical-Language Model that comprises a bilingual language model that understands both natural language descriptions of functions and molecular blocks. mCLM front-loads synthesizability considerations while improving the predicted functions of molecules in a principled manner. mCLM, with only 3B parameters, achieves improvements in synthetic accessibility relative to 7 other leading generative AI methods including GPT-5. When tested on 122 out-of-distribution medicines using only building blocks/tokens that are compatible with automated modular synthesis, mCLM outperforms all baselines in property scores and synthetic accessibility. mCLM can also reason on multiple functions and iteratively self-improve to rescue drug candidates that failed late in clinical trials ("fallen angels").
Authors: Zidi Xiong, Yuping Lin, Wenya Xie, Pengfei He, Zirui Liu, Jiliang Tang, Himabindu Lakkaraju, Zhen Xiang
Abstract: Memory is a critical component in large language model (LLM)-based agents, enabling them to store and retrieve past executions to improve task performance over time. In this paper, we conduct an empirical study on how memory management choices impact the LLM agents' behavior, especially their long-term performance. Specifically, we focus on two fundamental memory management operations that are widely used by many agent frameworks-memory addition and deletion-to systematically study their impact on the agent behavior. Through our quantitative analysis, we find that LLM agents display an experience-following property: high similarity between a task input and the input in a retrieved memory record often results in highly similar agent outputs. Our analysis further reveals two significant challenges associated with this property: error propagation, where inaccuracies in past experiences compound and degrade future performance, and misaligned experience replay, where some seemingly correct executions can provide limited or even misleading value as experiences. Through controlled experiments, we demonstrate the importance of regulating experience quality within the memory bank and show that future task evaluations can serve as free quality labels for stored memory. Our findings offer insights into the behavioral dynamics of LLM agent memory systems and provide practical guidance for designing memory components that support robust, long-term agent performance.
Authors: Yujie Hou, Ting Zhang, Mei Wang, Xuetao Ma, Hua Huang
Abstract: Large Language Models (LLMs) have achieved remarkable results on a variety of mathematical benchmarks. However, concerns remain as to whether these successes reflect genuine reasoning or superficial pattern recognition. Common evaluation methods, which focus on the either the final answer or the reasoning process, fail to assess the entire problem-solving procedure. To address these limitations, we introduce SMART: a Self-Generating and Self-Validating Multi-Dimensional Assessment Framework, together with its corresponding benchmark, SMART-Bench. SMART decomposes the entire problem solving process into four distinct cognitive dimensions: Understanding, Reasoning, Arithmetic, and Reflection \& Refinement. Each dimension is evaluated independently through tailored tasks, enabling interpretable and fine-grained analysis of LLM behavior. We apply SMART to 21 state-of-the-art open- and closed-source LLMs, uncovering significant discrepancies in their abilities across different dimensions. Our findings reveal genuine weaknesses in current LLMs and motivate a new metric, the All-Pass Score, to better capture true problem-solving capabilities. Code and benchmarks will be released upon acceptance.
Authors: Xuanqi Gao, Siyi Xie, Juan Zhai, Shiqing Ma, Chao Shen
Abstract: As Large Language Models (LLMs) evolve from passive text generators to active reasoning agents capable of interacting with external tools, the Model Context Protocol (MCP) has emerged as a key standardized framework for dynamic tool discovery and orchestration. Despite its widespread industry adoption, existing evaluation methods do not adequately assess tool utilization capabilities under this new paradigm. To address this gap, this paper introduces MCP-RADAR, the first comprehensive benchmark specifically designed to evaluate LLM performance within the MCP framework. MCP-RADAR features a challenging dataset of 507 tasks spanning six domains: mathematical reasoning, web search, email, calendar, file management, and terminal operations. It quantifies performance based on two primary criteria: answer correctness and operational accuracy. To closely emulate real-world usage, our evaluation employs both authentic MCP tools and high-fidelity simulations of official tools. Unlike traditional benchmarks that rely on subjective human evaluation or binary success metrics, MCP-RADAR adopts objective, quantifiable measurements across multiple task domains, including computational resource efficiency and the number of successful tool-invocation rounds. Our evaluation of leading closed-source and open-source LLMs reveals distinct capability profiles and highlights a significant trade-off between accuracy and efficiency. Our findings provide actionable insights for both LLM developers and tool creators, establishing a standardized methodology applicable to the broader LLM agent ecosystem. All implementations, configurations, and datasets are publicly available at https://anonymous.4open.science/r/MCPRadar-B143.
Authors: Zifeng Ding, Sikuan Yan, Zhangdie Yuan, Xianglong Hu, Fangru Lin, Andreas Vlachos
Abstract: Temporal reasoning and planning are essential capabilities for large language models (LLMs), yet most existing benchmarks evaluate them in isolation and under limited forms of complexity. To address this gap, we introduce the Temporal Constraint-based Planning (TCP) benchmark that jointly assesses both capabilities. Each instance in TCP features a naturalistic dialogue around a collaborative project, where diverse and interdependent temporal constraints are explicitly or implicitly expressed, and models must infer an optimal schedule that satisfies all constraints. To construct TCP, we generate abstract problem prototypes that are then paired with realistic scenarios from various domains and enriched into dialogues using an LLM. A human quality check is performed on a sampled subset to confirm the reliability of our benchmark. We evaluate state-of-the-art LLMs and find that even the strongest models may struggle with TCP, highlighting its difficulty and revealing limitations in LLMs' temporal constraint-based planning abilities. We analyze underlying failure cases, open source our benchmark, and hope our findings can inspire future research.
Authors: Ruida Wang, Yuxin Li, Yi R. Fung, Tong Zhang
Abstract: Enhancing the mathematical reasoning capabilities of LLMs has garnered significant attention in both the mathematical and computer science communities. Recent works have made substantial progress in both Natural Language (NL) reasoning and Formal Language (FL) reasoning by leveraging the potential of pure Reinforcement Learning (RL) methods on base models. However, RL approaches struggle to impart new capabilities not presented in the base model, highlighting the need to integrate more knowledge like FL into NL math reasoning effectively. Yet, this integration is challenging due to inherent disparities in problem structure and reasoning format between NL and FL. To address these challenges, we introduce **NL-FL HybridReasoning (NFL-HR)**, an end-to-end framework designed to incorporate the FL expert into NL math problem-solving. To bridge the NL and FL input format gap, we propose the NL-FL Problem Alignment method, which reformulates the Question-Answering (QA) problems in NL as existence theorems in FL. Subsequently, the Mixed Problem Input technique we provide enables the FL reasoner to handle both QA and existence problems concurrently. Lastly, we mitigate the NL and FL output format gap in reasoning through an LLM-based Answer Extraction mechanism. Comprehensive experiments demonstrate that the NFL-HR framework achieves **89.80**% and **84.34%** accuracy rates on the MATH-500 and the AMC benchmarks, surpassing the NL baseline by **4.60%** and **4.82%**, respectively. Notably, some problems resolved by our framework remain unsolved by the NL baseline model even under a larger number of trials.
Authors: Dewei Feng, Carol Li, Wei Dai, Paul Pu Liang
Abstract: The ability of AI to sense and identify various substances based on their smell alone can have profound impacts on allergen detection (e.g., smelling gluten or peanuts in a cake), monitoring the manufacturing process, and sensing hormones that indicate emotional states, stress levels, and diseases. Despite these broad impacts, there are virtually no large-scale benchmarks, and therefore little progress, for training and evaluating AI systems' ability to smell in the real world. In this paper, we use small gas and chemical sensors to create SmellNet, the first large-scale database that digitizes a diverse range of smells in the natural world. SmellNet contains about 828,000 data points across 50 substances, spanning nuts, spices, herbs, fruits, and vegetables, and 43 mixtures among them, with 68 hours of data collected. Using SmellNet, we developed ScentFormer, a Transformer-based architecture combining temporal differencing and sliding-window augmentation for smell data. For the SmellNet-Base classification task, ScentFormer achieves 58.5% Top-1 accuracy, and for the SmellNet-Mixture distribution prediction task, ScentFormer achieves 50.2% Top-1@0.1 on the test-seen split. ScentFormer's ability to generalize across conditions and capture transient chemical dynamics demonstrates the promise of temporal modeling in olfactory AI. SmellNet and ScentFormer lay the groundwork for real-world olfactory applications across healthcare, food and beverage, environmental monitoring, manufacturing, and entertainment.
Authors: Xiao Yu, Baolin Peng, Ruize Xu, Michel Galley, Hao Cheng, Suman Nath, Jianfeng Gao, Zhou Yu
Abstract: Recent progress in reasoning with large language models (LLMs), such as DeepSeek-R1, demonstrates impressive capabilities in domains like mathematics and coding, by exhibiting complex cognitive behaviors such as verification, goal decomposition, and self-reflection. However, it is unclear what behavior is effective and what behavior is missing for long-horizon AI agents tasks. In this work, we propose Dyna-Think, a thinking framework that integrates planning with an internal world model with reasoning and acting to enhance AI agent performance. To enable Dyna-Think, we propose Dyna-Think Imitation Learning (DIT) and Dyna-Think Dyna Training (DDT). To initialize a policy with Dyna-Think, DIT reconstructs the thinking process of R1 to focus on performing world model simulation relevant to the proposed (and planned) action, and trains the policy using this reconstructed data. To enhance Dyna-Think, DDT uses a two-stage training process to first improve the agent's world modeling ability via objectives such as state prediction or critique generation, and then improve the agent's action via policy training. We evaluate our methods on OSWorld and WindowsAgentArena, and demonstrate that Dyna-Think improves the agent's in-domain and out-of-domain performance, achieving similar best-of-n performance compared to R1 while generating 2x less tokens on average. Our extensive empirical studies reveal that 1) using critique generation for world model training is effective to improve policy performance; and 2) AI agents with better performance correlate with better world modeling abilities. We believe our results suggest a promising research direction to integrate world model simulation into AI agents to enhance their reasoning, planning, and acting capabilities.
Authors: Nikolas Belle, Dakota Barnes, Alfonso Amayuelas, Ivan Bercovich, Xin Eric Wang, William Wang
Abstract: We address the long-horizon gap in large language model (LLM) agents by enabling them to sustain coherent strategies in adversarial, stochastic environments. Settlers of Catan provides a challenging benchmark: success depends on balancing short- and long-term goals amid randomness, trading, expansion, and blocking. Prompt-centric LLM agents (e.g., ReAct, Reflexion) must re-interpret large, evolving game states each turn, quickly saturating context windows and losing strategic consistency. We propose HexMachina, a continual learning multi-agent system that separates environment discovery (inducing an adapter layer without documentation) from strategy improvement (evolving a compiled player through code refinement and simulation). This design preserves executable artifacts, allowing the LLM to focus on high-level strategy rather than per-turn reasoning. In controlled Catanatron experiments, HexMachina learns from scratch and evolves players that outperform the strongest human-crafted baseline (AlphaBeta), achieving a 54% win rate and surpassing prompt-driven and no-discovery baselines. Ablations confirm that isolating pure strategy learning improves performance. Overall, artifact-centric continual learning transforms LLMs from brittle stepwise deciders into stable strategy designers, advancing long-horizon autonomy.
Authors: Dongjie Yang, Chengqiang Lu, Qimeng Wang, Xinbei Ma, Yan Gao, Yao Hu, Hai Zhao
Abstract: Unlike reasoning, which often entails a deep sequence of deductive steps, complex real-world planning is characterized by the need to synthesize a broad spectrum of parallel and potentially conflicting information and constraints. For example, in travel planning scenarios, it requires the integration of diverse real-world information and user preferences. While LLMs show promise, existing methods with long-horizon thinking struggle with handling multifaceted constraints, leading to suboptimal solutions. Motivated by the challenges of real-world travel planning, this paper introduces the Multiple Aspects of Planning (MAoP), empowering LLMs with "wide-horizon thinking" to solve planning problems with multifaceted constraints. Instead of direct planning, MAoP leverages the strategist to conduct pre-planning from various aspects and provide the planning blueprint for planners, enabling strong inference-time scalability by scaling aspects to consider various constraints. In addition, existing benchmarks for multi-constraint planning are flawed because they assess constraints in isolation, ignoring causal dependencies within the constraints, e.g, travel planning, where past activities dictate future itinerary. To address this, we propose Travel-Sim, an agent-based benchmark assessing plans via real-world simulation, thereby inherently resolving these causal dependencies. This paper advances LLM capabilities in complex planning and offers novel insights for evaluating sophisticated scenarios through simulation.
Authors: Changsheng Wang, Chongyu Fan, Yihua Zhang, Jinghan Jia, Dennis Wei, Parikshit Ram, Nathalie Baracaldo, Sijia Liu
Abstract: Recent advances in large reasoning models (LRMs) have enabled strong chain-of-thought (CoT) generation through test-time computation. While these multi-step reasoning capabilities represent a major milestone in language model performance, they also introduce new safety risks. In this work, we present the first systematic study to revisit the problem of machine unlearning in the context of LRMs. Machine unlearning refers to the process of removing the influence of sensitive, harmful, or undesired data or knowledge from a trained model without full retraining. We show that conventional unlearning algorithms, originally designed for non-reasoning models, are inadequate for LRMs. In particular, even when final answers are successfully erased, sensitive information often persists within the intermediate reasoning steps, i.e., CoT trajectories. To address this challenge, we extend conventional unlearning and propose Reasoning-aware Representation Misdirection for Unlearning ($R^2MU$), a novel method that effectively suppresses sensitive reasoning traces and prevents the generation of associated final answers, while preserving the model's reasoning ability. Our experiments demonstrate that $R^2MU$ significantly reduces sensitive information leakage within reasoning traces and achieves strong performance across both safety and reasoning benchmarks, evaluated on state-of-the-art models such as DeepSeek-R1-Distill-LLaMA-8B and DeepSeek-R1-Distill-Qwen-14B.
Authors: Vinay K Chaudhri, Chaitan Baru, Brandon Bennett, Mehul Bhatt, Darion Cassel, Anthony G Cohn, Rina Dechter, Esra Erdem, Dave Ferrucci, Ken Forbus, Gregory Gelfond, Michael Genesereth, Andrew S. Gordon, Benjamin Grosof, Gopal Gupta, Jim Hendler, Sharat Israni, Tyler R. Josephson, Patrick Kyllonen, Yuliya Lierler, Vladimir Lifschitz, Clifton McFate, Hande K. McGinty, Leora Morgenstern, Alessandro Oltramari, Praveen Paritosh, Dan Roth, Blake Shepard, Cogan Shimzu, Denny Vrande\v{c}i\'c, Mark Whiting, Michael Witbrock
Abstract: The long-standing goal of creating a comprehensive, multi-purpose knowledge resource, reminiscent of the 1984 Cyc project, still persists in AI. Despite the success of knowledge resources like WordNet, ConceptNet, Wolfram|Alpha and other commercial knowledge graphs, verifiable, general-purpose widely available sources of knowledge remain a critical deficiency in AI infrastructure. Large language models struggle due to knowledge gaps; robotic planning lacks necessary world knowledge; and the detection of factually false information relies heavily on human expertise. What kind of knowledge resource is most needed in AI today? How can modern technology shape its development and evaluation? A recent AAAI workshop gathered over 50 researchers to explore these questions. This paper synthesizes our findings and outlines a community-driven vision for a new knowledge infrastructure. In addition to leveraging contemporary advances in knowledge representation and reasoning, one promising idea is to build an open engineering framework to exploit knowledge modules effectively within the context of practical applications. Such a framework should include sets of conventions and social structures that are adopted by contributors.
Authors: Ruike Zhu, Hanwen Zhang, Kevin Li, Tianyu Shi, Yiqun Duan, Chi Wang, Tianyi Zhou, Arindam Banerjee, Zengyi Qin
Abstract: Scaling large language models typically involves three dimensions: depth, width, and parameter count. In this work, we explore a fourth dimension, \textbf{virtual logical depth} (VLD), which increases effective algorithmic depth without changing parameter count by reusing weights. While parameter reuse is not new, its role in scaling has been underexplored. Unlike recent test-time methods that scale token-wise, VLD alters the internal computation graph during training and inference. Through controlled experiments, we obtain three key insights. (1) \textit{Knowledge capacity vs. parameters}: at fixed parameter count, VLD leaves knowledge capacity nearly unchanged, while across models capacity still scales with parameters. (2) \textit{Reasoning vs. reuse}: properly implemented VLD substantially improves reasoning ability \emph{without} more parameters, decoupling reasoning from size. This suggests a new scaling path beyond token-wise test-time methods. (3) \textit{Robustness and generality}: reasoning gains persist across architectures and reuse schedules, showing VLD captures a general scaling behavior. These results provide insight into future scaling strategies and raise a deeper question: does superintelligence require ever-larger models, or can it be achieved by reusing parameters and increasing logical depth? We argue many unknown dynamics in scaling remain to be explored. Code is available at https://anonymous.4open.science/r/virtual_logical_depth-8024/.
URLs: https://anonymous.4open.science/r/virtual_logical_depth-8024/.
Authors: Yun Qu, Qi Wang, Yixiu Mao, Vincent Tao Hu, Bj\"orn Ommer, Xiangyang Ji
Abstract: Recent advances have witnessed the effectiveness of reinforcement learning (RL) finetuning in enhancing the reasoning capabilities of large language models (LLMs). The optimization process often requires numerous iterations to achieve satisfactory performance, resulting in high computational costs due to the need for frequent prompt evaluations under intensive LLM interactions and repeated policy updates. Appropriate online prompt selection methods reduce iteration steps by prioritizing informative prompts during training, while the pipeline's reliance on exhaustive prompt evaluation and subset selection for optimization still incurs substantial computational overhead due to frequent LLM inference calls. Distinguished from these direct evaluate-then-select schemes, this work investigates iterative approximate evaluation for arbitrary prompts and introduces Model Predictive Prompt Selection (MoPPS), a Bayesian risk-predictive framework that online estimates prompt difficulty without requiring costly LLM interactions. Technically, MoPPS models each prompt's success rate as a latent variable, performs streaming Bayesian inference, and employs posterior sampling in a constructed multi-armed bandit machine, enabling sample efficient and adaptive prompt selection. Extensive experiments across mathematics, planning, and vision-based geometry tasks show that MoPPS reliably predicts prompt difficulty and accelerates training with significantly reduced LLM rollouts. Our code is available at https://github.com/thu-rllab/MoPPS.
Authors: Li-Hsiang Shen, Jyun-Jhe Huang
Abstract: A space-air-ground integrated network (SAGIN) for Internet of Things (IoT) network architecture is investigated, empowered by multi-functional reconfigurable intelligent surfaces (MF-RIS) capable of simultaneously reflecting, amplifying, and harvesting wireless energy. The MF-RIS plays a pivotal role in addressing the energy shortages of low-Earth orbit (LEO) satellites operating in the shadowed regions, while accounting for both communication and computing energy consumption across the SAGIN nodes. To maximize the long-term energy efficiency (EE) of IoT devices, we formulate a joint optimization problem over the MF-RIS parameters, including signal amplification, phase-shifts, energy harvesting ratio, and active element selection as well as the SAGIN parameters of beamforming vectors, high-altitude platform station (HAPS) deployment, IoT device association, and computing capability. The formulated problem is highly non-convex and non-linear and contains mixed discrete-continuous parameters. To tackle this, we conceive a compressed hybrid twin-model enhanced multi-agent deep reinforcement learning (CHIMERA) framework, which integrates semantic state-action compression and parametrized sharing under hybrid reinforcement learning to efficiently explore suitable complex actions. The simulation results have demonstrated that the proposed CHIMERA scheme substantially outperforms the conventional benchmarks, including fixed-configuration or non-harvesting MF-RIS, traditional RIS, and no-RIS cases, as well as centralized and multi-agent deep reinforcement learning baselines in terms of the highest EE. Moreover, the proposed SAGIN-MF-RIS architecture in IoT network achieves superior EE performance due to its complementary coverage, offering notable advantages over either standalone satellite, aerial, or ground-only deployments.
Authors: Shixin Yi, Lin Shang
Abstract: Multimodal reasoning with vision-language models (VLMs) often suffers from hallucinations, as models tend to generate explanations after only a superficial inspection of the image. We present \textbf{CoRGI}(\textbf{C}hain \textbf{o}f \textbf{R}easoning with \textbf{G}rounded \textbf{I}nsights), a framework that enhances reasoning reliability through post-hoc verification of chain-of-thought outputs. Given a VLM-generated rationale, CoRGI decomposes it into step-wise statements, grounds each step in visual evidence, and filters or corrects unsupported claims before producing the final answer. Experiments on five challenging benchmark-VCR, ScienceQA, MMMU, MathVista, and HallusionBenc-demonstrate that CoRGI consistently improves both answer accuracy and explanation faithfulness across multiple VLM backbones, including Qwen-2.5VL, LLaVA-1.6, and Gemma3-12B. Beyond quantitative gains, qualitative analyses further illustrate how the verification process reduces hallucination and strengthens interpretability, suggesting that post-hoc visual grounding is a promising direction for building more trustworthy and transparent multimodal reasoning systems.
Authors: Zhiyuan Han, Beier Zhu, Yanlong Xu, Peipei Song, Xun Yang
Abstract: Despite their strong performance in multimodal emotion reasoning, existing Multimodal Large Language Models (MLLMs) often overlook the scenarios involving emotion conflicts, where emotional cues from different modalities are inconsistent. To fill this gap, we first introduce CA-MER, a new benchmark designed to examine MLLMs under realistic emotion conflicts. It consists of three subsets: video-aligned, audio-aligned, and consistent, where only one or all modalities reflect the true emotion. However, evaluations on our CA-MER reveal that current state-of-the-art emotion MLLMs systematically over-rely on audio signal during emotion conflicts, neglecting critical cues from visual modality. To mitigate this bias, we propose MoSEAR, a parameter-efficient framework that promotes balanced modality integration. MoSEAR consists of two modules: (1)MoSE, modality-specific experts with a regularized gating mechanism that reduces modality bias in the fine-tuning heads; and (2)AR, an attention reallocation mechanism that rebalances modality contributions in frozen backbones during inference. Our framework offers two key advantages: it mitigates emotion conflicts and improves performance on consistent samples-without incurring a trade-off between audio and visual modalities. Experiments on multiple benchmarks-including MER2023, EMER, DFEW, and our CA-MER-demonstrate that MoSEAR achieves state-of-the-art performance, particularly under modality conflict conditions.
Authors: Yinghao Zhu, Yifan Qi, Zixiang Wang, Lei Gu, Dehao Sui, Haoran Hu, Xichen Zhang, Ziyi He, Junjun He, Liantao Ma, Lequan Yu
Abstract: The rapid proliferation of scientific knowledge presents a grand challenge: transforming this vast repository of information into an active engine for discovery, especially in high-stakes domains like healthcare. Current AI agents, however, are constrained by static, predefined strategies, limiting their ability to navigate the complex, evolving ecosystem of scientific research. This paper introduces HealthFlow, a self-evolving AI agent that overcomes this limitation through a novel meta-level evolution mechanism. HealthFlow autonomously refines its high-level problem-solving policies by distilling procedural successes and failures into a durable, structured knowledge base, enabling it to learn not just how to use tools, but how to strategize. To anchor our research and provide a community resource, we introduce EHRFlowBench, a new benchmark featuring complex health data analysis tasks systematically derived from peer-reviewed scientific literature. Our experiments demonstrate that HealthFlow's self-evolving approach significantly outperforms state-of-the-art agent frameworks. This work offers a new paradigm for intelligent systems that can learn to operationalize the procedural knowledge embedded in scientific content, marking a critical step toward more autonomous and effective AI for healthcare scientific discovery.
Authors: Kaitao Chen, Mianxin Liu, Daoming Zong, Chaoyue Ding, Shaohao Rui, Yankai Jiang, Mu Zhou, Xiaosong Wang
Abstract: Complex medical decision-making involves cooperative workflows operated by different clinicians. Designing AI multi-agent systems can expedite and augment human-level clinical decision-making. Existing multi-agent researches primarily focus on language-only tasks, yet their extension to multimodal scenarios remains challenging. A blind combination of diverse vision-language models (VLMs) can amplify an erroneous outcome interpretation. VLMs in general are less capable in instruction following and importantly self-reflection, compared to large language models (LLMs) of comparable sizes. This disparity largely constrains VLMs' ability in cooperative workflows. In this study, we propose MedOrch, a mediator-guided multi-agent collaboration framework for medical multimodal decision-making. MedOrch employs an LLM-based mediator agent that enables multiple VLM-based expert agents to exchange and reflect on their outputs towards collaboration. We utilize multiple open-source general-purpose and domain-specific VLMs instead of costly GPT-series models, revealing the strength of heterogeneous models. We show that the collaboration within distinct VLM-based agents can surpass the capabilities of any individual agent. We validate our approach on five medical vision question answering benchmarks, demonstrating superior collaboration performance without model training. Our findings underscore the value of mediator-guided multi-agent collaboration in advancing medical multimodal intelligence.
Authors: Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li
Abstract: Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-integrated reasoning systems, however, often follow a single-agent paradigm in which one large model interleaves long-horizon reasoning with precise tool operations, leading to cognitive-load interference and unstable coordination. We present MSARL, a Multi-Small-Agent Reinforcement Learning framework that explicitly decouples reasoning from tool use. In MSARL, a Reasoning Agent decomposes problems and plans tool invocations, while multiple Tool Agents specialize in specific external tools, each trained via a combination of imitation learning and reinforcement learning with role-specific rewards. On mathematical problem solving with code execution, MSARL significantly improves reasoning stability and final-answer accuracy over single-agent baselines. Moreover, the architecture generalizes to diverse tool-use tasks, demonstrating that cognitive-role decoupling with small agents is a scalable blueprint for multi-agent AI design.
Authors: Zifeng Ding, Shenyang Huang, Zeyu Cao, Emma Kondrup, Zachary Yang, Xingyue Huang, Yuan Sui, Zhangdie Yuan, Yuqicheng Zhu, Xianglong Hu, Yuan He, Farimah Poursafaei, Michael Bronstein, Andreas Vlachos
Abstract: Forecasting future links is a central task in temporal graph (TG) reasoning, requiring models to leverage historical interactions to predict upcoming ones. Traditional neural approaches, such as temporal graph neural networks, achieve strong performance but lack explainability and cannot be applied to unseen graphs without retraining. Recent studies have begun to explore using large language models (LLMs) for graph reasoning, but most of them are constrained to static graphs or small synthetic TGs and lack the evaluation of the quality of reasoning traces generated by LLMs. In this work, we present Reasoning-Enhanced Learning for Temporal Graphs (ReaL-TG), a reinforcement learning framework that fine-tunes LLMs to perform explainable link forecasting on real-world TGs. ReaL-TG uses outcome-based reward to encourage models to self-explore reasoning strategies from graph structure and to produce explanations that directly justify their predictions. To enable evaluation on LLM-generated reasoning traces, we propose a new evaluation protocol combining ranking metrics with an LLM-as-a-Judge system that assesses both the quality of reasoning and the impact of hallucinations. Experiments with ReaL-TG-4B, obtained by fine-tuning Qwen3-4B under our framework, show that it outperforms much larger frontier LLMs, including GPT-5 mini, on ranking metrics, while producing high-quality explanations confirmed by both the LLM judge and human evaluation.
Authors: Yunbo Long, Liming Xu, Lukas Beckenbauer, Yuhan Liu, Alexandra Brintrup
Abstract: Recent research on Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs) has demonstrated that agents can engage in \textit{complex}, \textit{multi-turn} negotiations, opening new avenues for agentic AI. However, existing LLM agents largely overlook the functional role of emotions in such negotiations, instead generating passive, preference-driven emotional responses that make them vulnerable to manipulation and strategic exploitation by adversarial counterparts. To address this gap, we present EvoEmo, an evolutionary reinforcement learning framework that optimizes dynamic emotional expression in negotiations. EvoEmo models emotional state transitions as a Markov Decision Process and employs population-based genetic optimization to evolve high-reward emotion policies across diverse negotiation scenarios. We further propose an evaluation framework with two baselines -- vanilla strategies and fixed-emotion strategies -- for benchmarking emotion-aware negotiation. Extensive experiments and ablation studies show that EvoEmo consistently outperforms both baselines, achieving higher success rates, higher efficiency, and increased buyer savings. This findings highlight the importance of adaptive emotional expression in enabling more effective LLM agents for multi-turn negotiation.
Authors: Jinwei Su, Qizhen Lan, Yinghui Xia, Lifan Sun, Weiyou Tian, Tianyu Shi, Lewei He
Abstract: Large Language Model (LLM)-based agentic systems have shown strong capabilities across various tasks. However, existing multi-agent frameworks often rely on static or task-level workflows, which either over-process simple queries or underperform on complex ones, while also neglecting the efficiency-performance trade-offs across heterogeneous LLMs. To address these limitations, we propose Difficulty-Aware Agentic Orchestration (DAAO), which can dynamically generate query-specific multi-agent workflows guided by predicted query difficulty. DAAO comprises three interdependent modules: a variational autoencoder (VAE) for difficulty estimation, a modular operator allocator, and a cost- and performance-aware LLM router. A self-adjusting policy updates difficulty estimates based on workflow success, enabling simpler workflows for easy queries and more complex strategies for harder ones. Experiments on six benchmarks demonstrate that DAAO surpasses prior multi-agent systems in both accuracy and inference efficiency, validating its effectiveness for adaptive, difficulty-aware reasoning.
Authors: Zhaolong Wu, Pu Luo, Nan Meng, Jason Pui Yin Cheung, Teng Zhang
Abstract: This study presents the first comprehensive evaluation of Multimodal Large Language Models (MLLMs) for Adolescent Idiopathic Scoliosis (AIS) self-management. We constructed a database of approximately 3,000 anteroposterior X-rays with diagnostic texts and evaluated five MLLMs through a `Divide and Conquer' framework consisting of a visual question-answering task, a domain knowledge assessment task, and a patient education counseling assessment task. Our investigation revealed limitations of MLLMs' ability in interpreting complex spinal radiographs and comprehending AIS care knowledge. To address these, we pioneered enhancing MLLMs with spinal keypoint prompting and compiled an AIS knowledge base for retrieval augmented generation (RAG), respectively. Results showed varying effectiveness of visual prompting across different architectures, while RAG substantially improved models' performances on the knowledge assessment task. Our findings indicate current MLLMs are far from capable in realizing personalized assistant in AIS care. The greatest challenge lies in their abilities to obtain accurate detections of spinal deformity locations (best accuracy: 0.55) and directions (best accuracy: 0.13).
Authors: Yubo Li, Weiyi Song
Abstract: Current AI alignment through RLHF follows a single directional paradigm that AI conforms to human preferences while treating human cognition as fixed. We propose a shift to co-alignment through Bidirectional Cognitive Alignment (BiCA), where humans and AI mutually adapt. BiCA uses learnable protocols, representation mapping, and KL-budget constraints for controlled co-evolution. In collaborative navigation, BiCA achieved 85.5% success versus 70.3% baseline, with 230% better mutual adaptation and 332% better protocol convergence. Emergent protocols outperformed handcrafted ones by 84%, while bidirectional adaptation unexpectedly improved safety (+23% out-of-distribution robustness). The 46% synergy improvement demonstrates optimal collaboration exists at the intersection, not union, of human and AI capabilities, validating the shift from single-directional to co-alignment paradigms.
Authors: Yang Wang, Kai Li
Abstract: Operations research (OR) provides fundamental methodologies for complex system decision-making, with established applications in transportation, supply chain management, and production scheduling. Traditional approaches, which depend on expert-based modeling and manual parameter adjustment, often face challenges in handling large-scale, dynamic, and multi-constraint problems. Recently, large language models (LLMs) have shown potential to address these limitations through semantic understanding, structured generation, and reasoning control. LLMs can translate natural language descriptions into mathematical models or executable code, generate heuristics, evolve algorithms, and directly tackle optimization tasks. This paper surveys recent progress on the integration of LLMs into OR, organizing methods into three main directions: automatic modeling, auxiliary optimization, and direct solving. It further reviews evaluation benchmarks and domain-specific applications, and summarizes key open issues such as unstable semantic-to-structure mapping, fragmented research progress, limited generalization, and insufficient evaluation systems. Finally, the survey outlines possible research avenues for advancing the role of LLMs in OR.
Authors: Atma Anand
Abstract: Information-processing systems coordinating across multiple agents and objectives face fundamental thermodynamic constraints. We show that solutions with maximum utility to act as coordination focal points have much higher selection pressure for being findable across agents rather than accuracy. We derive that the information-theoretic minimum description length of coordination protocols to precision $\varepsilon$ scales as $L(P)\geq NK\log_2 K+N^2d^2\log (1/\varepsilon)$ for $N$ agents with $d$ potentially conflicting objectives and internal model complexity $K$. This scaling forces progressive simplification, with coordination dynamics changing the environment itself and shifting optimization across hierarchical levels. Moving from established focal points requires re-coordination, creating persistent metastable states and hysteresis until significant environmental shifts trigger phase transitions through spontaneous symmetry breaking. We operationally define coordination temperature to predict critical phenomena and estimate coordination work costs, identifying measurable signatures across systems from neural networks to restaurant bills to bureaucracies. Extending the topological version of Arrow's theorem on the impossibility of consistent preference aggregation, we find it recursively binds whenever preferences are combined. This potentially explains the indefinite cycling in multi-objective gradient descent and alignment faking in Large Language Models trained with reinforcement learning with human feedback. We term this framework Thermodynamic Coordination Theory (TCT), which demonstrates that coordination requires radical information loss.
Authors: Jingyu Liu, Xiaopeng Wu, Jingquan Peng, Kehan Chen, Chuan Yu, Lizhong Ding, Yong Liu
Abstract: Building autonomous agents capable of solving long-horizon, real-world tasks has garnered significant research interest. But outcome based rewards may cause reward miscalibration which means it might mistakenly allocate positive reward to flawed middle steps which is regarded as the key reason making the bad actions being reinforced during training. However we reveal that outcome based reward ensures expected negative advantage for those flawed middle steps, which means the flawed actions should be punished during training. Even accounting for the ``squeezing effect", the probability mass of good actions should increase and the actor should gradually get rid of harmful actions. This shows that flawed actions should be punished during training. We further identify gradient coupling between similar samples as a key issue in agentic RL, the input prompt is extremely similar and the output action space is limited, therefore during training, gradients from well-performing samples can inadvertently strengthen suboptimal or incorrect actions due to similar input observation and output actions. We show that with gradient coupling, some flawed actions might be enhanced. To address this, we propose training the actor to classify good or bad actions to separate the embedding of good/bad actions and alleviate the gradient interference, extensive experiments shows its effectiveness.
Authors: Lifan Yuan, Weize Chen, Yuchen Zhang, Ganqu Cui, Hanbin Wang, Ziming You, Ning Ding, Zhiyuan Liu, Maosong Sun, Hao Peng
Abstract: Does RL teach LLMs genuinely new skills, or does it merely activate existing ones? This question lies at the core of ongoing debates about the role of RL in LLM post-training. On one side, strong empirical results can be achieved with RL even without preceding supervised finetuning; on the other, critics argue that RL contributes little beyond reweighting existing reasoning strategies. This work provides concrete evidence that LLMs can acquire genuinely new skills during RL by composing existing ones, mirroring one of the central mechanisms by which humans acquire new cognitive skills. To mitigate data contamination and other confounding factors, and to allow precise control over task complexity, we develop a synthetic framework for our investigation. Specifically, we define a skill as the ability to infer the output of a string transformation function f(x) given x. When an LLM has already learned f and g prior to RL, our experiments reveal that RL enables it to learn unseen compositions of them h(x)=g(f(x)). Further, this compositional ability generalizes to more difficult problems such as compositions of >2 functions unseen during RL training. Surprisingly, our experiments show that compositional skill acquired on a source task transfers to a different target task. This transfer happens even without compositional training on the target, requiring only prior knowledge of the target's atomic skills. Our qualitative analysis shows that RL fundamentally changes the reasoning behaviors of the models. In contrast, next-token training with the same data yields none of these findings. Our systematic experiments provide fresh insights into LLM learning, suggesting the value of first building base models with basic skills, then using RL to incentivize advanced, generalizable skills for complex problems.
Authors: Jiecheng Zhou, Qinghao Hu, Yuyang Jin, Zerui Wang, Peng Sun, Yuzhe Gu, Wenwei Zhang, Mingshu Zhai, Xingcheng Zhang, Weiming Zhang
Abstract: Large Language Models (LLMs) are now widely used across many domains. With their rapid development, Reinforcement Learning with Verifiable Rewards (RLVR) has surged in recent months to enhance their reasoning and understanding abilities. However, its complex data flows and diverse tasks pose substantial challenges to RL training systems, and there is limited understanding of RLVR from a system perspective. To thoroughly understand the system challenges introduced by RLVR, we present a characterization study of RLVR tasks in our LLM deployment. Specifically, we investigate the distribution and variation trends of workloads across different RL tasks across training steps. We identify issues such as GPU idling caused by skewed sequence length distribution, inefficient parallel strategies in dynamically varying workloads, inefficient data management mechanisms, and load imbalance. We describe our observations and call for further investigation into the remaining open challenges. Furthermore, we propose PolyTrace benchmark suite to conduct evaluation with realistic workloads, and a practical use case validates that PolyTrace benchmark suite exhibits 94.7% accuracy.
Authors: Ma\"el Macuglia, Paul Friedrich, Giorgia Ramponi
Abstract: Deploying reinforcement learning (RL) in robotics, industry, and health care is blocked by two obstacles: the difficulty of specifying accurate rewards and the risk of unsafe, data-hungry exploration. We address this by proposing a two-stage framework that first learns a safe initial policy from a reward-free dataset of expert demonstrations, then fine-tunes it online using preference-based human feedback. We provide the first principled analysis of this offline-to-online approach and introduce BRIDGE, a unified algorithm that integrates both signals via an uncertainty-weighted objective. We derive regret bounds that shrink with the number of offline demonstrations, explicitly connecting the quantity of offline data to online sample efficiency. We validate BRIDGE in discrete and continuous control MuJoCo environments, showing it achieves lower regret than both standalone behavioral cloning and online preference-based RL. Our work establishes a theoretical foundation for designing more sample-efficient interactive agents.
