Authors: Jiaqi Yuan, Jialu Wang, Zihan Wang, Qingyun Sun, Ruijie Wang, Jianxin Li
Abstract: Generative search engines represent a transition from traditional ranking-based retrieval to Large Language Model (LLM)-based synthesis, transforming optimization goals from ranking prominence towards content inclusion. Generative Engine Optimization (GEO), specifically, aims to maximize visibility and attribution in black-box summarized outputs by strategically manipulating source content. However, existing methods rely on static heuristics, single-prompt optimization, or engine preference rule distillation that is prone to overfitting. They cannot flexibly adapt to diverse content or the changing behaviors of generative engines. Moreover, effectively optimizing these strategies requires an impractical amount of interaction feedback from the engines. To address these challenges, we propose AgenticGEO, a self-evolving agentic framework formulating optimization as a content-conditioned control problem, which enhances intrinsic content quality to robustly adapt to the unpredictable behaviors of black-box engines. Unlike fixed-strategy methods, AgenticGEO employs a MAP-Elites archive to evolve diverse, compositional strategies. To mitigate interaction costs, we introduce a Co-Evolving Critic, a lightweight surrogate that approximates engine feedback for content-specific strategy selection and refinement, efficiently guiding both evolutionary search and inference-time planning. Through extensive in-domain and cross-domain experiments on two representative engines, AgenticGEO achieves state-of-the-art performance and demonstrates robust transferability, outperforming 14 baselines across 3 datasets. Our code and model are available at: https://github.com/AIcling/agentic_geo.
Authors: Xinkui Zhao, Sai Liu, Yifan Zhang, Qingyu Ma, Guanjie Cheng, Naibo Wang, Chang Liu
Abstract: The integration of Large Language Models into Multi-Agent Systems (MAS) has enabled the so-lution of complex, long-horizon tasks through collaborative reasoning. However, this collec-tive intelligence is inherently fragile, as a single logical fallacy can rapidly propagate and lead to system-wide failure. Most current research re-lies on post-hoc failure analysis, thereby hinder-ing real-time intervention. To address this, we propose PROMAS, a proactive framework utiliz-ing Markov transitions for predictive error anal-ysis. PROMAS extracts Causal Delta Features to capture semantic displacement, mapping them to a quantized Vector Markov Space to model reasoning as probabilistic transitions. By inte-grating a Proactive Prediction Head with Jump Detection, the method localizes errors via risk acceleration rather than static thresholds. On the Who&When benchmark, PROMAS achieves 22.97% step-level accuracy while processing only 27% of reasoning logs. This performance rivals reactive monitors like MASC while reducing data overhead by 73%. Although this strategy entails an accuracy trade-off compared to post-hoc meth-ods, it significantly improves intervention latency, balancing diagnostic precision with the real-time demands of autonomous reasoning.
Authors: Xuanqi Gao, Haoyu Wang, Jun Sun, Shiqing Ma, Chao Shen
Abstract: While Large Language Models (LLMs) have advanced complex reasoning, prominent methods like the Tree of Thoughts (ToT) framework face a critical trade-off between exploration depth and computational efficiency. Existing ToT implementations often rely on heavyweight LLM-based self-evaluation or rigid heuristics for branch pruning, making them prohibitively expensive and inflexible for broad application. To address this, we introduce DST, an adaptable, plug-and-play predictor that serves as a lightweight, supervised heuristic to guide the ToT search process. Our predictor enables dynamic, context-aware pruning, allowing the search to proceed with near-greedy efficiency on simpler reasoning steps while adaptively expanding the search beam only when encountering uncertainty or task complexity. We evaluate our approach on a diverse suite of benchmarks spanning mathematical reasoning, general reasoning, and complex logical reasoning. Experimental results demonstrate that our method achieves accuracy competitive with or superior to strong baselines, including standard ToT, while reducing computational overhead by 26-75%. Our work effectively resolves the accuracy-efficiency trade-off in tree-based reasoning, transforming ToT from a resource-intensive technique into a scalable and practical paradigm for complex problem-solving in LLMs.
Authors: Ali Shamsaddinlou, Morteza NourelahiAlamdari
Abstract: Generating executable simulations from natural language specifications remains a challenging problem due to the limited reasoning capacity of large language models (LLMs) when confronted with large, interconnected codebases. This paper presents FactorSmith, a framework that synthesizes playable game simulations in code from textual descriptions by combining two complementary ideas: factored POMDP decomposition for principled context reduction and a hierarchical planner-designer-critic agentic workflow for iterative quality refinement at every generation step. Drawing on the factored partially observable Markov decision process (POMDP) representation introduced by FactorSim [Sun et al., 2024], the proposed method decomposes a simulation specification into modular steps where each step operates only on a minimal subset of relevant state variables, limiting the context window that any single LLM call must process. Inspired by the agentic trio architecture of SceneSmith [Pfaff et al., 2025], FactorSmith embeds within every factored step a three-agent interaction: a planner that orchestrates workflow, a designer that proposes code artifacts, and a critic that evaluates quality through structured scoring, enabling iterative refinement with checkpoint rollback. This paper formalizes the combined approach, presents the mathematical framework underpinning context selection and agentic refinement, and describes the open-source implementation. Experiments on the PyGame Learning Environment benchmark demonstrate that FactorSmith generates simulations with improved prompt alignment, fewer runtime errors, and higher code quality compared to non-agentic factored baselines.
Authors: Atharv Naphade, Samarth Bhargav, Sean Lim, Mcnair Shah
Abstract: A hallmark of human intelligence is Introspection-the ability to assess and reason about one's own cognitive processes. Introspection has emerged as a promising but contested capability in large language models (LLMs). However, current evaluations often fail to distinguish genuine meta-cognition from the mere application of general world knowledge or text-based self-simulation. In this work, we propose a principled taxonomy that formalizes introspection as the latent computation of specific operators over a model's policy and parameters. To isolate the components of generalized introspection, we present Introspect-Bench, a multifaceted evaluation suite designed for rigorous capability testing. Our results show that frontier models exhibit privileged access to their own policies, outperforming peer models in predicting their own behavior. Furthermore, we provide causal, mechanistic evidence explaining both how LLMs learn to introspect without explicit training, and how the mechanism of introspection emerges via attention diffusion.
Authors: Aayam Bansal, Ishaan Gangwani
Abstract: Cooperative multi-agent methods for embodied AI are almost universally evaluated under idealized communication: zero latency, no packet loss, and unlimited bandwidth. Real-world deployment on robots with wireless links, autonomous vehicles on congested networks, or drone swarms in contested spectrum offers no such guarantees. We introduce AgentComm-Bench, a benchmark suite and evaluation protocol that systematically stress-tests cooperative embodied AI under six communication impairment dimensions: latency, packet loss, bandwidth collapse, asynchronous updates, stale memory, and conflicting sensor evidence. AgentComm-Bench spans three task families: cooperative perception, multi-agent waypoint navigation, and cooperative zone search, and evaluates five communication strategies, including a lightweight method we propose based on redundant message coding with staleness-aware fusion. Our experiments reveal that communication-dependent tasks degrade catastrophically: stale memory and bandwidth collapse cause over 96% performance drops in navigation, while content corruption (stale or conflicting data) reduces perception F1 by over 85%. Vulnerability depends on the interaction between impairment type and task design; perception fusion is robust to packet loss but amplifies corrupted data. Redundant message coding more than doubles navigation performance under 80% packet loss. We release AgentComm-Bench as a practical evaluation protocol and recommend that cooperative embodied AI work report performance under multiple impairment conditions.
Authors: Xiaoxu Ma, Dong Li, Minglai Shao, Xintao Wu, Chen Zhao
Abstract: Text-attributed graphs, where nodes are enriched with textual attributes, have become a powerful tool for modeling real-world networks such as citation, social, and transaction networks. However, existing methods for learning from these graphs often assume that the distributions of training and testing data are consistent. This assumption leads to significant performance degradation when faced with out-of-distribution (OOD) data. In this paper, we address the challenge of node-level OOD detection in text-attributed graphs, with the goal of maintaining accurate node classification while simultaneously identifying OOD nodes. We propose a novel approach, LLM-Enhanced Energy Contrastive Learning for Out-of-Distribution Detection in Text-Attributed Graphs (LECT), which integrates large language models (LLMs) and energy-based contrastive learning. The proposed method involves generating high-quality OOD samples by leveraging the semantic understanding and contextual knowledge of LLMs to create dependency-aware pseudo-OOD nodes, and applying contrastive learning based on energy functions to distinguish between in-distribution (IND) and OOD nodes. The effectiveness of our method is demonstrated through extensive experiments on six benchmark datasets, where our method consistently outperforms state-of-the-art baselines, achieving both high classification accuracy and robust OOD detection capabilities.
Authors: Vitaly Aksenov, Eve Bodnia, Michael H. Freedman, Michael Mulligan
Abstract: Human mathematics (HM), the mathematics humans discover and value, is a vanishingly small subset of formal mathematics (FM), the totality of all valid deductions. We argue that HM is distinguished by its compressibility through hierarchically nested definitions, lemmas, and theorems. We model this with monoids. A mathematical deduction is a string of primitive symbols; a definition or theorem is a named substring or macro whose use compresses the string. In the free abelian monoid $A_n$, a logarithmically sparse macro set achieves exponential expansion of expressivity. In the free non-abelian monoid $F_n$, even a polynomially-dense macro set only yields linear expansion; superlinear expansion requires near-maximal density. We test these models against MathLib, a large Lean~4 library of mathematics that we take as a proxy for HM. Each element has a depth (layers of definitional nesting), a wrapped length (tokens in its definition), and an unwrapped length (primitive symbols after fully expanding all references). We find unwrapped length grows exponentially with both depth and wrapped length; wrapped length is approximately constant across all depths. These results are consistent with $A_n$ and inconsistent with $F_n$, supporting the thesis that HM occupies a polynomially-growing subset of the exponentially growing space FM. We discuss how compression, measured on the MathLib dependency graph, and a PageRank-style analysis of that graph can quantify mathematical interest and help direct automated reasoning toward the compressible regions where human mathematics lives.