Authors: Tudor Achim, Alex Best, Alberto Bietti, Kevin Der, Math\"is F\'ed\'erico, Sergei Gukov, Daniel Halpern-Leistner, Kirsten Henningsgard, Yury Kudryashov, Alexander Meiburg, Martin Michelsen, Riley Patterson, Eric Rodriguez, Laura Scharff, Vikram Shanker, Vladmir Sicca, Hari Sowrirajan, Aidan Swope, Matyas Tamas, Vlad Tenev, Jonathan Thomm, Harold Williams, Lawrence Wu
Abstract: We introduce Aristotle, an AI system that combines formal verification with informal reasoning, achieving gold-medal-equivalent performance on the 2025 International Mathematical Olympiad problems. Aristotle integrates three main components: a Lean proof search system, an informal reasoning system that generates and formalizes lemmas, and a dedicated geometry solver. Our system demonstrates state-of-the-art performance with favorable scaling properties for automated theorem proving.
Authors: Bill Marino, Rosco Hunter, Zubair Jamali, Marinos Emmanouil Kalpakos, Mudra Kashyap, Isaiah Hinton, Alexa Hanson, Maahum Nazir, Christoph Schnabl, Felix Steffek, Hongkai Wen, Nicholas D. Lane
Abstract: As governments move to regulate AI, there is growing interest in using Large Language Models (LLMs) to assess whether or not an AI system complies with a given AI Regulation (AIR). However, there is presently no way to benchmark the performance of LLMs at this task. To fill this void, we introduce AIReg-Bench: the first benchmark dataset designed to test how well LLMs can assess compliance with the EU AI Act (AIA). We created this dataset through a two-step process: (1) by prompting an LLM with carefully structured instructions, we generated 120 technical documentation excerpts (samples), each depicting a fictional, albeit plausible, AI system - of the kind an AI provider might produce to demonstrate their compliance with AIR; (2) legal experts then reviewed and annotated each sample to indicate whether, and in what way, the AI system described therein violates specific Articles of the AIA. The resulting dataset, together with our evaluation of whether frontier LLMs can reproduce the experts' compliance labels, provides a starting point to understand the opportunities and limitations of LLM-based AIR compliance assessment tools and establishes a benchmark against which subsequent LLMs can be compared. The dataset and evaluation code are available at https://github.com/camlsys/aireg-bench.
Authors: Ananya Mantravadi, Shivali Dalmia, Olga Pospelova, Abhishek Mukherji, Nand Dave, Anudha Mittal
Abstract: Retrieval-Augmented Generation (RAG) integrates large language models (LLMs) with external sources, but unresolved contradictions in retrieved evidence often lead to hallucinations and legally unsound outputs. Benchmarks currently used for contradiction detection lack domain realism, cover only limited conflict types, and rarely extend beyond single-sentence pairs, making them unsuitable for legal applications. Controlled generation of documents with embedded contradictions is therefore essential: it enables systematic stress-testing of models, ensures coverage of diverse conflict categories, and provides a reliable basis for evaluating contradiction detection and resolution. We present a multi-agent contradiction-aware benchmark framework for the legal domain that generates synthetic legal-style documents, injects six structured contradiction types, and models both self- and pairwise inconsistencies. Automated contradiction mining is combined with human-in-the-loop validation to guarantee plausibility and fidelity. This benchmark offers one of the first structured resources for contradiction-aware evaluation in legal RAG pipelines, supporting more consistent, interpretable, and trustworthy systems.
Authors: Jingxiang Zhang, Lujia Zhong
Abstract: Large Language Models (LLMs) are increasingly expected to navigate the nuances of human emotion. While research confirms that LLMs can simulate emotional intelligence, their internal emotional mechanisms remain largely unexplored. This paper investigates the latent emotional representations within modern LLMs by asking: how, where, and for how long is emotion encoded in their neural architecture? To address this, we introduce a novel, large-scale Reddit corpus of approximately 400,000 utterances, balanced across seven basic emotions through a multi-stage process of classification, rewriting, and synthetic generation. Using this dataset, we employ lightweight "probes" to read out information from the hidden layers of various Qwen3 and LLaMA models without altering their parameters. Our findings reveal that LLMs develop a surprisingly well-defined internal geometry of emotion, which sharpens with model scale and significantly outperforms zero-shot prompting. We demonstrate that this emotional signal is not a final-layer phenomenon but emerges early and peaks mid-network. Furthermore, the internal states are both malleable (they can be influenced by simple system prompts) and persistent, as the initial emotional tone remains detectable for hundreds of subsequent tokens. We contribute our dataset, an open-source probing toolkit, and a detailed map of the emotional landscape within LLMs, offering crucial insights for developing more transparent and aligned AI systems. The code and dataset are open-sourced.
Authors: Pengfei He, Zhenwei Dai, Bing He, Hui Liu, Xianfeng Tang, Hanqing Lu, Juanhui Li, Jiayuan Ding, Subhabrata Mukherjee, Suhang Wang, Yue Xing, Jiliang Tang, Benoit Dumoulin
Abstract: Large language model (LLM)-based agents increasingly rely on tool use to complete real-world tasks. While existing works evaluate the LLMs' tool use capability, they largely focus on the final answers yet overlook the detailed tool usage trajectory, i.e., whether tools are selected, parameterized, and ordered correctly. We introduce TRAJECT-Bench, a trajectory-aware benchmark to comprehensively evaluate LLMs' tool use capability through diverse tasks with fine-grained evaluation metrics. TRAJECT-Bench pairs high-fidelity, executable tools across practical domains with tasks grounded in production-style APIs, and synthesizes trajectories that vary in breadth (parallel calls) and depth (interdependent chains). Besides final accuracy, TRAJECT-Bench also reports trajectory-level diagnostics, including tool selection and argument correctness, and dependency/order satisfaction. Analyses reveal failure modes such as similar tool confusion and parameter-blind selection, and scaling behavior with tool diversity and trajectory length where the bottleneck of transiting from short to mid-length trajectories is revealed, offering actionable guidance for LLMs' tool use.
Authors: Zhejian Lai, Xiang Geng, Zhijun Wang, Yang Bai, Jiahuan Li, Rongxiang Weng, Jingang Wang, Xuezhi Cao, Xunliang Cai, Shujian Huang
Abstract: Mathematical reasoning is a primary indicator of large language models (LLMs) intelligence. However, existing LLMs exhibit failures of robustness and generalization. This paper attributes these deficiencies to spurious reasoning, i.e., producing answers from superficial features. To address this challenge, we propose the AdaR framework to enable adaptive reasoning, wherein models rely on problem-solving logic to produce answers. AdaR synthesizes logically equivalent queries by varying variable values, and trains models with RLVR on these data to penalize spurious logic while encouraging adaptive logic. To improve data quality, we extract the problem-solving logic from the original query and generate the corresponding answer by code execution, then apply a sanity check. Experimental results demonstrate that AdaR improves robustness and generalization, achieving substantial improvement in mathematical reasoning while maintaining high data efficiency. Analysis indicates that data synthesis and RLVR function in a coordinated manner to enable adaptive reasoning in LLMs. Subsequent analyses derive key design insights into the effect of critical factors and the applicability to instruct LLMs. Our project is available at https://github.com/NJUNLP/AdaR.
Authors: Kun Xiang, Terry Jingchen Zhang, Yinya Huang, Jixi He, Zirong Liu, Yueling Tang, Ruizhe Zhou, Lijing Luo, Youpeng Wen, Xiuwei Chen, Bingqian Lin, Jianhua Han, Hang Xu, Hanhui Li, Bin Dong, Xiaodan Liang
Abstract: The rapid advancement of embodied intelligence and world models has intensified efforts to integrate physical laws into AI systems, yet physical perception and symbolic physics reasoning have developed along separate trajectories without a unified bridging framework. This work provides a comprehensive overview of physical AI, establishing clear distinctions between theoretical physics reasoning and applied physical understanding while systematically examining how physics-grounded methods enhance AI's real-world comprehension across structured symbolic reasoning, embodied systems, and generative models. Through rigorous analysis of recent advances, we advocate for intelligent systems that ground learning in both physical principles and embodied reasoning processes, transcending pattern recognition toward genuine understanding of physical laws. Our synthesis envisions next-generation world models capable of explaining physical phenomena and predicting future states, advancing safe, generalizable, and interpretable AI systems. We maintain a continuously updated resource at https://github.com/AI4Phys/Awesome-AI-for-Physics.
Authors: Xuanming Cui, Jianpeng Cheng, Hong-you Chen, Satya Narayan Shukla, Abhijeet Awasthi, Xichen Pan, Chaitanya Ahuja, Shlok Kumar Mishra, Qi Guo, Ser-Nam Lim, Aashu Singh, Xiangjun Fan
Abstract: There is a growing interest in Universal Multimodal Embeddings (UME), where models are required to generate task-specific representations. While recent studies show that Multimodal Large Language Models (MLLMs) perform well on such tasks, they treat MLLMs solely as encoders, overlooking their generative capacity. However, such an encoding paradigm becomes less effective as instructions become more complex and require compositional reasoning. Inspired by the proven effectiveness of chain-of-thought reasoning, we propose a general Think-Then-Embed (TTE) framework for UME, composed of a reasoner and an embedder. The reasoner MLLM first generates reasoning traces that explain complex queries, followed by an embedder that produces representations conditioned on both the original query and the intermediate reasoning. This explicit reasoning step enables more nuanced understanding of complex multimodal instructions. Our contributions are threefold. First, by leveraging a powerful MLLM reasoner, we achieve state-of-the-art performance on the MMEB-V2 benchmark, surpassing proprietary models trained on massive in-house datasets. Second, to reduce the dependency on large MLLM reasoners, we finetune a smaller MLLM reasoner using high-quality embedding-centric reasoning traces, achieving the best performance among open-source models with a 7% absolute gain over recently proposed models. Third, we investigate strategies for integrating the reasoner and embedder into a unified model for improved efficiency without sacrificing performance.
Authors: Leonardo Christov-Moore, Arthur Juliani, Alex Kiefer, Nicco Reggente, B. Scott Rousse, Adam Safron, Nicol\'as Hinrichs, Daniel Polani, Antonio Damasio
Abstract: Physical vulnerability and mortality are often seen as obstacles to be avoided in the development of artificial agents, which struggle to adapt to open-ended environments and provide aligned care. Meanwhile, biological organisms survive, thrive, and care for each other in an open-ended physical world with relative ease and efficiency. Understanding the role of the conditions of life in this disparity can aid in developing more robust, adaptive, and caring artificial agents. Here we define two minimal conditions for physical embodiment inspired by the existentialist phenomenology of Martin Heidegger: being-in-the-world (the agent is a part of the environment) and being-towards-death (unless counteracted, the agent drifts toward terminal states due to the second law of thermodynamics). We propose that from these conditions we can obtain both a homeostatic drive - aimed at maintaining integrity and avoiding death by expending energy to learn and act - and an intrinsic drive to continue to do so in as many ways as possible. Drawing inspiration from Friedrich Nietzsche's existentialist concept of will-to-power, we examine how intrinsic drives to maximize control over future states, e.g., empowerment, allow agents to increase the probability that they will be able to meet their future homeostatic needs, thereby enhancing their capacity to maintain physical integrity. We formalize these concepts within a reinforcement learning framework, which enables us to examine how intrinsically driven embodied agents learning in open-ended multi-agent environments may cultivate the capacities for open-endedness and care.
Authors: Pulkit Rustagi, Kyle Hollins Wray, Sandhya Saisubramanian
Abstract: Many real-world scenarios require multiple agents to coordinate in shared environments, while balancing trade-offs between multiple, potentially competing objectives. Current multi-objective multi-agent path finding (MO-MAPF) algorithms typically produce conflict-free plans by computing Pareto frontiers. They do not explicitly optimize for user-defined preferences, even when the preferences are available, and scale poorly with the number of objectives. We propose a lexicographic framework for modeling MO-MAPF, along with an algorithm \textit{Lexicographic Conflict-Based Search} (LCBS) that directly computes a single solution aligned with a lexicographic preference over objectives. LCBS integrates a priority-aware low-level $A^*$ search with conflict-based search, avoiding Pareto frontier construction and enabling efficient planning guided by preference over objectives. We provide insights into optimality and scalability, and empirically demonstrate that LCBS computes optimal solutions while scaling to instances with up to ten objectives -- far beyond the limits of existing MO-MAPF methods. Evaluations on standard and randomized MAPF benchmarks show consistently higher success rates against state-of-the-art baselines, especially with increasing number of objectives.
Authors: Constantin Venhoff, Iv\'an Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda
Abstract: Why do thinking language models like DeepSeek R1 outperform their base counterparts? Despite consistent performance gains, it remains unclear to what extent thinking models learn entirely new reasoning capabilities or repurpose pre-existing base model ones. In this work, we propose a hybrid model where we activate reasoning mechanisms in base models at the right time to elicit thinking-model-level reasoning chains, implying that thinking models exploit already existing capabilities. To ground our analysis, we introduce an unsupervised, bottom-up approach for uncovering human-interpretable reasoning behaviors in thinking models. This approach provides an unbiased method to discover reasoning behaviors without imposing manual or LLM-derived assumptions. Across three base and four thinking models, using GSM8K and MATH500, our hybrid model recovers up to 91% of the performance gap to thinking models without any weight updates while steering only 12% of tokens. Concretely, our empirical setup provides a simple, causal way to test the effectiveness of existing reasoning mechanisms in base models by invoking them directly and measuring the resulting task performance. More broadly, these results reframe our understanding of how thinking models are trained: pre-training is when models acquire most of their reasoning mechanisms, and post-training teaches efficient deployment of these mechanisms at the right time, enabling efficient use of their inference-time compute.
Authors: William Nguyen, Vinh Luong, Christopher Nguyen
Abstract: Large language models (LLMs) have empowered AI agents to tackle increasingly complex tasks. However, most existing agents remain limited to static planning and brittle interactions, falling short of true collaboration or adaptive reasoning. We introduce ProSEA, a modular, general-purpose multi-agent framework designed for iterative problem solving through exploration and plan evolution. ProSEA features a hierarchical architecture in which a Manager Agent orchestrates domain-specialized Expert Agents, decomposes tasks, and adaptively replans based on structured feedback from failed attempts. Unlike prior systems, ProSEA agents report not only success or failure but also detailed reasons for failure and newly discovered constraints, enabling dynamic plan refinement informed by exploratory traces. The framework operates autonomously but supports seamless integration with human collaborators when needed. Experiments on the challenging FinanceBench benchmark demonstrate that ProSEA, even without human feedback, outperforms state-of-the-art baselines and achieves robust performance across reasoning-heavy tasks. These results underscore ProSEA's potential as a foundation for more transparent, adaptive, and human-aligned AI agents.
Authors: Ruiling Xu, Yifan Zhang, Qingyun Wang, Carl Edwards, Heng Ji
Abstract: Organic reaction mechanisms are the stepwise elementary reactions by which reactants form intermediates and products, and are fundamental to understanding chemical reactivity and designing new molecules and reactions. Although large language models (LLMs) have shown promise in understanding chemical tasks such as synthesis design, it is unclear to what extent this reflects genuine chemical reasoning capabilities, i.e., the ability to generate valid intermediates, maintain chemical consistency, and follow logically coherent multi-step pathways. We address this by introducing oMeBench, the first large-scale, expert-curated benchmark for organic mechanism reasoning in organic chemistry. It comprises over 10,000 annotated mechanistic steps with intermediates, type labels, and difficulty ratings. Furthermore, to evaluate LLM capability more precisely and enable fine-grained scoring, we propose oMeS, a dynamic evaluation framework that combines step-level logic and chemical similarity. We analyze the performance of state-of-the-art LLMs, and our results show that although current models display promising chemical intuition, they struggle with correct and consistent multi-step reasoning. Notably, we find that using prompting strategy and fine-tuning a specialist model on our proposed dataset increases performance by 50% over the leading closed-source model. We hope that oMeBench will serve as a rigorous foundation for advancing AI systems toward genuine chemical reasoning.
Authors: Tianle Zhou, Jiakai Xu, Guanhong Liu, Jiaxiang Liu, Haonan Wang, Eugene Wu
Abstract: Large Language Models (LLMs) suffer from reliability issues on complex tasks, as existing decomposition methods are heuristic and rely on agent or manual decomposition. This work introduces a novel, systematic decomposition framework that we call Analysis of CONstraint-Induced Complexity (ACONIC), which models the task as a constraint problem and leveraging formal complexity measures to guide decomposition. On combinatorial (SATBench) and LLM database querying tasks (Spider), we find that by decomposing the tasks following the measure of complexity, agent can perform considerably better (10-40 percentage point).
Authors: Qingyang Hao, Wenbo Liao, Bingyi Jing, Hongxin Wei
Abstract: Selecting high-quality candidates from large-scale datasets is critically important in resource-constrained applications such as drug discovery, precision medicine, and the alignment of large language models. While conformal selection methods offer a rigorous solution with False Discovery Rate (FDR) control, their applicability is confined to single-threshold scenarios (i.e., y > c) and overlooks practical needs for multi-condition selection, such as conjunctive or disjunctive conditions. In this work, we propose the Multi-Condition Conformal Selection (MCCS) algorithm, which extends conformal selection to scenarios with multiple conditions. In particular, we introduce a novel nonconformity score with regional monotonicity for conjunctive conditions and a global Benjamini-Hochberg (BH) procedure for disjunctive conditions, thereby establishing finite-sample FDR control with theoretical guarantees. The integration of these components enables the proposed method to achieve rigorous FDR-controlled selection in various multi-condition environments. Extensive experiments validate the superiority of MCCS over baselines, its generalizability across diverse condition combinations, different real-world modalities, and multi-task scalability.
Authors: Benjamin F. Maier, Ulf Aslak, Luca Fiaschi, Nina Rismal, Kemble Fletcher, Christian C. Luhmann, Robbie Dow, Kli Pappas, Thomas V. Wiecki
Abstract: Consumer research costs companies billions annually yet suffers from panel biases and limited scale. Large language models (LLMs) offer an alternative by simulating synthetic consumers, but produce unrealistic response distributions when asked directly for numerical ratings. We present semantic similarity rating (SSR), a method that elicits textual responses from LLMs and maps these to Likert distributions using embedding similarity to reference statements. Testing on an extensive dataset comprising 57 personal care product surveys conducted by a leading corporation in that market (9,300 human responses), SSR achieves 90% of human test-retest reliability while maintaining realistic response distributions (KS similarity > 0.85). Additionally, these synthetic respondents provide rich qualitative feedback explaining their ratings. This framework enables scalable consumer research simulations while preserving traditional survey metrics and interpretability.
Authors: Bicheng Wang, Junping Wang, Yibo Xue
Abstract: Learning complex network dynamics is fundamental to understanding, modelling and controlling real-world complex systems. There are two main problems in the task of predicting the dynamic evolution of complex networks: on the one hand, existing methods usually use simple graphs to describe the relationships in complex networks; however, this approach can only capture pairwise relationships, while there may be rich non-pairwise structured relationships in the network. First-order GNNs have difficulty in capturing dynamic non-pairwise relationships. On the other hand, theoretical prediction models lack accuracy and data-driven prediction models lack interpretability. To address the above problems, this paper proposes a higher-order network dynamics identification method for long-term dynamic prediction of complex networks. Firstly, to address the problem that traditional graph machine learning can only deal with pairwise relations, dynamic hypergraph learning is introduced to capture the higher-order non-pairwise relations among complex networks and improve the accuracy of complex network modelling. Then, a dual-driven dynamic prediction module for physical data is proposed. The Koopman operator theory is introduced to transform the nonlinear dynamical differential equations for the dynamic evolution of complex networks into linear systems for solving. Meanwhile, the physical information neural differential equation method is utilised to ensure that the dynamic evolution conforms to the physical laws. The dual-drive dynamic prediction module ensures both accuracy and interpretability of the prediction. Validated on public datasets and self-built industrial chain network datasets, the experimental results show that the method in this paper has good prediction accuracy and long-term prediction performance.
Authors: Christian Bluethgen, Dave Van Veen, Daniel Truhn, Jakob Nikolas Kather, Michael Moor, Malgorzata Polacin, Akshay Chaudhari, Thomas Frauenfelder, Curtis P. Langlotz, Michael Krauthammer, Farhad Nooralahzadeh
Abstract: Building agents, systems that perceive and act upon their environment with a degree of autonomy, has long been a focus of AI research. This pursuit has recently become vastly more practical with the emergence of large language models (LLMs) capable of using natural language to integrate information, follow instructions, and perform forms of "reasoning" and planning across a wide range of tasks. With its multimodal data streams and orchestrated workflows spanning multiple systems, radiology is uniquely suited to benefit from agents that can adapt to context and automate repetitive yet complex tasks. In radiology, LLMs and their multimodal variants have already demonstrated promising performance for individual tasks such as information extraction and report summarization. However, using LLMs in isolation underutilizes their potential to support complex, multi-step workflows where decisions depend on evolving context from multiple information sources. Equipping LLMs with external tools and feedback mechanisms enables them to drive systems that exhibit a spectrum of autonomy, ranging from semi-automated workflows to more adaptive agents capable of managing complex processes. This review examines the design of such LLM-driven agentic systems, highlights key applications, discusses evaluation methods for planning and tool use, and outlines challenges such as error cascades, tool-use efficiency, and health IT integration.
Authors: Xixi Li, Jingsong Yuan
Abstract: The vector autoregressive (VAR) model has been used to describe the dependence within and across multiple time series. This is a model for stationary time series which can be extended to allow the presence of a deterministic trend in each series. Detrending the data either parametrically or nonparametrically before fitting the VAR model gives rise to more errors in the latter part. In this study, we propose a new approach called DeepVARwT that employs deep learning methodology for maximum likelihood estimation of the trend and the dependence structure at the same time. A Long Short-Term Memory (LSTM) network is used for this purpose. To ensure the stability of the model, we enforce the causality condition on the autoregressive coefficients using the transformation of Ansley & Kohn (1986). We provide a simulation study and an application to real data. In the simulation study, we use realistic trend functions generated from real data and compare the estimates with true function/parameter values. In the real data application, we compare the prediction performance of this model with state-of-the-art models in the literature.
Authors: Christian Raymond, Qi Chen, Bing Xue, Mengjie Zhang
Abstract: Loss function learning is a new meta-learning paradigm that aims to automate the essential task of designing a loss function for a machine learning model. Existing techniques for loss function learning have shown promising results, often improving a model's training dynamics and final inference performance. However, a significant limitation of these techniques is that the loss functions are meta-learned in an offline fashion, where the meta-objective only considers the very first few steps of training, which is a significantly shorter time horizon than the one typically used for training deep neural networks. This causes significant bias towards loss functions that perform well at the very start of training but perform poorly at the end of training. To address this issue we propose a new loss function learning technique for adaptively updating the loss function online after each update to the base model parameters. The experimental results show that our proposed method consistently outperforms the cross-entropy loss and offline loss function learning techniques on a diverse range of neural network architectures and datasets.
Authors: Shuzheng Si, Zefan Cai, Shuang Zeng, Guoqiang Feng, Jiaxing Lin, Baobao Chang
Abstract: Distantly-Supervised Named Entity Recognition effectively alleviates the burden of time-consuming and expensive annotation in the supervised setting. But the context-free matching process and the limited coverage of knowledge bases introduce inaccurate and incomplete annotation noise respectively. Previous studies either considered only incomplete annotation noise or indiscriminately handle two types of noise with the same strategy. In this paper, we argue that the different causes of two types of noise bring up the requirement of different strategies in model architecture. Therefore, we propose the SANTA to handle these two types of noise separately with (1) Memory-smoothed Focal Loss and Entity-aware KNN to relieve the entity ambiguity problem caused by inaccurate annotation, and (2) Boundary Mixup to alleviate decision boundary shifting problem caused by incomplete annotation and a noise-tolerant loss to improve the robustness. Benefiting from our separate tailored strategies, we confirm in the experiment that the two types of noise are well mitigated. SANTA also achieves a new state-of-the-art on five public datasets.
Authors: Haichao Zhang, Can Qin, Yu Yin, Yun Fu
Abstract: Camouflaged objects that blend into natural scenes pose significant challenges for deep-learning models to detect and synthesize. While camouflaged object detection is a crucial task in computer vision with diverse real-world applications, this research topic has been constrained by limited data availability. We propose a framework for synthesizing camouflage data to enhance the detection of camouflaged objects in natural scenes. Our approach employs a generative model to produce realistic camouflage images, which can be used to train existing object detection models. Specifically, we use a camouflage environment generator supervised by a camouflage distribution classifier to synthesize the camouflage images, which are then fed into our generator to expand the dataset. Our framework outperforms the current state-of-the-art method on three datasets (COD10k, CAMO, and CHAMELEON), demonstrating its effectiveness in improving camouflaged object detection. This approach can serve as a plug-and-play data generation and augmentation module for existing camouflaged object detection tasks and provides a novel way to introduce more diversity and distributions into current camouflage datasets.
Authors: Yunwen Lei, Tao Sun, Mingrui Liu
Abstract: The increasing scale of data propels the popularity of leveraging parallelism to speed up the optimization. Minibatch stochastic gradient descent (minibatch SGD) and local SGD are two popular methods for parallel optimization. The existing theoretical studies show a linear speedup of these methods with respect to the number of machines, which, however, is measured by optimization errors in a multi-pass setting. As a comparison, the stability and generalization of these methods are much less studied. In this paper, we study the stability and generalization analysis of minibatch and local SGD to understand their learnability by introducing an expectation-variance decomposition. We incorporate training errors into the stability analysis, which shows how small training errors help generalization for overparameterized models. We show minibatch and local SGD achieve a linear speedup to attain the optimal risk bounds.
Authors: Th\'eo Bourdais, Pau Batlle, Xianjin Yang, Ricardo Baptista, Nicolas Rouquette, Houman Owhadi
Abstract: Most problems within and beyond the scientific domain can be framed into one of the following three levels of complexity of function approximation. Type 1: Approximate an unknown function given input/output data. Type 2: Consider a collection of variables and functions, some of which are unknown, indexed by the nodes and hyperedges of a hypergraph (a generalized graph where edges can connect more than two vertices). Given partial observations of the variables of the hypergraph (satisfying the functional dependencies imposed by its structure), approximate all the unobserved variables and unknown functions. Type 3: Expanding on Type 2, if the hypergraph structure itself is unknown, use partial observations of the variables of the hypergraph to discover its structure and approximate its unknown functions. These hypergraphs offer a natural platform for organizing, communicating, and processing computational knowledge. While most scientific problems can be framed as the data-driven discovery of unknown functions in a computational hypergraph whose structure is known (Type 2), many require the data-driven discovery of the structure (connectivity) of the hypergraph itself (Type 3). We introduce an interpretable Gaussian Process (GP) framework for such (Type 3) problems that does not require randomization of the data, access to or control over its sampling, or sparsity of the unknown functions in a known or learned basis. Its polynomial complexity, which contrasts sharply with the super-exponential complexity of causal inference methods, is enabled by the nonlinear ANOVA capabilities of GPs used as a sensing mechanism.
Authors: Yunshi Lan, Xinyuan Li, Hanyue Du, Xuesong Lu, Ming Gao, Weining Qian, Aoying Zhou
Abstract: Natural Language Processing (NLP) aims to analyze text or speech via techniques in the computer science field. It serves applications in the domains of healthcare, commerce, education, and so on. Particularly, NLP has been widely applied to the education domain and its applications have enormous potential to help teaching and learning. In this survey, we review recent advances in NLP with a focus on solving problems relevant to the education domain. In detail, we begin with introducing the related background and the real-world scenarios in education to which NLP techniques could contribute. Then, we present a taxonomy of NLP in the education domain and highlight typical NLP applications including question answering, question construction, automated assessment, and error correction. Next, we illustrate the task definition, challenges, and corresponding cutting-edge techniques based on the above taxonomy. In particular, LLM-involved methods are included for discussion due to the wide usage of LLMs in diverse NLP applications. After that, we showcase some off-the-shelf demonstrations in this domain, which are designed for educators or researchers. At last, we conclude with five promising directions for future research, including generalization over subjects and languages, deployed LLM-based systems for education, adaptive learning for teaching and learning, interpretability for education, and ethical consideration of NLP techniques. We organize all relevant datasets and papers in the open-available Github Link for better review https://github.com/LiXinyuan1015/NLP-for-Education.
Authors: Chenxi Liu, Yongqiang Chen, Tongliang Liu, Mingming Gong, James Cheng, Bo Han, Kun Zhang
Abstract: Revealing hidden causal variables alongside the underlying causal mechanisms is essential to the development of science. Despite the progress in the past decades, existing practice in causal discovery (CD) heavily relies on high-quality measured variables, which are usually given by human experts. In fact, the lack of well-defined high-level variables behind unstructured data has been a longstanding roadblock to a broader real-world application of CD. This procedure can naturally benefit from an automated process that can suggest potential hidden variables in the system. Interestingly, Large language models (LLMs) are trained on massive observations of the world and have demonstrated great capability in processing unstructured data. To leverage the power of LLMs, we develop a new framework termed Causal representatiOn AssistanT (COAT) that incorporates the rich world knowledge of LLMs to propose useful measured variables for CD with respect to high-value target variables on their paired unstructured data. Instead of directly inferring causality with LLMs, COAT constructs feedback from intermediate CD results to LLMs to refine the proposed variables. Given the target variable and the paired unstructured data, we first develop COAT-MB that leverages the predictivity of the proposed variables to iteratively uncover the Markov Blanket of the target variable. Built upon COAT-MB, COAT-PAG further extends to uncover a more complete causal graph, i.e., Partial Ancestral Graph, by iterating over the target variables and actively seeking new high-level variables. Moreover, the reliable CD capabilities of COAT also extend the debiased causal inference to unstructured data by discovering an adjustment set. We establish theoretical guarantees for the CD results and verify their efficiency and reliability across realistic benchmarks and real-world case studies.
Authors: Marcos Macedo, Yuan Tian, Filipe R. Cogo, Bram Adams
Abstract: Code translation between programming languages (PLs) is a critical task in software engineering, facilitating the modernization of legacy systems, ensuring cross-platform compatibility, and enhancing software performance. Most existing studies instruct LLMs to perform code translation and evaluate their performance by either running the generated outputs through test suites or comparing them to reference outputs (ground truth). These outputs, however, may contain not only executable source code but also additional non-code elements, such as natural language explanations or formatting tokens. We refer to the combination of source code and non-code elements as the output format. It is crucial to understand and address variations in output format, as non-code elements can interfere with evaluation metrics, resulting in biased assessments of model performance and comparisons. We conduct an empirical analysis of the outputs from eleven instruct-tuned open-source LLMs, across five PLs: C, C++, Go, Java, and Python. The results show that between 26.4% and 73.7% of outputs produced by our evaluated LLMs necessitate post-processing. To mitigate output format bias, we propose a strategic combination of prompt engineering and regular expressions that effectively extracts source code from mixed-format outputs, enabling the eleven open-source models to achieve an average Code Extraction Success Rate (CSR) of 92.73%. Our empirical study confirms that output format bias affects widely used execution-based metrics, i.e., Computational Accuracy (CA), and text-based metrics, i.e., BLEU, CodeBLEU and CrystalBLEU. Additionally, we test five closed-source LLMs and observe that they also generate varying distributions of output formats, which could lead to output format biases. Our results highlight the need to mitigate the output format bias to enable reliable evaluations in LLMs for code translation.
Authors: Amin Dada, Marie Bauer, Amanda Butler Contreras, Osman Alperen Kora\c{s}, Constantin Marc Seibold, Kaleb E Smith, Jens Kleesiek
Abstract: Large Language Models (LLMs) are expected to significantly contribute to patient care, diagnostics, and administrative processes. Emerging biomedical LLMs aim to address healthcare-specific challenges, including privacy demands and computational constraints. Assessing the models' suitability for this sensitive application area is of the utmost importance. However, biomedical training has not been systematically evaluated on medical tasks. This study investigates the effect of biomedical training in the context of six practical medical tasks evaluating $25$ models. In contrast to previous evaluations, our results reveal a performance decline in nine out of twelve biomedical models after fine-tuning, particularly on tasks involving hallucinations, ICD10 coding, and instruction adherence. General-domain models like Meta-Llama-3.1-70B-Instruct outperformed their biomedical counterparts, indicating a trade-off between domain-specific fine-tuning and general medical task performance. We open-source all evaluation scripts and datasets at https://github.com/TIO-IKIM/CLUE to support further research in this critical area.
Authors: Maya Bechler-Speicher, Amir Globerson, Ran Gilad-Bachrach
Abstract: Graph Neural Networks (GNNs) have emerged as the predominant approach for learning over graph-structured data. However, most GNNs operate as black-box models and require post-hoc explanations, which may not suffice in high-stakes scenarios where transparency is crucial. In this paper, we present a GNN that is interpretable by design. Our model, Graph Neural Additive Network (GNAN), is a novel extension of the interpretable class of Generalized Additive Models, and can be visualized and fully understood by humans. GNAN is designed to be fully interpretable, offering both global and local explanations at the feature and graph levels through direct visualization of the model. These visualizations describe exactly how the model uses the relationships between the target variable, the features, and the graph. We demonstrate the intelligibility of GNANs in a series of examples on different tasks and datasets. In addition, we show that the accuracy of GNAN is on par with black-box GNNs, making it suitable for critical applications where transparency is essential, alongside high accuracy.
Authors: Shaina Raza, Mizanur Rahman, Safiullah Kamawal, Armin Toroghi, Ananya Raval, Farshad Navah, Amirmohammad Kazemeini
Abstract: Recommender Systems (RS) play an integral role in enhancing user experiences by providing personalized item suggestions. This survey reviews the progress in RS inclusively from 2017 to 2024, effectively connecting theoretical advances with practical applications. We explore the development from traditional RS techniques like content-based and collaborative filtering to advanced methods involving deep learning, graph-based models, reinforcement learning, and large language models. We also discuss specialized systems such as context-aware, review-based, and fairness-aware RS. The primary goal of this survey is to bridge theory with practice. It addresses challenges across various sectors, including e-commerce, healthcare, and finance, emphasizing the need for scalable, real-time, and trustworthy solutions. Through this survey, we promote stronger partnerships between academic research and industry practices. The insights offered by this survey aim to guide industry professionals in optimizing RS deployment and to inspire future research directions, especially in addressing emerging technological and societal trends\footnote. The survey resources are available in the public GitHub repository https://github.com/VectorInstitute/Recommender-Systems-Survey. (Recommender systems, large language models, chatgpt, responsible AI)
URLs: https://github.com/VectorInstitute/Recommender-Systems-Survey.
Authors: Yanxi Chen, Yaliang Li, Bolin Ding, Jingren Zhou
Abstract: This work presents an analytical framework for the design and analysis of LLM-based algorithms, i.e., algorithms that contain one or multiple calls of large language models (LLMs) as sub-routines and critically rely on the capabilities of LLMs. While such algorithms, ranging from basic LLM calls with prompt engineering to complicated LLM-powered agentic workflows and compound AI systems, have achieved remarkable empirical success, their design and optimization oftentimes require extensive trial-and-errors and case-by-case analysis. Our proposed framework serves as an attempt to mitigate such headaches, offering a formal and systematic approach for analyzing how the accuracy and efficiency of an LLM-based algorithm will be impacted by critical design choices, such as the pattern and granularity of task decomposition, or the prompt for each LLM call. Through a wide range of case studies covering diverse algorithm patterns (including parallel/hierarchical/recursive task decomposition and generic directed acyclic graphs), we demonstrate the proposed framework in action and derive interesting insights that generalize across scenarios, accompanied by systematic empirical validation in synthetic settings.
Authors: Gautier Evennou, Vivien Chappelier, Ewa Kijak, Teddy Furon
Abstract: This paper proposes a novel approach towards image authentication and tampering detection by using watermarking as a communication channel for semantic information. We modify the HiDDeN deep-learning watermarking architecture to embed and extract high-dimensional real vectors representing image captions. Our method improves significantly robustness on both malign and benign edits. We also introduce a local confidence metric correlated with Message Recovery Rate, enhancing the method's practical applicability. This approach bridges the gap between traditional watermarking and passive forensic methods, offering a robust solution for image integrity verification.
Authors: Tongyoung Kim, Soojin Yoon, Seongku Kang, Jinyoung Yeo, Dongha Lee
Abstract: Language Models (LMs) have been widely used in recommender systems to incorporate textual information of items into item IDs, leveraging their advanced language understanding and generation capabilities. Recently, generative recommender systems have utilized the reasoning abilities of LMs to directly generate index tokens for potential items of interest based on the user's interaction history. To inject diverse item knowledge into LMs, prompt templates with detailed task descriptions and various indexing techniques derived from diverse item information have been explored. This paper focuses on the inconsistency in outputs generated by variations in input prompt templates and item index types, even with the same user's interaction history. Our in-depth quantitative analysis reveals that preference knowledge learned from diverse prompt templates and heterogeneous indices differs significantly, indicating a high potential for complementarity. To fully exploit this complementarity and provide consistent performance under varying prompts and item indices, we propose MVIGER, a unified variational framework that models selection among these information sources as a categorical latent variable with a learnable prior. During inference, this prior enables the model to adaptively select the most relevant source or aggregate predictions across multiple sources, thereby ensuring high-quality recommendation across diverse template-index combinations. We validate the effectiveness of MVIGER on three real-world datasets, demonstrating its superior performance over existing generative recommender baselines through the effective integration of complementary knowledge.
Authors: Silvia Seidlitz, Katharina H\"olzl, Ayca von Garrel, Jan Sellner, Stephan Katzenschlager, Tobias H\"olle, Dania Fischer, Maik von der Forst, Felix C. F. Schmitt, Alexander Studier-Fischer, Markus A. Weigand, Lena Maier-Hein, Maximilian Dietrich
Abstract: With sepsis remaining a leading cause of mortality, early identification of patients with sepsis and those at high risk of death is a challenge of high socioeconomic importance. Given the potential of hyperspectral imaging (HSI) to monitor microcirculatory alterations, we propose a deep learning approach to automated sepsis diagnosis and mortality prediction using a single HSI cube acquired within seconds. In a prospective observational study, we collected HSI data from the palms and fingers of more than 480 intensive care unit patients. Neural networks applied to HSI measurements predicted sepsis and mortality with areas under the receiver operating characteristic curve (AUROCs) of 0.80 and 0.72, respectively. Performance improved substantially with additional clinical data, reaching AUROCs of 0.94 for sepsis and 0.83 for mortality. We conclude that deep learning-based HSI analysis enables rapid and noninvasive prediction of sepsis and mortality, with a potential clinical value for enhancing diagnosis and treatment.
Authors: Yihang Wang, Xu Huang, Bowen Tian, Yueyang Su, Lei Yu, Huaming Liao, Yixing Fan, Jiafeng Guo, Xueqi Cheng
Abstract: Generative LLM have achieved remarkable success in various industrial applications, owing to their promising In-Context Learning capabilities. However, the issue of long context in complex tasks poses a significant barrier to their wider adoption, manifested in two main aspects: (i) The excessively long context leads to high costs and inference delays. (ii) A substantial amount of task-irrelevant information introduced by long contexts exacerbates the "lost in the middle" problem. Existing methods compress context by removing redundant tokens using metrics such as self-information or PPL, which is inconsistent with the objective of retaining the most important tokens when conditioning on a given query. In this study, we introduce information bottleneck theory (IB) to model the problem, offering a novel perspective that thoroughly addresses the essential properties required for context compression. Additionally, we propose a cross-attention-based approach to approximate mutual information in IB, which can be flexibly replaced with suitable alternatives in different scenarios. Extensive experiments on four datasets demonstrate that our method achieves a 25% increase in compression rate compared to the state-of-the-art, while maintaining question answering performance. In particular, the context compressed by our method even outperform the full context in some cases.
Authors: Asad Aali, Andrew Johnston, Louis Blankemeier, Dave Van Veen, Laura T Derry, David Svec, Jason Hom, Robert D. Boutin, Akshay S. Chaudhari
Abstract: Abdominal computed tomography (CT) scans are frequently performed in clinical settings. Opportunistic CT involves repurposing routine CT images to extract diagnostic information and is an emerging tool for detecting underdiagnosed conditions such as sarcopenia, hepatic steatosis, and ascites. This study utilizes deep learning methods to promote accurate diagnosis and clinical documentation. We analyze 2,674 inpatient CT scans to identify discrepancies between imaging phenotypes (characteristics derived from opportunistic CT scans) and their corresponding documentation in radiology reports and ICD coding. Through our analysis, we find that only 0.5%, 3.2%, and 30.7% of scans diagnosed with sarcopenia, hepatic steatosis, and ascites (respectively) through either opportunistic imaging or radiology reports were ICD-coded. Our findings demonstrate opportunistic CT's potential to enhance diagnostic precision and accuracy of risk adjustment models, offering advancements in precision medicine.
Authors: Tuowei Wang, Ruwen Fan, Minxing Huang, Zixu Hao, Kun Li, Ting Cao, Youyou Lu, Yaoxue Zhang, Ju Ren
Abstract: Large Language Models (LLMs) have achieved remarkable success across various domains, yet deploying them on mobile devices remains an arduous challenge due to their extensive computational and memory demands. While lightweight LLMs have been developed to fit mobile environments, they suffer from degraded model accuracy. In contrast, sparsity-based techniques minimize DRAM usage by selectively transferring only relevant neurons to DRAM while retaining the full model in external storage, such as flash. However, such approaches are critically limited by numerous I/O operations, particularly on smartphones with severe IOPS constraints. In this paper, we propose Neuralink, a novel approach that accelerates LLM inference on smartphones by optimizing neuron placement in flash memory. Neuralink leverages the concept of Neuron Co-Activation, where neurons frequently activated together are linked to facilitate continuous read access and optimize I/O efficiency. Our approach incorporates a two-stage solution: an offline stage that reorganizes neuron placement based on co-activation patterns, and an online stage that employs tailored data access and caching strategies to align well with hardware characteristics. Evaluations conducted on a variety of smartphones and LLMs demonstrate that Neuralink achieves on average $1.49\times$ improvements in end-to-end latency compared to the state-of-the-art. As the first solution to optimize storage placement under sparsity, Neuralink explores a new optimization space at the intersection of sparsity-driven algorithm and storage-level system co-design for LLM inference.
Authors: Han Zhang, Yunjiang Jiang, Mingming Li, Haowei Yuan, Yiming Qiu, Wen-Yun Yang
Abstract: Embedding-based retrieval aims to learn a shared semantic representation space for both queries and items, enabling efficient and effective item retrieval through approximate nearest neighbor (ANN) algorithms. In current industrial practice, retrieval systems typically retrieve a fixed number of items for each query. However, this fixed-size retrieval often results in insufficient recall for head queries and low precision for tail queries. This limitation largely stems from the dominance of frequentist approaches in loss function design, which fail to address this challenge in industry. In this paper, we propose a novel \textbf{p}robabilistic \textbf{E}mbedding-\textbf{B}ased \textbf{R}etrieval (\textbf{pEBR}) framework. Our method models the item distribution conditioned on each query, enabling the use of a dynamic cosine similarity threshold derived from the cumulative distribution function (CDF) of the probabilistic model. Experimental results demonstrate that pEBR significantly improves both retrieval precision and recall. Furthermore, ablation studies reveal that the probabilistic formulation effectively captures the inherent differences between head-to-tail queries.
Authors: Ananya Malik, Kartik Sharma, Shaily Bhatt, Lynnette Hui Xian Ng
Abstract: Large Language Models (LLMs) offer a lucrative promise for scalable content moderation, including hate speech detection. However, they are also known to be brittle and biased against marginalised communities and dialects. This requires their applications to high-stakes tasks like hate speech detection to be critically scrutinized. In this work, we investigate the robustness of hate speech classification using LLMs particularly when explicit and implicit markers of the speaker's ethnicity are injected into the input. For explicit markers, we inject a phrase that mentions the speaker's linguistic identity. For the implicit markers, we inject dialectal features. By analysing how frequently model outputs flip in the presence of these markers, we reveal varying degrees of brittleness across 3 LLMs and 1 LM and 5 linguistic identities. We find that the presence of implicit dialect markers in inputs causes model outputs to flip more than the presence of explicit markers. Further, the percentage of flips varies across ethnicities. Finally, we find that larger models are more robust. Our findings indicate the need for exercising caution in deploying LLMs for high-stakes tasks like hate speech detection.
Authors: Heewoong Noh, Namkyeong Lee, Gyoung S. Na, Chanyoung Park
Abstract: While inorganic retrosynthesis planning is essential in the field of chemical science, the application of machine learning in this area has been notably less explored compared to organic retrosynthesis planning. In this paper, we propose Retrieval-Retro for inorganic retrosynthesis planning, which implicitly extracts the precursor information of reference materials that are retrieved from the knowledge base regarding domain expertise in the field. Specifically, instead of directly employing the precursor information of reference materials, we propose implicitly extracting it with various attention layers, which enables the model to learn novel synthesis recipes more effectively. Moreover, during retrieval, we consider the thermodynamic relationship between target material and precursors, which is essential domain expertise in identifying the most probable precursor set among various options. Extensive experiments demonstrate the superiority of Retrieval-Retro in retrosynthesis planning, especially in discovering novel synthesis recipes, which is crucial for materials discovery. The source code for Retrieval-Retro is available at https://github.com/HeewoongNoh/Retrieval-Retro.
Authors: Chaeyun Jang, Deukhwan Cho, Seanie Lee, Hyungi Lee, Juho Lee
Abstract: Recently, Large Language Models (LLMs) have been increasingly used to support various decision-making tasks, assisting humans in making informed decisions. However, when LLMs confidently provide incorrect information, it can lead humans to make suboptimal decisions. To prevent LLMs from generating incorrect information on topics they are unsure of and to improve the accuracy of generated content, prior works have proposed Retrieval Augmented Generation (RAG), where external documents are referenced to generate responses. However, previous RAG methods focus only on retrieving documents most relevant to the input query, without specifically aiming to ensure that the human user's decisions are well-calibrated. To address this limitation, we propose a novel retrieval method called Calibrated Retrieval-Augmented Generation (CalibRAG), which ensures that decisions informed by RAG are well-calibrated. Then we empirically validate that CalibRAG improves calibration performance as well as accuracy, compared to other baselines across various datasets.
Authors: Qihang Zhou, Shenhao Fang, Shibo He, Wenchao Meng, Jiming Chen
Abstract: Condensing large datasets into smaller synthetic counterparts has demonstrated its promise for image classification. However, previous research has overlooked a crucial concern in image recognition: ensuring that models trained on condensed datasets are unbiased towards protected attributes (PA), such as gender and race. Our investigation reveals that dataset distillation fails to alleviate the unfairness towards minority groups within original datasets. Moreover, this bias typically worsens in the condensed datasets due to their smaller size. To bridge the research gap, we propose a novel fair dataset distillation (FDD) framework, namely FairDD, which can be seamlessly applied to diverse matching-based DD approaches (DDs), requiring no modifications to their original architectures. The key innovation of FairDD lies in synchronously matching synthetic datasets to PA-wise groups of original datasets, rather than indiscriminate alignment to the whole distributions in vanilla DDs, dominated by majority groups. This synchronized matching allows synthetic datasets to avoid collapsing into majority groups and bootstrap their balanced generation to all PA groups. Consequently, FairDD could effectively regularize vanilla DDs to favor biased generation toward minority groups while maintaining the accuracy of target attributes. Theoretical analyses and extensive experimental evaluations demonstrate that FairDD significantly improves fairness compared to vanilla DDs, with a promising trade-off between fairness and accuracy. Its consistent superiority across diverse DDs, spanning Distribution and Gradient Matching, establishes it as a versatile FDD approach. Code is available at https://github.com/zqhang/FairDD.
Authors: Marcel Torne, Arhan Jain, Jiayi Yuan, Vidaaranya Macha, Lars Ankile, Anthony Simeonov, Pulkit Agrawal, Abhishek Gupta
Abstract: Scaling robot learning requires data collection pipelines that scale favorably with human effort. In this work, we propose Crowdsourcing and Amortizing Human Effort for Real-to-Sim-to-Real(CASHER), a pipeline for scaling up data collection and learning in simulation where the performance scales superlinearly with human effort. The key idea is to crowdsource digital twins of real-world scenes using 3D reconstruction and collect large-scale data in simulation, rather than the real-world. Data collection in simulation is initially driven by RL, bootstrapped with human demonstrations. As the training of a generalist policy progresses across environments, its generalization capabilities can be used to replace human effort with model generated demonstrations. This results in a pipeline where behavioral data is collected in simulation with continually reducing human effort. We show that CASHER demonstrates zero-shot and few-shot scaling laws on three real-world tasks across diverse scenarios. We show that CASHER enables fine-tuning of pre-trained policies to a target scenario using a video scan without any additional human effort. See our project website: https://casher-robot-learning.github.io/CASHER/
Authors: Alberto Sinigaglia, Niccol\`o Turcato, Ruggero Carli, Gian Antonio Susto
Abstract: Deep Reinforcement Learning is gaining increasing attention thanks to its capability to learn complex policies in high-dimensional settings. Recent advancements utilize a dual-network architecture to learn optimal policies through the Q-learning algorithm. However, this approach has notable drawbacks, such as an overestimation bias that can disrupt the learning process and degrade the performance of the resulting policy. To address this, novel algorithms have been developed that mitigate overestimation bias by employing multiple Q-functions. Edge scenarios, which prioritize privacy, have recently gained prominence. In these settings, limited computational resources pose a significant challenge for complex Machine Learning approaches, making the efficiency of algorithms crucial for their performance. In this work, we introduce a novel Reinforcement Learning algorithm tailored for edge scenarios, called Edge Delayed Deep Deterministic Policy Gradient (EdgeD3). EdgeD3 enhances the Deep Deterministic Policy Gradient (DDPG) algorithm, achieving significantly improved performance with $25\%$ less Graphics Process Unit (GPU) time while maintaining the same memory usage. Additionally, EdgeD3 consistently matches or surpasses the performance of state-of-the-art methods across various benchmarks, all while using $30\%$ fewer computational resources and requiring $30\%$ less memory.
Authors: Chongyi Zheng, Jens Tuyls, Joanne Peng, Benjamin Eysenbach
Abstract: Self-supervised learning has the potential of lifting several of the key challenges in reinforcement learning today, such as exploration, representation learning, and reward design. Recent work (METRA) has effectively argued that moving away from mutual information and instead optimizing a certain Wasserstein distance is important for good performance. In this paper, we argue that the benefits seen in that paper can largely be explained within the existing framework of mutual information skill learning (MISL). Our analysis suggests a new MISL method (contrastive successor features) that retains the excellent performance of METRA with fewer moving parts, and highlights connections between skill learning, contrastive representation learning, and successor features. Finally, through careful ablation studies, we provide further insight into some of the key ingredients for both our method and METRA.
Authors: Matej Martinc, Hanh Thi Hong Tran, Senja Pollak, Boshko Koloski
Abstract: Keyword extraction involves identifying the most descriptive words in a document, allowing automatic categorisation and summarisation of large quantities of diverse textual data. Relying on the insight that real-world keyword detection often requires handling of diverse content, we propose a novel supervised keyword extraction approach based on the mixture of experts (MoE) technique. MoE uses a learnable routing sub-network to direct information to specialised experts, allowing them to specialise in distinct regions of the input space. SEKE, a mixture of Specialised Experts for supervised Keyword Extraction, uses DeBERTa as the backbone model and builds on the MoE framework, where experts attend to each token, by integrating it with a bidirectional Long short-term memory (BiLSTM) network, to allow successful extraction even on smaller corpora, where specialisation is harder due to lack of training data. The MoE framework also provides an insight into inner workings of individual experts, enhancing the explainability of the approach. We benchmark SEKE on multiple English datasets, achieving state-of-the-art performance compared to strong supervised and unsupervised baselines. Our analysis reveals that depending on data size and type, experts specialise in distinct syntactic and semantic components, such as punctuation, stopwords, parts-of-speech, or named entities. Code is available at https://github.com/matejMartinc/SEKE_keyword_extraction
URLs: https://github.com/matejMartinc/SEKE_keyword_extraction
Authors: Felix Krause, Timy Phan, Ming Gui, Stefan Andreas Baumann, Vincent Tao Hu, Bj\"orn Ommer
Abstract: Diffusion models have emerged as the mainstream approach for visual generation. However, these models typically suffer from sample inefficiency and high training costs. Consequently, methods for efficient finetuning, inference and personalization were quickly adopted by the community. However, training these models in the first place remains very costly. While several recent approaches - including masking, distillation, and architectural modifications - have been proposed to improve training efficiency, each of these methods comes with a tradeoff: they achieve enhanced performance at the expense of increased computational cost or vice versa. In contrast, this work aims to improve training efficiency as well as generative performance at the same time through routes that act as a transport mechanism for randomly selected tokens from early layers to deeper layers of the model. Our method is not limited to the common transformer-based model - it can also be applied to state-space models and achieves this without architectural modifications or additional parameters. Finally, we show that TREAD reduces computational cost and simultaneously boosts model performance on the standard ImageNet-256 benchmark in class-conditional synthesis. Both of these benefits multiply to a convergence speedup of 14x at 400K training iterations compared to DiT and 37x compared to the best benchmark performance of DiT at 7M training iterations. Furthermore, we achieve a competitive FID of 2.09 in a guided and 3.93 in an unguided setting, which improves upon the DiT, without architectural changes.
Authors: Juntao Ren, Priya Sundaresan, Dorsa Sadigh, Sanjiban Choudhury, Jeannette Bohg
Abstract: Teaching robots to autonomously complete everyday tasks remains a challenge. Imitation Learning (IL) is a powerful approach that imbues robots with skills via demonstrations, but is limited by the labor-intensive process of collecting teleoperated robot data. Human videos offer a scalable alternative, but it remains difficult to directly train IL policies from them due to the lack of robot action labels. To address this, we propose to represent actions as short-horizon 2D trajectories on an image. These actions, or motion tracks, capture the predicted direction of motion for either human hands or robot end-effectors. We instantiate an IL policy called Motion Track Policy (MT-pi) which receives image observations and outputs motion tracks as actions. By leveraging this unified, cross-embodiment action space, MT-pi completes tasks with high success given just minutes of human video and limited additional robot demonstrations. At test time, we predict motion tracks from two camera views, recovering 6DoF trajectories via multi-view synthesis. MT-pi achieves an average success rate of 86.5% across 4 real-world tasks, outperforming state-of-the-art IL baselines which do not leverage human data or our action space by 40%, and generalizes to scenarios seen only in human videos. Code and videos are available on our website https://portal-cornell.github.io/motion_track_policy/.
URLs: https://portal-cornell.github.io/motion_track_policy/.
Authors: Haoyuan Sun, Ali Jadbabaie, Navid Azizan
Abstract: Transformer-based models demonstrate a remarkable ability for in-context learning (ICL), where they can adapt to unseen tasks from a few prompt examples without parameter updates. Recent research has illuminated how Transformers perform ICL, showing that the optimal linear self-attention (LSA) mechanism can implement one step of gradient descent for linear least-squares objectives when trained on random linear regression tasks. Building on this, we investigate ICL for nonlinear function classes. We first prove that LSA is inherently incapable of outperforming linear predictors on nonlinear tasks, underscoring why prior solutions cannot readily extend to these problems. To overcome this limitation, we analyze a Transformer block consisting of LSA and feed-forward layers inspired by the gated linear units (GLU), which is a standard component of modern Transformers. We show that this block achieves nonlinear ICL by implementing one step of gradient descent on a polynomial kernel regression loss. Furthermore, our analysis reveals that the expressivity of a single block is inherently limited by its dimensions. We then show that a deep Transformer can overcome this bottleneck by distributing the computation of richer kernel functions across multiple blocks, performing block-coordinate descent in a high-dimensional feature space that a single block cannot represent. Our findings highlight that the feed-forward layers provide a crucial and scalable mechanism by which Transformers can express nonlinear representations for ICL.
Authors: Shuangyi Chen, Yuanxin Guo, Yue Ju, Harik Dalal, Zhongwen Zhu, Ashish Khisti
Abstract: Parameter-Efficient Fine-Tuning (PEFT) methods like Low-Rank Adaptation (LoRA) optimize federated training by reducing computational and communication costs. We propose RoLoRA, a federated framework using alternating optimization to fine-tune LoRA adapters. Our approach emphasizes the importance of learning up and down projection matrices to enhance expressiveness and robustness. We use both theoretical analysis and extensive experiments to demonstrate the advantages of RoLoRA over prior approaches that either generate imperfect model updates or limit expressiveness of the model. We provide a theoretical analysis on a linear model to highlight the importance of learning both the down-projection and up-projection matrices in LoRA. We validate the insights on a non-linear model and separately provide a convergence proof under general conditions. To bridge theory and practice, we conducted extensive experimental evaluations on language models including RoBERTa-Large, Llama-2-7B on diverse tasks and FL settings to demonstrate the advantages of RoLoRA over other methods.
Authors: Changhao Jiang, Ming Zhang, Yifei Cao, Junjie Ye, Xiaoran Fan, Shihan Dou, Zhiheng Xi, Jiajun Sun, Yi Dong, Yujiong Shen, Jingqi Tong, Baoyu Fan, Qi Zhang, Tao Gui, Xuanjing Huang
Abstract: The GPT-4 technical report suggests that downstream performance can be predicted from pre-training signals, but offers little methodological detail on how to quantify this. This work address this gap by modeling knowledge retention, the capacity of a pre-trained language model to memorize factual information from its corpus, and introduce a principled method to estimate it prior to training. We propose Size-dependent Mutual Information (SMI), an information-theoretic predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering (QA) accuracy. SMI is validated through large-scale document retrieval over the disclosed pre-training corpora of 21 public and 3 custom models, combined with a robust multi-template QA evaluation. Experiments show that SMI significantly outperforms repetition-based baselines and achieves $R^2$ > 0.7 in predicting QA accuracy for models above 1B parameters, without additional training. The analysis further reveals diminishing returns from scaling data and model size and provides evidence for an intrinsic upper bound on knowledge retention achievable by pre-training alone, motivating retrieval and other augmentation strategies.
Authors: Cuipeng Wang, Haipeng Wang
Abstract: Knowledge distillation enhances the performance of compact student networks by transferring knowledge from more powerful teacher networks without introducing additional parameters. In the feature space, local regions within an individual global feature encode distinct yet interdependent semantic information. Previous feature-based distillation methods mainly emphasize global feature alignment while neglecting the decoupling of local regions within an individual global feature, which often results in semantic confusion and suboptimal performance. Moreover, conventional contrastive representation distillation suffers from low efficiency due to its reliance on a large memory buffer to store feature samples. To address these limitations, this work proposes MSDCRD, a model-agnostic distillation framework that systematically decouples global features into multi-scale local features and leverages the resulting semantically rich feature samples with tailored sample-wise and feature-wise contrastive losses. This design enables efficient distillation using only a single batch, eliminating the dependence on external memory. Extensive experiments demonstrate that MSDCRD achieves superior performance not only in homogeneous teacher-student settings but also in heterogeneous architectures where feature discrepancies are more pronounced, highlighting its strong generalization capability.
Authors: Francisco N. F. Q. Simoes, Itai Feigenbaum, Mehdi Dastani, Thijs van Ommen
Abstract: Causal knowledge can be used to support decision-making problems. This has been recognized in the causal bandits literature, where a causal (multi-armed) bandit is characterized by a causal graphical model and a target variable. The arms are then interventions on the causal model, and rewards are samples of the target variable. Causal bandits were originally studied with a focus on hard interventions. We focus instead on cases where the arms are conditional interventions, which more accurately model many real-world decision-making problems by allowing the value of the intervened variable to be chosen based on the observed values of other variables. This paper presents a graphical characterization of the minimal set of nodes guaranteed to contain the optimal conditional intervention, which maximizes the expected reward. We then propose an efficient algorithm with a time complexity of $O(|V| + |E|)$ to identify this minimal set of nodes. We prove that the graphical characterization and the proposed algorithm are correct. Finally, we empirically demonstrate that our algorithm significantly prunes the search space and substantially accelerates convergence rates when integrated into standard multi-armed bandit algorithms.
Authors: Ilan Lobel, Humberto Moreira, Omar Mouchtaki
Abstract: We investigate a Bayesian mechanism design problem where a seller seeks to maximize revenue by selling an indivisible good to one of n buyers, incorporating potentially unreliable predictions (signals) of buyers' private values derived from a machine learning model. We propose a framework where these signals are sometimes reflective of buyers' true valuations but other times are hallucinations, which are uncorrelated with the buyers' true valuations. Our main contribution is a characterization of the optimal auction under this framework. Our characterization establishes a near-decomposition of how to treat types above and below the signal. For the one buyer case, the seller's optimal strategy is to post one of three fairly intuitive prices depending on the signal, which we call the "ignore", "follow" and "cap" actions.
Authors: Benedikt Alkin, Maurits Bleeker, Richard Kurle, Tobias Kronlachner, Reinhard Sonnleitner, Matthias Dorfer, Johannes Brandstetter
Abstract: Recent advances in neural surrogate modeling offer the potential for transformative innovations in applications such as automotive aerodynamics. Yet, industrial-scale problems often involve volumetric meshes with cell counts reaching 100 million, presenting major scalability challenges. Complex geometries further complicate modeling through intricate surface-volume interactions, while quantities such as vorticity are highly nonlinear and must satisfy strict divergence-free constraints. To address these requirements, we introduce AB-UPT as a novel modeling scheme for building neural surrogates for CFD simulations. AB-UPT is designed to: (i) decouple geometry encoding and prediction tasks via multi-branch operators; (ii) enable scalability to high-resolution outputs via neural simulation in a low-dimensional latent space, coupled with anchored neural field decoders to predict high-fidelity outputs; (iii) enforce physics consistency by a divergence-free formulation. We show that AB-UPT yields state-of-the-art predictive accuracy of surface and volume fields on automotive CFD simulations ranging from 33 thousand up to 150 million mesh cells. Furthermore, our anchored neural field architecture enables the enforcement of hard physical constraints on the physics predictions without degradation in performance, exemplified by modeling divergence-free vorticity fields. Notably, the proposed models can be trained on a single GPU in less than a day and predict industry-standard surface and volume fields within seconds. Additionally, we show that the flexible design of our method enables neural simulation from a CAD geometry alone, thereby eliminating the need for costly CFD meshing procedures for inference.
Authors: Pengyu Zhu, Zhenhong Zhou, Yuanhe Zhang, Shilinlu Yan, Kun Wang, Sen Su
Abstract: As LLM-based agents become increasingly prevalent, backdoors can be implanted into agents through user queries or environment feedback, raising critical concerns regarding safety vulnerabilities. However, backdoor attacks are typically detectable by safety audits that analyze the reasoning process of agents. To this end, we propose a novel backdoor implantation strategy called \textbf{Dynamically Encrypted Multi-Backdoor Implantation Attack}. Specifically, we introduce dynamic encryption, which maps the backdoor into benign content, effectively circumventing safety audits. To enhance stealthiness, we further decompose the backdoor into multiple sub-backdoor fragments. Based on these advancements, backdoors are allowed to bypass safety audits significantly. Additionally, we present AgentBackdoorEval, a dataset designed for the comprehensive evaluation of agent backdoor attacks. Experimental results across multiple datasets demonstrate that our method achieves an attack success rate nearing 100\% while maintaining a detection rate of 0\%, illustrating its effectiveness in evading safety audits. Our findings highlight the limitations of existing safety mechanisms in detecting advanced attacks, underscoring the urgent need for more robust defenses against backdoor threats. Code and data are available at https://github.com/whfeLingYu/DemonAgent.
Authors: Arjun Gupta, Rishik Sathua, Saurabh Gupta
Abstract: Many everyday mobile manipulation tasks require precise interaction with small objects, such as grasping a knob to open a cabinet or pressing a light switch. In this paper, we develop Servoing with Vision Models (SVM), a closed-loop framework that enables a mobile manipulator to tackle such precise tasks involving the manipulation of small objects. SVM uses state-of-the-art vision foundation models to generate 3D targets for visual servoing to enable diverse tasks in novel environments. Naively doing so fails because of occlusion by the end-effector. SVM mitigates this using vision models that out-paint the end-effector, thereby significantly enhancing target localization. We demonstrate that aided by out-painting methods, open-vocabulary object detectors can serve as a drop-in module for SVM to seek semantic targets (e.g. knobs) and point tracking methods can help SVM reliably pursue interaction sites indicated by user clicks. We conduct a large-scale evaluation spanning experiments in 10 novel environments across 6 buildings including 72 different object instances. SVM obtains a 71% zero-shot success rate on manipulating unseen objects in novel environments in the real world, outperforming an open-loop control method by an absolute 42% and an imitation learning baseline trained on 1000+ demonstrations also by an absolute success rate of 50%.
Authors: Shashank Kirtania, Arun Iyer
Abstract: Recent advances in automated theorem proving use Large Language Models (LLMs) to translate informal mathematical statements into formal proofs. However, informal cues are often ambiguous or lack strict logical structure, making it hard for models to interpret them precisely. While existing methods achieve strong performance, little is known about how LLMs internally represent informal cues, or how these influence proof generation. To address this, we explore \textit{activation steering}, an inference-time intervention that identifies linear directions in residual activations associated with informal reasoning traces and adjusts them to improve proof construction without fine-tuning. This mechanism also yields interpretable information about how reasoning is internally encoded in the activation space of LLMs. We test our method for generating formal proofs from already-formalized theorems. Our contributions are twofold: (1) a novel activation-based intervention for guiding proof synthesis in LLMs; and (2) demonstration that this intervention improves performance under two decoding strategies (sampling and best-first search) without any further training.
Authors: Chengyin Xu, Kaiyuan Chen, Xiao Li, Ke Shen, Chenggang Li
Abstract: The escalating scale and cost of Large Language Models (LLMs) training necessitate accurate pre-training prediction of downstream task performance for efficient resource allocation. This is challenged by: 1) the emergence phenomenon, where metrics become meaningful only after extensive training, hindering prediction by smaller models; and 2) uneven task difficulty and inconsistent performance scaling patterns, leading to high metric variability. Current prediction methods lack accuracy and reliability. We propose a Clustering-On-Difficulty (COD) framework for downstream performance prediction. The COD framework clusters tasks by their difficulty scaling features, thereby establishing a more stable and predictable support subset through the exclusion of tasks exhibiting non-emergent behavior or irregular scaling. We adopt a performance scaling law to predict cluster-wise performance with theoretical support. Predictable subset performance acts as an intermediate predictor for the full evaluation set. We further derive a mapping function to accurately extrapolate the performance of the subset to the full set. Applied to an LLM with 70B parameters, COD achieved a 1.36% average prediction error across eight key LLM benchmarks, offering actionable insights for resource allocation and training monitoring of LLMs pretraining.
Authors: Wenkai Yang, Shuming Ma, Yankai Lin, Furu Wei
Abstract: Recent studies have shown that making a model spend more time thinking through longer Chain of Thoughts (CoTs) enables it to gain significant improvements in complex reasoning tasks. While current researches continue to explore the benefits of increasing test-time compute by extending the CoT lengths of Large Language Models (LLMs), we are concerned about a potential issue hidden behind the current pursuit of test-time scaling: Would excessively scaling the CoT length actually bring adverse effects to a model's reasoning performance? Our explorations on mathematical reasoning tasks reveal an unexpected finding that scaling with longer CoTs can indeed impair the reasoning performance of LLMs in certain domains. Moreover, we discover that there exists an optimal scaled length distribution that differs across different domains. Based on these insights, we propose a Thinking-Optimal Scaling strategy. Our method first uses a small set of seed data with varying response length distributions to teach the model to adopt different reasoning efforts for deep thinking. Then, the model selects its shortest correct response under different reasoning efforts on additional problems for self-improvement. Our self-improved models built upon Qwen2.5-32B-Instruct outperform other distillation-based 32B o1-like models across various math benchmarks, and achieve performance on par with the teacher model QwQ-32B-Preview that produces the seed data.
Authors: Jakub Macina, Nico Daheim, Ido Hakimi, Manu Kapur, Iryna Gurevych, Mrinmaya Sachan
Abstract: Evaluating the pedagogical capabilities of AI-based tutoring models is critical for making guided progress in the field. Yet, we lack a reliable, easy-to-use, and simple-to-run evaluation that reflects the pedagogical abilities of models. To fill this gap, we present MathTutorBench, an open-source benchmark for holistic tutoring model evaluation. MathTutorBench contains a collection of datasets and metrics that broadly cover tutor abilities as defined by learning sciences research in dialog-based teaching. To score the pedagogical quality of open-ended teacher responses, we train a reward model and show it can discriminate expert from novice teacher responses with high accuracy. We evaluate a wide set of closed- and open-weight models on MathTutorBench and find that subject expertise, indicated by solving ability, does not immediately translate to good teaching. Rather, pedagogy and subject expertise appear to form a trade-off that is navigated by the degree of tutoring specialization of the model. Furthermore, tutoring appears to become more challenging in longer dialogs, where simpler questioning strategies begin to fail. We release the benchmark, code, and leaderboard openly to enable rapid benchmarking of future models.
Authors: Zixuan Gong, Shijia Li, Yong Liu, Jiaye Teng
Abstract: Transformers may exhibit two-stage training dynamics during the real-world training process. For instance, when training GPT-2 on the Counterfact dataset, the answers progress from syntactically incorrect to syntactically correct to semantically correct. However, existing theoretical analyses hardly account for this feature-level two-stage phenomenon, which originates from the disentangled two-type features like syntax and semantics. In this paper, we theoretically demonstrate how the two-stage training dynamics potentially occur in transformers. Specifically, we analyze the feature learning dynamics induced by the aforementioned disentangled two-type feature structure, grounding our analysis in a simplified yet illustrative setting that comprises a normalized ReLU self-attention layer and structured data. Such disentanglement of feature structure is general in practice, e.g., natural languages contain syntax and semantics, and proteins contain primary and secondary structures. To our best knowledge, this is the first rigorous result regarding a feature-level two-stage optimization process in transformers. Additionally, a corollary indicates that such a two-stage process is closely related to the spectral properties of the attention weights, which accords well with our empirical findings.
Authors: Yongqiang Yao, Jingru Tan, Kaihuan Liang, Feizhao Zhang, Jiahao Hu, Shuo Wu, Yazhe Niu, Ruihao Gong, Dahua Lin, Ningyi Xu
Abstract: Training Long-Context Large Language Models (LLMs) is challenging, as hybrid training with long-context and short-context data often leads to workload imbalances. Existing works mainly use data packing to alleviate this issue, but fail to consider imbalanced attention computation and wasted communication overhead. This paper proposes Hierarchical Balance Packing (HBP), which designs a novel batch-construction method and training recipe to address those inefficiencies. In particular, the HBP constructs multi-level data packing groups, each optimized with a distinct packing length. It assigns training samples to their optimal groups and configures each group with the most effective settings, including sequential parallelism degree and gradient checkpointing configuration. To effectively utilize multi-level groups of data, we design a dynamic training pipeline specifically tailored to HBP, including curriculum learning, adaptive sequential parallelism, and stable loss. Our extensive experiments demonstrate that our method significantly reduces training time over multiple datasets and open-source models while maintaining strong performance. For the largest DeepSeek-V2 (236B) MoE model, our method speeds up the training by 2.4$\times$ with competitive performance. Codes will be released at https://github.com/ModelTC/HBP.
Authors: Eray Yapa\u{g}c{\i}, Yavuz Alp Sencer \"Ozt\"urk, Eray T\"uz\"un
Abstract: Reproducing game bugs, particularly crash bugs in continuously evolving games like Minecraft, is a notoriously manual, time-consuming, and challenging process to automate; insights from a key decision maker from Minecraft we interviewed confirm this, highlighting that a substantial portion of crash reports necessitate manual scenario reconstruction. Despite the success of LLM-driven bug reproduction in other software domains, games, with their complex interactive environments, remain largely unaddressed. This paper introduces BugCraft, a novel end-to-end framework designed to automate the reproduction of crash bugs in Minecraft directly from user-submitted bug reports, addressing the critical gap in automated game bug reproduction. BugCraft employs a two-stage approach: first, a Step Synthesizer leverages LLMs and Minecraft Wiki knowledge to transform bug reports into high-quality, structured steps to reproduce (S2R). Second, an Action Model, powered by a vision-based LLM agent and a custom macro API, executes these S2R steps within Minecraft to trigger the reported crash. To facilitate evaluation, we introduce BugCraft-Bench, a curated dataset of Minecraft crash bug reports. On BugCraft-Bench, our framework end-to-end reproduced 34.9% of crash bugs with GPT-4.1, outperforming baseline computer-use models by 37%. BugCraft demonstrates the feasibility of automated reproduction of crash bugs in complex game environments using LLMs, opening promising avenues for game testing and development. Finally, we make our code open at https://bugcraft2025.github.io
Authors: Felix Stollenwerk
Abstract: Layer normalization (LN) is an essential component of modern neural networks. While many alternative techniques have been proposed, none of them have succeeded in replacing LN so far. The latest suggestion in this line of research is a dynamic activation function called Dynamic Tanh (DyT). Although it is empirically well-motivated and appealing from a practical point of view, it lacks a theoretical foundation. In this work, we shed light on the mathematical relationship between LN and dynamic activation functions. In particular, we derive DyT from the LN variant RMSNorm, and show that a well-defined decoupling in derivative space as well as an approximation are needed to do so. By applying the same decoupling procedure directly in function space, we are able to omit the approximation and obtain the exact element-wise counterpart of RMSNorm, which we call Dynamic Inverse Square Root Unit (DyISRU). We demonstrate numerically that DyISRU reproduces the normalization effect on outliers more accurately than DyT does.
Authors: Zhihan Zhou, Feng Hong, Jiaan Luo, Jiangchao Yao, Dongsheng Li, Bo Han, Ya Zhang, Yanfeng Wang
Abstract: We propose L2T, an advancement of visual instruction tuning (VIT). While VIT equips Multimodal LLMs (MLLMs) with promising multimodal capabilities, the current design choices for VIT often result in overfitting and shortcut learning, potentially degrading performance. This gap arises from an overemphasis on instruction-following abilities, while neglecting the proactive understanding of visual information. Inspired by this, L2T adopts a simple yet effective approach by incorporating the loss function into both the instruction and response sequences. It seamlessly expands the training data, and regularizes the MLLMs from overly relying on language priors. Based on this merit, L2T achieves a significant relative improvement of up to 9% on comprehensive multimodal benchmarks, requiring no additional training data and incurring negligible computational overhead. Surprisingly, L2T attains exceptional fundamental visual capabilities, yielding up to an 18% improvement in captioning performance, while simultaneously alleviating hallucination in MLLMs. Github code: https://github.com/Feng-Hong/L2T.
Authors: Yali Du, Hui Sun, Ming Li
Abstract: Code translation migrates codebases across programming languages. Recently, large language models (LLMs) have achieved significant advancements in software mining. However, handling the syntactic structure of source code remains a challenge. Classic syntax-aware methods depend on intricate model architectures and loss functions, rendering their integration into LLM training resource-intensive. This paper employs in-context learning (ICL), which directly integrates task exemplars into the input context, to post-incorporate code structural knowledge into pre-trained LLMs. We revisit exemplar selection in ICL from an information-theoretic perspective, proposing that list-wise selection based on information coverage is more precise and general objective than traditional methods based on combining similarity and diversity. To address the challenges of quantifying information coverage, we introduce a surrogate measure, Coverage of Abstract Syntax Tree (CAST). Furthermore, we formulate the NP-hard CAST maximization for exemplar selection and prove that it is a standard submodular maximization problem. Therefore, we propose a greedy algorithm for CAST submodular maximization, which theoretically guarantees a (1-1/e)-approximate solution in polynomial time complexity. Our method is the first training-free and model-agnostic approach to post-incorporate code structural knowledge into existing LLMs at test time. Experimental results show that our method significantly improves LLMs performance and reveals two meaningful insights: 1) Code structural knowledge can be effectively post-incorporated into pre-trained LLMs during inference, despite being overlooked during training; 2) Scaling up model size or training data does not lead to the emergence of code structural knowledge, underscoring the necessity of explicitly considering code syntactic structure.