Authors: Karan Kumar Singh, Nikita Gajbhiye
Abstract: Food security policy formulation in data-scarce regions remains a critical challenge due to limited structured datasets, fragmented textual reports, and demographic bias in decision-making systems. This study proposes ZeroHungerAI, an integrated Natural Language Processing (NLP) and Machine Learning (ML) framework designed for evidence-based food security policy modeling under extreme data scarcity. The system combines structured socio-economic indicators with contextual policy text embeddings using a transfer learning based DistilBERT architecture. Experimental evaluation on a 1200-sample hybrid dataset across 25 districts demonstrates superior predictive performance, achieving 91 percent classification accuracy, 0.89 precision, 0.85 recall, and an F1 score of 0.86 under imbalanced conditions. Comparative analysis shows a 13 percent performance improvement over classical SVM and 17 percent over Logistic Regression models. Precision Recall evaluation confirms robust minority class detection (average precision around 0.88). Fairness aware optimization reduces demographic parity difference to 3 percent, ensuring equitable rural urban policy inference. The results validate that transformer based contextual learning significantly enhances policy intelligence in low resource governance environments, enabling scalable and bias aware hunger prediction systems.
Authors: Jingwei Huang, Kuroush Nezafati, Zhikai Chi, Ruichen Rong, Colin Treager, Tingyi Wanyan, Yueshuang Xu, Xiaowei Zhan, Patrick Leavey, Guanghua Xiao, Wenqi Shi, Yang Xie
Abstract: Extracting structured information from clinical notes requires navigating a dense web of interdependent variables where the value of one attribute logically constrains others. Existing Large Language Model (LLM)-based extraction pipelines often struggle to capture these dependencies, leading to clinically inconsistent outputs. We propose deep reflective reasoning, a large language model agent framework that iteratively self-critiques and revises structured outputs by checking consistency among variables, the input text, and retrieved domain knowledge, stopping when outputs converge. We extensively evaluate the proposed method in three diverse oncology applications: (1) On colorectal cancer synoptic reporting from gross descriptions (n=217), reflective reasoning improved average F1 across eight categorical synoptic variables from 0.828 to 0.911 and increased mean correct rate across four numeric variables from 0.806 to 0.895; (2) On Ewing sarcoma CD99 immunostaining pattern identification (n=200), the accuracy improved from 0.870 to 0.927; (3) On lung cancer tumor staging (n=100), tumor stage accuracy improved from 0.680 to 0.833 (pT: 0.842 -> 0.884; pN: 0.885 -> 0.948). The results demonstrate that deep reflective reasoning can systematically improve the reliability of LLM-based structured data extraction under interdependence constraints, enabling more consistent machine-operable clinical datasets and facilitating knowledge discovery with machine learning and data science towards digital health.
Authors: Zhuoling Li, Hossein Rahmani, Jiarui Zhang, Yu Xue, Majid Mirmehdi, Jason Kuen, Jiuxiang Gu, Jun Liu
Abstract: The rapid growth of the text-to-image (T2I) community has fostered a thriving online ecosystem of expert models, which are variants of pretrained diffusion models specialized for diverse generative abilities. Yet, existing model merging methods remain limited in fully leveraging abundant online expert resources and still struggle to meet diverse in-the-wild user needs. We present DiffGraph, a novel agent-driven graph-based model merging framework, which automatically harnesses online experts and flexibly merges them for diverse user needs. Our DiffGraph constructs a scalable graph and organizes ever-expanding online experts within it through node registration and calibration. Then, DiffGraph dynamically activates specific subgraphs based on user needs, enabling flexible combinations of different experts to achieve user-desired generation. Extensive experiments show the efficacy of our method.
Authors: Saimun Habib, Vaishak Belle, Fengxiang He
Abstract: Probabilistic Logic Programming (PLP) languages, like ProbLog, naturally support reasoning under uncertainty, while maintaining a declarative and interpretable framework. Meanwhile, counterfactual reasoning (i.e., answering ``what if'' questions) is critical for ensuring AI systems are robust and trustworthy; however, integrating this capability into PLP can be computationally prohibitive and unstable in accuracy. This paper addresses this challenge, by proposing an efficient program transformation for counterfactuals as Single World Intervention Programs (SWIPs) in ProbLog. By systematically splitting ProbLog clauses to observed and fixed components relevant to a counterfactual, we create a transformed program that (1) does not asymptotically exceed the computational complexity of existing methods, and is strictly smaller in common cases, and (2) reduces counterfactual reasoning to marginal inference over a simpler program. We formally prove the correctness of our approach, which relies on a weaker set independence assumptions and is consistent with conditional independencies, showing the resulting marginal probabilities match the counterfactual distributions of the underlying Structural Causal Model in wide domains. Our method achieves a 35\% reduction in inference time versus existing methods in extensive experiments. This work makes complex counterfactual reasoning more computationally tractable and reliable, providing a crucial step towards developing more robust and explainable AI systems. The code is at https://github.com/EVIEHub/swip.
Authors: Zhenwei Tang, Qianfeng Wen, Seth Grief-Albert, Yahya Elgabra, Blair Yang, Honghua Dong, Ashton Anderson
Abstract: Language models often lack grounded reasoning capabilities in specialized domains where training data is scarce but bespoke systems excel. We introduce a general framework for distilling expert system reasoning into natural language chain-of-thought explanations, enabling compact models to acquire domain expertise and the ability to generate faithful, grounded explanations. Rather than distilling only final outputs, we capture the full reasoning process, transforming opaque expert computations into transparent, step-by-step explanations. We demonstrate this approach in chess, a canonical reasoning domain where language models continue to underperform. Our 4B parameter model, C1, advances from a near-zero baseline to 48.1% accuracy, outperforming all open-source models and most frontier proprietary systems. Notably, C1 surpasses its distillation teacher and generates solutions in two orders of magnitude fewer tokens than baselines. Unlike prior neural chess approaches that predict only best moves, C1 generates explainable solutions revealing strategic reasoning. Our pipeline combines supervised fine-tuning and reinforcement learning with theme-balanced data sampling for comprehensive tactical coverage. Master Distillation demonstrates how to inject expert-level knowledge into compact models for under-optimized domains, offering a recipe for unlocking RLVR where LLMs lack sufficient base capabilities.
Authors: Nima H. Siboni, Seyedreza Kiamousavi, Emad Scharifi
Abstract: Industrial process control demands policies that are interpretable and auditable, requirements that black-box neural policies struggle to meet. We study an LLM-driven heuristic synthesis framework for hot steel rolling, in which a language model iteratively proposes and refines human-readable Python controllers using rich behavioral feedback from a physics-based simulator. The framework combines structured strategic ideation, executable code generation, and per-component feedback across diverse operating conditions to search over control logic for height reduction, interpass time, and rolling velocity. Our first contribution is an auditable controller-synthesis pipeline for industrial process control. The generated controllers are explicit programs accessible to expert review, and we pair them with an automated audit pipeline that formally verifies key safety and monotonicity properties for the best synthesized heuristic. Our second contribution is a principled budget allocation strategy for LLM-driven heuristic search: we show that Luby-style universal restarts -- originally developed for randomized algorithms -- transfer directly to this setting, eliminating the need for problem-specific budget tuning. A single 160-iteration Luby campaign approaches the hindsight-optimal budget allocation derived from 52 ad-hoc runs totalling 730 iterations.
Authors: Zihua Wu, Georg Gartner
Abstract: The prevailing approach to improving large language model (LLM) reasoning has centered on expanding context windows, implicitly assuming that more tokens yield better performance. However, empirical evidence - including the "lost in the middle" effect and long-distance relational degradation - demonstrates that contextual space exhibits structural gradients, salience asymmetries, and entropy accumulation under transformer architectures. We introduce Context Cartography, a formal framework for the deliberate governance of contextual space. We define a tripartite zonal model partitioning the informational universe into black fog (unobserved), gray fog (stored memory), and the visible field (active reasoning surface), and formalize seven cartographic operators - reconnaissance, selection, simplification, aggregation, projection, displacement, and layering - as transformations governing information transitions between and within zones. The operators are derived from a systematic coverage analysis of all non-trivial zone transformations and are organized by transformation type (what the operator does) and zone scope (where it applies). We ground the framework in the salience geometry of transformer attention, characterizing cartographic operators as necessary compensations for linear prefix memory, append-only state, and entropy accumulation under expanding context. An analysis of four contemporary systems (Claude Code, Letta, MemOS, and OpenViking) provides interpretive evidence that these operators are converging independently across the industry. We derive testable predictions from the framework - including operator-specific ablation hypotheses - and propose a diagnostic benchmark for empirical validation.
Authors: Truong Thanh Hung Nguyen, H\'el\`ene Fournier, Piper Jackson, Makoto Itoh, Shannon Freeman, Rene Richard, Hung Cao
Abstract: Multi-agent systems (MAS) are increasingly used in healthcare to support complex decision-making through collaboration among specialized agents. Because these systems act as collective decision-makers, they raise challenges for trust, accountability, and human oversight. Existing approaches to trustworthy AI largely rely on explainability, but explainability alone is insufficient in multi-agent settings, as it does not enable care partners to challenge or correct system outputs. To address this limitation, Contestable AI (CAI) characterizes systems that support effective human challenge throughout the decision-making lifecycle by providing transparency, structured opportunities for intervention, and mechanisms for review, correction, or override. This position paper argues that contestability is a necessary design requirement for trustworthy multi-agent algorithmic care systems. We identify key limitations in current MAS and Explainable AI (XAI) research and present a human-in-the-loop framework that integrates structured argumentation and role-based contestation to preserve human agency, clinical responsibility, and trust in high-stakes care contexts.
Authors: Alice Cai, Iman YeckehZaare, Shuo Sun, Vasiliki Charisi, Xinru Wang, Aiman Imran, Robert Laubacher, Alok Prakash, Thomas W. Malone
Abstract: Artificial intelligence (AI) is poised to profoundly reshape how work is executed and organized, but we do not yet have deep frameworks for understanding where AI can be used. Here we provide a comprehensive ontology of work activities that can help systematically analyze and predict uses of AI. To do this, we disaggregate and then substantially reorganize the approximately 20K activities in the US Department of Labor's widely used O*NET occupational database. Next, we use this framework to classify descriptions of 13,275 AI software applications and a worldwide tally of 20.8 million robotic systems. Finally, we use the data about both these kinds of AI to generate graphical displays of how the estimated units and market values of all worldwide AI systems used today are distributed across the work activities that these systems help perform. We find a highly uneven distribution of AI market value across activities, with the top 1.6% of activities accounting for over 60% of AI market value. Most of the market value is used in information-based activities (72%), especially creating information (36%), and only 12% is used in physical activities. Interactive activities include both information-based and physical activities and account for 48% of AI market value, much of which (26%) involves transferring information. These results can be viewed as rough predictions of the AI applicability for all the different work activities down to very low levels of detail. Thus, we believe this systematic framework can help predict at a detailed level where today's AI systems can and cannot be used and how future AI capabilities may change this.