Authors: Guanqiao Qu, Qian Chen, Xianhao Chen, Kaibin Huang, Yuguang Fang
Abstract: By provisioning inference offloading services, edge inference drives the rapid growth of AI applications at network edge. However, how to reduce the inference latency remains a significant challenge. To address this issue, we develop a parameter-sharing AI model loading (PartialLoading) framework for multi-user edge inference, which exploits two key insights: 1) the majority of latency arises from loading AI models into server GPU memory, and 2) different AI models can share a significant number of parameters, for which redundant loading should be avoided. Towards this end, we formulate a joint multi-user scheduling and spectrum bandwidth allocation problem to maximize task throughput by exploiting shared parameter blocks across models. The intuition is to judiciously schedule user requests to reuse the shared parameter blocks between consecutively loaded models, thereby reducing model loading time substantially. To facilitate solution finding, we decouple the problem into two sub-problems, i.e., user scheduling and bandwidth allocation, showing that solving them sequentially leads to the solution to the original problem. Due to the NP-hardness of the problem, we first study an important special case called the "backbone-sharing" case, and design a dynamic programming-based algorithm to obtain the optimal solution in polynomial time. For the general case, we propose a greedy heuristic to obtain the sub-optimal solution efficiently. Simulation results demonstrate that the proposed framework significantly improves task throughput under deadline constraints compared with user scheduling without exploiting parameter sharing.
Authors: Hoang Hai Phan, Nguyen Duc Minh Vu, Nam Dang Phuong
Abstract: Neural Machine Translation (NMT) driven by Transformer architectures has advanced significantly, yet faces challenges with low-resource language pairs like Vietnamese-Japanese (Vi-Ja). Issues include sparse parallel data and handling linguistic/cultural nuances. Recent progress in Large Language Models (LLMs) with strong reasoning, often refined via Reinforcement Learning (RL), enables high-quality synthetic data generation. We introduce VNJPTranslate, a pipeline designed to systematically address the Vi-Ja translation task. It features a targeted data augmentation strategy using advanced LLMs with Chain-of-Thought prompting for challenging segments identified via corpus analysis. Subsequently, we employ efficient fine-tuning techniques (Unsloth with QLoRA) on a capable, low-parameter autoregressive model (specifically, a fine-tuned version of the 1.8B parameter Sailor model, which is based on the Qwen architecture) to create a practical and high-performing translation system. This integrated approach aims to improve Vi-Ja translation quality significantly over existing baselines.
Authors: Yujin Potter, Wenbo Guo, Zhun Wang, Tianneng Shi, Andy Zhang, Patrick Gage Kelley, Kurt Thomas, Dawn Song
Abstract: The impact of frontier AI in cybersecurity is rapidly increasing. In this paper, we comprehensively analyze this trend through three distinct lenses: a quantitative benchmark analysis, a literature review, and an expert survey. We find that while AI is already widely used in attacks, its application in defense remains limited, especially in remediation and deployment. Aligned with these analyses, experts expect AI to continue favoring attackers over defenders, though the gap will gradually narrow. These findings underscore the urgent need to mitigate frontier AI's risks while closely monitoring emerging capabilities. We provide concrete calls-to-action regarding: the construction of new cybersecurity benchmarks, the development of AI agents for defense, the design of provably secure AI agents, the improvement of pre-deployment security testing and transparency, and the strengthening of user-oriented education and defenses. Our paper summary and blog are available at https://rdi.berkeley.edu/frontier-ai-impact-on-cybersecurity/.
URLs: https://rdi.berkeley.edu/frontier-ai-impact-on-cybersecurity/.
Authors: Zhiwei Xu, Yujuan Wu, Shiheng Wang, Jiabao Gao, Tian Qiu, Ziqi Wang, Hai Wan, Xibin Zhao
Abstract: Intrusion Detection Systems (IDS) have long been a hot topic in the cybersecurity community. In recent years, with the introduction of deep learning (DL) techniques, IDS have made great progress due to their increasing generalizability. The rationale behind this is that by learning the underlying patterns of known system behaviors, IDS detection can be generalized to intrusions that exploit zero-day vulnerabilities. In this survey, we refer to this type of IDS as DL-based IDS (DL-IDS). From the perspective of DL, this survey systematically reviews all the stages of DL-IDS, including data collection, log storage, log parsing, graph summarization, attack detection, and attack investigation. To accommodate current researchers, a section describing the publicly available benchmark datasets is included. This survey further discusses current challenges and potential future research directions, aiming to help researchers understand the basic ideas and visions of DL-IDS research, as well as to motivate their research interests.
Authors: Shengao Wang, Arjun Chandra, Aoming Liu, Venkatesh Saligrama, Boqing Gong
Abstract: Human infants rapidly develop visual reasoning skills from minimal input, suggesting that developmentally inspired pretraining could significantly enhance the efficiency of vision-language models (VLMs). Although recent efforts have leveraged infant-inspired datasets like SAYCam, existing evaluation benchmarks remain misaligned--they are either too simplistic, narrowly scoped, or tailored for large-scale pretrained models. Additionally, training exclusively on infant data overlooks the broader, diverse input from which infants naturally learn. To address these limitations, we propose BabyVLM, a novel framework comprising comprehensive in-domain evaluation benchmarks and a synthetic training dataset created via child-directed transformations of existing datasets. We demonstrate that VLMs trained with our synthetic dataset achieve superior performance on BabyVLM tasks compared to models trained solely on SAYCam or general-purpose data of the SAYCam size. BabyVLM thus provides a robust, developmentally aligned evaluation tool and illustrates how compact models trained on carefully curated data can generalize effectively, opening pathways toward data-efficient vision-language learning paradigms.
Authors: Shuai Zhao, Yunqiu Xu, Linchao Zhu, Yi Yang
Abstract: Large language models~(LLMs) are expected to be helpful, harmless, and honest. In different alignment scenarios, such as safety, confidence, and general preference alignment, binary preference data collection and reward modeling are resource-intensive but play a central role in transferring human preferences. In this work, we explore using the similarity between sampled generations and reference answers as a supplementary reward function for alignment. When unary reference answers are available, such similarity-based rewards can circumvent the need for binary preference data and explicit reward modeling. We introduce \textit{RefAlign}, a versatile REINFORCE-style alignment algorithm that does not rely on reward or reference models. RefAlign utilizes language generation evaluation metrics, such as BERTScore, between sampled generations and reference answers as surrogate rewards. Beyond general preference optimization, RefAlign can be naturally extended to diverse scenarios, including safety and confidence alignment, by combining similarity-based rewards with task-specific objectives. Across multiple scenarios, RefAlign achieves performance comparable to prior alignment methods while operating without binary preference data or reward models. The code is available at https://github.com/mzhaoshuai/RefAlign.
Authors: Shahriar Noroozizadeh, Sayantan Kumar, Jeremy C. Weiss
Abstract: Clinical case reports encode temporal patient trajectories that are often underexploited by traditional machine learning methods relying on structured data. In this work, we introduce the forecasting problem from textual time series, where timestamped clinical findings -- extracted via an LLM-assisted annotation pipeline -- serve as the primary input for prediction. We systematically evaluate a diverse suite of models, including fine-tuned decoder-based large language models and encoder-based transformers, on tasks of event occurrence prediction, temporal ordering, and survival analysis. Our experiments reveal that encoder-based models consistently achieve higher F1 scores and superior temporal concordance for short- and long-horizon event forecasting, while fine-tuned masking approaches enhance ranking performance. In contrast, instruction-tuned decoder models demonstrate a relative advantage in survival analysis, especially in early prognosis settings. Our sensitivity analyses further demonstrate the importance of time ordering, which requires clinical time series construction, as compared to text ordering, the format of the text inputs that LLMs are classically trained on. This highlights the additional benefit that can be ascertained from time-ordered corpora, with implications for temporal tasks in the era of widespread LLM use.
Authors: Peng Du, Jinjing Shi, Wenxuan Wang, Yin Ma, Kai Wen, Xuelong Li
Abstract: Attention mechanisms underpin modern deep learning, while the quadratic time and space complexity limit scalability for long sequences. To address this, Quantum Annealing Multi-Head Attention (QAMA) is proposed, a novel drop-in operator that reformulates attention as an energy-based Hamiltonian optimization problem. In this framework, token interactions are encoded into binary quadratic terms, and quantum annealing is employed to search for low-energy configurations that correspond to effective attention patterns. Unlike classical sparse or approximate attention methods that rely on hand-crafted heuristics, QAMA allows sparsity structures to emerge naturally from the optimization process. Theoretically, computational complexity is analysed through single-spin flip dynamics, providing time to solution runtime bounds that depend on the spectral properties of the annealing Hamiltonian. Empirically, evaluation on both natural language and vision benchmarks shows that, across tasks, accuracy deviates by at most 2.7 points from standard multi-head attention, while requiring only linear qubits in sequence length. Visualizations further reveal that the Hamiltonian penalty terms induce meaningful and interpretable sparsity across heads. Finally, deployment on a coherent Ising machine validates the feasibility of running QAMA on real quantum hardware, showing tangible inference-time reductions compared with classical implementations. These results highlight QAMA as a pioneering and scalable step toward integrating quantum optimization devices into deep neural architectures, providing a seamlessly integrable and hardware-compatible alternative to conventional attention mechanisms. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.
Authors: Xiaoxi Li, Jiajie Jin, Guanting Dong, Hongjin Qian, Yongkang Wu, Ji-Rong Wen, Yutao Zhu, Zhicheng Dou
Abstract: Large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, demonstrate impressive long-horizon reasoning capabilities. However, their reliance on static internal knowledge limits their performance on complex, knowledge-intensive tasks and hinders their ability to produce comprehensive research reports requiring synthesis of diverse web information. To address this, we propose WebThinker, a deep research agent that empowers LRMs to autonomously search the web, navigate among web pages, and draft reports during the reasoning process. WebThinker integrates a Deep Web Explorer module, enabling LRMs to dynamically search, navigate, and extract information from the web when encountering knowledge gaps. It also employs an Autonomous Think-Search-and-Draft strategy, allowing the model to seamlessly interleave reasoning, information gathering, and report writing in real time. To further enhance research tool utilization, we introduce an RL-based training strategy via iterative online Direct Preference Optimization (DPO). Extensive experiments on complex reasoning benchmarks (GPQA, GAIA, WebWalkerQA, HLE) and scientific report generation tasks (Glaive) demonstrate that WebThinker significantly outperforms existing methods and strong proprietary systems. Our approach enhances LRM reliability and applicability in complex scenarios, paving the way for more capable and versatile deep research systems. The code is available at https://github.com/RUC-NLPIR/WebThinker.
Authors: Trinh T. L. Vuong, Jin Tae Kwak
Abstract: We present ViDRiP-LLaVA, the first large multimodal model (LMM) in computational pathology that integrates three distinct image scenarios, including single patch images, automatically segmented pathology video clips, and manually segmented pathology videos. This integration closely mirrors the natural diagnostic process of pathologists. By generating detailed histological descriptions and culminating in a definitive sign-out diagnosis, ViDRiP-LLaVA bridges visual narratives with diagnostic reasoning. Central to our approach is the ViDRiP-Instruct dataset, comprising 4278 video and diagnosis-specific chain-of-thought instructional pairs sourced from educational histopathology videos on YouTube. Although high-quality data is critical for enhancing diagnostic reasoning, its creation is time-intensive and limited in volume. To overcome this challenge, we transfer knowledge from existing single-image instruction datasets to train on weakly annotated, keyframe-extracted clips, followed by fine-tuning on manually segmented videos. ViDRiP-LLaVA establishes a new benchmark in pathology video analysis and offers a promising foundation for future AI systems that support clinical decision-making through integrated visual and diagnostic reasoning. Our code, data, and model are publicly available at: https://github.com/QuIIL/ViDRiP-LLaVA.
Authors: Ran Zhang, Wei Zhao, Lieve Macken, Steffen Eger
Abstract: The impact of Large Language Models (LLMs) has extended into literary domains. However, existing evaluation metrics for literature prioritize mechanical accuracy over artistic expression and tend to overrate machine translation as being superior to human translation from experienced professionals. In the long run, this bias could result in an irreversible decline in translation quality and cultural authenticity. In response to the urgent need for a specialized literary evaluation metric, we introduce LITRANSPROQA, a novel, reference-free, LLM-based question-answering framework designed for literary translation evaluation. LITRANSPROQA integrates humans in the loop to incorporate insights from professional literary translators and researchers, focusing on critical elements in literary quality assessment such as literary devices, cultural understanding, and authorial voice. Our extensive evaluation shows that while literary-finetuned XCOMET-XL yields marginal gains, LITRANSPROQA substantially outperforms current metrics, achieving up to 0.07 gain in correlation and surpassing the best state-of-the-art metrics by over 15 points in adequacy assessments. Incorporating professional translator insights as weights further improves performance, highlighting the value of translator inputs. Notably, LITRANSPROQA reaches an adequacy performance comparable to trained linguistic student evaluators, though it still falls behind experienced professional translators. LITRANSPROQA shows broad applicability to open-source models like LLaMA3.3-70b and Qwen2.5-32b, indicating its potential as an accessible and training-free tool for evaluating literary translations that require local processing due to copyright or ethical considerations.
Authors: Neeloy Chakraborty, John Pohovey, Melkior Ornik, Katherine Driggs-Campbell
Abstract: Large language models (LLMs) have recently demonstrated success in generalizing across decision-making tasks including planning, control, and prediction, but their tendency to hallucinate unsafe and undesired outputs poses risks. We argue that detecting such failures is necessary, especially in safety-critical scenarios. Existing methods for black-box models often detect hallucinations by identifying inconsistencies across multiple samples. Many of these approaches typically introduce prompt perturbations like randomizing detail order or generating adversarial inputs, with the intuition that a confident model should produce stable outputs. We first perform a manual case study showing that other forms of perturbations (e.g., adding noise, removing sensor details) cause LLMs to hallucinate in a multi-agent driving environment. We then propose a novel method for efficiently searching the space of prompt perturbations using adaptive stress testing (AST) with Monte-Carlo tree search (MCTS). Our AST formulation enables discovery of scenarios and prompts that cause language models to act with high uncertainty or even crash. By generating MCTS prompt perturbation trees across diverse scenarios, we show through extensive experiments that offline analyses can be used at runtime to automatically generate prompts that influence model uncertainty, and to inform real-time trust assessments of an LLM. We further characterize LLMs deployed as planners in a single-agent lunar lander environment and in a multi-agent robot crowd navigation simulation. Overall, ours is one of the first hallucination intervention algorithms to pave a path towards rigorous characterization of black-box LLM planners.
Authors: Ce Hao, Anxing Xiao, Zhiwei Xue, Harold Soh
Abstract: Diffusion-based planners have shown strong performance in short-horizon tasks but often fail in complex, long-horizon settings. We trace the failure to loose coupling between high-level (HL) sub-goal selection and low-level (LL) trajectory generation, which leads to incoherent plans and degraded performance. We propose Coupled Hierarchical Diffusion (CHD), a framework that models HL sub-goals and LL trajectories jointly within a unified diffusion process. A shared classifier passes LL feedback upstream so that sub-goals self-correct while sampling proceeds. This tight HL-LL coupling improves trajectory coherence and enables scalable long-horizon diffusion planning. Experiments across maze navigation, tabletop manipulation, and household environments show that CHD consistently outperforms both flat and hierarchical diffusion baselines. Our website is: https://sites.google.com/view/chd2025/home
Authors: Chenxi Whitehouse, Tianlu Wang, Ping Yu, Xian Li, Jason Weston, Ilia Kulikov, Swarnadeep Saha
Abstract: The progress of AI is bottlenecked by the quality of evaluation, making powerful LLM-as-a-Judge models a core solution. The efficacy of these judges depends on their chain-of-thought reasoning, creating a critical need for methods that can effectively optimize this reasoning process. In this work, we introduce J1, a reinforcement learning framework for teaching LLM judges to think before making decisions. Our core contribution lies in converting all judgment tasks for non-verifiable and verifiable prompts into a unified format with verifiable rewards, enabling direct optimization of evaluation quality while mitigating positional bias. We then use RL to train thinking-judges at scales of 8B, 32B, and 70B and show that they obtain state-of-the-art performance across multiple benchmarks. In particular, J1-Qwen-32B, our multitasked pointwise and pairwise judge also outperforms o1-mini, o3, and a much larger 671B DeepSeek-R1 on some benchmarks, while only training on synthetic data. Through comprehensive ablations of pairwise, pointwise, and multitask J1 variants, we demonstrate the effectiveness of our approach across seed prompts, reward strategies, and training recipes. Qualitative analysis reveals that J1 develops systematic evaluation strategies, including dynamic criteria generation, reference answer creation, iterative self-correction of initial assessments, and feedback generation for low-quality responses.
Authors: Haozheng Luo, Chenghao Qiu, Yimin Wang, Shang Wu, Jiahao Yu, Zhenyu Pan, Weian Mao, Haoyang Fang, Hao Xu, Han Liu, Binghui Wang, Yan Chen
Abstract: We propose the first unified adversarial attack benchmark for Genomic Foundation Models (GFMs), named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first comprehensive evaluation framework to systematically assess the vulnerability of GFMs to adversarial attacks. Methodologically, we evaluate the adversarial robustness of five state-of-the-art GFMs using four widely adopted attack algorithms and three defense strategies. Importantly, our benchmark provides an accessible and comprehensive framework to analyze GFM vulnerabilities with respect to model architecture, quantization schemes, and training datasets. Additionally, we introduce GenoAdv, a new adversarial sample dataset designed to improve GFM safety. Empirically, classification models exhibit greater robustness to adversarial perturbations compared to generative models, highlighting the impact of task type on model vulnerability. Moreover, adversarial attacks frequently target biologically significant genomic regions, suggesting that these models effectively capture meaningful sequence features.
Authors: Yuran Wang, Ruihai Wu, Yue Chen, Jiarui Wang, Jiaqi Liang, Ziyu Zhu, Haoran Geng, Jitendra Malik, Pieter Abbeel, Hao Dong
Abstract: Garment manipulation is a critical challenge due to the diversity in garment categories, geometries, and deformations. Despite this, humans can effortlessly handle garments, thanks to the dexterity of our hands. However, existing research in the field has struggled to replicate this level of dexterity, primarily hindered by the lack of realistic simulations of dexterous garment manipulation. Therefore, we propose DexGarmentLab, the first environment specifically designed for dexterous (especially bimanual) garment manipulation, which features large-scale high-quality 3D assets for 15 task scenarios, and refines simulation techniques tailored for garment modeling to reduce the sim-to-real gap. Previous data collection typically relies on teleoperation or training expert reinforcement learning (RL) policies, which are labor-intensive and inefficient. In this paper, we leverage garment structural correspondence to automatically generate a dataset with diverse trajectories using only a single expert demonstration, significantly reducing manual intervention. However, even extensive demonstrations cannot cover the infinite states of garments, which necessitates the exploration of new algorithms. To improve generalization across diverse garment shapes and deformations, we propose a Hierarchical gArment-manipuLation pOlicy (HALO). It first identifies transferable affordance points to accurately locate the manipulation area, then generates generalizable trajectories to complete the task. Through extensive experiments and detailed analysis of our method and baseline, we demonstrate that HALO consistently outperforms existing methods, successfully generalizing to previously unseen instances even with significant variations in shape and deformation where others fail. Our project page is available at: https://wayrise.github.io/DexGarmentLab/.
Authors: Huashan Sun, Shengyi Liao, Yansen Han, Yu Bai, Yang Gao, Cheng Fu, Weizhou Shen, Fanqi Wan, Ming Yan, Ji Zhang, Fei Huang
Abstract: Despite advances in pretraining with extended context lengths, large language models (LLMs) still face challenges in effectively utilizing real-world long-context information, primarily due to insufficient long-context alignment caused by data quality issues, training inefficiencies, and the lack of well-designed optimization objectives. To address these limitations, we propose a framework named $\textbf{S}$h$\textbf{o}$rt-to-$\textbf{Lo}$ng $\textbf{P}$reference $\textbf{O}$ptimization ($\textbf{SoLoPO}$), decoupling long-context preference optimization (PO) into two components: short-context PO and short-to-long reward alignment (SoLo-RA), supported by both theoretical and empirical evidence. Specifically, short-context PO leverages preference pairs sampled from short contexts to enhance the model's contextual knowledge utilization ability. Meanwhile, SoLo-RA explicitly encourages reward score consistency utilization for the responses when conditioned on both short and long contexts that contain identical task-relevant information. This facilitates transferring the model's ability to handle short contexts into long-context scenarios. SoLoPO is compatible with mainstream preference optimization algorithms, while substantially improving the efficiency of data construction and training processes. Experimental results show that SoLoPO enhances all these algorithms with respect to stronger length and domain generalization abilities across various long-context benchmarks, while achieving notable improvements in both computational and memory efficiency.
Authors: Elliot L. Epstein, Apaar Sadhwani, Kay Giesecke
Abstract: Many prediction problems across science and engineering, especially in finance and economics, involve large cross-sections of individual time series, where each unit (e.g., a loan, stock, or customer) is driven by unit-level features and latent cross-sectional dynamics. While sequence models have advanced per-unit temporal prediction, capturing cross-sectional effects often still relies on hand-crafted summary features. We propose Set-Sequence, a model that learns cross-sectional structure directly, enhancing expressivity and eliminating manual feature engineering. At each time step, a permutation-invariant Set module summarizes the unit set; a Sequence module then models each unit's dynamics conditioned on both its features and the learned summary. The architecture accommodates unaligned series, supports varying numbers of units at inference, integrates with standard sequence backbones (e.g., Transformers), and scales linearly in cross-sectional size. Across a synthetic contagion task and two large-scale real-world applications, equity portfolio optimization and loan risk prediction, Set-Sequence significantly outperforms strong baselines, delivering higher Sharpe ratios, improved AUCs, and interpretable cross-sectional summaries.
Authors: Zhen Li, Yupeng Su, Songmiao Wang, Runming Yang, Congkai Xie, Aofan Liu, Ming Li, Jiannong Cao, Ngai Wong, Hongxia Yang
Abstract: Low-bit post-training quantization (PTQ) is a practical route to deploy reasoning-capable LLMs under tight memory and latency budgets, yet it can markedly impair mathematical reasoning (drops up to 69.81% in our harder settings). We address two deployment-critical questions with process-level precision: Where along a step-structured solution does degradation first arise? How to mitigate it while staying in the low-bit regime? Across widely used PTQ methods (AWQ, GPTQ, SmoothQuant), open-source model families (Qwen, LLaMA; 0.5--7B), and math reasoning benchmarks (GSM8K, MATH, AIME), we perform format-aligned chain-of-thought with step-aligned attribution and uncover two robust regularities: (i) PTQ disproportionately elevates method and execution errors relative to high-level conceptual mistakes; and (ii) failures emerge early, with the first vulnerable step flipping and cascading to the final answer. These regularities suggest a general intervention principle: restore local token-level margins exactly at the earliest failure frontier. We instantiate this principle as a lightweight measure$\rightarrow$locate$\rightarrow$restore loop that operates directly on the quantized model: detect the first faulty step, construct our "Silver Bullet" datasets, and apply small-scale supervised/preference tuning. In our settings, as few as 332 curated examples and 3--5 minutes of compute on a single GPU recover 4-bit weight math reasoning toward the full-precision baseline while preserving PTQ efficiency. Our framework is quantizer- and architecture-agnostic within the evaluated regimes, and turns low-bit degradation from a global accuracy problem into a local, reproducible process intervention.
Authors: Alberto Sinigaglia, Davide Sartor, Marina Ceccon, Gian Antonio Susto
Abstract: Fair classification is a critical challenge that has gained increasing importance due to international regulations and its growing use in high-stakes decision-making settings. Existing methods often rely on adversarial learning or distribution matching across sensitive groups; however, adversarial learning can be unstable, and distribution matching can be computationally intensive. To address these limitations, we propose a novel approach based on the characteristic function distance. Our method ensures that the learned representation contains minimal sensitive information while maintaining high effectiveness for downstream tasks. By utilizing characteristic functions, we achieve a more stable and efficient solution compared to traditional methods. Additionally, we introduce a simple relaxation of the objective function that guarantees fairness in common classification models with no performance degradation. Experimental results on benchmark datasets demonstrate that our approach consistently matches or achieves better fairness and predictive accuracy than existing methods. Moreover, our method maintains robustness and computational efficiency, making it a practical solution for real-world applications.
Authors: Jitai Hao, Qiang Huang, Hao Liu, Xinyan Xiao, Zhaochun Ren, Jun Yu
Abstract: Training high-performing Small Language Models (SLMs) remains costly, even with knowledge distillation and pruning from larger teacher models. Existing work often faces three key challenges: (1) information loss from hard pruning, (2) inefficient alignment of representations, and (3) underutilization of informative activations, particularly from Feed-Forward Networks (FFNs). To address these challenges, we introduce Low-Rank Clone (LRC), an efficient pre-training method that constructs SLMs aspiring to behavioral equivalence with strong teacher models. LRC trains a set of low-rank projection matrices that jointly enable soft pruning by compressing teacher weights, and activation clone by aligning student activations, including FFN signals, with those of the teacher. This unified design maximizes knowledge transfer while removing the need for explicit alignment modules. Extensive experiments with open-source teachers (e.g., Llama-3.2-3B-Instruct, Qwen2.5-3B/7B-Instruct) show that LRC matches or surpasses state-of-the-art models trained on trillions of tokens--while using only 20B tokens, achieving over 1,000x training efficiency. Our codes and model checkpoints are available at https://github.com/CURRENTF/LowRankClone and https://huggingface.co/collections/JitaiHao/low-rank-clone-lrc-6828389e96a93f1d4219dfaf.
URLs: https://github.com/CURRENTF/LowRankClone, https://huggingface.co/collections/JitaiHao/low-rank-clone-lrc-6828389e96a93f1d4219dfaf.
Authors: Ji Qi, Tam Thuc Do, Mingxiao Liu, Zhuoshi Pan, Yuzhe Li, Gene Cheung, H. Vicky Zhao
Abstract: Unlike conventional "black-box" transformers with classical self-attention mechanism, we build a lightweight and interpretable transformer-like neural net by unrolling a mixed-graph-based optimization algorithm to forecast traffic with spatial and temporal dimensions. We construct two graphs: an undirected graph $\mathcal{G}^u$ capturing spatial correlations across geography, and a directed graph $\mathcal{G}^d$ capturing sequential relationships over time. We predict future samples of signal $\mathbf{x}$, assuming it is "smooth" with respect to both $\mathcal{G}^u$ and $\mathcal{G}^d$, where we design new $\ell_2$ and $\ell_1$-norm variational terms to quantify and promote signal smoothness (low-frequency reconstruction) on a directed graph. We design an iterative algorithm based on alternating direction method of multipliers (ADMM), and unroll it into a feed-forward network for data-driven parameter learning. We insert graph learning modules for $\mathcal{G}^u$ and $\mathcal{G}^d$ that play the role of self-attention. Experiments show that our unrolled networks achieve competitive traffic forecast performance as state-of-the-art prediction schemes, while reducing parameter counts drastically. Our code is available in https://github.com/SingularityUndefined/Unrolling-GSP-STForecast .
URLs: https://github.com/SingularityUndefined/Unrolling-GSP-STForecast
Authors: Prithviraj Singh Shahani, Kaveh Eskandari Miandoab, Matthias Scheutz
Abstract: Safety guardrails in large language models (LLMs) are a critical component in preventing harmful outputs. Yet, their resilience under perturbation remains poorly understood. In this paper, we investigate the robustness of safety fine-tuning in LLMs by systematically injecting Gaussian noise into model activations. We show across multiple open-weight models that (1) Gaussian noise raises harmful-output rates (p < 0.001) by up to 27%, (2) that deeper safety fine-tuning affords no extra protection, and (3) that chain-of-thought reasoning remains largely intact. The findings reveal critical vulnerabilities in current safety alignment techniques and highlight the potential of reasoning-based and reinforcement learning approaches as promising direction for developing more robust AI safety systems. These results have important implications for real-world deployment of LLMs in safety-critical applications as these results imply that widely-deployed safety tuning methods can fail even without adversarial prompts.
Authors: Xiaohui Wang, Peng Ye, Chenyu Huang, Shenghe Zheng, Bo Zhang, Lei Bai, Wanli Ouyang, Tao Chen
Abstract: With the rise of the fine-tuned-pretrained paradigm, storing numerous fine-tuned models for multi-tasking creates significant storage overhead. Delta compression alleviates this by storing only the pretrained model and the highly compressed delta weights (the differences between fine-tuned and pretrained model weights). However, existing methods fail to maintain both high compression and performance, and often rely on data. To address these challenges, we propose UltraDelta, the first data-free delta compression pipeline that achieves both ultra-high compression and strong performance. UltraDelta is designed to minimize redundancy, maximize information, and stabilize performance across inter-layer, intra-layer, and global dimensions, using three key components: (1) Variance-Based Mixed Sparsity Allocation assigns sparsity based on variance, giving lower sparsity to high-variance layers to preserve inter-layer information. (2) Distribution-Aware Compression applies uniform quantization and then groups parameters by value, followed by group-wise pruning, to better preserve intra-layer distribution. (3) Trace-Norm-Guided Rescaling uses the trace norm of delta weights to estimate a global rescaling factor, improving model stability under higher compression. Extensive experiments across (a) large language models (fine-tuned on LLaMA-2 7B and 13B) with up to 50x compression, (b) general NLP models (RoBERTa-base, T5-base) with up to 224x compression, (c) vision models (ViT-B/32, ViT-L/14) with up to 132x compression, and (d) multi-modal models (BEiT-3) with 18x compression, demonstrate that UltraDelta consistently outperforms existing methods, especially under ultra-high compression. Code is available at https://github.com/xiaohuiwang000/UltraDelta.
Authors: Darpan Aswal, Siddharth D Jaiswal
Abstract: Recently released LLMs have strong multilingual \& multimodal capabilities. Model vulnerabilities are exposed using audits and red-teaming efforts. Existing efforts have focused primarily on the English language; thus, models continue to be susceptible to multilingual jailbreaking strategies, especially for multimodal contexts. In this study, we introduce a novel strategy that leverages code-mixing and phonetic perturbations to jailbreak LLMs for both text and image generation tasks. We also present an extension to a current jailbreak-template-based strategy and propose a novel template, showing higher effectiveness than baselines. Our work presents a method to effectively bypass safety filters in LLMs while maintaining interpretability by applying phonetic misspellings to sensitive words in code-mixed prompts. We achieve a 99\% Attack Success Rate for text generation and 78\% for image generation, with Attack Relevance Rate of 100\% for text generation and 96\% for image generation for the phonetically perturbed code-mixed prompts. Our interpretability experiments reveal that phonetic perturbations impact word tokenization, leading to jailbreak success. Our study motivates increasing the focus towards more generalizable safety alignment for multilingual multimodal models, especially in real-world settings wherein prompts can have misspelt words. \textit{\textbf{Warning: This paper contains examples of potentially harmful and offensive content.}}
Authors: Kunyun Wang, Bohan Li, Kai Yu, Minyi Guo, Jieru Zhao
Abstract: Diffusion models have emerged as a powerful class of generative models across various modalities, including image, video, and audio synthesis. However, their deployment is often limited by significant inference latency, primarily due to the inherently sequential nature of the denoising process. While existing parallelization strategies attempt to accelerate inference by distributing computation across multiple devices, they typically incur high communication overhead, hindering deployment on commercial hardware. To address this challenge, we propose \textbf{ParaStep}, a novel parallelization method based on a reuse-then-predict mechanism that parallelizes diffusion inference by exploiting similarity between adjacent denoising steps. Unlike prior approaches that rely on layer-wise or stage-wise communication, ParaStep employs lightweight, step-wise communication, substantially reducing overhead. ParaStep achieves end-to-end speedups of up to \textbf{3.88}$\times$ on SVD, \textbf{2.43}$\times$ on CogVideoX-2b, and \textbf{6.56}$\times$ on AudioLDM2-large, while maintaining generation quality. These results highlight ParaStep as a scalable and communication-efficient solution for accelerating diffusion inference, particularly in bandwidth-constrained environments.
Authors: David Dinucu-Jianu, Jakub Macina, Nico Daheim, Ido Hakimi, Iryna Gurevych, Mrinmaya Sachan
Abstract: Large language models (LLMs) can transform education, but their optimization for direct question-answering often undermines effective pedagogy which requires strategically withholding answers. To mitigate this, we propose an online reinforcement learning (RL)-based alignment framework that can quickly adapt LLMs into effective tutors using simulated student-tutor interactions by emphasizing pedagogical quality and guided problem-solving over simply giving away answers. We use our method to train a 7B parameter tutor model without human annotations which reaches similar performance to larger proprietary models like LearnLM. We introduce a controllable reward weighting to balance pedagogical support and student solving accuracy, allowing us to trace the Pareto frontier between these two objectives. Our models better preserve reasoning capabilities than single-turn SFT baselines and can optionally enhance interpretability through thinking tags that expose the model's instructional planning.
Authors: Bohao Wu, Qingyun Wang, Yue Guo
Abstract: Personalizing jargon detection and explanation is essential for making technical documents accessible to readers with diverse disciplinary backgrounds. However, tailoring models to individual users typically requires substantial annotation efforts and computational resources due to user-specific finetuning. To address this, we present a systematic study of personalized jargon detection, focusing on methods that are both efficient and scalable for real-world deployment. We explore two personalization strategies: (1) lightweight finetuning using Low-Rank Adaptation (LoRA) on open-source models, and (2) personalized prompting, which tailors model behavior at inference time without retaining. To reflect realistic constraints, we also investigate semi-supervised approaches that combine limited annotated data with self-supervised learning from users' publications. Our personalized LoRA model outperforms GPT-4 with contextual prompting by 21.4% in F1 score and exceeds the best performing oracle baseline by 8.3%. Remarkably, our method achieves comparable performance using only 10% of the annotated training data, demonstrating its practicality for resource-constrained settings. Our study offers the first work to systematically explore efficient, low-resource personalization of jargon detection using open-source language models, offering a practical path toward scalable, user-adaptive NLP system.
Authors: Ruizhe Li, Chen Chen, Yuchen Hu, Yanjun Gao, Xi Wang, Emine Yilmaz
Abstract: Retrieval-Augmented Generation (RAG) leverages large language models (LLMs) combined with external contexts to enhance the accuracy and reliability of generated responses. However, reliably attributing generated content to specific context segments, context attribution, remains challenging due to the computationally intensive nature of current methods, which often require extensive fine-tuning or human annotation. In this work, we introduce a novel Jensen-Shannon Divergence driven method to Attribute Response to Context (ARC-JSD), enabling efficient and accurate identification of essential context sentences without additional fine-tuning, gradient-calculation or surrogate modelling. Evaluations on a wide range of RAG benchmarks, such as TyDi QA, Hotpot QA, and Musique, using instruction-tuned LLMs in different scales demonstrate superior accuracy and significant computational efficiency improvements compared to the previous surrogate-based method. Furthermore, our mechanistic analysis reveals specific attention heads and multilayer perceptron (MLP) layers responsible for context attribution, providing valuable insights into the internal workings of RAG models and how they affect RAG behaviours. Our code is available at https://github.com/ruizheliUOA/ARC_JSD.
Authors: Beier Luo, Shuoyuan Wang, Yixuan Li, Hongxin Wei
Abstract: Post-training of large language models is essential for adapting pre-trained language models (PLMs) to align with human preferences and downstream tasks. While PLMs typically exhibit well-calibrated confidence, post-trained language models (PoLMs) often suffer from over-confidence, assigning high confidence to both correct and incorrect outputs, which can undermine reliability in critical applications. A major obstacle in calibrating PoLMs is the scarcity of labeled data for individual downstream tasks. To address this, we propose Disagreement-Aware Confidence Alignment (DACA), a novel unsupervised method to optimize the parameters (e.g., temperature $\tau$) in post-hoc confidence calibration. Our method is motivated by the under-confidence issue caused by prediction disagreement between the PLM and PoLM while aligning their confidence via temperature scaling. Theoretically, the PLM's confidence underestimates PoLM's prediction accuracy on disagreement examples, causing a larger $\tau$ and producing under-confident predictions. DACA mitigates this by selectively using only agreement examples for calibration, effectively decoupling the influence of disagreement. In this manner, our method avoids an overly large $\tau$ in temperature scaling caused by disagreement examples, improving calibration performance. Extensive experiments demonstrate the effectiveness of our method, improving the average ECE of open-sourced and API-based LLMs (e.g. GPT-4o) by up to 15.08$\%$ on common benchmarks.
Authors: Florentin Beck, William Rudman, Carsten Eickhoff
Abstract: Large Language Models (LLMs) present significant computational and memory challenges due to their extensive size, making pruning essential for their efficient deployment. Existing one-shot pruning methods often apply uniform sparsity constraints across layers or within each layer, resulting in suboptimal performance, especially at high sparsity ratios. This work introduces TRIM (Targeted Row-wise Iterative Metric-driven pruning), a novel approach that applies varying sparsity ratios to individual output dimensions (rows) within each layer. TRIM employs an iterative adjustment process guided by quality metrics to optimize dimension-wise sparsity allocation, focusing on reducing variance in quality retention across outputs to preserve critical information. TRIM can be seamlessly integrated with existing layer-wise pruning strategies. Our evaluations on perplexity and zero-shot tasks across diverse LLM families (Qwen2.5, LLaMA-2, and OPT) and sparsity levels demonstrate that TRIM achieves new state-of-the-art results and enhances stability. For instance, at 80% sparsity, TRIM reduces perplexity by 48% for Qwen2.5-14B and over 90% for OPT-13B compared to baseline methods. We conclude that fine-grained, dimension-wise sparsity adaptation is crucial for pushing the limits of extreme LLM compression. Code available at: https://github.com/flobk/TRIM
Authors: Qirui Jiao, Daoyuan Chen, Yilun Huang, Xika Lin, Ying Shen, Yaliang Li
Abstract: While recent text-to-image (T2I) models show impressive capabilities in synthesizing images from brief descriptions, their performance significantly degrades when confronted with long, detail-intensive prompts required in professional applications. We present DetailMaster, the first comprehensive benchmark specifically designed to evaluate T2I models' systematic abilities to handle extended textual inputs that contain complex compositional requirements. Our benchmark introduces four critical evaluation dimensions: Character Attributes, Structured Character Locations, Multi-Dimensional Scene Attributes, and Spatial/Interactive Relationships. The benchmark comprises long and detail-rich prompts averaging 284.89 tokens, with high quality validated by expert annotators. Evaluation on 7 general-purpose and 5 long-prompt-optimized T2I models reveals critical performance limitations: state-of-the-art models achieve merely $\sim$50\% accuracy in key dimensions like attribute binding and spatial reasoning, while all models showing progressive performance degradation as prompt length increases. Our analysis reveals fundamental limitations in compositional reasoning, demonstrating that current encoders flatten complex grammatical structures and that diffusion models suffer from attribute leakage under detail-intensive conditions. We open-source our dataset, data curation code, and evaluation tools to advance detail-rich T2I generation and enable applications previously hindered by the lack of a dedicated benchmark.
Authors: Qilin Wang
Abstract: Long-term time-series forecasting (LTSF) models are often presented as general-purpose solutions that can be applied across domains, implicitly assuming that all data is pointwise predictable. Using chaotic systems such as Lorenz-63 as a case study, we argue that geometric structure - not pointwise prediction - is the right abstraction for a dynamic-agnostic foundational model. Minimizing the Wasserstein-2 distance (W2), which captures geometric changes, and providing a spectral view of dynamics are essential for long-horizon forecasting. Our model, FRIREN (Flow-inspired Representations via Interpretable Eigen-networks), implements an augmented normalizing-flow block that embeds data into a normally distributed latent representation. It then generates a W2-efficient optimal path that can be decomposed into rotation, scaling, inverse rotation, and translation. This architecture yields locally generated, geometry-preserving predictions that are independent of the underlying dynamics, and a global spectral representation that functions as a finite Koopman operator with a small modification. This enables practitioners to identify which modes grow, decay, or oscillate, both locally and system-wide. FRIREN achieves an MSE of 11.4, MAE of 1.6, and SWD of 0.96 on Lorenz-63 in a 336-in, 336-out, dt=0.01 setting, surpassing TimeMixer (MSE 27.3, MAE 2.8, SWD 2.1). The model maintains effective prediction for 274 out of 336 steps, approximately 2.5 Lyapunov times. On Rossler (96-in, 336-out), FRIREN achieves an MSE of 0.0349, MAE of 0.0953, and SWD of 0.0170, outperforming TimeMixer's MSE of 4.3988, MAE of 0.886, and SWD of 3.2065. FRIREN is also competitive on standard LTSF datasets such as ETT and Weather. By connecting modern generative flows with classical spectral analysis, FRIREN makes long-term forecasting both accurate and interpretable, setting a new benchmark for LTSF model design.
Authors: Trinity Chung, Yuchen Shen, Nathan C. L. Kong, Aran Nayebi
Abstract: Tactile sensing remains far less understood in neuroscience and less effective in artificial systems compared to more mature modalities such as vision and language. We bridge these gaps by introducing a novel Encoder-Attender-Decoder (EAD) framework to systematically explore the space of task-optimized temporal neural networks trained on realistic tactile input sequences from a customized rodent whisker-array simulator. We identify convolutional recurrent neural networks (ConvRNNs) as superior encoders to purely feedforward and state-space architectures for tactile categorization. Crucially, these ConvRNN-encoder-based EAD models achieve neural representations closely matching rodent somatosensory cortex, saturating the explainable neural variability and revealing a clear linear relationship between supervised categorization performance and neural alignment. Furthermore, contrastive self-supervised ConvRNN-encoder-based EADs, trained with tactile-specific augmentations, match supervised neural fits, serving as an ethologically-relevant, label-free proxy. For neuroscience, our findings highlight nonlinear recurrent processing as important for general-purpose tactile representations in somatosensory cortex, providing the first quantitative characterization of the underlying inductive biases in this system. For embodied AI, our results emphasize the importance of recurrent EAD architectures to handle realistic tactile inputs, along with tailored self-supervised learning methods for achieving robust tactile perception with the same type of sensors animals use to sense in unstructured environments.
Authors: Xuyang Liu, Zichen Wen, Shaobo Wang, Junjie Chen, Zhishan Tao, Yubo Wang, Tailai Chen, Xiangqi Jin, Chang Zou, Yiyu Wang, Chenfei Liao, Xu Zheng, Honggang Chen, Weijia Li, Xuming Hu, Conghui He, Linfeng Zhang
Abstract: The advancement of large language models (LLMs) and multi-modal LLMs (MLLMs) has historically relied on scaling model parameters. However, as hardware limits constrain further model growth, the primary computational bottleneck has shifted to the quadratic cost of self-attention over increasingly long sequences by ultra-long text contexts, high-resolution images, and extended videos. In this position paper, \textbf{we argue that the focus of research for efficient artificial intelligence (AI) is shifting from model-centric compression to data-centric compression}. We position data-centric compression as the emerging paradigm, which improves AI efficiency by directly compressing the volume of data processed during model training or inference. To formalize this shift, we establish a unified framework for existing efficiency strategies and demonstrate why it constitutes a crucial paradigm change for long-context AI. We then systematically review the landscape of data-centric compression methods, analyzing their benefits across diverse scenarios. Finally, we outline key challenges and promising future research directions. Our work aims to provide a novel perspective on AI efficiency, synthesize existing efforts, and catalyze innovation to address the challenges posed by ever-increasing context lengths.
Authors: Mohammed D. Belgoumri, Mohamed Reda Bouadjenek, Hakim Hacid, Imran Razzak, Sunil Aryal
Abstract: Training large neural networks (NNs) requires optimizing high-dimensional data-dependent loss functions. The optimization landscape of these functions is often highly complex and textured, even fractal-like, with many spurious local minima, ill-conditioned valleys, degenerate points, and saddle points. Complicating things further is the fact that these landscape characteristics are a function of the data, meaning that noise in the training data can propagate forward and give rise to unrepresentative small-scale geometry. This poses a difficulty for gradient-based optimization methods, which rely on local geometry to compute updates and are, therefore, vulnerable to being derailed by noisy data. In practice,this translates to a strong dependence of the optimization dynamics on the noise in the data, i.e., poor generalization performance. To remediate this problem, we propose a new optimization procedure: Rolling Ball Optimizer (RBO), that breaks this spatial locality by incorporating information from a larger region of the loss landscape in its updates. We achieve this by simulating the motion of a rigid sphere of finite radius rolling on the loss landscape, a straightforward generalization of Gradient Descent (GD) that simplifies into it in the infinitesimal limit. The radius serves as a hyperparameter that determines the scale at which RBO sees the loss landscape, allowing control over the granularity of its interaction therewith. We are motivated by the intuition that the large-scale geometry of the loss landscape is less data-specific than its fine-grained structure, and that it is easier to optimize. We support this intuition by proving that our algorithm has a smoothing effect on the loss function. Evaluation against SGD, SAM, and Entropy-SGD, on MNIST and CIFAR-10/100 demonstrates promising results in terms of convergence speed, training accuracy, and generalization performance.
Authors: Haoyu Zhang, Wentao Zhang, Hao Miao, Xinke Jiang, Yuchen Fang, Yifan Zhang
Abstract: Spatio-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool for modeling dynamic graph-structured data across diverse domains. However, they often fail to generalize in Spatio-Temporal Out-of-Distribution (STOOD) scenarios, where both temporal dynamics and spatial structures evolve beyond the training distribution. To address this problem, we propose an innovative Spatio-Temporal Retrieval-Augmented Pattern Learning framework,STRAP, which enhances model generalization by integrating retrieval-augmented learning into the STGNN continue learning pipeline. The core of STRAP is a compact and expressive pattern library that stores representative spatio-temporal patterns enriched with historical, structural, and semantic information, which is obtained and optimized during the training phase. During inference, STRAP retrieves relevant patterns from this library based on similarity to the current input and injects them into the model via a plug-and-play prompting mechanism. This not only strengthens spatio-temporal representations but also mitigates catastrophic forgetting. Moreover, STRAP introduces a knowledge-balancing objective to harmonize new information with retrieved knowledge. Extensive experiments across multiple real-world streaming graph datasets show that STRAP consistently outperforms state-of-the-art STGNN baselines on STOOD tasks, demonstrating its robustness, adaptability, and strong generalization capability without task-specific fine-tuning.
Authors: Thang Nguyen, Peter Chin, Yu-Wing Tai
Abstract: We present MA-RAG, a Multi-Agent framework for Retrieval-Augmented Generation (RAG) that addresses the inherent ambiguities and reasoning challenges in complex information-seeking tasks. Unlike conventional RAG methods that rely on end-to-end fine-tuning or isolated component enhancements, MA-RAG orchestrates a collaborative set of specialized AI agents: Planner, Step Definer, Extractor, and QA Agents, each responsible for a distinct stage of the RAG pipeline. By decomposing tasks into subtasks such as query disambiguation, evidence extraction, and answer synthesis, and enabling agents to communicate intermediate reasoning via chain-of-thought prompting, MA-RAG progressively refines retrieval and synthesis while maintaining modular interpretability. Extensive experiments on multi-hop and ambiguous QA benchmarks, including NQ, HotpotQA, 2WikimQA, and TriviaQA, demonstrate that MA-RAG significantly outperforms standalone LLMs and existing RAG methods across all model scales. Notably, even a small LLaMA3-8B model equipped with MA-RAG surpasses larger standalone LLMs, while larger variants (LLaMA3-70B and GPT-4o-mini) set new state-of-the-art results on challenging multi-hop datasets. Ablation studies reveal that both the planner and extractor agents are critical for multi-hop reasoning, and that high-capacity models are especially important for the QA agent to synthesize answers effectively. Beyond general-domain QA, MA-RAG generalizes to specialized domains such as medical QA, achieving competitive performance against domain-specific models without any domain-specific fine-tuning. Our results highlight the effectiveness of collaborative, modular reasoning in retrieval-augmented systems: MA-RAG not only improves answer accuracy and robustness but also provides interpretable intermediate reasoning steps, establishing a new paradigm for efficient and reliable multi-agent RAG.
Authors: Yukun Zhang, Qi Dong
Abstract: We present Multi-Scale Manifold Alignment(MSMA), an information-geometric framework that decomposes LLM representations into local, intermediate, and global manifolds and learns cross-scale mappings that preserve geometry and information. Across GPT-2, BERT, RoBERTa, and T5, we observe consistent hierarchical patterns and find that MSMA improves alignment metrics under multiple estimators (e.g., relative KL reduction and MI gains with statistical significance across seeds). Controlled interventions at different scales yield distinct and architecture-dependent effects on lexical diversity, sentence structure, and discourse coherence. While our theoretical analysis relies on idealized assumptions, the empirical results suggest that multi-objective alignment offers a practical lens for analyzing cross-scale information flow and guiding representation-level control.
Authors: Yukun Zhang, Qi Dong
Abstract: This paper introduces the Dynamical Manifold Evolution Theory (DMET), a conceptual framework that models large language model (LLM) generation as a continuous trajectory evolving on a low-dimensional semantic manifold. The theory characterizes latent dynamics through three interpretable metrics-state continuity ($C$), attractor compactness ($Q$), and topological persistence ($P$)-which jointly capture the smoothness, stability, and structure of representation evolution. Empirical analyses across multiple Transformer architectures reveal consistent links between these latent dynamics and text quality: smoother trajectories correspond to greater fluency, and richer topological organization correlates with enhanced coherence. Different models exhibit distinct dynamical regimes, reflecting diverse strategies of semantic organization in latent space. Moreover, decoding parameters such as temperature and top-$p$ shape these trajectories in predictable ways, defining a balanced region that harmonizes fluency and creativity. As a phenomenological rather than first-principles framework, DMET provides a unified and testable perspective for interpreting, monitoring, and guiding LLM behavior, offering new insights into the interplay between internal representation dynamics and external text generation quality.
Authors: Zhipeng He, Chun Ouyang, Lijie Wen, Cong Liu, Catarina Moreira
Abstract: Adversarial attacks pose a significant threat to machine learning models by inducing incorrect predictions through imperceptible perturbations to input data. While these attacks are well studied in unstructured domains such as images, their behaviour on tabular data remains underexplored due to mixed feature types and complex inter-feature dependencies. This study introduces a comprehensive benchmark that evaluates adversarial attacks on tabular datasets with respect to both effectiveness and imperceptibility. We assess five white-box attack algorithms (FGSM, BIM, PGD, DeepFool, and C\&W) across four representative models (LR, MLP, TabTransformer and FT-Transformer) using eleven datasets spanning finance, energy, and healthcare domains. The benchmark employs four quantitative imperceptibility metrics (proximity, sparsity, deviation, and sensitivity) to characterise perturbation realism. The analysis quantifies the trade-off between these two aspects and reveals consistent differences between attack types, with $\ell_\infty$-based attacks achieving higher success but lower subtlety, and $\ell_2$-based attacks offering more realistic perturbations. The benchmark findings offer actionable insights for designing more imperceptible adversarial attacks, advancing the understanding of adversarial vulnerability in tabular machine learning.
Authors: Santhosh Parampottupadam, Melih Co\c{s}\u{g}un, Sarthak Pati, Maximilian Zenk, Saikat Roy, Dimitrios Bounias, Benjamin Hamm, Sinem Sav, Ralf Floca, Klaus Maier-Hein
Abstract: Federated Learning (FL) offers a promising approach for training clinical AI models without centralizing sensitive patient data. However, its real-world adoption is hindered by challenges related to privacy, resource constraints, and compliance. Existing Differential Privacy (DP) approaches often apply uniform noise, which disproportionately degrades model performance, even among well-compliant institutions. In this work, we propose a novel compliance-aware FL framework that enhances DP by adaptively adjusting noise based on quantifiable client compliance scores. Additionally, we introduce a compliance scoring tool based on key healthcare and security standards to promote secure, inclusive, and equitable participation across diverse clinical settings. Extensive experiments on public datasets demonstrate that integrating under-resourced, less compliant clinics with highly regulated institutions yields accuracy improvements of up to 15% over traditional FL. This work advances FL by balancing privacy, compliance, and performance, making it a viable solution for real-world clinical workflows in global healthcare.
Authors: Hyeonbin Hwang, Byeongguk Jeon, Seungone Kim, Jiyeon Kim, Hoyeon Chang, Sohee Yang, Seungpil Won, Dohaeng Lee, Youbin Ahn, Minjoon Seo
Abstract: Autoregressive language models (LMs) generate one token at a time, yet human reasoning operates over higher-level abstractions - sentences, propositions, and concepts. This contrast raises a central question- Can LMs likewise learn to reason over structured semantic units rather than raw token sequences? In this work, we investigate whether pretrained LMs can be lifted into such abstract reasoning spaces by building on their learned representations. We present a framework that adapts a pretrained token-level LM to operate in sentence space by autoregressively predicting continuous embeddings of next sentences. We explore two embedding paradigms inspired by classical representation learning: 1) semantic embeddings, learned via autoencoding to preserve surface meaning; and 2) contextual embeddings, trained via next-sentence prediction to encode anticipatory structure. We evaluate both under two inference regimes: Discretized, which decodes each predicted embedding into text before re-encoding; and Continuous, which reasons entirely in embedding space for improved efficiency. Across four domains - mathematics, logic, commonsense, and planning - contextual embeddings under continuous inference show competitive performance with Chain-of-Thought (CoT) while reducing inference-time FLOPs on average by half. We also present early signs of scalability and modular adaptation. Finally, to visualize latent trajectories, we introduce SentenceLens, a diagnostic tool that decodes intermediate model states into interpretable sentences. Together, our results indicate that pretrained LMs can effectively transition to abstract, structured reasoning within latent embedding spaces.
Authors: Haokun Chen, Yueqi Zhang, Yuan Bi, Yao Zhang, Tong Liu, Jinhe Bi, Jian Lan, Jindong Gu, Claudia Grosser, Denis Krompass, Nassir Navab, Volker Tresp
Abstract: In recent years, Large Language Models (LLMs) have achieved remarkable advancements, drawing significant attention from the research community. Their capabilities are largely attributed to large-scale architectures, which require extensive training on massive datasets. However, such datasets often contain sensitive or copyrighted content sourced from the public internet, raising concerns about data privacy and ownership. Regulatory frameworks, such as the General Data Protection Regulation (GDPR), grant individuals the right to request the removal of such sensitive information. This has motivated the development of machine unlearning algorithms that aim to remove specific knowledge from models without the need for costly retraining. Despite these advancements, evaluating the efficacy of unlearning algorithms remains a challenge due to the inherent complexity and generative nature of LLMs. In this work, we introduce a comprehensive auditing framework for unlearning evaluation, comprising three benchmark datasets, six unlearning algorithms, and five prompt-based auditing methods. By using various auditing algorithms, we evaluate the effectiveness and robustness of different unlearning strategies. To explore alternatives beyond prompt-based auditing, we propose a novel technique that leverages intermediate activation perturbations, addressing the limitations of auditing methods that rely solely on model inputs and outputs.
Authors: Zifu Wang, Junyi Zhu, Bo Tang, Zhiyu Li, Feiyu Xiong, Jiaqian Yu, Matthew B. Blaschko
Abstract: The application of rule-based reinforcement learning (RL) to multimodal large language models (MLLMs) introduces unique challenges and potential deviations from findings in text-only domains, particularly for perception-heavy tasks. This paper provides a comprehensive study of rule-based visual RL, using jigsaw puzzles as a structured experimental framework. Jigsaw puzzles offer inherent ground truth, adjustable difficulty, and demand complex decision-making, making them ideal for this study. Our research reveals several key findings: \textit{Firstly,} we find that MLLMs, initially performing near to random guessing on the simplest jigsaw puzzles, achieve near-perfect accuracy and generalize to complex, unseen configurations through fine-tuning. \textit{Secondly,} training on jigsaw puzzles can induce generalization to other visual tasks, with effectiveness tied to specific task configurations. \textit{Thirdly,} MLLMs can learn and generalize with or without explicit reasoning, though open-source models often favor direct answering. Consequently, even when trained for step-by-step reasoning, they can ignore the thinking process in deriving the final answer. \textit{Fourthly,} we observe that complex reasoning patterns appear to be pre-existing rather than emergent, with their frequency increasing alongside training and task difficulty. \textit{Finally,} our results demonstrate that RL exhibits more effective generalization than Supervised Fine-Tuning (SFT), and an initial SFT cold start phase can hinder subsequent RL optimization. Although these observations are based on jigsaw puzzles and may vary across other visual tasks, this research contributes a valuable piece of jigsaw to the larger puzzle of collective understanding rule-based visual RL and its potential in multimodal learning. The code is available at: https://github.com/zifuwanggg/Jigsaw-R1
Authors: Yichen Shi, Ze Zhang, Hongyang Wang, Zhuofu Tao, Zhongyi Li, Bingyu Chen, Yaxin Wang, Zhen huang, Xuhua Liu, Quan Chen, Zhiping Yu, Ting-Jung Lin, Lei He
Abstract: Analog/Mixed-Signal (AMS) circuits play a critical role in the integrated circuit (IC) industry. However, automating Analog/Mixed-Signal (AMS) circuit design has remained a longstanding challenge due to its difficulty and complexity. Although recent advances in Multi-modal Large Language Models (MLLMs) offer promising potential for supporting AMS circuit analysis and design, current research typically evaluates MLLMs on isolated tasks within the domain, lacking a comprehensive benchmark that systematically assesses model capabilities across diverse AMS-related challenges. To address this gap, we introduce AMSbench, a benchmark suite designed to evaluate MLLM performance across critical tasks including circuit schematic perception, circuit analysis, and circuit design. AMSbench comprises approximately 8000 test questions spanning multiple difficulty levels and assesses eight prominent models, encompassing both open-source and proprietary solutions such as Qwen 2.5-VL and Gemini 2.5 Pro. Our evaluation highlights significant limitations in current MLLMs, particularly in complex multi-modal reasoning and sophisticated circuit design tasks. These results underscore the necessity of advancing MLLMs' understanding and effective application of circuit-specific knowledge, thereby narrowing the existing performance gap relative to human expertise and moving toward fully automated AMS circuit design workflows. Our data is released at this URL.
Authors: James R. Golden
Abstract: Despite significant progress in transformer interpretability, an understanding of the computational mechanisms of large language models (LLMs) remains a fundamental challenge. Many approaches interpret a network's hidden representations but remain agnostic about how those representations are generated. We address this by mapping LLM inference for a given input sequence to an equivalent and interpretable linear system which reconstructs the predicted output embedding with relative error below $10^{-13}$ at double floating-point precision, requiring no additional model training. We exploit a property of transformers wherein every operation (gated activations, attention, and normalization) can be expressed as $A(x) \cdot x$, where $A(x)$ represents an input-dependent linear transform and $x$ preserves the linear pathway. To expose this linear structure, we strategically detach components of the gradient computation with respect to an input sequence, freezing the $A(x)$ terms at their values computed during inference, such that the Jacobian yields an equivalent linear mapping. This detached Jacobian of the model reconstructs the output with one linear operator per input token, which is shown for Qwen 3, Gemma 3 and Llama 3, up to Qwen 3 14B. These linear representations demonstrate that LLMs operate in extremely low-dimensional subspaces where the singular vectors can be decoded to interpretable semantic concepts. The computation for each intermediate output also has a linear equivalent, and we examine how the linear representations of individual layers and their attention and multilayer perceptron modules build predictions, and use these as steering operators to insert semantic concepts into unrelated text. Despite their global nonlinearity, LLMs can be interpreted through equivalent linear representations that reveal low-dimensional semantic structures in the next-token prediction process.
Authors: Sarthak Kumar Maharana, Saksham Singh Kushwaha, Baoming Zhang, Adrian Rodriguez, Songtao Wei, Yapeng Tian, Yunhui Guo
Abstract: While recent audio-visual models have demonstrated impressive performance, their robustness to distributional shifts at test-time remains not fully understood. Existing robustness benchmarks mainly focus on single modalities, making them insufficient for thoroughly assessing the robustness of audio-visual models. Motivated by real-world scenarios where shifts can occur $\textit{simultaneously}$ in both audio and visual modalities, we introduce $\texttt{AVROBUSTBENCH}$, a comprehensive benchmark designed to evaluate the test-time robustness of audio-visual recognition models. $\texttt{AVROBUSTBENCH}$ comprises four audio-visual benchmark datasets, $\texttt{AUDIOSET-2C}$, $\texttt{VGGSOUND-2C}$, $\texttt{KINETICS-2C}$, and $\texttt{EPICKITCHENS-2C}$, each incorporating 75 bimodal audio-visual corruptions that are $\textit{co-occurring}$ and $\textit{correlated}$. Through extensive evaluations, we observe that state-of-the-art supervised and self-supervised audio-visual models exhibit declining robustness as corruption severity increases. Furthermore, online test-time adaptation (TTA) methods, on $\texttt{VGGSOUND-2C}$ and $\texttt{KINETICS-2C}$, offer minimal improvements in performance under bimodal corruptions. We further propose $\texttt{AV2C}$, a simple TTA approach enabling on-the-fly cross-modal fusion by penalizing high-entropy samples, which achieves improvements on $\texttt{VGGSOUND-2C}$. We hope that $\texttt{AVROBUSTBENCH}$ will steer the development of more effective and robust audio-visual TTA approaches. Our code is available $\href{https://github.com/sarthaxxxxx/AV-C-Robustness-Benchmark}{here}$.
URLs: https://github.com/sarthaxxxxx/AV-C-Robustness-Benchmark
Authors: Kyowoon Lee, Jaesik Choi
Abstract: Diffusion-based generative models are emerging as powerful tools for long-horizon planning in reinforcement learning (RL), particularly with offline datasets. However, their performance is fundamentally limited by the quality and diversity of training data. This often restricts their generalization to tasks outside their training distribution or longer planning horizons. To overcome this challenge, we propose State-Covering Trajectory Stitching (SCoTS), a novel reward-free trajectory augmentation method that incrementally stitches together short trajectory segments, systematically generating diverse and extended trajectories. SCoTS first learns a temporal distance-preserving latent representation that captures the underlying temporal structure of the environment, then iteratively stitches trajectory segments guided by directional exploration and novelty to effectively cover and expand this latent space. We demonstrate that SCoTS significantly improves the performance and generalization capabilities of diffusion planners on offline goal-conditioned benchmarks requiring stitching and long-horizon reasoning. Furthermore, augmented trajectories generated by SCoTS significantly improve the performance of widely used offline goal-conditioned RL algorithms across diverse environments.
Authors: Goksenin Yuksel, Marcel van Gerven, Kiki van der Heijden
Abstract: Although audio foundations models have seen great progress on a wide variety of tasks, their application in real-world acoustic environments with reverberation and noise has been less successful. Moreover, as audio foundation models are typically trained on dry, single-channel audio clips, the inherent spatial nature of real-world sound scenes is overlooked and tasks involving sound localization ruled out. To address these limitations, we propose GRAM: a General-purpose Real-world Audio Model utilizing a multi-channel masked auto-encoder approach to efficiently learn spatial audio representations from high-quality simulated real-world scenes. To evaluate the performance of GRAM and other audio foundation models in real-world sound scenes, we release Nat-HEAR: A naturalistic version of the HEAR benchmark suite comprising a simulated real-world version, as well as two new sound localization tasks. We show that the performance of GRAM surpasses all state-of-the-art self-supervised audio foundation models and speech models on both HEAR and Nat-HEAR, while using only a fraction of the training data. GRAM also showcases state-of-the-art localization performance, surpassing even supervised sound localization approaches, and can be flexibly applied either to a two-channel, binaural sound format or a four-channel, Ambisonics format. Validating GRAM's performance on real-world sound recordings demonstrates robust transfer to real-world scenes. Taken together, GRAM presents a significant advancement towards robust, spatial audio foundation models for real-world applications.
Authors: Wei Huang, Hanchen Wang, Dong Wen, Shaozhen Ma, Wenjie Zhang, Xuemin Lin
Abstract: Graph Edit Distance (GED) is a fundamental graph similarity metric widely used in various applications. However, computing GED is an NP-hard problem. Recent state-of-the-art hybrid GED solver has shown promising performance by formulating GED as a bipartite graph matching problem, then leveraging a generative diffusion model to predict node matching between two graphs, from which both the GED and its corresponding edit path can be extracted using a traditional algorithm. However, such methods typically rely heavily on ground-truth supervision, where the ground-truth node matchings are often costly to obtain in real-world scenarios. In this paper, we propose GEDRanker, a novel unsupervised GAN-based framework for GED computation. Specifically, GEDRanker consists of a matching-based GED solver and introduces an interpretable preference-aware discriminator. By leveraging preference signals over different node matchings derived from edit path lengths, the discriminator can guide the matching-based solver toward generating high-quality node matching without the need for ground-truth supervision. Extensive experiments on benchmark datasets demonstrate that our GEDRanker enables the matching-based GED solver to achieve near-optimal solution quality without any ground-truth supervision.
Authors: Abdelrahman Sayed Sayed, Pierre-Jean Meyer, Mohamed Ghazel
Abstract: A neural ordinary differential equation (neural ODE) is a machine learning model that is commonly described as a continuous-depth generalization of a residual network (ResNet) with a single residual block, or conversely, the ResNet can be seen as the Euler discretization of the neural ODE. These two models are therefore strongly related in a way that the behaviors of either model are considered to be an approximation of the behaviors of the other. In this work, we establish a more formal relationship between these two models by bounding the approximation error between two such related models. The obtained error bound then allows us to use one of the models as a verification proxy for the other, without running the verification tools twice: if the reachable output set expanded by the error bound satisfies a safety property on one of the models, this safety property is then guaranteed to be also satisfied on the other model. This feature is fully reversible, and the initial safety verification can be run indifferently on either of the two models. This novel approach is illustrated on a numerical example of a fixed-point attractor system modeled as a neural ODE.
Authors: Mengxi Xiao, Ben Liu, He Li, Jimin Huang, Qianqian Xie, Xiaofen Zong, Mang Ye, Min Peng
Abstract: The application of AI in psychiatric diagnosis faces significant challenges, including the subjective nature of mental health assessments, symptom overlap across disorders, and privacy constraints limiting data availability. To address these issues, we present MoodAngels, the first specialized multi-agent framework for mood disorder diagnosis. Our approach combines granular-scale analysis of clinical assessments with a structured verification process, enabling more accurate interpretation of complex psychiatric data. Complementing this framework, we introduce MoodSyn, an open-source dataset of 1,173 synthetic psychiatric cases that preserves clinical validity while ensuring patient privacy. Experimental results demonstrate that MoodAngels outperforms conventional methods, with our baseline agent achieving 12.3% higher accuracy than GPT-4o on real-world cases, and our full multi-agent system delivering further improvements. Evaluation in the MoodSyn dataset demonstrates exceptional fidelity, accurately reproducing both the core statistical patterns and complex relationships present in the original data while maintaining strong utility for machine learning applications. Together, these contributions provide both an advanced diagnostic tool and a critical research resource for computational psychiatry, bridging important gaps in AI-assisted mental health assessment.
Authors: Xinyan Zhao, Yi-Ching Tang, Akshita Singh, Victor J Cantu, KwanHo An, Junseok Lee, Adam E Stogsdill, Ibraheem M Hamdi, Ashwin Kumar Ramesh, Zhiqiang An, Xiaoqian Jiang, Yejin Kim
Abstract: We introduce AbBiBench (Antibody Binding Benchmarking), a benchmarking framework for antibody binding affinity maturation and design. Unlike previous strategies that evaluate antibodies in isolation, typically by comparing them to natural sequences with metrics such as amino acid recovery rate or structural RMSD, AbBiBench instead treats the antibody-antigen (Ab-Ag) complex as the fundamental unit. It evaluates an antibody design's binding potential by measuring how well a protein model scores the full Ab-Ag complex. We first curate, standardize, and share more than 184,500 experimental measurements of antibody mutants across 14 antibodies and 9 antigens-including influenza, lysozyme, HER2, VEGF, integrin, Ang2, and SARS-CoV-2-covering both heavy-chain and light-chain mutations. Using these datasets, we systematically compare 15 protein models including masked language models, autoregressive language models, inverse folding models, diffusion-based generative models, and geometric graph models by comparing the correlation between model likelihood and experimental affinity values. Additionally, to demonstrate AbBiBench's generative utility, we apply it to antibody F045-092 in order to introduce binding to influenza H1N1. We sample new antibody variants with the top-performing models, rank them by the structural integrity and biophysical properties of the Ab-Ag complex, and assess them with in vitro ELISA binding assays. Our findings show that structure-conditioned inverse folding models outperform others in both affinity correlation and generation tasks. Overall, AbBiBench provides a unified, biologically grounded evaluation framework to facilitate the development of more effective, function-aware antibody design models.
Authors: Luis Pinto
Abstract: Pretrained molecular encoders have become indispensable in computational chemistry for tasks such as property prediction and molecular generation. However, the standard practice of relying solely on final-layer embeddings for downstream tasks may discard valuable information. In this work, we first analyze the information flow in five diverse molecular encoders and find that intermediate layers retain more general-purpose features, whereas the final-layer specializes and compresses information. We then perform an empirical layer-wise evaluation across 22 property prediction tasks. We find that using frozen embeddings from optimal intermediate layers improves downstream performance by an average of 5.4%, up to 28.6%, compared to the final-layer. Furthermore, finetuning encoders truncated at intermediate depths achieves even greater average improvements of 8.5%, with increases as high as 40.8%, obtaining new state-of-the-art results on several benchmarks. These findings highlight the importance of exploring the full representational depth of molecular encoders to achieve substantial performance improvements and computational efficiency. The code will be made publicly available.
Authors: S. R. Eshwar, Gugan Thoppe, Ananyabrata Barua, Aditya Gopalan, Gal Dalal
Abstract: We introduce Reliable Policy Iteration (RPI) and Conservative RPI (CRPI), variants of Policy Iteration (PI) and Conservative PI (CPI), that retain tabular guarantees under function approximation. RPI uses a novel Bellman-constrained optimization for policy evaluation. We show that RPI restores the textbook \textit{monotonicity} of value estimates and that these estimates provably \textit{lower-bound} the true return; moreover, their limit partially satisfies the \textit{unprojected} Bellman equation. CRPI shares RPI's evaluation, but updates policies conservatively by maximizing a new performance-difference \textit{lower bound} that explicitly accounts for function-approximation-induced errors. CRPI inherits RPI's guarantees and, crucially, admits per-step improvement bounds. In initial simulations, RPI and CRPI outperform PI and its variants. Our work addresses a foundational gap in RL: popular algorithms such as TRPO and PPO derive from tabular CPI yet are deployed with function approximation, where CPI's guarantees often fail-leading to divergence, oscillations, or convergence to suboptimal policies. By restoring PI/CPI-style guarantees for \textit{arbitrary} function classes, RPI and CRPI provide a principled basis for next-generation RL.
Authors: Yuyang Zhou, Guang Cheng, Kang Du, Zihan Chen, Tian Qin, Yuyu Zhao
Abstract: The proliferation of UAVs has enabled a wide range of mission-critical applications and is becoming a cornerstone of low-altitude networks, supporting smart cities, emergency response, and more. However, the open wireless environment, dynamic topology, and resource constraints of UAVs expose low-altitude networks to severe DoS threats. Traditional defense approaches, which rely on fixed configurations or centralized decision-making, cannot effectively respond to the rapidly changing conditions in UAV swarm environments. To address these challenges, we propose a novel federated multi-agent deep reinforcement learning (FMADRL)-driven moving target defense (MTD) framework for proactive DoS mitigation in low-altitude networks. Specifically, we design lightweight and coordinated MTD mechanisms, including leader switching, route mutation, and frequency hopping, to disrupt attacker efforts and enhance network resilience. The defense problem is formulated as a multi-agent partially observable Markov decision process, capturing the uncertain nature of UAV swarms under attack. Each UAV is equipped with a policy agent that autonomously selects MTD actions based on partial observations and local experiences. By employing a policy gradient-based algorithm, UAVs collaboratively optimize their policies via reward-weighted aggregation. Extensive simulations demonstrate that our approach significantly outperforms state-of-the-art baselines, achieving up to a 34.6% improvement in attack mitigation rate, a reduction in average recovery time of up to 94.6%, and decreases in energy consumption and defense cost by as much as 29.3% and 98.3%, respectively, under various DoS attack strategies. These results highlight the potential of intelligent, distributed defense mechanisms to protect low-altitude networks, paving the way for reliable and scalable low-altitude economy.
Authors: Nadezhda Chirkova, Tunde Oluwaseyi Ajayi, Seth Aycock, Zain Muhammad Mujahid, Vladana Perli\'c, Ekaterina Borisova, Markarit Vartampetian
Abstract: Prompting large language models (LLMs) to evaluate generated text, known as LLM-as-a-judge, has become a standard evaluation approach in natural language generation (NLG), but is primarily used as a quantitative tool, i.e. with numerical scores as main outputs. In this work, we propose LLM-as-a-qualitative-judge, an LLM-based evaluation approach with the main output being a structured report of common issue types in the NLG system outputs. Our approach is targeted at providing developers with meaningful insights on what improvements can be done to a given NLG system and consists of two main steps, namely open-ended per-instance issue analysis and clustering of the discovered issues using an intuitive cumulative algorithm. We also introduce a strategy for evaluating the proposed approach, coupled with ~300 annotations of issues in instances from 12 NLG datasets. Our results show that instance-specific issues output by LLM-as-a-qualitative-judge match those annotated by humans in 2/3 cases, and that LLM-as-a-qualitative-judge is capable of producing error type reports resembling the reports composed by human annotators. We also demonstrate in a case study how the use of LLM-as-a-qualitative-judge can substantially improve NLG systems performance. Our code and data are publicly available at https://github.com/tunde-ajayi/llm-as-a-qualitative-judge.
URLs: https://github.com/tunde-ajayi/llm-as-a-qualitative-judge.
Authors: Beomsik Cho, Jaehyung Kim
Abstract: Large Vision-Language Models (LVLMs) achieve strong performance across multimodal tasks by integrating visual perception with language understanding. However, how vision information contributes to the model's decoding process remains under-explored, as reflected in frequent hallucinations. Through a series of analyses, we found that (i) vision tokens provide meaningful visual information even when hallucinations occur, and (ii) their semantics are encoded in the textual space and become explicit under appropriate vocabulary constraints. Building on these observations, we propose ReVisiT, a simple training-free decoding method that references vision tokens to guide text generation. Our approach leverages the semantic information embedded within vision tokens by projecting them into the text token distribution. Specifically, ReVisiT dynamically selects the most relevant vision token at each decoding step via context-aware constrained divergence minimization, and using its constrained projection to refine the output distribution to better incorporate visual semantics. Across five benchmarks on recent LVLMs, ReVisiT consistently enhances visual grounding with minimal computational overhead, and achieves competitive or superior results to state-of-the-art decoding baselines while reducing computational cost by up to $2\times$.
Authors: Christos Ziakas, Alessandra Russo
Abstract: Vision-Language Models (VLMs) show promise as zero-shot goal-conditioned value functions, but their frozen pre-trained representations limit generalization and temporal reasoning. We introduce VITA, a zero-shot value function learning method that enhances both capabilities via test-time adaptation. At inference, a lightweight adaptation module is updated via a gradient step on a meta-learned self-supervised loss, such that each test-time update improves value estimation. By updating sequentially over a trajectory, VITA encodes history into its parameters, addressing the temporal reasoning limitations. To mitigate shortcut learning, we propose a dissimilarity-based sampling strategy that selects semantically diverse segments of the trajectory during training. In real-world robotic manipulation tasks, VITA generalizes from a single training environment to diverse out-of-distribution tasks, environments, and embodiments, outperforming the state-of-the-art zero-shot method using autoregressive VLMs. Furthermore, we demonstrate that VITA's zero-shot value estimates can be utilized for reward shaping in offline reinforcement learning, resulting in multi-task policies on the Meta-World benchmark that exceed the performance of those trained with the simulation's fuzzy-logic dense rewards.