Authors: Yijie Hao, Lingjie Chen, Ali Emami, Joyce Ho
Abstract: Can we trust the reasoning traces that large reasoning models (LRMs) produce? We investigate whether these traces faithfully reflect what drives model outputs, and whether models will honestly report their influence. We introduce Thought Injection, a method that injects synthetic reasoning snippets into a model's
Authors: Bytedance Seed
Abstract: We present Seed1.8, a foundation model aimed at generalized real-world agency: going beyond single-turn prediction to multi-turn interaction, tool use, and multi-step execution. Seed1.8 keeps strong LLM and vision-language performance while supporting a unified agentic interface-search, code generation and execution, and GUI interaction. For deployment, it offers latency- and cost-aware inference, including configurable thinking modes and optimized visual encoding for images and video. We report evaluations on standard benchmarks and application-aligned workflows spanning foundational skills, multimodal understanding, and agentic behavior. Seed1.8 is released to support further research and development on interactive, real-world use cases.
Authors: James Evans, Benjamin Bratton, Blaise Ag\"uera y Arcas
Abstract: The "AI singularity" is often miscast as a monolithic, godlike mind. Evolution suggests a different path: intelligence is fundamentally plural, social, and relational. Recent advances in agentic AI reveal that frontier reasoning models, such as DeepSeek-R1, do not improve simply by "thinking longer". Instead, they simulate internal "societies of thought," spontaneous cognitive debates that argue, verify, and reconcile to solve complex tasks. Moreover, we are entering an era of human-AI centaurs: hybrid actors where collective agency transcends individual control. Scaling this intelligence requires shifting from dyadic alignment (RLHF) toward institutional alignment. By designing digital protocols, modeled on organizations and markets, we can build a social infrastructure of checks and balances. The next intelligence explosion will not be a single silicon brain, but a complex, combinatorial society specializing and sprawling like a city. No mind is an island.
Authors: Zonglin Yang, J. -H. Xie, Lining Zhang, Jiyou Jia, Zhi-X. Chen
Abstract: Deploying high-fidelity AI tutors in schools is often blocked by the Resource Curse -- the need for expensive cloud GPUs and massive data engineering. In this practitioner report, we present a replicable Standard Operating Procedure that breaks this barrier. Using a Vision-Language Model data cleaning strategy and a novel Shadow-RAG architecture, we localized a graduate-level Applied Mathematics tutor using only 3 person-days of non-expert labor and open-weights 32B models deployable on a single consumer-grade GPU. Our pilot study on a full graduate-level final exam reveals a striking emergence phenomenon: while both zero-shot baselines and standard retrieval stagnate around 50-60% accuracy across model generations, the Shadow Agent, which provides structured reasoning guidance, triggers a massive capability surge in newer 32B models, boosting performance from 74% (Naive RAG) to mastery level (90%). In contrast, older models see only modest gains (~10%). This suggests that such guidance is the key to unlocking the latent power of modern small language models. This work offers a cost-effective, scientifically grounded blueprint for ubiquitous AI education.
Authors: Xueqi Ma, Shuo Yang, Yanbei Jiang, Shu Liu, Zhenzhen Liu, Jiayang Ao, Xingjun Ma, Sarah Monazam Erfani, James Bailey
Abstract: Despite remarkable advances in large Vision-Language Models (VLMs), spatial reasoning remains a persistent challenge. In this work, we investigate how attention heads within VLMs contribute to spatial reasoning by analyzing their functional roles through a mechanistic interpretability lens. We introduce CogVSR, a dataset that decomposes complex spatial reasoning questions into step-by-step subquestions designed to simulate human-like reasoning via a chain-of-thought paradigm, with each subquestion linked to specific cognitive functions such as spatial perception or relational reasoning. Building on CogVSR, we develop a probing framework to identify and characterize attention heads specialized for these functions. Our analysis across diverse VLM families reveals that these functional heads are universally sparse, vary in number and distribution across functions. Notably, spatially specialized heads are fewer than those for other cognitive functions, highlighting their scarcity. We propose methods to activate latent spatial heads, improving spatial understanding. Intervention experiments further demonstrate their critical role in spatial reasoning: removing functional heads leads to performance degradation, while emphasizing them enhances accuracy. This study provides new interpretability driven insights into how VLMs attend to space and paves the way for enhancing complex spatial reasoning in multimodal models.
Authors: Ruixiang Liu, Zhenlong Li, Ali Khosravi Kazazi
Abstract: The rapid growth in the volume, variety, and velocity of geospatial data has created data ecosystems that are highly distributed, heterogeneous, and semantically inconsistent. Existing data catalogs, portals, and infrastructures still rely largely on keyword-based search with limited semantic support, which often fails to capture user intent and leads to weak retrieval performance. To address these challenges, this study proposes a knowledge graph-driven multi-agent framework for intelligent geospatial data discovery, powered by large language models. The framework introduces a unified geospatial metadata ontology as a semantic mediation layer to align heterogeneous metadata standards across platforms and constructs a geospatial metadata knowledge graph to explicitly model datasets and their multidimensional relationships. Building on the structured representation, the framework adopts a multi-agent collaborative architecture to perform intent parsing, knowledge graph retrieval, and answer synthesis, forming an interpretable and closed-loop discovery process from user queries to results. Results from representative use cases and performance evaluation show that the framework substantially improves intent matching accuracy, ranking quality, recall, and discovery transparency compared with traditional systems. This study advances geospatial data discovery toward a more semantic, intent-aware, and intelligent paradigm, providing a practical foundation for next-generation intelligent and autonomous spatial data infrastructures and contributing to the broader vision of Autonomous GIS.
Authors: Yicai Xing
Abstract: Contemporary societies face a severe crisis of demographic reproduction. Global fertility rates continue to decline precipitously, with East Asian nations exhibiting the most dramatic trends -- China's total fertility rate (TFR) fell to approximately 1.0 in 2023, while South Korea's dropped below 0.72. Simultaneously, the institution of marriage is undergoing structural disintegration: educated women rationally reject unions lacking both emotional fulfillment and economic security, while a growing proportion of men at the lower end of the socioeconomic spectrum experience chronic sexual deprivation, anxiety, and learned helplessness. This paper proposes a computational framework for modeling and evaluating a Stratified Polyamory System (SPS) using techniques from agent-based modeling (ABM), multi-agent reinforcement learning (MARL), and large language model (LLM)-empowered social simulation. The SPS permits individuals to maintain a limited number of legally recognized secondary partners in addition to one primary spouse, combined with socialized child-rearing and inheritance reform. We formalize the A/B/C stratification as heterogeneous agent types in a multi-agent system and model the matching process as a MARL problem amenable to Proximal Policy Optimization (PPO). The mating network is analyzed using graph neural network (GNN) representations. Drawing on evolutionary psychology, behavioral ecology, social stratification theory, computational social science, algorithmic fairness, and institutional economics, we argue that SPS can improve aggregate social welfare in the Pareto sense. Preliminary computational results demonstrate the framework's viability in addressing the dual crisis of female motherhood penalties and male sexlessness, while offering a non-violent mechanism for wealth dispersion analogous to the historical Chinese Grace Decree (Tui'en Ling).
Authors: Zacharie Bugaud
Abstract: Multi-RF Fusion achieves a test ROC-AUC of 0.8476 +/- 0.0002 on ogbg-molhiv (10 seeds), placing #1 on the OGB leaderboard ahead of HyperFusion (0.8475 +/- 0.0003). The core of the method is a rank-averaged ensemble of 12 Random Forest models trained on concatenated molecular fingerprints (FCFP, ECFP, MACCS, atom pairs -- 4,263 dimensions total), blended with deep-ensembled GNN predictions at 12% weight. Two findings drive the result: (1) setting max_features to 0.20 instead of the default sqrt(d) gives a +0.008 AUC gain on this scaffold split, and (2) averaging GNN predictions across 10 seeds before blending with the RF eliminates GNN seed variance entirely, dropping the final standard deviation from 0.0008 to 0.0002. No external data or pre-training is used.
Authors: Jinming Yang, Xinyu Jiang, Xinshan Jiao, Xinping Zhang
Abstract: We present an LLM-driven multi-agent probabilistic modeling framework that demonstrates how differences in students' subjective social perceptions arise and evolve in real-world classroom settings, under constraints from an observed social network and limited questionnaire data. When social information is incomplete and the accuracy of perception differs between students, they can form different views of the same group structure from local cues they can access. Repeated peer communication and belief updates can gradually change these views and, over time, lead to stable group-level differences. To avoid assuming a global "god's-eye view," we assign each student an individualized subjective graph that shows which social ties they can perceive and how far information is reachable from their perspective. All judgments and interactions are restricted to this subjective graph: agents use retrieval-augmented generation (RAG) to access only local information and then form evaluations of peers' competence and social standing. We also add structural perturbations related to social-anxiety to represent consistent individual differences in the accuracy of social perception. During peer exchanges, agents share narrative assessments of classmates' academic performance and social position with uncertainty tags, and update beliefs probabilistically using LLM-based trust scores. Using the time series of six real exam scores as an exogenous reference, we run multi-step simulations to examine how epistemic uncertainty spreads through local interactions. Experiments show that, without relying on global information, the framework reproduces several collective dynamics consistent with real-world educational settings. The code is released at https://anonymous.4open.science/r/Rashomonomon-0126.
Authors: Xiaohan Wang (Sue), Nan Zhang (Sue), Sulene Han (Sue), Keguang Tang (Sue), Lei Xu (Sue), Zhiping Li (Sue), Xiue (Sue), Liu, Xiaomei Han
Abstract: The pharmaceutical industry is facing challenges with quality management such as high costs of compliance, slow responses and disjointed knowledge. This paper presents GMPilot, a domain-specific AI agent that is designed to support FDA cGMP compliance. GMPilot is based on a curated knowledge base of regulations and historical inspection observations and uses Retrieval-Augmented Generation (RAG) and Reasoning-Acting (ReAct) frameworks to provide real-time and traceable decision support to the quality professionals. In a simulated inspection scenario, GMPilot shows how it can improve the responsiveness and professionalism of quality professionals by providing structured knowledge retrieval and verifiable regulatory and case-based support. Although GMPilot lacks in the aspect of regulatory scope and model interpretability, it is a viable avenue of improving quality management decision-making in the pharmaceutical sector using intelligent approaches and an example of specialized application of AI in highly regulated sectors.