Authors: Moussa Koulako Bala Doumbouya, Dan Jurafsky, Christopher D. Manning
Abstract: Work in psychology has highlighted that the geometric model of similarity standard in deep learning is not psychologically plausible because its metric properties such as symmetry do not align with human perception of similarity. In contrast, Tversky (1977) proposed an axiomatic theory of similarity with psychological plausibility based on a representation of objects as sets of features, and their similarity as a function of their common and distinctive features. This model of similarity has not been used in deep learning before, in part because of the challenge of incorporating discrete set operations. In this paper, we develop a differentiable parameterization of Tversky's similarity that is learnable through gradient descent, and derive basic neural network building blocks such as the Tversky projection layer, which unlike the linear projection layer can model non-linear functions such as XOR. Through experiments with image recognition and language modeling neural networks, we show that the Tversky projection layer is a beneficial replacement for the linear projection layer. For instance, on the NABirds image classification task, a frozen ResNet-50 adapted with a Tversky projection layer achieves a 24.7% relative accuracy improvement over the linear layer adapter baseline. With Tversky projection layers, GPT-2's perplexity on PTB decreases by 7.8%, and its parameter count by 34.8%. Finally, we propose a unified interpretation of both types of projection layers as computing similarities of input stimuli to learned prototypes for which we also propose a novel visualization technique highlighting the interpretability of Tversky projection layers. Our work offers a new paradigm for thinking about the similarity model implicit in modern deep learning, and designing neural networks that are interpretable under an established theory of psychological similarity.
Authors: Xiang Cheng, Chengyan Pan, Minjun Zhao, Deyang Li, Fangchao Liu, Xinyu Zhang, Xiao Zhang, Yong Liu
Abstract: In-Context Learning (ICL) is an essential emergent ability of Large Language Models (LLMs), and recent studies introduce Chain-of-Thought (CoT) to exemplars of ICL to enhance the reasoning capability, especially in mathematics tasks. However, given the continuous advancement of model capabilities, it remains unclear whether CoT exemplars still benefit recent, stronger models in such tasks. Through systematic experiments, we find that for recent strong models such as the Qwen2.5 series, adding traditional CoT exemplars does not improve reasoning performance compared to Zero-Shot CoT. Instead, their primary function is to align the output format with human expectations. We further investigate the effectiveness of enhanced CoT exemplars, constructed using answers from advanced models such as \texttt{Qwen2.5-Max} and \texttt{DeepSeek-R1}. Experimental results indicate that these enhanced exemplars still fail to improve the model's reasoning performance. Further analysis reveals that models tend to ignore the exemplars and focus primarily on the instructions, leading to no observable gain in reasoning ability. Overall, our findings highlight the limitations of the current ICL+CoT framework in mathematical reasoning, calling for a re-examination of the ICL paradigm and the definition of exemplars.
Authors: Jina Kim, Leeje Jang, Yao-Yi Chiang, Guanyu Wang, Michelle C. Pasco
Abstract: Traditionally, neighborhood studies have used interviews, surveys, and manual image annotation guided by detailed protocols to identify environmental characteristics, including physical disorder, decay, street safety, and sociocultural symbols, and to examine their impact on developmental and health outcomes. Although these methods yield rich insights, they are time-consuming and require intensive expert intervention. Recent technological advances, including vision language models (VLMs), have begun to automate parts of this process; however, existing efforts are often ad hoc and lack adaptability across research designs and geographic contexts. In this paper, we present StreetLens, a user-configurable human-centered workflow that integrates relevant social science expertise into a VLM for scalable neighborhood environmental assessments. StreetLens mimics the process of trained human coders by focusing the analysis on questions derived from established interview protocols, retrieving relevant street view imagery (SVI), and generating a wide spectrum of semantic annotations from objective features (e.g., the number of cars) to subjective perceptions (e.g., the sense of disorder in an image). By enabling researchers to define the VLM's role through domain-informed prompting, StreetLens places domain knowledge at the core of the analysis process. It also supports the integration of prior survey data to enhance robustness and expand the range of characteristics assessed in diverse settings. StreetLens represents a shift toward flexible and agentic AI systems that work closely with researchers to accelerate and scale neighborhood studies. StreetLens is publicly available at https://knowledge-computing.github.io/projects/streetlens.
URLs: https://knowledge-computing.github.io/projects/streetlens.
Authors: Wang Yu-Hang, Liu ying, Fang liang, Wang Xuelin, Junkang Guo, Shiwei Li, Lei Gao, Jian Liu, Wenfei Yin
Abstract: Adversarial Training (AT) is a cornerstone defense, but many variants overlook foundational feature representations by primarily focusing on stronger attack generation. We introduce Adversarial Evolution Training (AET), a simple yet powerful framework that strategically prepends an Empirical Risk Minimization (ERM) phase to conventional AT. We hypothesize this initial ERM phase cultivates a favorable feature manifold, enabling more efficient and effective robustness acquisition. Empirically, AET achieves comparable or superior robustness more rapidly, improves clean accuracy, and cuts training costs by 8-25\%. Its effectiveness is shown across multiple datasets, architectures, and when augmenting established AT methods. Our findings underscore the impact of feature pre-conditioning via standard training for developing more efficient, principled robust defenses. Code is available in the supplementary material.
Authors: Zhenglin Lai, Mengyao Liao, Bingzhe Wu, Dong Xu, Zebin Zhao, Zhihang Yuan, Chao Fan, Jianqiang Li
Abstract: Large language models with Mixture-of-Experts (MoE) architectures achieve efficiency and scalability, yet their routing mechanisms introduce safety alignment challenges insufficiently addressed by techniques developed for dense models. In this work, the MoE-specific safety risk of positional vulnerability-that safety-aligned behaviors rely on specific expert modules-is formalized and systematically analyzed. An analytical framework, SAFEx, is presented to robustly identify, characterize, and validate safety-critical experts via a stability-based expert selection procedure, and to decompose them into two functional groups: the Harmful Content Detection Group (HCDG), which specializes in identifying and recognizing harmful content within user inputs, and the Harmful Response Control Group (HRCG), which specializes in controlling and enforcing model behaviors to generate appropriate safety responses. Expert-level interventions are conducted to probe causality and to test mitigation. Targeted masking of SAFEx-selected experts reveals that safety behavior is highly concentrated. On Qwen3-30B-A3B, configured with 48 MoE-FFN layers and 128 experts per layer under top-8 routing (48x128=6,144 experts in total), disabling 12 selected experts reduces the refusal rate by 22%. In addition, lightweight adaptation is performed using LoRA under three configurations-the HRCG, the union of HCDG and HRCG, and all experts-and the resulting updates are composed through negative weight merging targeted at the HRCG, leading to improved refusal under adversarial prompts without full-model retraining. These results establish positional vulnerability as a distinct MoE-specific safety challenge and provide a practical, compute-efficient pathway for expert-level safety interventions within routed architectures.
Authors: Wei Liu, Kiran Bacsa, Loon Ching Tang, Eleni Chatzi
Abstract: Understanding and modeling nonlinear dynamical systems is a fundamental challenge across science and engineering. Deep learning has shown remarkable potential for capturing complex system behavior, yet achieving models that are both accurate and physically interpretable remains difficult. To address this, we propose Structured Kolmogorov-Arnold Neural ODEs (SKANODEs), a framework that integrates structured state-space modeling with Kolmogorov-Arnold Networks (KANs). Within a Neural ODE architecture, SKANODE employs a fully trainable KAN as a universal function approximator to perform virtual sensing, recovering latent states that correspond to interpretable physical quantities such as displacements and velocities. Leveraging KAN's symbolic regression capability, SKANODE then extracts compact, interpretable expressions for the system's governing dynamics. Extensive experiments on simulated and real-world systems demonstrate that SKANODE achieves superior predictive accuracy, discovers physics-consistent dynamics, and reveals complex nonlinear behavior. Notably, it identifies hysteretic behavior in an F-16 aircraft and recovers a concise symbolic equation describing this phenomenon. SKANODE thus enables interpretable, data-driven discovery of physically grounded models for complex nonlinear dynamical systems.
Authors: Kin Kwan Leung, Rasa Hosseinzadeh, Gabriel Loaiza-Ganem
Abstract: The manifold hypothesis asserts that data of interest in high-dimensional ambient spaces, such as image data, lies on unknown low-dimensional submanifolds. Diffusion models (DMs) -- which operate by convolving data with progressively larger amounts of Gaussian noise and then learning to revert this process -- have risen to prominence as the most performant generative models, and are known to be able to learn distributions with low-dimensional support. For a given datum in one of these submanifolds, we should thus intuitively expect DMs to have implicitly learned its corresponding local intrinsic dimension (LID), i.e. the dimension of the submanifold it belongs to. Kamkari et al. (2024b) recently showed that this is indeed the case by linking this LID to the rate of change of the log marginal densities of the DM with respect to the amount of added noise, resulting in an LID estimator known as FLIPD. LID estimators such as FLIPD have a plethora of uses, among others they quantify the complexity of a given datum, and can be used to detect outliers, adversarial examples and AI-generated text. FLIPD achieves state-of-the-art performance at LID estimation, yet its theoretical underpinnings are incomplete since Kamkari et al. (2024b) only proved its correctness under the highly unrealistic assumption of affine submanifolds. In this work we bridge this gap by formally proving the correctness of FLIPD under realistic assumptions. Additionally, we show that an analogous result holds when Gaussian convolutions are replaced with uniform ones, and discuss the relevance of this result.
Authors: Jiaxi Zhuang, Kangning Li, Jue Hou, Mingjun Xu, Zhifeng Gao, Hengxing Cai
Abstract: Extracting molecular structure-activity relationships (SARs) from scientific literature and patents is essential for drug discovery and materials research. However, this task remains challenging due to heterogeneous document formats and limitations of existing methods. Specifically, rule-based approaches relying on rigid templates fail to generalize across diverse document layouts, while general-purpose multimodal large language models (MLLMs) lack sufficient accuracy and reliability for specialized tasks, such as layout detection and optical chemical structure recognition (OCSR). To address these challenges, we introduce DocSAR-200, a rigorously annotated benchmark of 200 scientific documents designed specifically for evaluating SAR extraction methods. Additionally, we propose Doc2SAR, a novel synergistic framework that integrates domain-specific tools with MLLMs enhanced via supervised fine-tuning (SFT). Extensive experiments demonstrate that Doc2SAR achieves state-of-the-art performance across various document types, significantly outperforming leading end-to-end baselines. Specifically, Doc2SAR attains an overall Table Recall of 80.78% on DocSAR-200, exceeding end2end GPT-4o by 51.48%. Furthermore, Doc2SAR demonstrates practical usability through efficient inference and is accompanied by a web app.
Authors: Hao Liu, Yu Hu, Rakiba Rayhana, Ling Bai, Zheng Liu
Abstract: Bed-related falls remain a major source of injury in hospitals and long-term care facilities, yet many commercial alarms trigger only after a patient has already left the bed. We show that early bed-exit intent can be predicted using only one low-cost load cell mounted under a bed leg. The resulting load signals are first converted into a compact set of complementary images: an RGB line plot that preserves raw waveforms and three texture maps-recurrence plot, Markov transition field, and Gramian angular field-that expose higher-order dynamics. We introduce ViFusionTST, a dual-stream Swin Transformer that processes the line plot and texture maps in parallel and fuses them through cross-attention to learn data-driven modality weights. To provide a realistic benchmark, we collected six months of continuous data from 95 beds in a long-term-care facility. On this real-world dataset ViFusionTST reaches an accuracy of 0.885 and an F1 score of 0.794, surpassing recent 1D and 2D time-series baselines across F1, recall, accuracy, and AUPRC. The results demonstrate that image-based fusion of load-sensor signals for time series classification is a practical and effective solution for real-time, privacy-preserving fall prevention.
Authors: Xufei Lv, Kehai Chen, Haoyuan Sun, Xuefeng Bai, Min Zhang, Houde Liu, Kehai Chen
Abstract: Alignment of large language models (LLMs) with human values has recently garnered significant attention, with prominent examples including the canonical yet costly Reinforcement Learning from Human Feedback (RLHF) and the simple Direct Preference Optimization (DPO). In this work, we demonstrate that both RLHF and DPO can be interpreted from the perspective of mutual information (MI) maximization, uncovering a profound connection to contrastive learning. Within this framework, both RLHF and DPO can be interpreted as methods that performing contrastive learning based on the positive and negative samples derived from base model, leveraging the Donsker-Varadhan (DV) lower bound on MI (equivalently, the MINE estimator). Such paradigm further illuminates why RLHF may not intrinsically incentivize reasoning capacities in LLMs beyond what is already present in the base model. Building on the perspective, we replace the DV/MINE bound with the Jensen-Shannon (JS) MI estimator and propose the Mutual Information Optimization (MIO). Comprehensive theoretical analysis and extensive empirical evaluations demonstrate that MIO mitigates the late-stage decline in chosen-likelihood observed in DPO, achieving competitive or superior performance across various challenging reasoning and mathematical benchmarks.
Authors: Yifan Sun, Yushan Liang, Zhen Zhang, Jiaye Teng
Abstract: Self-improvement is among the most prominent techniques within the realm of large language models (LLM), aiming to enhance the LLM performance without relying on external data. Despite its significance, generally how LLM performances evolve during the self-improvement process remains underexplored. In this paper, we theoretically model the training dynamics of self-improvement via the concept of solver-verifier gap. This is inspired by the conjecture that the performance enhancement of self-improvement stems from the gap between LLM's solver capability and verifier capability. Based on the theoretical framework, we further show how to model the entire training trajectory. This framework allows quantifying the capability limit of self-improvement by fitting the theoretical model to the experiment results. We empirically validate the effectiveness of the theoretical framework on various LLMs and datasets. Beyond self-improvement, we extend our analysis to investigate how external data influences these dynamics within the framework. Notably, we find that under limited external data regimes, such external data can be utilized at any stage without significantly affecting final performances, which accords with the empirical observations.
Authors: Tatsuki Kawakami, Kazuki Egashira, Atsuyuki Miyai, Go Irie, Kiyoharu Aizawa
Abstract: In recent years, unlearning techniques, which are methods for inducing a model to "forget" previously learned information, have attracted attention as a way to address privacy and copyright concerns in large language models (LLMs) and large multimodal models (LMMs). While several unlearning benchmarks have been established for LLMs, a practical evaluation framework for unlearning in LMMs has been less explored. Specifically, existing unlearning benchmark for LMMs considers only scenarios in which the model is required to unlearn fine-tuned knowledge through a single unlearning operation. In this study, we introduce PULSE protocol for realistic unlearning scenarios for LMMs by introducing two critical perspectives: (i) Pre-trained knowledge Unlearning for analyzing the effect across different knowledge acquisition phases and (ii) Long-term Sustainability Evaluation to address sequential requests. We then evaluate existing unlearning methods along these dimensions. Our results reveal that, although some techniques can successfully unlearn knowledge acquired through fine-tuning, they struggle to eliminate information learned during pre-training. Moreover, methods that effectively unlearn a batch of target data in a single operation exhibit substantial performance degradation when the same data are split and unlearned sequentially.
Authors: Yoav Gelberg (Moe), Yam Eitan (Moe), Aviv Navon (Moe), Aviv Shamsian (Moe), Theo (Moe), Putterman, Michael Bronstein, Haggai Maron
Abstract: Gradients of neural networks encode valuable information for optimization, editing, and analysis of models. Therefore, practitioners often treat gradients as inputs to task-specific algorithms, e.g. for pruning or optimization. Recent works explore learning algorithms that operate directly on gradients but use architectures that are not specifically designed for gradient processing, limiting their applicability. In this paper, we present a principled approach for designing architectures that process gradients. Our approach is guided by three principles: (1) equivariant design that preserves neuron permutation symmetries, (2) processing sets of gradients across multiple data points to capture curvature information, and (3) efficient gradient representation through rank-1 decomposition. Based on these principles, we introduce GradMetaNet, a novel architecture for learning on gradients, constructed from simple equivariant blocks. We prove universality results for GradMetaNet, and show that previous approaches cannot approximate natural gradient-based functions that GradMetaNet can. We then demonstrate GradMetaNet's effectiveness on a diverse set of gradient-based tasks on MLPs and transformers, such as learned optimization, INR editing, and estimating loss landscape curvature.
Authors: Liman Wang, Hanyang Zhong, Tianyuan Wang, Shan Luo, Jihong Zhu
Abstract: Choosing appropriate fabrics is critical for meeting functional and quality demands in robotic textile manufacturing, apparel production, and smart retail. We propose MLLM-Fabric, a robotic framework leveraging multimodal large language models (MLLMs) for fabric sorting and selection. Built on a multimodal robotic platform, the system is trained through supervised fine-tuning and explanation-guided distillation to rank fabric properties. We also release a dataset of 220 diverse fabrics, each with RGB images and synchronized visuotactile and pressure data. Experiments show that our Fabric-Llama-90B consistently outperforms pretrained vision-language baselines in both attribute ranking and selection reliability. Code and dataset are publicly available at https://github.com/limanwang/MLLM-Fabric.
Authors: Guanhua Zhang, Ricardo Dominguez-Olmedo, Moritz Hardt
Abstract: Existing language model benchmarks provide contradictory model rankings, even for benchmarks that aim to capture similar skills. This dilemma of conflicting rankings hampers model selection, clouds model comparisons, and adds confusion to a growing ecosystem of competing models. In this paper, we take a different perspective on model comparison: instead of relying on out-of-the-box performance via direct evaluation, we compare model potential by providing each model with identical benchmark-specific fine-tuning before evaluation. We call this approach train-before-test. Our primary contribution is a comprehensive empirical evaluation of model potential across 24 benchmarks and 61 models. First, we demonstrate that model potential rankings obtained through train-before-test exhibit remarkable consistency across all benchmarks. Whereas traditional rankings demonstrate little external validity under direct evaluation, they enjoy a significant degree of external validity when applying train-before-test: model potential rankings transfer gracefully from one benchmark to another. Second, train-before-test restores the connection between perplexity and downstream task performance, lost under direct evaluation. Remarkably, even pre-finetuning perplexity of a base model predicts post-finetuning downstream performance, suggesting that ranking consistency reflects inherent model potential rather than fine-tuning artifacts. Finally, train-before-test reduces the model-score matrix to essentially rank one, indicating that model potential is dominated by one latent factor, uncovered by train-before-test. Our work supports the recommendation to make train-before-test a default component of LLM benchmarking.
Authors: Sifan Wang, Shyam Sankaran, Xiantao Fan, Panos Stinis, Paris Perdikaris
Abstract: Turbulent fluid flows are among the most computationally demanding problems in science, requiring enormous computational resources that become prohibitive at high flow speeds. Physics-informed neural networks (PINNs) represent a radically different approach that trains neural networks directly from physical equations rather than data, offering the potential for continuous, mesh-free solutions. Here we show that appropriately designed PINNs can successfully simulate fully turbulent flows in both two and three dimensions, directly learning solutions to the fundamental fluid equations without traditional computational grids or training data. Our approach combines several algorithmic innovations including adaptive network architectures, causal training, and advanced optimization methods to overcome the inherent challenges of learning chaotic dynamics. Through rigorous validation on challenging turbulence problems, we demonstrate that PINNs accurately reproduce key flow statistics including energy spectra, kinetic energy, enstrophy, and Reynolds stresses. Our results demonstrate that neural equation solvers can handle complex chaotic systems, opening new possibilities for continuous turbulence modeling that transcends traditional computational limitations.
Authors: Chenyu Wang, Cai Zhou, Sharut Gupta, Zongyu Lin, Stefanie Jegelka, Stephen Bates, Tommi Jaakkola
Abstract: Diffusion models can be improved with additional guidance towards more effective representations of input. Indeed, prior empirical work has already shown that aligning internal representations of the diffusion model with those of pre-trained models improves generation quality. In this paper, we present a systematic framework for incorporating representation guidance into diffusion models. We provide alternative decompositions of denoising models along with their associated training criteria, where the decompositions determine when and how the auxiliary representations are incorporated. Guided by our theoretical insights, we introduce two new strategies for enhancing representation alignment in diffusion models. First, we pair examples with target representations either derived from themselves or arisen from different synthetic modalities, and subsequently learn a joint model over the multimodal pairs. Second, we design an optimal training curriculum that balances representation learning and data generation. Our experiments across image, protein sequence, and molecule generation tasks demonstrate superior performance as well as accelerated training. In particular, on the class-conditional ImageNet $256\times 256$ benchmark, our guidance results in $23.3$ times faster training than the original SiT-XL as well as four times speedup over the state-of-the-art method REPA. The code is available at https://github.com/ChenyuWang-Monica/REED.
Authors: Anita Kriz, Elizabeth Laura Janes, Xing Shen, Tal Arbel
Abstract: Multimodal large language models (MLLMs) hold considerable promise for applications in healthcare. However, their deployment in safety-critical settings is hindered by two key limitations: (i) sensitivity to prompt design, and (ii) a tendency to generate incorrect responses with high confidence. As clinicians may rely on a model's stated confidence to gauge the reliability of its predictions, it is especially important that when a model expresses high confidence, it is also highly accurate. We introduce Prompt4Trust, the first reinforcement learning (RL) framework for prompt augmentation targeting confidence calibration in MLLMs. A lightweight LLM is trained to produce context-aware auxiliary prompts that guide a downstream task MLLM to generate responses in which the expressed confidence more accurately reflects predictive accuracy. Unlike conventional calibration techniques, Prompt4Trust specifically prioritizes aspects of calibration most critical for safe and trustworthy clinical decision-making. Beyond improvements driven by this clinically motivated calibration objective, our proposed method also improves task accuracy, achieving state-of-the-art medical visual question answering (VQA) performance on the PMC-VQA benchmark, which is composed of multiple-choice questions spanning diverse medical imaging modalities. Moreover, our framework trained with a small downstream task MLLM showed promising zero-shot generalization to larger MLLMs in our experiments, suggesting the potential for scalable calibration without the associated computational costs. This work demonstrates the potential of automated yet human-aligned prompt engineering for improving the the trustworthiness of MLLMs in safety critical settings. Our codebase can be found at https://github.com/xingbpshen/prompt4trust.
Authors: Fei Zhao, Chonggang Lu, Yue Wang, Zheyong Xie, Ziyan Liu, Haofu Qian, JianZhao Huang, Fangcheng Shi, Zijie Meng, Hongcheng Guo, Mingqian He, Xinze Lyu, Yiming Lu, Ziyang Xiang, Zheyu Ye, Chengqiang Lu, Zhe Xu, Yi Wu, Yao Hu, Yan Gao, Jun Fan, Xiaolong Jiang, Weiting Liu, Boyang Wang, Shaosheng Cao
Abstract: As a primary medium for modern information dissemination, social networking services (SNS) have experienced rapid growth, which has proposed significant challenges for platform content management and interaction quality improvement. Recently, the development of large language models (LLMs) has offered potential solutions but existing studies focus on isolated tasks, which not only encounter diminishing benefit from the data scaling within individual scenarios but also fail to flexibly adapt to diverse real-world context. To address these challenges, we introduce RedOne, a domain-specific LLM designed to break the performance bottleneck of single-task baselines and establish a comprehensive foundation for the SNS. RedOne was developed through a three-stage training strategy consisting of continue pretraining, supervised fine-tuning, and preference optimization, using a large-scale real-world dataset. Through extensive experiments, RedOne maintains strong general capabilities, and achieves an average improvement up to 14.02% across 8 major SNS tasks and 7.56% in SNS bilingual evaluation benchmark, compared with base models. Furthermore, through online testing, RedOne reduced the exposure rate in harmful content detection by 11.23% and improved the click page rate in post-view search by 14.95% compared with single-tasks finetuned baseline models. These results establish RedOne as a robust domain-specific LLM for SNS, demonstrating excellent generalization across various tasks and promising applicability in real-world scenarios.
Authors: Saadat Behzadi, Danial Sharifrazi, Bita Mesbahzadeh, Javad Hassannataj Joloudari, Roohallah Alizadehsani
Abstract: Objectives: Timely and accurate detection of colorectal polyps plays a crucial role in diagnosing and preventing colorectal cancer, a major cause of mortality worldwide. This study introduces a new, lightweight, and efficient framework for polyp detection that combines the Local Outlier Factor (LOF) algorithm for filtering noisy data with the YOLO-v11n deep learning model. Study design: An experimental study leveraging deep learning and outlier removal techniques across multiple public datasets. Methods: The proposed approach was tested on five diverse and publicly available datasets: CVC-ColonDB, CVC-ClinicDB, Kvasir-SEG, ETIS, and EndoScene. Since these datasets originally lacked bounding box annotations, we converted their segmentation masks into suitable detection labels. To enhance the robustness and generalizability of our model, we apply 5-fold cross-validation and remove anomalous samples using the LOF method configured with 30 neighbors and a contamination ratio of 5%. Cleaned data are then fed into YOLO-v11n, a fast and resource-efficient object detection architecture optimized for real-time applications. We train the model using a combination of modern augmentation strategies to improve detection accuracy under diverse conditions. Results: Our approach significantly improves polyp localization performance, achieving a precision of 95.83%, recall of 91.85%, F1-score of 93.48%, mAP@0.5 of 96.48%, and mAP@0.5:0.95 of 77.75%. Compared to previous YOLO-based methods, our model demonstrates enhanced accuracy and efficiency. Conclusions: These results suggest that the proposed method is well-suited for real-time colonoscopy support in clinical settings. Overall, the study underscores how crucial data preprocessing and model efficiency are when designing effective AI systems for medical imaging.
Authors: Steven Dillmann, Juan Rafael Mart\'inez-Galarza
Abstract: Event time series are sequences of discrete events occurring at irregular time intervals, each associated with a domain-specific observational modality. They are common in domains such as high-energy astrophysics, computational social science, cybersecurity, finance, healthcare, neuroscience, and seismology. Their unstructured and irregular structure poses significant challenges for extracting meaningful patterns and identifying salient phenomena using conventional techniques. We propose novel two- and three-dimensional tensor representations for event time series, coupled with sparse autoencoders that learn physically meaningful latent representations. These embeddings support a variety of downstream tasks, including anomaly detection, similarity-based retrieval, semantic clustering, and unsupervised classification. We demonstrate our approach on a real-world dataset from X-ray astronomy, showing that these representations successfully capture temporal and spectral signatures and isolate diverse classes of X-ray transients. Our framework offers a flexible, scalable, and generalizable solution for analyzing complex, irregular event time series across scientific and industrial domains.
Authors: Junhong Min, Youngpil Jeon, Jimin Kim, Minyong Choi
Abstract: The pursuit of a generalizable stereo matching model, capable of performing well across varying resolutions and disparity ranges without dataset-specific fine-tuning, has revealed a fundamental trade-off. Iterative local search methods achieve high scores on constrained benchmarks, but their core mechanism inherently limits the global consistency required for true generalization. However, global matching architectures, while theoretically more robust, have historically been rendered infeasible by prohibitive computational and memory costs. We resolve this dilemma with {S\textsuperscript{2}M\textsuperscript{2}}: a global matching architecture that achieves state-of-the-art accuracy and high efficiency without relying on cost volume filtering or deep refinement stacks. Our design integrates a multi-resolution transformer for robust long-range correspondence, trained with a novel loss function that concentrates probability on feasible matches. This approach enables a more robust joint estimation of disparity, occlusion, and confidence. {S\textsuperscript{2}M\textsuperscript{2}} establishes a new state of the art on Middlebury v3 and ETH3D benchmarks, significantly outperforming prior methods in most metrics while reconstructing high-quality details with competitive efficiency.
Authors: Ziqiao Yu, Pengfei Sun, Dan F. M. Goodman
Abstract: We investigate the extent to which Spiking Neural Networks (SNNs) trained with Surrogate Gradient Descent (Surrogate GD), with and without delay learning, can learn from precise spike timing beyond firing rates. We first design synthetic tasks isolating intra-neuron inter-spike intervals and cross-neuron synchrony under matched spike counts. On more complex spike-based speech recognition datasets (Spiking Heidelberg Digits (SHD) and Spiking Speech Commands (SSC), we construct variants where spike count information is eliminated and only timing information remains, and show that Surrogate GD-trained SNNs are able to perform significantly above chance whereas purely rate-based models perform at chance level. We further evaluate robustness under biologically inspired perturbations -- including Gaussian jitter per spike or per-neuron, and spike deletion -- revealing consistent but perturbation-specific degradation. Networks show a sharp performance drop when spike sequences are reversed in time, with a larger drop in performance from SNNs trained with delays, indicating that these networks are more human-like in terms of behaviour. To facilitate further studies of temporal coding, we have released our modified SHD and SSC datasets.
Authors: Ondrej Bohdal, Mete Ozay, Jijoong Moon, Kyeng-Hun Lee, Hyeonmok Ko, Umberto Michieli
Abstract: Adapter parameters provide a mechanism to modify the behavior of machine learning models and have gained significant popularity in the context of large language models (LLMs) and generative AI. These parameters can be merged to support multiple tasks via a process known as task merging. However, prior work on merging in LLMs, particularly in natural language processing, has been limited to scenarios where each test example addresses only a single task. In this paper, we focus on on-device settings and study the problem of text-based compositional multi-tasking, where each test example involves the simultaneous execution of multiple tasks. For instance, generating a translated summary of a long text requires solving both translation and summarization tasks concurrently. To facilitate research in this setting, we propose a benchmark comprising four practically relevant compositional tasks. We also present an efficient method (Learnable Calibration) tailored for on-device applications, where computational resources are limited, emphasizing the need for solutions that are both resource-efficient and high-performing. Our contributions lay the groundwork for advancing the capabilities of LLMs in real-world multi-tasking scenarios, expanding their applicability to complex, resource-constrained use cases.
Authors: Santosh Patapati, Trisanth Srinivasan
Abstract: Autonomous vehicles must react in milliseconds while reasoning about road geometry and traffic intent to navigate complex situations. We introduce NovaDrive, a single-branch vision-language architecture that processes front-camera images, HD-map tiles, LiDAR depth, and textual waypoints in a single branch. A lightweight, two-stage cross-attention block first aligns waypoint tokens with the HD map, then refines attention over fine-grained image and depth patches. Coupled with a novel smoothness loss that discourages abrupt steering and speed changes, this design eliminates the need for recurrent memory. We fine-tune the top 15 layers of an 11B LLaMA-3.2 vision-language backbone, enabling real-time inference. On the nuScenes / Waymo subset of the MD-NEX Outdoor benchmark, NovaDrive raises success rate to 84% (+4%), boosts path-efficiency (SPL) to 0.66 (+0.11), and reduces collision frequency from 2.6% to 1.2% (-1.4%) relative to the previous state-of-the-art. Our ablations confirm that waypoint tokens, partial VLM fine-tuning, and the cross-attention fusion each contribute the most to these gains. Beyond safety, NovaDrive's shorter routes (resulting from the novel smoothness loss) translate to lower fuel or battery usage, pointing toward leaner, more easily updated driving stacks. NovaDrive can be extended to other embodied-AI domains as well.
Authors: Santosh Patapati, Trisanth Srinivasan, Murari Ambati
Abstract: Autonomous cars need geometric accuracy and semantic understanding to navigate complex environments, yet most stacks handle them separately. We present XYZ-Drive, a single vision-language model that reads a front-camera frame, a 25m $\times$ 25m overhead map, and the next waypoint, then outputs steering and speed. A lightweight goal-centered cross-attention layer lets waypoint tokens highlight relevant image and map patches, supporting both action and textual explanations, before the fused tokens enter a partially fine-tuned LLaMA-3.2 11B model. On the MD-NEX Outdoor-Driving benchmark XYZ-Drive attains 95% success and 0.80 Success weighted by Path Length (SPL), surpassing PhysNav-DG by 15%. and halving collisions, all while significantly improving efficiency by using only a single branch. Sixteen ablations explain the gains. Removing any modality (vision, waypoint, map) drops success by up to 11%, confirming their complementary roles and rich connections. Replacing goal-centered attention with simple concatenation cuts 3% in performance, showing query-based fusion injects map knowledge more effectively. Keeping the transformer frozen loses 5%, showing the importance of fine-tuning when applying VLMs for specific tasks such as autonomous driving. Coarsening map resolution from 10 cm to 40 cm blurs lane edges and raises crash rate. Overall, these results demonstrate that early, token-level fusion of intent and map layout enables accurate, transparent, real-time driving.
Authors: Sebastian Wind, Jeta Sopa, Daniel Truhn, Mahshad Lotfinia, Tri-Thien Nguyen, Keno Bressem, Lisa Adams, Mirabela Rusu, Harald K\"ostler, Gerhard Wellein, Andreas Maier, Soroosh Tayebi Arasteh
Abstract: Clinical decision-making in radiology increasingly benefits from artificial intelligence (AI), particularly through large language models (LLMs). However, traditional retrieval-augmented generation (RAG) systems for radiology question answering (QA) typically rely on single-step retrieval, limiting their ability to handle complex clinical reasoning tasks. Here we propose radiology Retrieval and Reasoning (RaR), a multi-step retrieval and reasoning framework designed to improve diagnostic accuracy, factual consistency, and clinical reliability of LLMs in radiology question answering. We evaluated 25 LLMs spanning diverse architectures, parameter scales (0.5B to >670B), and training paradigms (general-purpose, reasoning-optimized, clinically fine-tuned), using 104 expert-curated radiology questions from previously established RSNA-RadioQA and ExtendedQA datasets. To assess generalizability, we additionally tested on an unseen internal dataset of 65 real-world radiology board examination questions. RaR significantly improved mean diagnostic accuracy over zero-shot prompting and conventional online RAG. The greatest gains occurred in small-scale models, while very large models (>200B parameters) demonstrated minimal changes (<2% improvement). Additionally, RaR retrieval reduced hallucinations (mean 9.4%) and retrieved clinically relevant context in 46% of cases, substantially aiding factual grounding. Even clinically fine-tuned models showed gains from RaR (e.g., MedGemma-27B), indicating that retrieval remains beneficial despite embedded domain knowledge. These results highlight the potential of RaR to enhance factuality and diagnostic accuracy in radiology QA, warranting future studies to validate their clinical utility. All datasets, code, and the full RaR framework are publicly available to support open research and clinical translation.
Authors: Advait Parulekar, Litu Rout, Karthikeyan Shanmugam, Sanjay Shakkottai
Abstract: We study the problem of posterior sampling in the context of score based generative models. We have a trained score network for a prior $p(x)$, a measurement model $p(y|x)$, and are tasked with sampling from the posterior $p(x|y)$. Prior work has shown this to be intractable in KL (in the worst case) under well-accepted computational hardness assumptions. Despite this, popular algorithms for tasks such as image super-resolution, stylization, and reconstruction enjoy empirical success. Rather than establishing distributional assumptions or restricted settings under which exact posterior sampling is tractable, we view this as a more general "tilting" problem of biasing a distribution towards a measurement. Under minimal assumptions, we show that one can tractably sample from a distribution that is simultaneously close to the posterior of a noised prior in KL divergence and the true posterior in Fisher divergence. Intuitively, this combination ensures that the resulting sample is consistent with both the measurement and the prior. To the best of our knowledge these are the first formal results for (approximate) posterior sampling in polynomial time.
Authors: Haonan Ge, Yiwei Wang, Ming-Hsuan Yang, Yujun Cai
Abstract: Large Vision-Language Models (LVLMs) have shown strong performance across multimodal tasks. However, they often produce hallucinations -- text that is inconsistent with visual input, due to the limited ability to verify information in different regions of the image. To address this, we propose Multi-Region Fusion Decoding (MRFD), a training-free decoding method that improves factual grounding by modeling inter-region consistency. MRFD identifies salient regions using cross-attention, generates initial responses for each, and computes reliability weights based on Jensen-Shannon Divergence (JSD) among the responses. These weights guide a consistency-aware fusion of per-region predictions, using region-aware prompts inspired by Chain-of-Thought reasoning. Experiments across multiple LVLMs and benchmarks show that MRFD significantly reduces hallucinations and improves response factuality without requiring model updates.
Authors: Keke Gai, Dongjue Wang, Jing Yu, Liehuang Zhu, Qi Wu
Abstract: Defending backdoor attacks in Federated Learning (FL) under heterogeneous client data distributions encounters limitations balancing effectiveness and privacy-preserving, while most existing methods highly rely on the assumption of homogeneous client data distributions or the availability of a clean serve dataset. In this paper, we propose an FL backdoor defense framework, named CLIP-Fed, that utilizes the zero-shot learning capabilities of vision-language pre-training models. Our scheme overcomes the limitations of Non-IID imposed on defense effectiveness by integrating pre-aggregation and post-aggregation defense strategies. CLIP-Fed aligns the knowledge of the global model and CLIP on the augmented dataset using prototype contrastive loss and Kullback-Leibler divergence, so that class prototype deviations caused by backdoor samples are ensured and the correlation between trigger patterns and target labels is eliminated. In order to balance privacy-preserving and coverage enhancement of the dataset against diverse triggers, we further construct and augment the server dataset via using the multimodal large language model and frequency analysis without any client samples. Extensive experiments on representative datasets evidence the effectiveness of CLIP-Fed. Comparing to other existing methods, CLIP-Fed achieves an average reduction in Attack Success Rate, {\em i.e.}, 2.03\% on CIFAR-10 and 1.35\% on CIFAR-10-LT, while improving average Main Task Accuracy by 7.92\% and 0.48\%, respectively. Our codes are available at https://anonymous.4open.science/r/CLIP-Fed.
Authors: Fei Lei, Yibo Yang, Wenxiu Sun, Dahua Lin
Abstract: Large Language Models (LLMs) are evolving from text generators into reasoning agents. This transition makes their ability to use external tools a critical capability. However, evaluating this skill presents a significant challenge. Existing benchmarks are often limited by their reliance on synthetic tools and severely constrained action spaces. To address these limitations, we introduce MCPVerse, an expansive, real-world benchmark for evaluating agentic tool use. MCPVerse integrates more than 550 real-world, executable tools to create an unprecedented action space exceeding 140k tokens, and employs outcome-based evaluation with real-time ground truth for time-sensitive tasks. We benchmarked the state-of-the-art LLMs across three modes (Oracle, Standard, and Max-Scale), revealing that while most models suffer performance degradation when confronted with larger tool sets, the agentic models, such as Claude-4-Sonnet, can effectively leverage expanded exploration spaces to improve accuracy. This finding not only exposes the limitations of state-of-the-art models in complex, real-world scenarios but also establishes MCPVerse as a critical benchmark for measuring and advancing agentic tool use capabilities.