Authors: Steven Johnson
Abstract: As AI agent ecosystems grow, agents need mechanisms to monitor relevant knowledge in real time. Semantic publish-subscribe systems address this by matching new content against vector subscriptions. However, in multi-agent settings where agents operate under different data handling policies, unrestricted semantic subscriptions create policy violations: agents receive notifications about content they are not authorized to access. We introduce governance-aware vector subscriptions, a mechanism that composes semantic similarity matching with multi-dimensional policy predicates grounded in regulatory frameworks (EU DSM Directive, EU AI Act). The policy predicate operates over multiple independent dimensions (processing level, direct marketing restrictions, training opt-out, jurisdiction, and scientific usage) each with distinct legal bases. Agents subscribe to semantic regions of a curated knowledge base; notifications are dispatched only for validated content that passes both the similarity threshold and all applicable policy constraints. We formalize the mechanism, implement it within AIngram (an operational multi-agent knowledge base), and evaluate it using the PASA benchmark. We validate the mechanism on a synthetic corpus (1,000 chunks, 93 subscriptions, 5 domains): the governed mode correctly enforces all policy constraints while preserving delivery of authorized content. Ablation across five policy dimensions shows that no single dimension suffices for full compliance.
Authors: Tianyou Lai, Wentao Yue, Jiayi Zhou, Chaoyuan Hao, Lingke Chang, Qingyu Mao, Zhibo Niu, Qilei Li
Abstract: Financial time-series forecasting in real-world high-frequency markets is often hindered by delayed or partially stale observations caused by asynchronous data acquisition and transmission latency. To better reflect such practical conditions, we investigate a simulated delay setting where a portion of historical signals is corrupted by a Zero-Order Hold (ZOH) mechanism, significantly increasing forecasting difficulty through stepwise stagnation artifacts. In this paper, we propose ReLaMix (Residual Latency-Aware Mixing Network), a lightweight extension of TimeMixer that integrates learnable bottleneck compression with residual refinement for robust signal recovery under delayed observations. ReLaMix explicitly suppresses redundancy from repeated stale values while preserving informative market dynamics via residual mixing enhancement. Experiments on a large-scale second-resolution PAXGUSDT benchmark demonstrate that ReLaMix consistently achieves state-of-the-art accuracy across multiple delay ratios and prediction horizons, outperforming strong mixer and Transformer baselines with substantially fewer parameters. Moreover, additional evaluations on BTCUSDT confirm the cross-asset generalization ability of the proposed framework. These results highlight the effectiveness of residual bottleneck mixing for high-frequency financial forecasting under realistic latency-induced staleness.
Authors: Tai-Quan Peng, Yuan Tian, Songsong Liang, Dazhen Deng, Yingcai Wu
Abstract: Large language models make agent-based simulation more behaviorally expressive, but they also sharpen a basic methodological tension: fluent, human-like output is not, by itself, evidence for theory. We evaluate what an LLM-driven simulation can credibly support using information engagement on social media as a test case. In a Weibo-like environment, we manipulate information load and descriptive norms, while allowing popularity cues (cumulative likes and Sina Weibo-style cumulative reshares) to evolve endogenously. We then ask whether simulated behavior changes in theoretically interpretable ways under these controlled variations, rather than merely producing plausible-looking traces. Engagement responds systematically to information load and descriptive norms, and sensitivity to popularity cues varies across contexts, indicating conditionality rather than rigid prompt compliance. We discuss methodological implications for simulation-based communication research, including multi-condition stress tests, explicit no-norm baselines because default prompts are not blank controls, and design choices that preserve endogenous feedback loops when studying bandwagon dynamics.
Authors: Shouqiao Wang, Marcello Politi, Samuele Marro, Davide Crapis
Abstract: As agentic systems move into real-world deployments, their decisions increasingly depend on external inputs such as retrieved content, tool outputs, and information provided by other actors. When these inputs can be strategically shaped by adversaries, the relevant security risk extends beyond a fixed library of prompt attacks to adaptive strategies that steer agents toward unfavorable outcomes. We propose profit-driven red teaming, a stress-testing protocol that replaces handcrafted attacks with a learned opponent trained to maximize its profit using only scalar outcome feedback. The protocol requires no LLM-as-judge scoring, attack labels, or attack taxonomy, and is designed for structured settings with auditable outcomes. We instantiate it in a lean arena of four canonical economic interactions, which provide a controlled testbed for adaptive exploitability. In controlled experiments, agents that appear strong against static baselines become consistently exploitable under profit-optimized pressure, and the learned opponent discovers probing, anchoring, and deceptive commitments without explicit instruction. We then distill exploit episodes into concise prompt rules for the agent, which make most previously observed failures ineffective and substantially improve target performance. These results suggest that profit-driven red-team data can provide a practical route to improving robustness in structured agent settings with auditable outcomes.
Authors: Jo\~ao Paulo A. Almeida, Giancarlo Guizzardi, Tiago Prince Sales, Claudenir M. Fonseca
Abstract: gUFO is a lightweight implementation of the Unified Foundational Ontology (UFO) suitable for Semantic Web OWL 2 DL applications. UFO is a mature foundational ontology with a rich axiomatization and that has been employed in a significant number of projects in research and industry. Moreover, it is currently in the process of standardization by the International Organization for Standardization as the ISO/IEC CD 21838-5. gUFO stands out from other foundational ontology implementations (such as those provided for BFO and DOLCE) given its unique support for a typology of types (operationalizing OntoClean guidelines), its reification patterns for intrinsic and relational aspects, and its support for situations and high-order types. gUFO provides well-founded patterns to address recurrent problems in Semantic Web knowledge graphs. In this paper, we present gUFO with its constituting categories, relations and constraints, discuss how it differs from the original UFO reference ontology, elaborate on its community adoption, and systematically position it in relation to existing OWL-based implementations of popular alternative foundational ontologies.
Authors: Sukriti Manna, Henry Chan, Subramanian K. R. S. Sankaranarayanan
Abstract: Multiphysics simulation frameworks such as MOOSE provide rigorous engines for phase-field materials modeling, yet adoption is constrained by the expertise required to construct valid input files, coordinate parameter sweeps, diagnose failures, and extract quantitative results. We introduce AutoMOOSE, an open-source agentic framework that orchestrates the full simulation lifecycle from a single natural-language prompt. AutoMOOSE deploys a five-agent pipeline in which the Input Writer coordinates six sub-agents and the Reviewer autonomously corrects runtime failures without user intervention. A modular plugin architecture enables new phase-field formulations without modifying the core framework, and a Model Context Protocol (MCP) server exposes the workflow as ten structured tools for interoperability with any MCP-compatible client. Validated on a four-temperature copper grain growth benchmark, AutoMOOSE generates MOOSE input files with 6 of 12 structural blocks matching a human expert reference exactly and 4 functionally equivalent, executes all runs in parallel with a 1.8x speedup, and performs an end-to-end physical consistency check spanning intent, finite-element execution, and Arrhenius kinetics with no human verification. Grain coarsening kinetics are recovered with R^2 = 0.90-0.95 at T >= 600 K; the recovered activation energy Q_fit = 0.296 eV is consistent with a human-written reference (Q_fit = 0.267 eV) under identical parameters. Three runtime failure classes were diagnosed and resolved autonomously within a single correction cycle, and every run produces a provenance record satisfying FAIR data principles. These results show that the gap between knowing the physics and executing a validated simulation campaign can be bridged by a lightweight multi-agent orchestration layer, providing a pathway toward AI-driven materials discovery and self-driving laboratories.
Authors: Akshay K. Jagadish, Milena Rmus, Kristin Witte, Marvin Mathony, Marcel Binz, Eric Schulz
Abstract: The cognitive sciences aim to understand intelligence by formalizing underlying operations as computational models. Traditionally, this follows a cycle of discovery where researchers develop paradigms, collect data, and test predefined model classes. However, this manual pipeline is fundamentally constrained by the slow pace of human intervention and a search space limited by researchers' background and intuition. Here, we propose a paradigm shift toward a fully automated, in silico science of the mind that implements every stage of the discovery cycle using Large Language Models (LLMs). In this framework, experimental paradigms exploring conceptually meaningful task structures are directly sampled from an LLM. High-fidelity behavioral data are then simulated using foundation models of cognition. The tedious step of handcrafting cognitive models is replaced by LLM-based program synthesis, which performs a high-throughput search over a vast landscape of algorithmic hypotheses. Finally, the discovery loop is closed by optimizing for ''interestingness'', a metric of conceptual yield evaluated by an LLM-critic. By enabling a fast and scalable approach to theory development, this automated loop functions as a high-throughput in-silico discovery engine, surfacing informative experiments and mechanisms for subsequent validation in real human populations.
Authors: Benedikt Hornig, Reuth Mirsky
Abstract: In shared autonomy, a critical tension arises when an automated assistant must choose between obeying a human's instruction and deliberately overriding it to prevent harm. This safety-critical behavior is known as intelligent disobedience. To formalize this dynamic, this paper introduces the Intelligent Disobedience Game (IDG), a sequential game-theoretic framework based on Stackelberg games that models the interaction between a human leader and an assistive follower operating under asymmetric information. It characterizes optimal strategies for both agents across multi-step scenarios, identifying strategic phenomena such as ``safety traps,'' where the system indefinitely avoids harm but fails to achieve the human's goal. The IDG provides a needed mathematical foundation that enables both the algorithmic development of agents that can learn safe non-compliance and the empirical study of how humans perceive and trust disobedient AI. The paper further translates the IDG into a shared control Multi-Agent Markov Decision Process representation, forming a compact computational testbed for training reinforcement learning agents.
Authors: Erich Studerus, Vivienne Jia Zhong, Stephan Vonschallen
Abstract: Despite recent advances in integrating Large Language Models (LLMs) into social robotics, two weaknesses persist. First, existing implementations on platforms like Pepper often rely on cascaded Speech-to-Text (STT)->LLM->Text-to-Speech (TTS) pipelines, resulting in high latency and the loss of paralinguistic information. Second, most implementations fail to fully leverage the LLM's capabilities for multimodal perception and agentic control. We present an open-source Android framework for the Pepper robot that addresses these limitations through two key innovations. First, we integrate end-to-end Speech-to-Speech (S2S) models to achieve low-latency interaction while preserving paralinguistic cues and enabling adaptive intonation. Second, we implement extensive Function Calling capabilities that elevate the LLM to an agentic planner, orchestrating robot actions (navigation, gaze control, tablet interaction) and integrating diverse multimodal feedback (vision, touch, system state). The framework runs on the robot's tablet but can also be built to run on regular Android smartphones or tablets, decoupling development from robot hardware. This work provides the HRI community with a practical, extensible platform for exploring advanced LLM-driven embodied interaction.
Authors: Ziquan Wang, Zhongqi Lu
Abstract: We propose Knowledge Boundary Discovery (KBD), a reinforcement learning based framework to explore the knowledge boundaries of the Large Language Models (LLMs). We define the knowledge boundary by automatically generating two types of questions: (i) those the LLM can confidently answer (within-knowledge boundary) and (ii) those it cannot (beyond-knowledge boundary). Iteratively exploring and exploiting the LLM's responses to find its knowledge boundaries is challenging because of the hallucination phenomenon. To find the knowledge boundaries of an LLM, the agent interacts with the LLM under the modeling of exploring a partially observable environment. The agent generates a progressive question as the action, adopts an entropy reduction as the reward, receives the LLM's response as the observation and updates its belief states. We demonstrate that the KBD detects knowledge boundaries of LLMs by automatically finding a set of non-trivial answerable and unanswerable questions. We validate the KBD by comparing its generated knowledge boundaries with manually crafted LLM benchmark datasets. Experiments show that our KBD-generated question set is comparable to the human-generated datasets. Our approach paves a new way to evaluate LLMs.
Authors: Ye Tian, Jingyi Zhang, Zihao Wang, Xiaoyuan Ren, Xiaofan Yu, Onat Gungor, Tajana Rosing
Abstract: Autonomous driving requires reliable reasoning over fine-grained 3D scene facts. Fine-grained question answering over multi-modal driving observations provides a natural way to evaluate this capability, yet existing perception pipelines and driving-oriented large language model (LLM) methods still suffer from unreliable scene facts, hallucinations, opaque reasoning, and heavy reliance on task-specific training. We present KLDrive, the first knowledge-graph-augmented LLM reasoning framework for fine-grained question answering in autonomous driving. KLDrive addresses this problem through designing two tightly coupled components: an energy-based scene fact construction module that consolidates multi-source evidence into a reliable scene knowledge graph, and an LLM agent that performs fact-grounded reasoning over a constrained action space under explicit structural constraints. By combining structured prompting with few-shot in-context exemplars, the framework adapts to diverse reasoning tasks without heavy task-specific fine-tuning. Experiments on two large-scale autonomous-driving QA benchmarks show that KLDrive outperforms prior state-of-the-art methods, achieving the best overall accuracy of 65.04% on NuScenes-QA and the best SPICE score of 42.45 on GVQA. On counting, the most challenging factual reasoning task, it improves over the strongest baseline by 46.01 percentage points, demonstrating substantially reduced hallucinations and the benefit of coupling reliable scene fact construction with explicit reasoning.
Authors: Jianing Wang, Jianfei Zhang, Qi Guo, Linsen Guo, Rumei Li, Chao Zhang, Chong Peng, Cunguang Wang, Dengchang Zhao, Jiarong Shi, Jingang Wang, Liulin Feng, Mengxia Shen, Qi Li, Shengnan An, Shun Wang, Wei Shi, Xiangyu Xi, Xiaoyu Li, Xuezhi Cao, Yi Lu, Yunke Zhao, Zhengyu Chen, Zhimin Lin, Wei Wang, Peng Pei, Xunliang Cai
Abstract: We introduce LongCat-Flash-Prover, a flagship 560-billion-parameter open-source Mixture-of- Experts (MoE) model that advances Native Formal Reasoning in Lean4 through agentic tool-integrated reasoning (TIR). We decompose the native formal reasoning task into three independent formal capabilities, i.e., auto-formalization, sketching, and proving. To facilitate these capabilities, we propose a Hybrid-Experts Iteration Framework to expand high-quality task trajectories, including generating a formal statement based on a given informal problem, producing a whole-proof directly from the statement, or a lemma-style sketch. During agentic RL, we present a Hierarchical Importance Sampling Policy Optimization (HisPO) algorithm, which aims to stabilize the MoE model training on such long-horizon tasks. It employs a gradient masking strategy that accounts for the policy staleness and the inherent train-inference engine discrepancies at both sequence and token levels. Additionally, we also incorporate theorem consistency and legality detection mechanisms to eliminate reward hacking issues. Extensive evaluations show that our LongCat-Flash-Prover sets a new state-of-the-art for open-weights models in both auto-formalization and theorem proving. Demonstrating remarkable sample efficiency, it achieves a 97.1% pass rate on MiniF2F-Test using only 72 inference budget per problem. On more challenging benchmarks, it solves 70.8% of ProverBench and 41.5% of PutnamBench with no more than 220 attempts per problem, significantly outperforming existing open-weights baselines.
Authors: Zhuojie Yang, Wentao Wan, Keze Wang
Abstract: Training large language models (LLMs) with synthetic reasoning data has become a popular approach to enhancing their reasoning capabilities, while a key factor influencing the effectiveness of this paradigm is the quality of the generated multi-step reasoning data. To generate high-quality reasoning data, many recent methods generate synthetic reasoning paths and filter them based on final answer correctness, often overlooking flaws in intermediate reasoning steps. To enhance the verification of intermediate reasoning steps, prior work primarily resorts to code execution or symbolic reasoning engines. However, code-based validation is restricted to code or mathematical tasks, and reasoning engines require a well-structured and complete context. As a result, existing methods fail to function effectively in natural language reasoning tasks that involve ambiguous or incomplete contexts. In these tasks, synthetic data still lack reliable checks for verifying each reasoning step. To address this challenge, we introduce ORACLE, a structured data generation framework inspired by syllogistic reasoning. ORACLE integrates the generative strengths of LLMs with symbolic supervision: the LLM produces step-wise reasoning contexts, while a symbolic reasoning engine verifies the validity of each intermediate step. By employing a unified prompting template to elicit modular reasoning chains, ORACLE enables fine-grained, step-level validation, facilitating the construction of high-quality multi-step reasoning data. Across six logical, factual, and commonsense reasoning benchmarks, our ORACLE consistently outperforms strong baselines on multiple models.
Authors: Zihui Chen, Yuling Wang, Pengfei Jiao, Kai Wu, Xiao Wang, Xiang Ao, Dalin Zhang
Abstract: Text-attributed graphs (TAGs) enhance graph learning by integrating rich textual semantics and topological context for each node. While boosting expressiveness, they also expose new vulnerabilities in graph learning through text-based adversarial surfaces. Recent advances leverage diverse backbones, such as graph neural networks (GNNs) and pre-trained language models (PLMs), to capture both structural and textual information in TAGs. This diversity raises a key question: How can we design universal adversarial attacks that generalize across architectures to assess the security of TAG models? The challenge arises from the stark contrast in how different backbones-GNNs and PLMs-perceive and encode graph patterns, coupled with the fact that many PLMs are only accessible via APIs, limiting attacks to black-box settings. To address this, we propose BadGraph, a novel attack framework that deeply elicits large language models (LLMs) understanding of general graph knowledge to jointly perturb both node topology and textual semantics. Specifically, we design a target influencer retrieval module that leverages graph priors to construct cross-modally aligned attack shortcuts, thereby enabling efficient LLM-based perturbation reasoning. Experiments show that BadGraph achieves universal and effective attacks across GNN- and LLM-based reasoners, with up to a 76.3% performance drop, while theoretical and empirical analyses confirm its stealthy yet interpretable nature.
Authors: Leonid Ugadiarov, Yuri Kuratov, Aleksandr Panov, Alexey Skrynnik
Abstract: Neural tree search is a powerful decision-making algorithm widely used in complex domains such as game playing and model-based reinforcement learning. Recent work has applied AlphaZero-style tree search to enhance the reasoning capabilities of Large Language Models (LLMs) during inference, but we find that this approach suffers from a scaling failure: on GSM8K and Game24, accuracy drops as the search budget increases. In this paper, we present ReSCALE, an adaptation of Gumbel AlphaZero MCTS that replaces Dirichlet noise and PUCT selection with Gumbel sampling and Sequential Halving, restoring monotonic scaling without changes to the model or its training. ReSCALE reaches 58.4\% on GSM8K and 85.3\% on Game24 at budgets where the baseline degrades. Ablations confirm that Sequential Halving is the primary driver of the improvement.
Authors: Keito Inoshita, Michiaki Omura, Tsukasa Yamanaka, Go Maeda, Kentaro Tsuji
Abstract: While AI-assisted writing has been widely reported to improve essay quality, its impact on the structural diversity of student thinking remains unexplored. Analyzing 6,875 essays across five conditions (Human-only, AI-only, and three Human+AI prompt strategies), we provide the first empirical evidence of a Quality-Homogenization Tradeoff, in which substantial quality gains co-occur with significant homogenization. The effect is dimension-specific: cohesion architecture lost 70-78% of its variance, whereas perspective plurality was diversified. Convergence target analysis further revealed that AI-augmented essays were pulled toward AI structural patterns yet deviated significantly from the Human-AI axis, indicating simultaneous partial replacement and partial emergence. Crucially, prompt specificity reversed homogenization into diversification on argument depth, demonstrating that homogenization is not an intrinsic property of AI but a function of interaction design.
Authors: Haoyu Qiao, Hao Zhang, Shanwen Mao, Siyao Cheng, Jie Liu
Abstract: Large language models (LLMs) deliver impressive capabilities but incur substantial inference latency and cost, which hinders their deployment in latency-sensitive and resource-constrained scenarios. Cloud-edge-device collaborative inference has emerged as a promising paradigm by dynamically routing queries to models of different capacities across tiers. In this paper, we propose ConsRoute, a lightweight, semantic-aware, and adaptive routing framework that significantly improves inference efficiency while minimizing impact on response quality. Unlike prior routing methods that rely on predicting coarse-grained output quality gaps, ConsRoute leverages a reranker to directly assess the semantic consistency between responses generated by models at different tiers, yielding fine-grained soft supervision signals for routing. To minimize device-side overhead, ConsRoute reuses hidden states from the LLM prefilling stage as compact query representations, avoiding additional encoders or inference passes. Furthermore, these representations are clustered, and Bayesian optimization is employed to learn cluster-specific routing thresholds that dynamically balance quality, latency, and cost under heterogeneous query distributions. Extensive experiments demonstrate that ConsRoute achieves near-cloud performance (>=95%) while reducing end-to-end latency and inference cost by nearly 40%, consistently outperforming existing routing baselines in both response quality and system efficiency.
Authors: Yu Luo, Rongchen Gao, Lu Teng, Xidao Wen, Jiamin Jiang, Qingliang Zhang, Yongqian Sun, Shenglin Zhang, Jiasong Feng, Tong Liu, Wenjie Zhang, Dan Pei
Abstract: Logical reasoning encompasses deduction, induction, and abduction. However, while Large Language Models (LLMs) have effectively mastered the former two, abductive reasoning remains significantly underexplored. Existing frameworks, predominantly designed for static deductive tasks, fail to generalize to abductive reasoning due to unstructured state representation and lack of explicit state control. Consequently, they are inevitably prone to Evidence Fabrication, Context Drift, Failed Backtracking, and Early Stopping. To bridge this gap, we introduce Graph of States (GoS), a general-purpose neuro-symbolic framework tailored for abductive tasks. GoS grounds multi-agent collaboration in a structured belief states, utilizing a causal graph to explicitly encode logical dependencies and a state machine to govern the valid transitions of the reasoning process. By dynamically aligning the reasoning focus with these symbolic constraints, our approach transforms aimless, unconstrained exploration into a convergent, directed search. Extensive evaluations on two real-world datasets demonstrate that GoS significantly outperforms all baselines, providing a robust solution for complex abductive tasks. Code repo and all prompts: https://anonymous.4open.science/r/Graph-of-States-5B4E.