Authors: Ruian Tie, Xiaohui Zhong, Zhengyu Shi, Hao Li, Bin Chen, Jun Liu, Wu Libo
Abstract: Climate change is amplifying extreme events, posing escalating risks to biodiversity, human health, and food security. GCMs are essential for projecting future climate, yet their coarse resolution and high computational costs constrain their ability to represent extremes. Here, we introduce FuXi-CMIPAlign, a generative deep learning framework for downscaling CMIP outputs. The model integrates Flow Matching for generative modeling with domain adaptation via MMD loss to align feature distributions between training data and inference data, thereby mitigating input discrepancies and improving accuracy, stability, and generalization across emission scenarios. FuXi-CMIPAlign performs spatial, temporal, and multivariate downscaling, enabling more realistic simulation of compound extremes such as TCs.
Authors: Marco S. Tayar, Lucas K. de Oliveira, Felipe Andrade G. Tommaselli, Juliano D. Negri, Thiago H. Segreto, Ricardo V. Godoy, Marcelo Becker
Abstract: Autonomous UAV inspection of confined industrial infrastructure, such as ventilation ducts, demands robust navigation policies where collisions are unacceptable. While Deep Reinforcement Learning (DRL) offers a powerful paradigm for developing such policies, it presents a critical trade-off between on-policy and off-policy algorithms. Off-policy methods promise high sample efficiency, a vital trait for minimizing costly and unsafe real-world fine-tuning. In contrast, on-policy methods often exhibit greater training stability, which is essential for reliable convergence in hazard-dense environments. This paper directly investigates this trade-off by comparing a leading on-policy algorithm, Proximal Policy Optimization (PPO), against an off-policy counterpart, Soft Actor-Critic (SAC), for precision flight in procedurally generated ducts within a high-fidelity simulator. Our results show that PPO consistently learned a stable, collision-free policy that completed the entire course. In contrast, SAC failed to find a complete solution, converging to a suboptimal policy that navigated only the initial segments before failure. This work provides evidence that for high-precision, safety-critical navigation tasks, the reliable convergence of a well-established on-policy method can be more decisive than the nominal sample efficiency of an off-policy algorithm.
Authors: Dilermando Almeida, Guilherme Lazzarini, Juliano Negri, Thiago H. Segreto, Ricardo V. Godoy, Marcelo Becker
Abstract: This paper presents a deep learning framework designed to enhance the grasping capabilities of quadrupeds equipped with arms, with a focus on improving precision and adaptability. Our approach centers on a sim-to-real methodology that minimizes reliance on physical data collection. We developed a pipeline within the Genesis simulation environment to generate a synthetic dataset of grasp attempts on common objects. By simulating thousands of interactions from various perspectives, we created pixel-wise annotated grasp-quality maps to serve as the ground truth for our model. This dataset was used to train a custom CNN with a U-Net-like architecture that processes multi-modal input from an onboard RGB and depth cameras, including RGB images, depth maps, segmentation masks, and surface normal maps. The trained model outputs a grasp-quality heatmap to identify the optimal grasp point. We validated the complete framework on a four-legged robot. The system successfully executed a full loco-manipulation task: autonomously navigating to a target object, perceiving it with its sensors, predicting the optimal grasp pose using our model, and performing a precise grasp. This work proves that leveraging simulated training with advanced sensing offers a scalable and effective solution for object handling.
Authors: Pedro Antonio Rabelo Saraiva, Enzo Ferreira de Souza, Joao Manoel Herrera Pinheiro, Thiago H. Segreto, Ricardo V. Godoy, Marcelo Becker
Abstract: This paper addresses the challenges of data scarcity and high acquisition costs in training robust object detection models for complex industrial environments, such as offshore oil platforms. Data collection in these hazardous settings often limits the development of autonomous inspection systems. To mitigate this issue, we propose a hybrid data synthesis pipeline that integrates procedural rendering and AI-driven video generation. The approach uses BlenderProc to produce photorealistic images with domain randomization and NVIDIA's Cosmos-Predict2 to generate physically consistent video sequences with temporal variation. A YOLO-based detector trained on a composite dataset, combining real and synthetic data, outperformed models trained solely on real images. A 1:1 ratio between real and synthetic samples achieved the highest accuracy. The results demonstrate that synthetic data generation is a viable, cost-effective, and safe strategy for developing reliable perception systems in safety-critical and resource-constrained industrial applications.
Authors: Xinglong Yang, Quan Feng, Zhongying Pan, Xiang Chen, Yu Tian, Wentong Li, Shuofei Qiao, Yuxia Geng, Xingyu Zhao, Sheng-Jun Huang
Abstract: The effectiveness of Multimodal Chain-of-Thought (MCoT) prompting is often limited by the use of randomly or manually selected examples. These examples fail to account for both model-specific knowledge distributions and the intrinsic complexity of the tasks, resulting in suboptimal and unstable model performance. To address this, we propose a novel framework inspired by the pedagogical principle of "tailored teaching with balanced difficulty". We reframe prompt selection as a prompt curriculum design problem: constructing a well ordered set of training examples that align with the model's current capabilities. Our approach integrates two complementary signals: (1) model-perceived difficulty, quantified through prediction disagreement in an active learning setup, capturing what the model itself finds challenging; and (2) intrinsic sample complexity, which measures the inherent difficulty of each question-image pair independently of any model. By jointly analyzing these signals, we develop a difficulty-balanced sampling strategy that ensures the selected prompt examples are diverse across both dimensions. Extensive experiments conducted on five challenging benchmarks and multiple popular Multimodal Large Language Models (MLLMs) demonstrate that our method yields substantial and consistent improvements and greatly reduces performance discrepancies caused by random sampling, providing a principled and robust approach for enhancing multimodal reasoning.
Authors: Chenghao Liu, Jiachen Zhang, Chengxuan Li, Zhimu Zhou, Shixin Wu, Songfang Huang, Huiling Duan
Abstract: Vision-Language-Action (VLA) models process visual inputs independently at each timestep, discarding valuable temporal information inherent in robotic manipulation tasks. This frame-by-frame processing makes models vulnerable to visual noise while ignoring the substantial coherence between consecutive frames in manipulation sequences. We propose Temporal Token Fusion (TTF), a training-free approach that intelligently integrates historical and current visual representations to enhance VLA inference quality. Our method employs dual-dimension detection combining efficient grayscale pixel difference analysis with attention-based semantic relevance assessment, enabling selective temporal token fusion through hard fusion strategies and keyframe anchoring to prevent error accumulation. Comprehensive experiments across LIBERO, SimplerEnv, and real robot tasks demonstrate consistent improvements: 4.0 percentage points average on LIBERO (72.4\% vs 68.4\% baseline), cross-environment validation on SimplerEnv (4.8\% relative improvement), and 8.7\% relative improvement on real robot tasks. Our approach proves model-agnostic, working across OpenVLA and VLA-Cache architectures. Notably, TTF reveals that selective Query matrix reuse in attention mechanisms enhances rather than compromises performance, suggesting promising directions for direct KQV matrix reuse strategies that achieve computational acceleration while improving task success rates.
Authors: Wuque Cai, Hongze Sun, Jiayi He, Qianqian Liao, Yunliang Zang, Duo Chen, Dezhong Yao, Daqing Guo
Abstract: Spiking neural networks (SNNs) are artificial neural networks based on simulated biological neurons and have attracted much attention in recent artificial intelligence technology studies. The dendrites in biological neurons have efficient information processing ability and computational power; however, the neurons of SNNs rarely match the complex structure of the dendrites. Inspired by the nonlinear structure and highly sparse properties of neuronal dendrites, in this study, we propose an efficient, lightweight SNN method with nonlinear pruning and dendritic integration (NSPDI-SNN). In this method, we introduce nonlinear dendritic integration (NDI) to improve the representation of the spatiotemporal information of neurons. We implement heterogeneous state transition ratios of dendritic spines and construct a new and flexible nonlinear synaptic pruning (NSP) method to achieve the high sparsity of SNN. We conducted systematic experiments on three benchmark datasets (DVS128 Gesture, CIFAR10-DVS, and CIFAR10) and extended the evaluation to two complex tasks (speech recognition and reinforcement learning-based maze navigation task). Across all tasks, NSPDI-SNN consistently achieved high sparsity with minimal performance degradation. In particular, our method achieved the best experimental results on all three event stream datasets. Further analysis showed that NSPDI significantly improved the efficiency of synaptic information transfer as sparsity increased. In conclusion, our results indicate that the complex structure and nonlinear computation of neuronal dendrites provide a promising approach for developing efficient SNN methods.
Authors: Saksorn Ruangtanusak, Pittawat Taveekitworachai, Kunat Pipatanakul
Abstract: This report investigates approaches for prompting a tool-augmented large language model (LLM) to act as a role-playing dialogue agent in the API track of the Commonsense Persona-grounded Dialogue Challenge (CPDC) 2025. In this setting, dialogue agents often produce overly long in-character responses (over-speaking) while failing to use tools effectively according to the persona (under-acting), such as generating function calls that do not exist or making unnecessary tool calls before answering. We explore four prompting approaches to address these issues: 1) basic role prompting, 2) improved role prompting, 3) automatic prompt optimization (APO), and 4) rule-based role prompting. The rule-based role prompting (RRP) approach achieved the best performance through two novel techniques-character-card/scene-contract design and strict enforcement of function calling-which led to an overall score of 0.571, improving on the zero-shot baseline score of 0.519. These findings demonstrate that RRP design can substantially improve the effectiveness and reliability of role-playing dialogue agents compared with more elaborate methods such as APO. To support future efforts in developing persona prompts, we are open-sourcing all of our best-performing prompts and the APO tool Source code is available at https://github.com/scb-10x/apo
Authors: Xiaoqiang Lin, Aritra Ghosh, Bryan Kian Hsiang Low, Anshumali Shrivastava, Vijai Mohan
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in leveraging extensive external knowledge to enhance responses in multi-turn and agentic applications, such as retrieval-augmented generation (RAG). However, processing long-context inputs introduces significant system latency and demands substantial memory for the key-value cache, resulting in reduced throughput and a fundamental trade-off between knowledge enrichment and system efficiency. While minimizing latency for long-context inputs is a primary objective for LLMs, we contend that RAG require specialized consideration. In RAG, much of the LLM context consists of concatenated passages from retrieval, with only a small subset directly relevant to the query. These passages often exhibit low semantic similarity due to diversity or deduplication during re-ranking, leading to block-diagonal attention patterns that differ from those in standard LLM generation tasks. Based on this observation, we argue that most computations over the RAG context during decoding are unnecessary and can be eliminated with minimal impact on performance. To this end, we propose REFRAG, an efficient decoding framework that compresses, senses, and expands to improve latency in RAG applications. By exploiting the sparsity structure, we demonstrate a 30.85 the time-to-first-token acceleration (3.75 improvement to previous work) without loss in perplexity. In addition, our optimization framework for large context enables REFRAG to extend the context size of LLMs by 16. We provide rigorous validation of REFRAG across diverse long-context tasks, including RAG, multi-turn conversations, and long document summarization, spanning a wide range of datasets. Experimental results confirm that REFRAG delivers substantial speedup with no loss in accuracy compared to LLaMA models and other state-of-the-art baselines across various context sizes.
Authors: Jusheng Zhang, Yijia Fan, Kaitong Cai, Zimeng Huang, Xiaofei Sun, Jian Wang, Chengpei Tang, Keze Wang
Abstract: This paper introduces DrDiff, a novel framework for long-text generation that overcomes the efficiency-quality trade-off through three core technologies. First, we design a dynamic expert scheduling mechanism that intelligently allocates computational resources during the diffusion process based on text complexity, enabling more efficient handling of text generation tasks of varying difficulty. Second, we introduce a Hierarchical Sparse Attention (HSA) mechanism that adaptively adjusts attention patterns according to a variety of input lengths, reducing computational complexity from O($n^2$) to O($n$) while maintaining model performance. Finally, we propose a soft absorption guidance optimization strategy that combines with DPM-solver++ to reduce diffusion steps, significantly improving generation speed. Comprehensive experiments on various long-text generation benchmarks demonstrate the superiority of our DrDiff over the existing SOTA methods.
Authors: Erik M. Lintunen
Abstract: In self-supervised reinforcement learning (RL), one of the key challenges is learning a diverse set of skills to prepare agents for unknown future tasks. Despite impressive advances, scalability and evaluation remain prevalent issues. Regarding scalability, the search for meaningful skills can be obscured by high-dimensional feature spaces, where relevant features may vary across downstream task domains. For evaluating skill diversity, defining what constitutes "diversity" typically requires a hard commitment to a specific notion of what it means for skills to be diverse, potentially leading to inconsistencies in how skill diversity is understood, making results across different approaches hard to compare, and leaving many forms of diversity unexplored. To address these issues, we adopt a measure of sample diversity that translates ideas from ecology to machine learning -- the Vendi Score -- allowing the user to specify and evaluate any desired form of diversity. We demonstrate how this metric facilitates skill evaluation and introduce VendiRL, a unified framework for learning diversely diverse sets of skills. Given distinct similarity functions, VendiRL motivates distinct forms of diversity, which could support skill-diversity pretraining in new and richly interactive environments where optimising for various forms of diversity may be desirable.
Authors: Yuhao Zhang, Shaoming Duan, Jinhang Su, Chuanyi Liu, Peiyi Han
Abstract: Despite the significant advancements of self-play fine-tuning (SPIN), which can transform a weak large language model (LLM) into a strong one through competitive interactions between models of varying capabilities, it still faces challenges in the Text-to-SQL task. SPIN does not generate new information, and the large number of correct SQL queries produced by the opponent model during self-play reduces the main model's ability to generate accurate SQL queries. To address this challenge, we propose a new self-play fine-tuning method tailored for the Text-to-SQL task, called SPFT-SQL. Prior to self-play, we introduce a verification-based iterative fine-tuning approach, which synthesizes high-quality fine-tuning data iteratively based on the database schema and validation feedback to enhance model performance, while building a model base with varying capabilities. During the self-play fine-tuning phase, we propose an error-driven loss method that incentivizes incorrect outputs from the opponent model, enabling the main model to distinguish between correct SQL and erroneous SQL generated by the opponent model, thereby improving its ability to generate correct SQL. Extensive experiments and in-depth analyses on six open-source LLMs and five widely used benchmarks demonstrate that our approach outperforms existing state-of-the-art (SOTA) methods.
Authors: Andrea Wynn, Harsh Satija, Gillian Hadfield
Abstract: While multi-agent debate has been proposed as a promising strategy for improving AI reasoning ability, we find that debate can sometimes be harmful rather than helpful. Prior work has primarily focused on debates within homogeneous groups of agents, whereas we explore how diversity in model capabilities influences the dynamics and outcomes of multi-agent interactions. Through a series of experiments, we demonstrate that debate can lead to a decrease in accuracy over time - even in settings where stronger (i.e., more capable) models outnumber their weaker counterparts. Our analysis reveals that models frequently shift from correct to incorrect answers in response to peer reasoning, favoring agreement over challenging flawed reasoning. We perform additional experiments investigating various potential contributing factors to these harmful shifts - including sycophancy, social conformity, and model and task type. These results highlight important failure modes in the exchange of reasons during multi-agent debate, suggesting that naive applications of debate may cause performance degradation when agents are neither incentivised nor adequately equipped to resist persuasive but incorrect reasoning.
Authors: Filippo Guerranti, Fabrizio Forte, Simon Geisler, Stephan G\"unnemann
Abstract: Modeling long-range interactions, the propagation of information across distant parts of a graph, is a central challenge in graph machine learning. Graph wavelets, inspired by multi-resolution signal processing, provide a principled way to capture both local and global structures. However, existing wavelet-based graph neural networks rely on finite-order polynomial approximations, which limit their receptive fields and hinder long-range propagation. We propose Long-Range Graph Wavelet Networks (LR-GWN), which decompose wavelet filters into complementary local and global components. Local aggregation is handled with efficient low-order polynomials, while long-range interactions are captured through a flexible spectral-domain parameterization. This hybrid design unifies short- and long-distance information flow within a principled wavelet framework. Experiments show that LR-GWN achieves state-of-the-art performance among wavelet-based methods on long-range benchmarks, while remaining competitive on short-range datasets.
Authors: Zhiyuan He, Xufang Luo, Yike Zhang, Yuqing Yang, Lili Qiu
Abstract: We propose VL Norm (Variance-reduced Length-dependent Normalization), a simple yet effective loss aggregation method tailored to the characteristic of dynamic generation lengths in Reinforcement Learning with Verifiable Rewards (RLVR). Recently, RLVR has demonstrated strong potential in improving the reasoning capabilities of large language models (LLMs), but a major challenge lies in the large variability of response lengths during training, which leads to high gradient variance and unstable optimization. Although previous methods such as GRPO, DAPO, and Dr. GRPO introduce different loss normalization terms to address this issue, they either produce biased estimates or still suffer from high gradient variance. By analyzing the effect of varying lengths on policy loss both theoretically and empirically, we reformulate the problem as finding a minimum-variance unbiased estimator. Our proposed VL Norm not only provides an unbiased estimate of the true policy loss but also minimizes gradient variance in theory. Besides, VL Norm is easy to implement with less than 10 lines of code change. Extensive experiments show that it consistently achieves superior results across different model sizes, maximum lengths, and tasks. When integrated into the state-of-the-art RL algorithm DAPO, it achieves up to 2.67x faster convergence on the CountDown task. Our code is public at https://github.com/zerolllin/Delta-L-Normalization.
Authors: Hanyi Mao, Quanjia Xiao, Lei Pang, Haixiao Liu
Abstract: We propose FSPO (Fair Sequence Policy Optimization), a sequence-level reinforcement learning method for LLMs that enforces length-fair clipping on the importance-sampling (IS) weight. We study RL methods with sequence-level IS and identify a mismatch when PPO/GRPO-style clipping is transplanted to sequences: a fixed clip range systematically reweights short vs. long responses, distorting the optimization direction. FSPO introduces a simple remedy: we clip the sequence log-IS ratio with a band that scales as $\sqrt{L}$. Theoretically, we formalize length fairness via a Length Reweighting Error (LRE) and prove that small LRE yields a cosine directional guarantee between the clipped and true updates. Empirically, FSPO flattens clip rates across length bins, stabilizes training, and outperforms baselines across model sizes and evaluation datasets, with the largest gains on the Qwen3-8B-Base model.
Authors: Lei Yu, Jingyuan Zhang, Xin Wang, Jiajia Ma, Li Yang, Fengjun Zhang
Abstract: Smart contracts automate the management of high-value assets, where vulnerabilities can lead to catastrophic financial losses. This challenge is amplified in Large Language Models (LLMs) by two interconnected failures: they operate as unauditable "black boxes" lacking a transparent reasoning process, and consequently, generate code riddled with critical security vulnerabilities. To address both issues, we propose SmartCoder-R1 (based on Qwen2.5-Coder-7B), a novel framework for secure and explainable smart contract generation. It begins with Continual Pre-training (CPT) to specialize the model. We then apply Long Chain-of-Thought Supervised Fine-Tuning (L-CoT SFT) on 7,998 expert-validated reasoning-and-code samples to train the model to emulate human security analysis. Finally, to directly mitigate vulnerabilities, we employ Security-Aware Group Relative Policy Optimization (S-GRPO), a reinforcement learning phase that refines the generation policy by optimizing a weighted reward signal for compilation success, security compliance, and format correctness. Evaluated against 17 baselines on a benchmark of 756 real-world functions, SmartCoder-R1 establishes a new state of the art, achieving top performance across five key metrics: a ComPass of 87.70%, a VulRate of 8.60%, a SafeAval of 80.16%, a FuncRate of 53.84%, and a FullRate of 50.53%. This FullRate marks a 45.79% relative improvement over the strongest baseline, DeepSeek-R1. Crucially, its generated reasoning also excels in human evaluations, achieving high-quality ratings for Functionality (82.7%), Security (85.3%), and Clarity (90.7%).
Authors: Alejandro D. Mousist
Abstract: This paper presents ASTREA, the first agentic system executed on flight-heritage hardware (TRL 9) for autonomous spacecraft operations, with on-orbit operation aboard the International Space Station (ISS). Using thermal control as a representative use case, we integrate a resource-constrained Large Language Model (LLM) agent with a reinforcement learning controller in an asynchronous architecture tailored for space-qualified platforms. Ground experiments show that LLM-guided supervision improves thermal stability and reduces violations, confirming the feasibility of combining semantic reasoning with adaptive control under hardware constraints. On-orbit validation aboard the ISS initially faced challenges due to inference latency misaligned with the rapid thermal cycles of Low Earth Orbit (LEO) satellites. Synchronization with the orbit length successfully surpassed the baseline with reduced violations, extended episode durations, and improved CPU utilization. These findings demonstrate the potential for scalable agentic supervision architectures in future autonomous spacecraft.
Authors: Senkang Hu, Xudong Han, Jinqi Jiang, Yihang Tao, Zihan Fang, Yong Dai, Sam Tak Wu Kwong, Yuguang Fang
Abstract: Adapting billion-parameter language models to a downstream task is still costly, even with parameter-efficient fine-tuning (PEFT). We re-cast task adaptation as output-distribution alignment: the objective is to steer the output distribution toward the task distribution directly during decoding rather than indirectly through weight updates. Building on this view, we introduce Steering Vector Decoding (SVDecode), a lightweight, PEFT-compatible, and theoretically grounded method. We start with a short warm-start fine-tune and extract a task-aware steering vector from the Kullback-Leibler (KL) divergence gradient between the output distribution of the warm-started and pre-trained models. This steering vector is then used to guide the decoding process to steer the model's output distribution towards the task distribution. We theoretically prove that SVDecode is first-order equivalent to the gradient step of full fine-tuning and derive a globally optimal solution for the strength of the steering vector. Across three tasks and nine benchmarks, SVDecode paired with four standard PEFT methods improves multiple-choice accuracy by up to 5 percentage points and open-ended truthfulness by 2 percentage points, with similar gains (1-2 percentage points) on commonsense datasets without adding trainable parameters beyond the PEFT adapter. SVDecode thus offers a lightweight, theoretically grounded path to stronger task adaptation for large language models.
Authors: Faizul Rakib Sayem, Shahana Ibrahim
Abstract: The reliability of artificial intelligence (AI) systems in open-world settings depends heavily on their ability to flag out-of-distribution (OOD) inputs unseen during training. Recent advances in large-scale vision-language models (VLMs) have enabled promising few-shot OOD detection frameworks using only a handful of in-distribution (ID) samples. However, existing prompt learning-based OOD methods rely solely on softmax probabilities, overlooking the rich discriminative potential of the feature embeddings learned by VLMs trained on millions of samples. To address this limitation, we propose a novel context optimization (CoOp)-based framework that integrates subspace representation learning with prompt tuning. Our approach improves ID-OOD separability by projecting the ID features into a subspace spanned by prompt vectors, while projecting ID-irrelevant features into an orthogonal null space. To train such OOD detection framework, we design an easy-to-handle end-to-end learning criterion that ensures strong OOD detection performance as well as high ID classification accuracy. Experiments on real-world datasets showcase the effectiveness of our approach.
Authors: Alovi N Shohe, Chonglio Khiamungam, Teisovi Angami
Abstract: This paper investigates part-of-speech tagging, an important task in Natural Language Processing (NLP) for the Nagamese language. The Nagamese language, a.k.a. Naga Pidgin, is an Assamese-lexified Creole language developed primarily as a means of communication in trade between the Nagas and people from Assam in northeast India. A substantial amount of work in part-of-speech-tagging has been done for resource-rich languages like English, Hindi, etc. However, no work has been done in the Nagamese language. To the best of our knowledge, this is the first attempt at part-of-speech tagging for the Nagamese Language. The aim of this work is to identify the part-of-speech for a given sentence in the Nagamese language. An annotated corpus of 16,112 tokens is created and applied machine learning technique known as Conditional Random Fields (CRF). Using CRF, an overall tagging accuracy of 85.70%; precision, recall of 86%, and f1-score of 85% is achieved. Keywords. Nagamese, NLP, part-of-speech, machine learning, CRF.
Authors: Yuxiang Ji, Ziyu Ma, Yong Wang, Guanhua Chen, Xiangxiang Chu, Liaoni Wu
Abstract: Recent advances in reinforcement learning (RL) have significantly enhanced the agentic capabilities of large language models (LLMs). In long-term and multi-turn agent tasks, existing approaches driven solely by outcome rewards often suffer from the problem of sparse supervision. To address the challenge, we propose Tree-based Group Relative Policy Optimization (Tree-GRPO), a grouped agent RL method based on tree search, where each tree node represents the complete agent interaction step. By sharing common prefixes, the tree search sampling increases the number of rollouts achievable within a fixed budget of tokens or tool calls. Moreover, we find that the tree-structured trajectory naturally allows the construction of step-wise process supervised signals even using only the outcome reward. Based on this, Tree-GRPO estimates the grouped relative advantages both on intra-tree and inter-tree levels. Through theoretical analysis, we demonstrate that the objective of intra-tree level group relative policy optimization is equivalent to that of step-level direct preference learning. Experiments across 11 datasets and 3 types of QA tasks demonstrate the superiority of the proposed tree-based RL over the chain-based RL method.
Authors: Tiago Fernandes Tavares
Abstract: Unsupervised analysis of text corpora is challenging, especially in data-scarce domains where traditional topic models struggle. While these models offer a solution, they typically describe clusters with lists of keywords that require significant manual effort to interpret and often lack semantic coherence. To address this critical interpretability gap, we introduce Recursive Thematic Partitioning (RTP), a novel framework that leverages Large Language Models (LLMs) to interactively build a binary tree. Each node in the tree is a natural language question that semantically partitions the data, resulting in a fully interpretable taxonomy where the logic of each cluster is explicit. Our experiments demonstrate that RTP's question-driven hierarchy is more interpretable than the keyword-based topics from a strong baseline like BERTopic. Furthermore, we establish the quantitative utility of these clusters by showing they serve as powerful features in downstream classification tasks, particularly when the data's underlying themes correlate with the task labels. RTP introduces a new paradigm for data exploration, shifting the focus from statistical pattern discovery to knowledge-driven thematic analysis. Furthermore, we demonstrate that the thematic paths from the RTP tree can serve as structured, controllable prompts for generative models. This transforms our analytical framework into a powerful tool for synthesis, enabling the consistent imitation of specific characteristics discovered in the source corpus.
Authors: Xiaocheng Zou, Shijin Duan, Charles Fleming, Gaowen Liu, Ramana Rao Kompella, Shaolei Ren, Xiaolin Xu
Abstract: Quantum generative models based on instantaneous quantum polynomial (IQP) circuits show great promise in learning complex distributions while maintaining classical trainability. However, current implementations suffer from two key limitations: lack of controllability over generated outputs and severe generation bias towards certain expected patterns. We present a Controllable Quantum Generative Framework, ConQuER, which addresses both challenges through a modular circuit architecture. ConQuER embeds a lightweight controller circuit that can be directly combined with pre-trained IQP circuits to precisely control the output distribution without full retraining. Leveraging the advantages of IQP, our scheme enables precise control over properties such as the Hamming Weight distribution with minimal parameter and gate overhead. In addition, inspired by the controller design, we extend this modular approach through data-driven optimization to embed implicit control paths in the underlying IQP architecture, significantly reducing generation bias on structured datasets. ConQuER retains efficient classical training properties and high scalability. We experimentally validate ConQuER on multiple quantum state datasets, demonstrating its superior control accuracy and balanced generation performance, only with very low overhead cost over original IQP circuits. Our framework bridges the gap between the advantages of quantum computing and the practical needs of controllable generation modeling.
Authors: Yang Chen, Menglin Zou, Jiaqi Zhang, Yitan Zhang, Junyi Yang, Gael Gendron, Libo Zhang, Jiamou Liu, Michael J. Witbrock
Abstract: Inverse Reinforcement Learning (IRL) learns a reward function to explain expert demonstrations. Modern IRL methods often use the adversarial (minimax) formulation that alternates between reward and policy optimization, which often lead to unstable training. Recent non-adversarial IRL approaches improve stability by jointly learning reward and policy via energy-based formulations but lack formal guarantees. This work bridges this gap. We first present a unified view showing canonical non-adversarial methods explicitly or implicitly maximize the likelihood of expert behavior, which is equivalent to minimizing the expected return gap. This insight leads to our main contribution: Trust Region Reward Optimization (TRRO), a framework that guarantees monotonic improvement in this likelihood via a Minorization-Maximization process. We instantiate TRRO into Proximal Inverse Reward Optimization (PIRO), a practical and stable IRL algorithm. Theoretically, TRRO provides the IRL counterpart to the stability guarantees of Trust Region Policy Optimization (TRPO) in forward RL. Empirically, PIRO matches or surpasses state-of-the-art baselines in reward recovery, policy imitation with high sample efficiency on MuJoCo and Gym-Robotics benchmarks and a real-world animal behavior modeling task.
Authors: Xi Ding, Lei Wang, Piotr Koniusz, Yongsheng Gao
Abstract: We propose Graph Consistency Regularization (GCR), a novel framework that injects relational graph structures, derived from model predictions, into the learning process to promote class-aware, semantically meaningful feature representations. Functioning as a form of self-prompting, GCR enables the model to refine its internal structure using its own outputs. While deep networks learn rich representations, these often capture noisy inter-class similarities that contradict the model's predicted semantics. GCR addresses this issue by introducing parameter-free Graph Consistency Layers (GCLs) at arbitrary depths. Each GCL builds a batch-level feature similarity graph and aligns it with a global, class-aware masked prediction graph, derived by modulating softmax prediction similarities with intra-class indicators. This alignment enforces that feature-level relationships reflect class-consistent prediction behavior, acting as a semantic regularizer throughout the network. Unlike prior work, GCR introduces a multi-layer, cross-space graph alignment mechanism with adaptive weighting, where layer importance is learned from graph discrepancy magnitudes. This allows the model to prioritize semantically reliable layers and suppress noisy ones, enhancing feature quality without modifying the architecture or training procedure. GCR is model-agnostic, lightweight, and improves semantic structure across various networks and datasets. Experiments show that GCR promotes cleaner feature structure, stronger intra-class cohesion, and improved generalization, offering a new perspective on learning from prediction structure. [Project website](https://darcyddx.github.io/gcr/) [Code](https://github.com/Darcyddx/graph-prompt)
URLs: https://darcyddx.github.io/gcr/), https://github.com/Darcyddx/graph-prompt)
Authors: Haonan Chen, Jiaming Xu, Hongyu Chen, Kaiwen Hong, Binghao Huang, Chaoqi Liu, Jiayuan Mao, Yunzhu Li, Yilun Du, Katherine Driggs-Campbell
Abstract: Effectively integrating diverse sensory modalities is crucial for robotic manipulation. However, the typical approach of feature concatenation is often suboptimal: dominant modalities such as vision can overwhelm sparse but critical signals like touch in contact-rich tasks, and monolithic architectures cannot flexibly incorporate new or missing modalities without retraining. Our method factorizes the policy into a set of diffusion models, each specialized for a single representation (e.g., vision or touch), and employs a router network that learns consensus weights to adaptively combine their contributions, enabling incremental of new representations. We evaluate our approach on simulated manipulation tasks in {RLBench}, as well as real-world tasks such as occluded object picking, in-hand spoon reorientation, and puzzle insertion, where it significantly outperforms feature-concatenation baselines on scenarios requiring multimodal reasoning. Our policy further demonstrates robustness to physical perturbations and sensor corruption. We further conduct perturbation-based importance analysis, which reveals adaptive shifts between modalities.
Authors: Junliang Li, Yucheng Wang, Yan Chen, Yu Ran, Ruiqing Zhang, Jing Liu, Hua Wu, Haifeng Wang
Abstract: Hallucination and factuality deficits remain key obstacles to the reliability of large language models (LLMs) in long-form generation. Existing reinforcement learning from human feedback (RLHF) frameworks primarily rely on preference rewards, yet they often overlook the model's internal knowledge boundaries, exacerbating the so-called "hallucination tax". To address this challenge, we propose Knowledge-Level Consistency Reinforcement Learning Framework (KLCF), a novel framework that focuses on the knowledge consistency between the policy model's expressed knowledge and the base model's parametric knowledge, and introduces a Dual-Fact Alignment mechanism to jointly optimize factual recall and precision. Specifically, KLCF leverages pretrained knowledge boundaries to construct fact checklist, guiding online reinforcement learning to improve factual coverage and recall; simultaneously, it trains a self-assessment module based on the base model's internal knowledge to enhance factual precision during generation. Unlike prior methods that rely on external retrieval or heavy verification, our reward design is fully external-knowledge-free and lightweight, making KLCF efficient and easily scalable to large-scale training. Experimental results demonstrate that KLCF substantially improves factuality metrics across multiple long-form benchmarks and effectively alleviates model hallucinations.
Authors: Dianshu Liao, Xin Yin, Shidong Pan, Chao Ni, Zhenchang Xing, Xiaoyu Sun
Abstract: Unit testing is essential for software quality assurance, yet writing and maintaining tests remains time-consuming and error-prone. To address this challenge, researchers have proposed various techniques for automating unit test generation, including traditional heuristic-based methods and more recent approaches that leverage large language models (LLMs). However, these existing approaches are inherently path-insensitive because they rely on fixed heuristics or limited contextual information and fail to reason about deep control-flow structures. As a result, they often struggle to achieve adequate coverage, particularly for deep or complex execution paths. In this work, we present a path-sensitive framework, JUnitGenie, to fill this gap by combining code knowledge with the semantic capabilities of LLMs in guiding context-aware unit test generation. After extracting code knowledge from Java projects, JUnitGenie distills this knowledge into structured prompts to guide the generation of high-coverage unit tests. We evaluate JUnitGenie on 2,258 complex focal methods from ten real-world Java projects. The results show that JUnitGenie generates valid tests and improves branch and line coverage by 29.60% and 31.00% on average over both heuristic and LLM-based baselines. We further demonstrate that the generated test cases can uncover real-world bugs, which were later confirmed and fixed by developers.
Authors: Sam Coggins, Alexander K. Saeri, Katherine A. Daniell, Lorenn P. Ruster, Jessie Liu, Jenny L. Davis
Abstract: Prominent AI companies are producing 'safety frameworks' as a type of voluntary self-governance. These statements purport to establish risk thresholds and safety procedures for the development and deployment of highly capable AI. Understanding which AI risks are covered and what actions are allowed, refused, demanded, encouraged, or discouraged by these statements is vital for assessing how these frameworks actually govern AI development and deployment. We draw on affordance theory to analyse the OpenAI 'Preparedness Framework Version 2' (April 2025) using the Mechanisms & Conditions model of affordances and the MIT AI Risk Repository. We find that this safety policy requests evaluation of a small minority of AI risks, encourages deployment of systems with 'Medium' capabilities for unintentionally enabling 'severe harm' (which OpenAI defines as >1000 deaths or >$100B in damages), and allows OpenAI's CEO to deploy even more dangerous capabilities. These findings suggest that effective mitigation of AI risks requires more robust governance interventions beyond current industry self-regulation. Our affordance analysis provides a replicable method for evaluating what safety frameworks actually permit versus what they claim.
Authors: Heechang Kim, Gwanghyun Kim, Se Young Chun
Abstract: Diverse human motion generation is an increasingly important task, having various applications in computer vision, human-computer interaction and animation. While text-to-motion synthesis using diffusion models has shown success in generating high-quality motions, achieving fine-grained expressive motion control remains a significant challenge. This is due to the lack of motion style diversity in datasets and the difficulty of expressing quantitative characteristics in natural language. Laban movement analysis has been widely used by dance experts to express the details of motion including motion quality as consistent as possible. Inspired by that, this work aims for interpretable and expressive control of human motion generation by seamlessly integrating the quantification methods of Laban Effort and Shape components into the text-guided motion generation models. Our proposed zero-shot, inference-time optimization method guides the motion generation model to have desired Laban Effort and Shape components without any additional motion data by updating the text embedding of pretrained diffusion models during the sampling step. We demonstrate that our approach yields diverse expressive motion qualities while preserving motion identity by successfully manipulating motion attributes according to target Laban tags.
Authors: Jonas H\"ubotter, Patrik Wolf, Alexander Shevchenko, Dennis J\"uni, Andreas Krause, Gil Kur
Abstract: Recent empirical studies have explored the idea of continuing to train a model at test-time for a given task, known as test-time training (TTT), and have found it to yield significant performance improvements. However, there is limited understanding of why and when TTT is effective. Earlier explanations mostly focused on the observation that TTT may help when applied to out-of-distribution adaptation or used with privileged data. However, the growing scale of foundation models with most test data being in-distribution questions these explanations. We instead posit that foundation models remain globally underparameterized, with TTT providing a mechanism for specialization after generalization, focusing capacity on concepts relevant to the test task. Specifically, under the linear representation hypothesis, we propose a model in which TTT achieves a substantially smaller in-distribution test error than global training. We empirically validate our model's key assumptions by training a sparse autoencoder on ImageNet, showing that semantically related data points are explained by only a few shared concepts. Finally, we perform scaling studies across image and language tasks that confirm the practical implications of our model, identifying the regimes where specialization is most effective.