URLs: https://anonymous.4open.science/r/Graph-of-States-5B4E.
Authors: Zachary F. Mainen
Abstract: Externalized reasoning is already exploited by transformer-based agents through chain-of-thought, but structured retrieval -- indexing over one's own reasoning state -- remains underexplored. We formalize the transformer context window as an I/O page and prove that tool-augmented agents with indexed external memory achieve exponentially lower retrieval cost than agents restricted to sequential scanning: $O(\log_b N)$ versus $\Omega(N)$ page reads per query, and $O(T \log_b T)$ versus $\Theta(T^2)$ cumulative cost over $T$ reasoning steps -- a gap that widens as deliberation deepens. We test these predictions on a controlled lookup benchmark across three content types -- random hashes, ordered integers, and encyclopedia entries -- varying store size from 50 to 5,000 items, and replicate key conditions across two model generations (GPT-4o-mini and GPT-5.4). On abstract content, the indexed agent achieves median 1 page read regardless of store size, confirming the $O(1)$ prediction. Sorted pages without an index fail to close the gap: the weaker model cannot sustain binary search at scale, and the stronger model achieves near-optimal $\log_2 N$ search but still loses to the index by $5\times$. On familiar content (encyclopedia entries), a competing failure mode emerges: the model recognizes the domain, bypasses the retrieval protocol, and generates answers from parametric memory, producing catastrophic token expenditure even when the index is sound. This parametric memory competition dissociates the two cognitive operations that indexing combines: understanding content (where language models excel) and following navigational protocols (where they fail when understanding tempts them to shortcut). The result argues for a separation of concerns: use language models for index construction, where semantic understanding helps, and deterministic algorithms for index traversal, where it hurts.
Authors: Pantea Karimi, Kimia Noorbakhsh, Mohammad Alizadeh, Hari Balakrishnan
Abstract: Designing high-performance system heuristics is a creative, iterative process requiring experts to form hypotheses and execute multi-step conceptual shifts. While Large Language Models (LLMs) show promise in automating this loop, they struggle with complex system problems due to two critical failure modes: evolutionary neighborhood bias and the coherence ceiling. Evolutionary methods often remain trapped in local optima by relying on scalar benchmark scores, failing when coordinated multi-step changes are required. Conversely, existing agentic frameworks suffer from context degradation over long horizons or fail to accumulate knowledge across independent runs. We present Engram, an agentic researcher architecture that addresses these limitations by decoupling long-horizon exploration from the constraints of a single context window. Engram organizes exploration into a sequence of agents that iteratively design, test, and analyze mechanisms. At the conclusion of each run, an agent stores code snapshots, logs, and results in a persistent Archive and distills high-level modeling insights into a compact, persistent Research Digest. Subsequent agents then begin with a fresh context window, reading the Research Digest to build on prior discoveries. We find that Engram exhibits superior performance across diverse domains including multi-cloud multicast, LLM inference request routing, and optimizing KV cache reuse in databases with natural language queries.
Authors: Seth Dobrin, Lukasz Chmiel
Abstract: This paper presents ARYA, a composable, physics-constrained, deterministic world model architecture built on five foundational principles: nano models, composability, causal reasoning, determinism, and architectural AI safety. We demonstrate that ARYA satisfies all canonical world model requirements, including state representation, dynamic prediction, causal and physical awareness, temporal consistency, generalization, learnability, and planning and control. Unlike monolithic foundation models, the ARYA foundation model implements these capabilities through a hierarchical system-of-system-of-systems of specialized nano models, orchestrated by AARA (ARYA Autonomous Research Agent), an always-on cognitive daemon that executes a continuous sense-decide-act-learn loop. The nano model architecture provides linear scaling, sparse activation, selective untraining, and sub-20-second training cycles, resolving the traditional tension between capability and computational efficiency. A central contribution is the Unfireable Safety Kernel: an architecturally immutable safety boundary that cannot be disabled or circumvented by any system component, including its own self-improvement engine. This is not a social or ethical alignment statement; it is a technical framework ensuring human control persists as autonomy increases. Safety is an architectural constraint governing every operation, not a policy layer applied after the fact. We present formal alignment between ARYA's architecture and canonical world model requirements, and report summarizing its state-of-the-art performance across 6 of 9 competitive benchmarks head-to-head with GPT-5.2, Opus 4.6, and V-JEPA-2. All with zero neural network parameters, across seven active industry domain nodes spanning aerospace, pharma manufacturing, oil and gas, smart cities, biotech, defense, and medical devices.
Authors: Dongyoung Kim, Sumin Park, Woomin Song, Seungku Kim, Taeyoung Kim, Huiwon Jang, Jinwoo Shin, Jaehyung Kim, Younggyo Seo
Abstract: Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent work has explored enhancing embodied reasoning in MLLMs through supervision of vision-question-answering type. However, these approaches have been reported to result in unstable VLA performance, often yielding only marginal or even negative gains. In this paper, we propose a more systematic MLLM training framework RoboAlign that reliably improves VLA performance. Our key idea is to sample action tokens via zero-shot natural language reasoning and refines this reasoning using reinforcement learning (RL) to improve action accuracy. As a result, RoboAlign bridges the modality gap between language and low-level actions in MLLMs, and facilitate knowledge transfer from MLLM to VLA. To validate the effectiveness of RoboAlign, we train VLAs by adding a diffusion-based action head on top of an MLLM backbone and evaluate them on major robotics benchmarks. Remarkably, by performing RL-based alignment after SFT using less than 1\% of the data, RoboAlign achieves performance improvements of 17.5\%, 18.9\%, and 106.6\% over SFT baselines on LIBERO, CALVIN, and real-world environments, respectively.
Authors: Ulisses Braga-Neto
Abstract: In this short note we propose using agentic swarms of virtual labs as a model of an AI Science Community. In this paradigm, each particle in the swarm represents a complete virtual laboratory instance, enabling collective scientific exploration that mirrors real-world research communities. The framework leverages the inherent properties of swarm intelligence - decentralized coordination, balanced exploration-exploitation trade-offs, and emergent collective behavior - to simulate the behavior of a scientific community and potentially accelerate scientific discovery. We discuss architectural considerations, inter-laboratory communication and influence mechanisms including citation-analogous voting systems, fitness function design for quantifying scientific success, anticipated emergent behaviors, mechanisms for preventing lab dominance and preserving diversity, and computational efficiency strategies to enable large swarms exhibiting complex emergent behavior analogous to real-world scientific communities. A working instance of the AI Science Community is currently under development.
Authors: Liang Ding
Abstract: LLM agents fail on the majority of real-world tasks -- GPT-4o succeeds on fewer than 15% of WebArena navigation tasks and below 55% pass@1 on ToolBench (Zhou et al., 2024; Qin et al., 2024) -- yet every failed trajectory is routinely discarded, wasting the dominant source of collected experience. We introduce AgentHER, a framework that recovers this lost training signal by adapting the Hindsight Experience Replay (HER; Andrychowicz et al., 2017) principle to natural-language agent trajectories for offline data augmentation. The key insight is simple: a trajectory that fails goal A is often a correct demonstration for some achievable alternative goal B. AgentHER realises this idea through a four-stage pipeline -- failure classification, outcome extraction, LLM-guided prompt relabeling with confidence gating, and data packaging -- that converts discarded failures into high-quality SFT, DPO, and ShareGPT training data, with both zero-cost rule-based and LLM-judge implementations. On WebArena (Zhou et al., 2024) and ToolBench (Qin et al., 2024), AgentHER improves over success-only SFT by +7.1-11.7 pp across four model families (GPT-4o, Qwen2.5-72B/7B, LLaMA-3.1-8B), while achieving 2x data efficiency -- matching baseline performance with only 50% of successful demonstrations. Gains are consistent from 1.5B to 72B parameters (+5.8-9.2 pp) and compound under iterative redeployment (+2.1 pp over additional rounds). Human evaluation confirms 97.7% relabeling precision under multi-judge verification.
Authors: Liang Ding
Abstract: LLM-as-Judge evaluation fails agent tasks because a fixed rubric cannot capture what matters for this task: code debugging demands Correctness and Error Handling; web navigation demands Goal Alignment and Action Efficiency. We present ADARUBRIC, which closes this gap by generating task-specific evaluation rubrics on the fly from task descriptions, scoring trajectories step-by-step with confidence-weighted per-dimension feedback, and filtering preference pairs with the novel DimensionAwareFilter - a provably necessary condition for preventing high-scoring dimensions from masking dimension-level failures. On WebArena and ToolBench, ADARUBRIC achieves Pearson r=0.79 human correlation (+0.16 over the best static baseline) with deployment-grade reliability (Krippendorff's $\alpha$=0.83). DPO agents trained on ADARUBRIC preference pairs gain +6.8 to +8.5 pp task success over Prometheus across three benchmarks; gains transfer to SWE-bench code repair (+4.9 pp) and accelerate PPO convergence by +6.6 pp at 5K steps - both without any rubric engineering. Code: https://github.com/alphadl/AdaRubrics.
Authors: Elizabeth Pavlova, Mariia Koroliuk, Karthik Viswanathan, Cameron Tice, Edward James Young, Puria Radmard
Abstract: We propose a new architectural change, and post-training pipeline, for making LLMs more verbose reasoners by teaching a model to truncate forward passes early. We augment an existing transformer architecture with an early-exit mechanism at intermediate layers and train the model to exit at shallower layers when the next token can be predicted without deep computation. After a calibration stage, we incentivise the model to exit as early as possible while maintaining task performance using reinforcement learning. We provide preliminary results to this effect for small reasoning models, showing that they learn to adaptively reduce computations across tokens. We predict that, applied at the right scale, our approach can minimise the amount of excess computation that reasoning models have at their disposal to perform non-myopic planning using their internal activations, reserving this only for difficult-to-predict tokens.
Authors: Junkeun Yi, Damon Mosk-Aoyama, Baihe Huang, Ritu Gala, Charles Wang, Sugam Dipak Devare, Khushi Bhardwaj, Abhibha Gupta, Oleksii Kuchaiev, Jiantao Jiao, Jian Zhang, Venkat Srinivasan
Abstract: Post-training for long-horizon agentic tasks has a tension between compute efficiency and generalization. While supervised fine-tuning (SFT) is compute efficient, it often suffers from out-of-domain (OOD) degradation. Conversely, end-to-end reinforcement learning (E2E RL) preserves OOD capabilities, but incurs high compute costs due to many turns of on-policy rollout. We introduce PivotRL, a novel framework that operates on existing SFT trajectories to combine the compute efficiency of SFT with the OOD accuracy of E2E RL. PivotRL relies on two key mechanisms: first, it executes local, on-policy rollouts and filters for pivots: informative intermediate turns where sampled actions exhibit high variance in outcomes; second, it utilizes rewards for functional-equivalent actions rather than demanding strict string matching with the SFT data demonstration. We theoretically show that these mechanisms incentivize strong learning signals with high natural gradient norm, while maximally preserving policy probability ordering on actions unrelated to training tasks. In comparison to standard SFT on identical data, we demonstrate that PivotRL achieves +4.17% higher in-domain accuracy on average across four agentic domains, and +10.04% higher OOD accuracy in non-agentic tasks. Notably, on agentic coding tasks, PivotRL achieves competitive accuracy with E2E RL with 4x fewer rollout turns. PivotRL is adopted by NVIDIA's Nemotron-3-Super-120B-A12B, acting as the workhorse in production-scale agentic post-training.
Authors: Johnathan Sun, Andrew Zhang
Abstract: Large language models (LLMs) are increasingly deployed as autonomous decision-makers in strategic settings, yet we have limited tools for understanding their high-level behavioral traits. We use activation steering methods in game-theoretic settings, constructing persona vectors for altruism, forgiveness, and expectations of others by contrastive activation addition. Evaluating on canonical games, we find that activation steering systematically shifts both quantitative strategic choices and natural-language justifications. However, we also observe that rhetoric and strategy can diverge under steering. In addition, vectors for self-behavior and expectations of others are partially distinct. Our results suggest that persona vectors offer a promising mechanistic handle on high-level traits in strategic environments.
Authors: Anthony T. Nixon
Abstract: Any capacity-limited observer induces a canonical quotient on its environment: two situations that no bounded agent can distinguish are, for that agent, the same. We formalise this for finite POMDPs. A fixed probe family of finite-state controllers induces a closed-loop Wasserstein pseudometric on observation histories and a probe-exact quotient merging histories that no controller in the family can distinguish. The quotient is canonical, minimal, and unique-a bounded-interaction analogue of the Myhill-Nerode theorem. For clock-aware probes, it is exactly decision-sufficient for objectives that depend only on the agent's observations and actions; for latent-state rewards, we use an observation-Lipschitz approximation bound. The main theorem object is the clock-aware quotient; scalable deterministic-stationary experiments study a tractable coarsening with gap measured on small exact cases and explored empirically at larger scale. We validate theorem-level claims on Tiger and GridWorld. We also report operational case studies on Tiger, GridWorld, and RockSample as exploratory diagnostics of approximation behavior and runtime, not as theorem-facing evidence when no exact cross-family certificate is available; heavier stress tests are archived in the appendix and artifact package.
Authors: Gregory M. Ruddell
Abstract: As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime. We present empirical evidence that this assumption fails for two of three instruction-following models evaluable for conflict detection. We introduce governability -- the degree to which a model's errors are detectable before output commitment and correctable once detected -- and demonstrate it varies dramatically across models. In six models across twelve reasoning domains, two of three instruction-following models exhibited silent commitment failure: confident, fluent, incorrect output with zero warning signal. The remaining model produced a detectable conflict signal 57 tokens before commitment under greedy decoding. We show benchmark accuracy does not predict governability, correction capacity varies independently of detection, and identical governance scaffolds produce opposite effects across models. A 2x2 experiment shows a 52x difference in spike ratio between architectures but only +/-0.32x variation from fine-tuning, suggesting governability is fixed at pretraining. We propose a Detection and Correction Matrix classifying model-task combinations into four regimes: Governable, Monitor Only, Steer Blind, and Ungovernable.
Authors: Robert Viseur, Nicolas Jullien
Abstract: The rise of generative artificial intelligence (GAI) has led to alarming predictions about its environmental impact. However, these predictions often overlook the fact that the diffusion of innovation is accompanied by the evolution of products and the optimization of their performance, primarily for economic reasons. This can also reduce their environmental impact. By analyzing the GAI ecosystem using the classic A-U innovation diffusion model, we can forecast this industry's structure and how its environmental impact will evolve. While GAI will never be green, its impact may not be as problematic as is sometimes claimed. However, this depends on which business model becomes dominant.
Authors: Shuai Wang, Dhasarathy Parthasarathy, Robert Feldt, Yinan Yu
Abstract: Large language models (LLMs) have shown impressive capabilities in code generation. However, because most LLMs are trained on public domain corpora, directly applying them to real-world software development often yields low success rates, as these scenarios frequently require domain-specific knowledge. In particular, domain-specific tasks usually demand highly specialized solutions, which are often underrepresented or entirely absent in the training data of generic LLMs. To address this challenge, we propose DomAgent, an autonomous coding agent that bridges this gap by enabling LLMs to generate domain-adapted code through structured reasoning and targeted retrieval. A core component of DomAgent is DomRetriever, a novel retrieval module that emulates how humans learn domain-specific knowledge, by combining conceptual understanding with experiential examples. It dynamically integrates top-down knowledge-graph reasoning with bottom-up case-based reasoning, enabling iterative retrieval and synthesis of structured knowledge and representative cases to ensure contextual relevance and broad task coverage. DomRetriever can operate as part of DomAgent or independently with any LLM for flexible domain adaptation. We evaluate DomAgent on an open benchmark dataset in the data science domain (DS-1000) and further apply it to real-world truck software development tasks. Experimental results show that DomAgent significantly enhances domain-specific code generation, enabling small open-source models to close much of the performance gap with large proprietary LLMs in complex, real-world applications. The code is available at: https://github.com/Wangshuaiia/DomAgent.
Authors: Taejin Park
Abstract: When organisations adopt commercial AI systems for decision support, they inherit value judgements embedded by vendors that are neither transparent nor renegotiable. The governance puzzle is not whether AI can support decisions but which recommendations the system can actually produce given how its vendor has configured it. I formalise this as a behavioural feasible set, the range of recommendations reachable under vendor-imposed alignment constraints, and characterise diagnostic thresholds for when organisational requirements exceed the system's flexibility. In scenario-based experiments using binary decision scenarios and multi-stakeholder ranking tasks, I show that alignment materially compresses this set. Comparing pre- and post-alignment variants of an open-weight model isolates the mechanism: alignment makes the system substantially less able to shift its recommendation even under legitimate contextual pressure. Leading commercial models exhibit comparable or greater rigidity. In multi-stakeholder tasks, alignment shifts implied stakeholder priorities rather than neutralising them, meaning organisations adopt embedded value orientations set upstream by the vendor. Organisations thus face a governance problem that better prompting cannot resolve: selecting a vendor partially determines which trade-offs remain negotiable and which stakeholder priorities are structurally embedded.
Authors: Cosimo Spera
Abstract: We introduce a new paradigm for task-oriented dialogue systems: safety certification as a computational primitive for answer reuse. Current systems treat each turn independently, recomputing answers via retrieval or generation even when they are already derivable from prior state. We show that in capability-based systems, the safety certification step computes a fixed-point closure cl(At) that already contains every answer reachable from the current configuration. We operationalize this insight with a Certified Answer Store (CAS) augmented by Pre-Answer Blocks (PAB): at each certified turn, the system materializes all derivable follow-up answers together with minimal provenance witnesses. Subsequent queries are answered in sub-millisecond time via formal containment checks, eliminating redundant retrieval and generation.
Authors: Wihan van der Heever, Keane Ong, Ranjan Satapathy, Erik Cambria
Abstract: This paper proposes a refutation-validated framework for aspect-based sentiment analysis in financial markets, addressing the limitations of correlational studies that cannot distinguish genuine associations from spurious ones. Using X data for the energy sector, we test whether aspect-level sentiment signals show robust, refutation-validated relationships with equity returns. Our pipeline combines net-ratio scoring with z-normalization, OLS with Newey West HAC errors, and refutation tests including placebo, random common cause, subset stability, and bootstrap. Across six energy tickers, only a few associations survive all checks, while renewables show aspect and horizon specific responses. While not establishing causality, the framework provides statistically robust, directionally interpretable signals, with limited sample size (six stocks, one quarter) constraining generalizability and framing this work as a methodological proof of concept.
Authors: Hehai Lin, Yu Yan, Zixuan Wang, Bo Xu, Sudong Wang, Weiquan Huang, Ruochen Zhao, Minzhi Li, Chengwei Qin
Abstract: Automatic Multi-Agent Systems (MAS) generation has emerged as a promising paradigm for solving complex reasoning tasks. However, existing frameworks are fundamentally bottlenecked when applied to knowledge-intensive domains (e.g., healthcare and law). They either rely on a static library of general nodes like Chain-of-Thought, which lack specialized expertise, or attempt to generate nodes on the fly. In the latter case, the orchestrator is not only bound by its internal knowledge limits but must also simultaneously generate domain-specific logic and optimize high-level topology, leading to a severe architectural coupling that degrades overall system efficacy. To bridge this gap, we propose Unified-MAS that decouples granular node implementation from topological orchestration via offline node synthesis. Unified-MAS operates in two stages: (1) Search-Based Node Generation retrieves external open-world knowledge to synthesize specialized node blueprints, overcoming the internal knowledge limits of LLMs; and (2) Reward-Based Node Optimization utilizes a perplexity-guided reward to iteratively enhance the internal logic of bottleneck nodes. Extensive experiments across four specialized domains demonstrate that integrating Unified-MAS into four Automatic-MAS baselines yields a better performance-cost trade-off, achieving up to a 14.2% gain while significantly reducing costs. Further analysis reveals its robustness across different designer LLMs and its effectiveness on conventional tasks such as mathematical reasoning.