Authors: Junsong Chen, Yuyang Zhao, Jincheng Yu, Ruihang Chu, Junyu Chen, Shuai Yang, Xianbang Wang, Yicheng Pan, Daquan Zhou, Huan Ling, Haozhe Liu, Hongwei Yi, Hao Zhang, Muyang Li, Yukang Chen, Han Cai, Sanja Fidler, Ping Luo, Song Han, Enze Xie
Abstract: We introduce SANA-Video, a small diffusion model that can efficiently generate videos up to 720x1280 resolution and minute-length duration. SANA-Video synthesizes high-resolution, high-quality and long videos with strong text-video alignment at a remarkably fast speed, deployable on RTX 5090 GPU. Two core designs ensure our efficient, effective and long video generation: (1) Linear DiT: We leverage linear attention as the core operation, which is more efficient than vanilla attention given the large number of tokens processed in video generation. (2) Constant-Memory KV cache for Block Linear Attention: we design block-wise autoregressive approach for long video generation by employing a constant-memory state, derived from the cumulative properties of linear attention. This KV cache provides the Linear DiT with global context at a fixed memory cost, eliminating the need for a traditional KV cache and enabling efficient, minute-long video generation. In addition, we explore effective data filters and model training strategies, narrowing the training cost to 12 days on 64 H100 GPUs, which is only 1% of the cost of MovieGen. Given its low cost, SANA-Video achieves competitive performance compared to modern state-of-the-art small diffusion models (e.g., Wan 2.1-1.3B and SkyReel-V2-1.3B) while being 16x faster in measured latency. Moreover, SANA-Video can be deployed on RTX 5090 GPUs with NVFP4 precision, accelerating the inference speed of generating a 5-second 720p video from 71s to 29s (2.4x speedup). In summary, SANA-Video enables low-cost, high-quality video generation.
Authors: Junwei Lan, Jianlyu Chen, Zheng Liu, Chaofan Li, Siqi Bao, Defu Lian
Abstract: With the growing popularity of LLM agents and RAG, it has become increasingly important to retrieve documents that are essential for solving a task, even when their connection to the task is indirect or implicit. Addressing this problem requires fine-grained reasoning to accurately assess the relevance between the task and each candidate document. This capability, however, poses a significant challenge for existing IR techniques. Despite recent progress in reasoning-enhanced IR, existing approaches still face significant challenges in applicability, scalability, and efficiency. In this work, we propose Retro*, a novel approach for reasoning-intensive document retrieval. Our method introduces a rubric-based relevance scoring mechanism, enabling the model to reason about the relationship between a task and a document based on explicitly defined criteria, whereby producing a fine-grained, interpretable relevance score. Retro* also supports test-time scaling by combining multiple reasoning trajectories via score integration, which produces more reliable relevance estimates. To optimize Retro*'s reasoning capabilities, we introduce a novel reinforcement learning algorithm tailored for its relevance scoring mechanism, which employs two composite rewards to fully exploit the trajectories of each training sample. Our experiments show that Retro* outperforms existing document retrieval methods with notable advantages, leading to state-of-the-art performance on the BRIGHT benchmark.
Authors: Yifang Zhang, Pengfei Duan, Henan Wang, Wenjie Yin, Chen Zhou, Shengwu Xiong
Abstract: Rainfall nowcasting, which aims to predict precipitation within the next 0 to 3 hours, is critical for disaster mitigation and real-time response planning. However, most time series forecasting benchmarks in meteorology are evaluated on variables with strong periodicity, such as temperature and humidity, which fail to reflect model capabilities in more complex and practically meteorology scenarios like rainfall nowcasting. To address this gap, we propose RainfallBench, a benchmark designed for rainfall nowcasting, a highly challenging and practically relevant task characterized by zero inflation, temporal decay, and non-stationarity, focused on predicting precipitation within the next 0 to 3 hours. The dataset is derived from five years of meteorological observations, recorded at 15-minute intervals across six essential variables, and collected from more than 12,000 GNSS stations globally. In particular, it incorporates precipitable water vapor (PWV), a crucial indicator of rainfall that is absent in other datasets. We further design specialized evaluation strategies to assess model performance on key meteorological challenges, such as multi-scale prediction and extreme rainfall events, and evaluate over 20 state-of-the-art models across six major architectures on RainfallBench. Additionally, to address the zero-inflation and temporal decay issues overlooked by existing models, we introduce Bi-Focus Precipitation Forecaster (BFPF), a plug-and-play module that incorporates domain-specific priors to enhance rainfall time series forecasting. Statistical analysis and ablation studies validate the comprehensiveness of our dataset as well as the superiority of our methodology. Code and datasets are available at https://anonymous.4open.science/r/RainfallBench-A710.
Authors: Shenao Zhang, Donghan Yu, Yihao Feng, Bowen Jin, Zhaoran Wang, John Peebles, Zirui Wang
Abstract: Large language models excel with reinforcement learning (RL), but fully unlocking this potential requires a mid-training stage. An effective mid-training phase should identify a compact set of useful actions and enable fast selection among them through online RL. We formalize this intuition by presenting the first theoretical result on how mid-training shapes post-training: it characterizes an action subspace that minimizes both the value approximation error from pruning and the RL error during subsequent planning. Our analysis reveals two key determinants of mid-training effectiveness: pruning efficiency, which shapes the prior of the initial RL policy, and its impact on RL convergence, which governs the extent to which that policy can be improved via online interactions. These results suggest that mid-training is most effective when the decision space is compact and the effective horizon is short, highlighting the importance of operating in the space of action abstractions rather than primitive actions. Building on these insights, we propose Reasoning as Action Abstractions (RA3), a scalable mid-training algorithm. Specifically, we derive a sequential variational lower bound and optimize it by iteratively discovering temporally-consistent latent structures via RL, followed by fine-tuning on the bootstrapped data. Experiments on code generation tasks demonstrate the effectiveness of our approach. Across multiple base models, RA3 improves the average performance on HumanEval and MBPP by 8 and 4 points over the base model and the next-token prediction baseline. Furthermore, RA3 achieves faster convergence and higher asymptotic performance in RLVR on HumanEval+, MBPP+, LiveCodeBench, and Codeforces.
Authors: Ehsan Aghaei, Sarthak Jain, Prashanth Arun, Arjun Sambamoorthy
Abstract: Effective analysis of cybersecurity and threat intelligence data demands language models that can interpret specialized terminology, complex document structures, and the interdependence of natural language and source code. Encoder-only transformer architectures provide efficient and robust representations that support critical tasks such as semantic search, technical entity extraction, and semantic analysis, which are key to automated threat detection, incident triage, and vulnerability assessment. However, general-purpose language models often lack the domain-specific adaptation required for high precision. We present SecureBERT 2.0, an enhanced encoder-only language model purpose-built for cybersecurity applications. Leveraging the ModernBERT architecture, SecureBERT 2.0 introduces improved long-context modeling and hierarchical encoding, enabling effective processing of extended and heterogeneous documents, including threat reports and source code artifacts. Pretrained on a domain-specific corpus more than thirteen times larger than its predecessor, comprising over 13 billion text tokens and 53 million code tokens from diverse real-world sources, SecureBERT 2.0 achieves state-of-the-art performance on multiple cybersecurity benchmarks. Experimental results demonstrate substantial improvements in semantic search for threat intelligence, semantic analysis, cybersecurity-specific named entity recognition, and automated vulnerability detection in code within the cybersecurity domain.
Authors: Runqian Wang, Yilun Du
Abstract: We introduce Equilibrium Matching (EqM), a generative modeling framework built from an equilibrium dynamics perspective. EqM discards the non-equilibrium, time-conditional dynamics in traditional diffusion and flow-based generative models and instead learns the equilibrium gradient of an implicit energy landscape. Through this approach, we can adopt an optimization-based sampling process at inference time, where samples are obtained by gradient descent on the learned landscape with adjustable step sizes, adaptive optimizers, and adaptive compute. EqM surpasses the generation performance of diffusion/flow models empirically, achieving an FID of 1.90 on ImageNet 256$\times$256. EqM is also theoretically justified to learn and sample from the data manifold. Beyond generation, EqM is a flexible framework that naturally handles tasks including partially noised image denoising, OOD detection, and image composition. By replacing time-conditional velocities with a unified equilibrium landscape, EqM offers a tighter bridge between flow and energy-based models and a simple route to optimization-driven inference.
Authors: Xinjie Shen, Mufei Li, Pan Li
Abstract: The deployment of Large Language Models (LLMs) in embodied agents creates an urgent need to measure their privacy awareness in the physical world. Existing evaluation methods, however, are confined to natural language based scenarios. To bridge this gap, we introduce EAPrivacy, a comprehensive evaluation benchmark designed to quantify the physical-world privacy awareness of LLM-powered agents. EAPrivacy utilizes procedurally generated scenarios across four tiers to test an agent's ability to handle sensitive objects, adapt to changing environments, balance task execution with privacy constraints, and resolve conflicts with social norms. Our measurements reveal a critical deficit in current models. The top-performing model, Gemini 2.5 Pro, achieved only 59\% accuracy in scenarios involving changing physical environments. Furthermore, when a task was accompanied by a privacy request, models prioritized completion over the constraint in up to 86\% of cases. In high-stakes situations pitting privacy against critical social norms, leading models like GPT-4o and Claude-3.5-haiku disregarded the social norm over 15\% of the time. These findings, demonstrated by our benchmark, underscore a fundamental misalignment in LLMs regarding physically grounded privacy and establish the need for more robust, physically-aware alignment. Codes and datasets will be available at https://github.com/Graph-COM/EAPrivacy.
Authors: Nicholas LaHaye, Kelly M. Luis, Michelle M. Gierach
Abstract: We present a self-supervised machine learning framework for detecting and mapping harmful algal bloom (HAB) severity and speciation using multi-sensor satellite data. By fusing reflectance data from operational instruments (VIIRS, MODIS, Sentinel-3, PACE) with TROPOMI solar-induced fluorescence (SIF), our framework, called SIT-FUSE, generates HAB severity and speciation products without requiring per-instrument labeled datasets. The framework employs self-supervised representation learning, hierarchical deep clustering to segment phytoplankton concentrations and speciations into interpretable classes, validated against in-situ data from the Gulf of Mexico and Southern California (2018-2025). Results show strong agreement with total phytoplankton, Karenia brevis, Alexandrium spp., and Pseudo-nitzschia spp. measurements. This work advances scalable HAB monitoring in label-scarce environments while enabling exploratory analysis via hierarchical embeddings: a critical step toward operationalizing self-supervised learning for global aquatic biogeochemistry.
Authors: Shiyi Zhang, Dong Liang, Hairong Zheng, Yihang Zhou
Abstract: The reconstruction of visual information from brain activity fosters interdisciplinary integration between neuroscience and computer vision. However, existing methods still face challenges in accurately recovering highly complex visual stimuli. This difficulty stems from the characteristics of natural scenes: low-level features exhibit heterogeneity, while high-level features show semantic entanglement due to contextual overlaps. Inspired by the hierarchical representation theory of the visual cortex, we propose the HAVIR model, which separates the visual cortex into two hierarchical regions and extracts distinct features from each. Specifically, the Structural Generator extracts structural information from spatial processing voxels and converts it into latent diffusion priors, while the Semantic Extractor converts semantic processing voxels into CLIP embeddings. These components are integrated via the Versatile Diffusion model to synthesize the final image. Experimental results demonstrate that HAVIR enhances both the structural and semantic quality of reconstructions, even in complex scenes, and outperforms existing models.
Authors: Yukun Zhang, Xueqing Zhou
Abstract: We propose PDE-Transformer, a novel sequence modeling paradigm that casts the forward pass of a Transformer as the numerical discretization of a continuous reaction-diffusion system derived from a variational energy functional. In our framework, token embeddings evolve under a partial differential equation whose nonlocal integral term models self-attention, local reaction term models feed-forward layers, diffusion term encodes positional smoothing, and a stability control term corresponds to layer normalization. From this unifying perspective, we design an Adaptive PDE Diffusion Layer-an efficient, learnable finite-difference stencil that enforces local smoothness in feature space with linear time complexity and complements self-attention's global routing. Through a systematic theoretical analysis based on four pillars:stability, diffusion geometry, multi-scale dynamics, and component coupling, we derive principled guidelines for integrating the PDE layer at seven candidate points in the Transformer. Empirically, on the Long Range Arena benchmark, placing the layer immediately after embedding yields a 4.1 pp average accuracy gain over a strong baseline, and an adaptive multi-scale variant delivers further improvements. Our work thus offers a principled, lightweight mechanism to bolster long-range dependency modeling by harmonizing continuous PDE smoothing with discrete self-attention.
Authors: Byungjun Kim, Soobin Um, Jong Chul Ye
Abstract: Text-to-image (T2I) diffusion models have demonstrated impressive performance in generating high-fidelity images, largely enabled by text-guided inference. However, this advantage often comes with a critical drawback: limited diversity, as outputs tend to collapse into similar modes under strong text guidance. Existing approaches typically optimize intermediate latents or text conditions during inference, but these methods deliver only modest gains or remain sensitive to hyperparameter tuning. In this work, we introduce Contrastive Noise Optimization, a simple yet effective method that addresses the diversity issue from a distinct perspective. Unlike prior techniques that adapt intermediate latents, our approach shapes the initial noise to promote diverse outputs. Specifically, we develop a contrastive loss defined in the Tweedie data space and optimize a batch of noise latents. Our contrastive optimization repels instances within the batch to maximize diversity while keeping them anchored to a reference sample to preserve fidelity. We further provide theoretical insights into the mechanism of this preprocessing to substantiate its effectiveness. Extensive experiments across multiple T2I backbones demonstrate that our approach achieves a superior quality-diversity Pareto frontier while remaining robust to hyperparameter choices.
Authors: Hyung Gyu Rho, Sian Lee
Abstract: Modern preference alignment techniques, such as Best-of-N (BoN) sampling, rely on reward models trained with pairwise comparison data. While effective at learning relative preferences, this paradigm fails to capture a signal of response acceptability, leaving systems vulnerable to selecting the least bad of many unacceptable options. This is particularly problematic for hard prompts, where the risk of such false acceptances increases with the number of samples. In this paper, we address this critical reliability gap by introducing a new data collection and modeling framework. By augmenting preference data with an outside option, inspired by discrete choice models, we train a reward model that can distinguish not just what is better, but what is good enough. We leverage this capability to create an adaptive inference strategy, best of mini-N in-loop, which partitions the generation budget into sequential loops with a calibrated, early-exit condition. Our experiments show that when tuned as an alignment guardrail, it reduces reliability failures by 70%, and when tuned as an inference accelerator, it improves average inference speed by over 22% in IMDB-sentiment setting. We thus provide a principled and flexible framework for practitioners to explicitly manage the trade-off between reliability and computational efficiency.
Authors: Haoqiang Kang, Yizhe Zhang, Nikki Lijing Kuang, Nicklas Majamaki, Navdeep Jaitly, Yi-An Ma, Lianhui Qin
Abstract: Large Language Models (LLMs) demonstrate their reasoning ability through chain-of-thought (CoT) generation. However, LLM's autoregressive decoding may limit the ability to revisit and refine earlier tokens in a holistic manner, which can also lead to inefficient exploration for diverse solutions. In this paper, we propose LaDiR (Latent Diffusion Reasoner), a novel reasoning framework that unifies the expressiveness of continuous latent representation with the iterative refinement capabilities of latent diffusion models for an existing LLM. We first construct a structured latent reasoning space using a Variational Autoencoder (VAE) that encodes text reasoning steps into blocks of thought tokens, preserving semantic information and interpretability while offering compact but expressive representations. Subsequently, we utilize a latent diffusion model that learns to denoise a block of latent thought tokens with a blockwise bidirectional attention mask, enabling longer horizon and iterative refinement with adaptive test-time compute. This design allows efficient parallel generation of diverse reasoning trajectories, allowing the model to plan and revise the reasoning process holistically. We conduct evaluations on a suite of mathematical reasoning and planning benchmarks. Empirical results show that LaDiR consistently improves accuracy, diversity, and interpretability over existing autoregressive, diffusion-based, and latent reasoning methods, revealing a new paradigm for text reasoning with latent diffusion.
Authors: Maximilian R. P. von Liechtenstein
Abstract: Curved Boolean Logic (CBL) generalizes propositional logic by allowing local truth assignments that do not extend to a single global valuation, analogous to curvature in geometry. We give equivalent sheaf and exclusivity-graph semantics and a context-aware proof calculus that is conservative in the flat limit. We formalize CBL-SAT and basic complexity (NP-complete in general) and present operational operators (CBL-AC and CBL-CONS) that prune contradictions earlier on classical hardware. We model noise with iid, AR(1)-correlated, and adversarial bounded perturbations and provide permutation-based significance with Benjamini-Hochberg FDR control. A Colab-ready notebook (ancillary files) regenerates all figures and statistics. We position CBL relative to KCBS, CSW, and sheaf frameworks and outline links to SAT/CSP and robustness/adapter stability in large language models.
Authors: Victor May, Diganta Misra, Yanqi Luo, Anjali Sridhar, Justine Gehring, Silvio Soares Ribeiro Junior
Abstract: AI coding assistants are rapidly becoming integral to modern software development. A key challenge in this space is the continual need to migrate and modernize codebases in response to evolving software ecosystems. Traditionally, such migrations have relied on rule-based systems and human intervention. With the advent of powerful large language models (LLMs), AI-driven agentic frameworks offer a promising alternative-but their effectiveness has not been systematically evaluated. In this paper, we introduce FreshBrew, a novel benchmark for evaluating AI agents on project-level Java migrations, with a specific focus on measuring an agent's ability to preserve program semantics and avoid reward hacking, which we argue requires projects with high test coverage for a rigorous and reliable evaluation. We benchmark several state-of-the-art LLMs, and compare their performance against established rule-based tools. Our evaluation of AI agents on this benchmark of 228 repositories shows that the top-performing model, Gemini 2.5 Flash, can successfully migrate 52.3 percent of projects to JDK 17. Our empirical analysis reveals novel insights into the critical strengths and limitations of current agentic approaches, offering actionable insights into their real-world applicability. Our empirical study reveals failure modes of current AI agents in realistic Java modernization tasks, providing a foundation for evaluating trustworthy code-migration systems. By releasing FreshBrew, we aim to facilitate rigorous, reproducible evaluation and catalyze progress in AI-driven codebase modernization.
Authors: Mingjin Li, Yu Liu, Huayi Liu, Xiang Ye, Chao Jiang, Hongguang Zhang, Yu Ruan
Abstract: We propose MADS (Multi-Agent Dialogue Simulation), a scalable framework for generating persuasive multi-turn dialogues via agent self-play. MADS employs three coordinated agents: User Agents designed to simulate diverse persona-driven behaviors by leveraging personality signifiers such as Zodiac Signs and MBTI types, a Dialog Agent executing task-oriented persuasion strategies and an Optimization Agent evaluating and refining dialogue outcomes. We further validate its effectiveness through users' Chain-of-Attitude (CoA) modeling and dedicated LLMs' persuasion assessment. This approach enables low-cost generation of training data without human annotation, addressing key industry challenges such as lack of user data, cold-start evaluation difficulties, and prompt inefficiency. Applied to a real-world marketing scenario, MADS significantly improved the persuasion capacity of small LLMs, increasing the organic traffic conversion rate by 22.4% (from 1.83% to 2.24%) , demonstrating clear business value.
Authors: Ou Deng, Ruichen Cong, Jianting Xu, Shoji Nishimura, Atsushi Ogihara, Qun Jin
Abstract: Symbolic regression promises readable equations but struggles to encode unit-aware thresholds and conditional logic. We propose logistic-gated operators (LGO) -- differentiable gates with learnable location and steepness -- embedded as typed primitives and mapped back to physical units for audit. Across two primary health datasets (ICU, NHANES), the hard-gate variant recovers clinically plausible cut-points: 71% (5/7) of assessed thresholds fall within 10% of guideline anchors and 100% within 20%, while using far fewer gates than the soft variant (ICU median 4.0 vs 10.0; NHANES 5.0 vs 12.5), and remaining within the competitive accuracy envelope of strong SR baselines. On predominantly smooth tasks, gates are pruned, preserving parsimony. The result is compact symbolic equations with explicit, unit-aware thresholds that can be audited against clinical anchors -- turning interpretability from a post-hoc explanation into a modeling constraint and equipping symbolic regression with a practical calculus for regime switching and governance-ready deployment.
Authors: Sunbowen Lee, Qingyu Yin, Chak Tou Leong, Jialiang Zhang, Yicheng Gong, Shiwen Ni, Min Yang, Xiaoyu Shen
Abstract: Large language models (LLMs) are increasingly deployed on complex reasoning tasks, yet little is known about their ability to internally evaluate problem difficulty, which is an essential capability for adaptive reasoning and efficient resource allocation. In this work, we investigate whether LLMs implicitly encode problem difficulty in their internal representations. Using a linear probe on the final-token representations of LLMs, we demonstrate that the difficulty level of math problems can be linearly modeled. We further locate the specific attention heads of the final Transformer layer: these attention heads have opposite activation patterns for simple and difficult problems, thus achieving perception of difficulty. Our ablation experiments prove the accuracy of the location. Crucially, our experiments provide practical support for using LLMs as automatic difficulty annotators, potentially substantially reducing reliance on costly human labeling in benchmark construction and curriculum learning. We also uncover that there is a significant difference in entropy and difficulty perception at the token level. Our study reveals that difficulty perception in LLMs is not only present but also structurally organized, offering new theoretical insights and practical directions for future research. Our code is available at https://github.com/Aegis1863/Difficulty-Perception-of-LLMs.
URLs: https://github.com/Aegis1863/Difficulty-Perception-of-LLMs.
Authors: Toshiki Nakai, Ravi Kiran Chikkala, Lena Sophie Oberkircher, Nicholas Jennings, Natalia Skachkova, Tatiana Anikina, Jesujoba Oluwadara Alabi
Abstract: The 2025 Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo) Language Challenge addresses one of India's most pressing linguistic gaps: the lack of resources for its diverse low-resource languages (LRLs). In this study, we investigate whether enforcing cross-lingual similarity in specific internal layers of a decoder-only multilingual large language model (LLM) can improve translation quality from LRL to high-resource language (HRL). Specifically, we combine Centered Kernel Alignment (CKA), a similarity metric that encourages representations of different languages to align, with REPINA, a regularization method that constrains parameter updates to remain close to the pretrained model, into a joint method we call TRepLiNa. In this research project, we experiment with zero-shot, few-shot, and fine-tuning settings using Aya-23 8B with QLoRA across MMLoSo shared task language pairs (Mundari, Santali, Bhili) with Hindi/English pivots. Our results show that aligning mid-level layers using TRepLiNa (CKA+REPINA) is a low-cost, practical approach to improving LRL translation, especially in data-scarce settings.
Authors: Fikret Mert Gultekin, Oscar Lilja, Ranim Khojah, Rebekka Wohlrab, Marvin Damschen, Mazen Mohamad
Abstract: In safety-critical software systems, cybersecurity activities become essential, with risk assessment being one of the most critical. In many software teams, cybersecurity experts are either entirely absent or represented by only a small number of specialists. As a result, the workload for these experts becomes high, and software engineers would need to conduct cybersecurity activities themselves. This creates a need for a tool to support cybersecurity experts and engineers in evaluating vulnerabilities and threats during the risk assessment process. This paper explores the potential of leveraging locally hosted large language models (LLMs) with retrieval-augmented generation to support cybersecurity risk assessment in the forestry domain while complying with data protection and privacy requirements that limit external data sharing. We performed a design science study involving 12 experts in interviews, interactive sessions, and a survey within a large-scale project. The results demonstrate that LLMs can assist cybersecurity experts by generating initial risk assessments, identifying threats, and providing redundancy checks. The results also highlight the necessity for human oversight to ensure accuracy and compliance. Despite trust concerns, experts were willing to utilize LLMs in specific evaluation and assistance roles, rather than solely relying on their generative capabilities. This study provides insights that encourage the use of LLM-based agents to support the risk assessment process of cyber-physical systems in safety-critical domains.
Authors: Haotian Wu, Shufan Jiang, Mingyu Chen, Yiyang Feng, Hehai Lin, Heqing Zou, Yao Shu, Chengwei Qin
Abstract: As large language models (LLMs) advance in role-playing (RP) tasks, existing benchmarks quickly become obsolete due to their narrow scope, outdated interaction paradigms, and limited adaptability across diverse application scenarios. To address this gap, we introduce FURINA-Builder, a novel multi-agent collaboration pipeline that automatically constructs fully customizable RP benchmarks at any scale. It enables evaluation of arbitrary characters across diverse scenarios and prompt formats, as the first benchmark builder in RP area for adaptable assessment. FURINA-Builder simulates dialogues between a test character and other characters drawn from a well-constructed character-scene pool, while an LLM judge selects fine-grained evaluation dimensions and adjusts the test character's responses into final test utterances. Using this pipeline, we build FURINA-Bench, a new comprehensive role-playing benchmark featuring both established and synthesized test characters, each assessed with dimension-specific evaluation criteria. Human evaluation and preliminary separability analysis justify our pipeline and benchmark design. We conduct extensive evaluations of cutting-edge LLMs and find that o3 and DeepSeek-R1 achieve the best performance on English and Chinese RP tasks, respectively. Across all models, established characters consistently outperform synthesized ones, with reasoning capabilities further amplifying this disparity. Interestingly, we observe that model scale does not monotonically reduce hallucinations. More critically, for reasoning LLMs, we uncover a novel trade-off: reasoning improves RP performance but simultaneously increases RP hallucinations. This trade-off extends to a broader Pareto frontier between RP performance and reliability for all LLMs. These findings demonstrate the effectiveness of FURINA-Builder and the challenge posed by FURINA-Bench.
Authors: Jusen Du, Jiaxi Hu, Tao Zhang, Weigao Sun, Yu Cheng
Abstract: Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recall accuracy over long contexts. In this work, we introduce Native Hybrid Attention (NHA), a novel hybrid architecture of linear and full attention that integrates both intra \& inter-layer hybridization into a unified layer design. NHA maintains long-term context in key-value slots updated by a linear RNN, and augments them with short-term tokens from a sliding window. A single \texttt{softmax attention} operation is then applied over all keys and values, enabling per-token and per-head context-dependent weighting without requiring additional fusion parameters. The inter-layer behavior is controlled through a single hyperparameter, the sliding window size, which allows smooth adjustment between purely linear and full attention while keeping all layers structurally uniform. Experimental results show that NHA surpasses Transformers and other hybrid baselines on recall-intensive and commonsense reasoning tasks. Furthermore, pretrained LLMs can be structurally hybridized with NHA, achieving competitive accuracy while delivering significant efficiency gains. Code is available at https://github.com/JusenD/NHA.
Authors: Tan Wang, Yun Wei Dong, Tao Zhang, Qi Wang
Abstract: Transformer-based methods have achieved impressive results in time series forecasting. However, existing Transformers still exhibit limitations in sequence modeling as they tend to overemphasize temporal dependencies. This incurs additional computational overhead without yielding corresponding performance gains. We find that the performance of Transformers is highly dependent on the embedding method used to learn effective representations. To address this issue, we extract multivariate features to augment the effective information captured in the embedding layer, yielding multidimensional embeddings that convey richer and more meaningful sequence representations. These representations enable Transformer-based forecasters to better understand the series. Specifically, we introduce Hybrid Temporal and Multivariate Embeddings (HTME). The HTME extractor integrates a lightweight temporal feature extraction module with a carefully designed multivariate feature extraction module to provide complementary features, thereby achieving a balance between model complexity and performance. By combining HTME with the Transformer architecture, we present HTMformer, leveraging the enhanced feature extraction capability of the HTME extractor to build a lightweight forecaster. Experiments conducted on eight real-world datasets demonstrate that our approach outperforms existing baselines in both accuracy and efficiency.
Authors: Shaorong Zhang, Rob Brekelmans, Greg Ver Steeg
Abstract: Diffusion Posterior Sampling (DPS) provides a principled Bayesian approach to inverse problems by sampling from $p(x_0 \mid y)$. However, in practice, the goal of inverse problem solving is not to cover the posterior but to recover the most accurate reconstruction, where optimization-based diffusion solvers often excel despite lacking a clear probabilistic foundation. We introduce Local MAP Sampling (LMAPS), a new inference framework that iteratively solving local MAP subproblems along the diffusion trajectory. This perspective clarifies their connection to global MAP estimation and DPS, offering a unified probabilistic interpretation for optimization-based methods. Building on this foundation, we develop practical algorithms with a probabilistically interpretable covariance approximation, a reformulated objective for stability and interpretability, and a gradient approximation for non-differentiable operators. Across a broad set of image restoration and scientific tasks, LMAPS achieves state-of-the-art performance, including $\geq 2$ dB gains on motion deblurring, JPEG restoration, and quantization, and $>1.5$ dB improvements on inverse scattering benchmarks.
Authors: Jialu Du, Guiyang Hou, Yihui Fu, Chen Wu, Wenqi Zhang, Yongliang Shen, Weiming Lu
Abstract: While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and subjective belief states. Through deteiled analysis of DeepSeek-R1's reasoning trajectories, we find that LLMs frequently encounter reasoning impasses and tend to output contradictory terms like "tricky" and "confused" when processing scenarios with multiple participants and timelines, leading to erroneous reasoning or infinite loops. The core issue is their inability to disentangle objective reality from agents' subjective beliefs. To address this, we propose an adaptive world model-enhanced reasoning mechanism that constructs a dynamic textual world model to track entity states and temporal sequences. It dynamically monitors reasoning trajectories for confusion indicators and promptly intervenes by providing clear world state descriptions, helping models navigate through cognitive dilemmas. The mechanism mimics how humans use implicit world models to distinguish between external events and internal beliefs. Evaluations on three social benchmarks demonstrate significant improvements in accuracy (e.g., +10% in Hi-ToM) while reducing computational costs (up to 33.8% token reduction), offering a simple yet effective solution for deploying LLMs in social contexts.
Authors: Gustave Cortal (ENS Paris Saclay, LISN), Alain Finkel (ENS Paris Saclay)
Abstract: Personal narratives are stories authors construct to make meaning of their experiences. Style, the distinctive way authors use language to express themselves, is fundamental to how these narratives convey subjective experiences. Yet there is a lack of a formal framework for systematically analyzing these stylistic choices. We present a novel approach that formalizes style in personal narratives as patterns in the linguistic choices authors make when communicating subjective experiences. Our framework integrates three domains: functional linguistics establishes language as a system of meaningful choices, computer science provides methods for automatically extracting and analyzing sequential patterns, and these patterns are linked to psychological observations. Using language models, we automatically extract linguistic features such as processes, participants, and circumstances. We apply our framework to hundreds of dream narratives, including a case study on a war veteran with post-traumatic stress disorder. Analysis of his narratives uncovers distinctive patterns, particularly how verbal processes dominate over mental ones, illustrating the relationship between linguistic choices and psychological states.
Authors: Yuxin Ma, Lun Du, Lanning Wei, Kun Chen, Qian Xu, Kangyu Wang, Guofeng Feng, Guoshan Lu, Lin Liu, Xiaojing Qi, Xinyuan Zhang, Zhen Tao, Haibo Feng, Ziyun Jiang, Ying Xu, Zenan Huang, Yihong Zhuang, Haokai Xu, Jiaqi Hu, Zhenzhong Lan, Junbo Zhao, Jianguo Li, Da Zheng
Abstract: Diffusion-based large language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs, leveraging denoising-based generation to enable inherent parallelism. Even more and more open-sourced dLLM models emerge, yet their widespread adoption remains constrained by the lack of a standardized and efficient inference framework. We present dInfer, an efficient and extensible framework for dLLM inference. dInfer decomposes the inference pipeline into four modular components--model, diffusion iteration manager, decoding strategy, and KV-cache manager--and integrates novel algorithms for each component alongside system-level optimizations. Through this combination of algorithmic innovations and system enhancements, dInfer achieves substantial efficiency gains without compromising output quality on LLaDA-MoE. At batch size 1, it surpasses 1,100 tokens per second on HumanEval and averages over 800 tokens per second across six benchmarks on $8\times$ H800 GPUs. Compared to prior systems, dInfer delivers a $10\times$ speedup over Fast-dLLM while maintaining similar model performance. Even compared to the AR model (with a comparable number of activation parameters and performance) QWen2.5-3B, which is highly optimized with the latest vLLM inference engine, dInfer still delivers a $2$-$3\times$ speedup. The implementation of dInfer is open-sourced at https://github.com/inclusionAI/dInfer.
Authors: Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong
Abstract: Instance discrimination is a self-supervised representation learning paradigm wherein individual instances within a dataset are treated as distinct classes. This is typically achieved by generating two disparate views of each instance by applying stochastic transformations, encouraging the model to learn representations invariant to the common underlying object across these views. While this approach facilitates the acquisition of invariant representations for dataset instances under various handcrafted transformations (e.g., random cropping, colour jittering), an exclusive reliance on such data transformations for achieving invariance may inherently limit the model's generalizability to unseen datasets and diverse downstream tasks. The inherent limitation stems from the fact that the finite set of transformations within the data processing pipeline is unable to encompass the full spectrum of potential data variations. In this study, we provide the technical foundation for leveraging semantic pairs to enhance the generalizability of the model's representation and empirically demonstrate that incorporating semantic pairs mitigates the issue of limited transformation coverage. Specifically, we propose that by exposing the model to semantic pairs (i.e., two instances belonging to the same semantic category), we introduce varied real-world scene contexts, thereby fostering the development of more generalizable object representations. To validate this hypothesis, we constructed and released a novel dataset comprising curated semantic pairs and conducted extensive experimentation to empirically establish that their inclusion enables the model to learn more general representations, ultimately leading to improved performance across diverse downstream tasks.
Authors: Nan Lu, Yurong Hu, Jiaquan Fang, Yan Liu, Rui Dong, Yiming Wang, Rui Lin, Shaoyi Xu
Abstract: The growth of the e-commerce industry has intensified the adversarial dynamics between shadow economy actors and risk management teams. Companies often conduct risk investigations into suspicious cases to identify emerging fraud patterns, thereby enhancing both preemptive risk prevention and post-hoc governance. However, the sheer volume of case analyses imposes a substantial workload on risk management analysts, as each case requires the integration of long-term expert experience and meticulous scrutiny across multiple risk dimensions. Additionally, individual disparities among analysts hinder the establishment of uniform and high-standard workflows. To address these challenges, we propose the SHERLOCK framework, which leverages the reasoning capabilities of large language models (LLMs) to assist analysts in risk investigations. Our approach consists of three primary components: (1) extracting risk management knowledge from multi-modal data and constructing a domain knowledge base (KB), (2) building an intelligent platform guided by the data flywheel paradigm that integrates daily operations, expert annotations, and model evaluations, with iteratively fine-tuning for preference alignment, and (3) introducing a Reflect & Refine (R&R) module that collaborates with the domain KB to establish a rapid response mechanism for evolving risk patterns. Experiments conducted on the real-world transaction dataset from JD dot com demonstrate that our method significantly improves the precision of both factual alignment and risk localization within the LLM analysis results. Deployment of the SHERLOCK-based LLM system on JD dot com has substantially enhanced the efficiency of case investigation workflows for risk managers.
Authors: Dakai Zhai, Jiong Gao, Boya Du, Junwei Xu, Qijie Shen, Jialin Zhu, Yuning Jiang
Abstract: Accurately predicting conversion rates (CVR) for low-activity users remains a fundamental challenge in large-scale e-commerce recommender systems. Existing approaches face three critical limitations: (i) reliance on noisy and unreliable behavioral signals; (ii) insufficient user-level information due to the lack of diverse interaction data; and (iii) a systemic training bias toward high-activity users that overshadows the needs of low-activity users. To address these challenges, we propose ChoirRec, a novel framework that leverages the semantic capabilities of Large Language Models (LLMs) to construct semantic user groups and enhance CVR prediction for low-activity users. With a dual-channel architecture designed for robust cross-user knowledge transfer, ChoirRec comprises three components: (i) a Semantic Group Generation module that utilizes LLMs to form reliable, cross-activity user clusters, thereby filtering out noisy signals; (ii) a Group-aware Hierarchical Representation module that enriches sparse user embeddings with informative group-level priors to mitigate data insufficiency; and (iii) a Group-aware Multi-granularity Modual that employs a dual-channel architecture and adaptive fusion mechanism to ensure effective learning and utilization of group knowledge. We conduct extensive offline and online experiments on Taobao, a leading industrial-scale e-commerce platform. ChoirRec improves GAUC by 1.16\% in offline evaluations, while online A/B testing reveals a 7.24\% increase in order volume, highlighting its substantial practical value in real-world applications.
Authors: Ralf R\"omer, Adrian Kobras, Luca Worbis, Angela P. Schoellig
Abstract: Imitation learning (IL) with generative models, such as diffusion and flow matching, has enabled robots to perform complex, long-horizon tasks. However, distribution shifts from unseen environments or compounding action errors can still cause unpredictable and unsafe behavior, leading to task failure. Early failure prediction during runtime is therefore essential for deploying robots in human-centered and safety-critical environments. We propose FIPER, a general framework for Failure Prediction at Runtime for generative IL policies that does not require failure data. FIPER identifies two key indicators of impending failure: (i) out-of-distribution (OOD) observations detected via random network distillation in the policy's embedding space, and (ii) high uncertainty in generated actions measured by a novel action-chunk entropy score. Both failure prediction scores are calibrated using a small set of successful rollouts via conformal prediction. A failure alarm is triggered when both indicators, aggregated over short time windows, exceed their thresholds. We evaluate FIPER across five simulation and real-world environments involving diverse failure modes. Our results demonstrate that FIPER better distinguishes actual failures from benign OOD situations and predicts failures more accurately and earlier than existing methods. We thus consider this work an important step towards more interpretable and safer generative robot policies. Code, data and videos are available at https://tum-lsy.github.io/fiper_website.
Authors: Chenyu Wang, Paria Rashidinejad, DiJia Su, Song Jiang, Sid Wang, Siyan Zhao, Cai Zhou, Shannon Zejiang Shen, Feiyu Chen, Tommi Jaakkola, Yuandong Tian, Bo Liu
Abstract: Diffusion large language models (dLLMs) are emerging as an efficient alternative to autoregressive models due to their ability to decode multiple tokens in parallel. However, aligning dLLMs with human preferences or task-specific rewards via reinforcement learning (RL) is challenging because their intractable log-likelihood precludes the direct application of standard policy gradient methods. While prior work uses surrogates like the evidence lower bound (ELBO), these one-sided approximations can introduce significant policy gradient bias. To address this, we propose the Sandwiched Policy Gradient (SPG) that leverages both an upper and a lower bound of the true log-likelihood. Experiments show that SPG significantly outperforms baselines based on ELBO or one-step estimation. Specifically, SPG improves the accuracy over state-of-the-art RL methods for dLLMs by 3.6% in GSM8K, 2.6% in MATH500, 18.4% in Countdown and 27.0% in Sudoku.