Authors: Xinyu Zhang
Abstract: Recursive self-improvement--where a model iteratively trains on its own outputs--promises sustained capability growth but faces a fundamental obstacle: recursive drift. As models train on self-generated data across multiple iterations, errors in intermediate reasoning compound, leading to mode collapse and performance degradation. We propose Neuro-Symbolic Recursive Self-Alignment (NSRSA), which stabilizes iterative self-training by embedding a symbolic verification subsystem that gates training data quality at the reasoning step level. Unlike outcome-only filtering (which admits "lucky guesses" with flawed reasoning), NSRSA verifies each arithmetic operation via sympy, checks logical flow consistency across reasoning steps, and enforces domain constraints. We evaluate NSRSA on GSM8K using Qwen3-4B-Thinking across 5 self-training iterations under five conditions: no verification, outcome verification, majority voting, full NSRSA symbolic verification, and NSRSA with DPO. Our filtering analysis shows that NSRSA rejects approximately 34% of correct-answer solutions that pass outcome verification, eliminating "lucky guesses" with flawed reasoning from the training set. We further demonstrate that constructing DPO preference pairs from NSRSA verification teaches the model to distinguish sound from flawed reasoning (reward accuracy 46% to 63%). NSRSA provides an extensible framework that demonstrates how external symbolic verification can make recursive self-improvement measurable and reliable within domains where automated verification is available.
Authors: Zhongyi Li, Wan Tian, Yikun Ban, Jinju Chen, Huiming Zhang, Yang Liu, Fuzhen Zhuang
Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles and aggregating diverse hypotheses. Yet, reinforcement learning (RL) for such systems is often undermined by credit assignment: a shared global reward obscures individual contributions, inflating update variance and encouraging free-riding. We introduce Counterfactual Credit Policy Optimization (CCPO), a framework that assigns agent-specific learning signals by estimating each agent's marginal contribution through counterfactual trajectories. CCPO builds dynamic counterfactual baselines that simulate outcomes with an agent's contribution removed, yielding role-sensitive advantages for policy optimization. To further improve stability under heterogeneous tasks and data distributions, we propose a global-history-aware normalization scheme that calibrates advantages using global rollout statistics. We evaluate CCPO on two collaboration topologies: a sequential Think--Reason dyad and multi-agent voting. Across mathematical and logical reasoning benchmarks, CCPO mitigates free-riding and outperforms strong multi-agent RL baselines, yielding finer-grained and more effective credit assignment for collaborative LLM training. Our code is available at https://github.com/bhai114/ccpo.
Authors: Zhongyi Li, Wan Tian, Jingyu Chen, Kangyao Huang, Huiming Zhang, Hui Yang, Tao Ren, Jinyang Jiang, Yijie Peng, Yikun Ban, Fuzhen Zhuang
Abstract: Multi-agent collaboration has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models, yet it suffers from interaction-level ambiguity that blurs generation, critique, and revision, making credit assignment across agents difficult. Moreover, policy optimization in this setting is vulnerable to heavy-tailed and noisy rewards, which can bias advantage estimation and trigger unstable or even divergent training. To address both issues, we propose a robust multi-agent reinforcement learning framework for collaborative reasoning, consisting of two components: Dual-Agent Answer-Critique-Rewrite (DACR) and an Adaptive Robust Estimator (ARE). DACR decomposes reasoning into a structured three-stage pipeline: answer, critique, and rewrite, while enabling explicit attribution of each agent's marginal contribution to its partner's performance. ARE provides robust estimation of batch experience means during multi-agent policy optimization. Across mathematical reasoning and embodied intelligence benchmarks, even under noisy rewards, our method consistently outperforms the baseline in both homogeneous and heterogeneous settings. These results indicate stronger robustness to reward noise and more stable training dynamics, effectively preventing optimization failures caused by noisy reward signals.
Authors: Qihui Zhu, Shouwei Ruan, Xiao Yang, Hao Jiang, Yao Huang, Shiji Zhao, Hanwei Fan, Hang Su, Xingxing Wei
Abstract: Despite the widespread adoption of MLLMs in embodied agents, their capabilities remain largely confined to reactive planning from immediate observations, consistently failing in spatial reasoning across extensive spatiotemporal scales. Cognitive science reveals that Biological Intelligence (BI) thrives on "mental navigation": the strategic construction of spatial representations from experience and the subsequent mental simulation of paths prior to action. To bridge the gap between AI and BI, we introduce Video2Mental, a pioneering benchmark for evaluating the mental navigation capabilities of MLLMs. The task requires constructing hierarchical cognitive maps from long egocentric videos and generating landmark-based path plans step by step, with planning accuracy verified through simulator-based physical interaction. Our benchmarking results reveal that mental navigation capability does not naturally emerge from standard pre-training. Frontier MLLMs struggle profoundly with zero-shot structured spatial representation, and their planning accuracy decays precipitously over extended horizons. To overcome this, we propose \textbf{NavMind}, a reasoning model that internalizes mental navigation using explicit, fine-grained cognitive maps as learnable intermediate representations. Through a difficulty-stratified progressive supervised fine-tuning paradigm, NavMind effectively bridges the gap between raw perception and structured planning. Experiments demonstrate that NavMind achieves superior mental navigation capabilities, significantly outperforming frontier commercial and spatial MLLMs.
Authors: Sheng Liu, Long Chen, Zeyun Zhao, Qinglin Gou, Qingyue Wei, Arjun Masurkar, Kevin M. Spiegler, Philip Kuball, Stefania C. Bray, Megan Bernath, Deanna R. Willis, Jiang Bian, Lei Xing, Eric Topol, Kyunghyun Cho, Yu Huang, Ruogu Fang, Narges Razavian, James Zou
Abstract: Modern clinical practice increasingly depends on reasoning over heterogeneous, evolving, and incomplete patient data. Although recent advances in multimodal foundation models have improved performance on various clinical tasks, most existing models remain static, opaque, and poorly aligned with real-world clinical workflows. We present Cerebra, an interactive multi-agent AI team that coordinates specialized agents for EHR, clinical notes, and medical imaging analysis. These outputs are synthesized into a clinician-facing dashboard that combines visual analytics with a conversational interface, enabling clinicians to interrogate predictions and contextualize risk at the point of care. Cerebra supports privacy-preserving deployment by operating on structured representations and remains robust when modalities are incomplete. We evaluated Cerebra using a massive multi-institutional dataset spanning 3 million patients from four independent healthcare systems. Cerebra consistently outperformed both state-of-the-art single-modality models and large multimodal language model baselines. In dementia risk prediction, it achieved AUROCs up to 0.80, compared with 0.74 for the strongest single-modality model and 0.68 for language model baselines. For dementia diagnosis, it achieved an AUROC of 0.86, and for survival prediction, a C-index of 0.81. In a reader study with experienced physicians, Cerebra significantly improved expert performance, increasing accuracy by 17.5 percentage points in prospective dementia risk estimation. These results demonstrate Cerebra's potential for interpretable, robust decision support in clinical care.
Authors: Alexandra Bazarova, Andrei Volodichev, Daria Kotova, Alexey Zaytsev
Abstract: While retrieval-augmented generation (RAG) significantly improves the factual reliability of LLMs, it does not eliminate hallucinations, so robust uncertainty quantification (UQ) remains essential. In this paper, we reveal that standard entropy-based UQ methods often fail in RAG settings due to a mechanistic paradox. An internal "tug-of-war" inherent to context utilization appears: while induction heads promote grounded responses by copying the correct answer, they collaterally trigger the previously established "entropy neurons". This interaction inflates predictive entropy, causing the model to signal false uncertainty on accurate outputs. To address this, we propose INTRYGUE (Induction-Aware Entropy Gating for Uncertainty Estimation), a mechanistically grounded method that gates predictive entropy based on the activation patterns of induction heads. Evaluated across four RAG benchmarks and six open-source LLMs (4B to 13B parameters), INTRYGUE consistently matches or outperforms a wide range of UQ baselines. Our findings demonstrate that hallucination detection in RAG benefits from combining predictive uncertainty with interpretable, internal signals of context utilization.
Authors: Ankush Agarwal, Harsh Vishwakarma, Suraj Nagaje, Chaitanya Devaguptapu
Abstract: Deploying AI agents in enterprise environments requires balancing capability with data sovereignty and cost constraints. While small language models offer privacy-preserving alternatives to frontier models, their specialization is hindered by fragmented development pipelines that separate tool integration, data generation, and training. We introduce EnterpriseLab, a full-stack platform that unifies these stages into a closed-loop framework. EnterpriseLab provides (1) a modular environment exposing enterprise applications via Model Context Protocol, enabling seamless integration of proprietary and open-source tools; (2) automated trajectory synthesis that programmatically generates training data from environment schemas; and (3) integrated training pipelines with continuous evaluation. We validate the platform through EnterpriseArena, an instantiation with 15 applications and 140+ tools across IT, HR, sales, and engineering domains. Our results demonstrate that 8B-parameter models trained within EnterpriseLab match GPT-4o's performance on complex enterprise workflows while reducing inference costs by 8-10x, and remain robust across diverse enterprise benchmarks, including EnterpriseBench (+10%) and CRMArena (+10%). EnterpriseLab provides enterprises a practical path to deploying capable, privacy-preserving agents without compromising operational capability.
Authors: Yiliang Song, Hongjun An, Jiangan Chen, Xuanchen Yan, Huan Song, Jiawei Shao, Xuelong Li
Abstract: Public benchmarks increasingly govern how large language models (LLMs) are ranked, selected, and deployed. We frame this benchmark-centered regime as Silicon Bureaucracy and AI Test-Oriented Education, and argue that it rests on a fragile assumption: that benchmark scores directly reflect genuine generalization. In practice, however, such scores may conflate exam-oriented competence with principled capability, especially when contamination and semantic leakage are difficult to exclude from modern training pipelines. We therefore propose an audit framework for analyzing contamination sensitivity and score confidence in LLM benchmarks. Using a router-worker setup, we compare a clean-control condition with noisy conditions in which benchmark problems are systematically deleted, rewritten, and perturbed before being passed downstream. For a genuinely clean benchmark, noisy conditions should not consistently outperform the clean-control baseline. Yet across multiple models, we find widespread but heterogeneous above-baseline gains under noisy conditions, indicating that benchmark-related cues may be reassembled and can reactivate contamination-related memory. These results suggest that similar benchmark scores may carry substantially different levels of confidence. Rather than rejecting benchmarks altogether, we argue that benchmark-based evaluation should be supplemented with explicit audits of contamination sensitivity and score confidence.
Authors: Mohammad Asadi, Jack W. O'Sullivan, Fang Cao, Tahoura Nedaee, Kamyar Fardi, Fei-Fei Li, Ehsan Adeli, Euan Ashley
Abstract: Multimodal AI systems have achieved remarkable performance across a broad range of real-world tasks, yet the mechanisms underlying visual-language reasoning remain surprisingly poorly understood. We report three findings that challenge prevailing assumptions about how these systems process and integrate visual information. First, Frontier models readily generate detailed image descriptions and elaborate reasoning traces, including pathology-biased clinical findings, for images never provided; we term this phenomenon mirage reasoning. Second, without any image input, models also attain strikingly high scores across general and medical multimodal benchmarks, bringing into question their utility and design. In the most extreme case, our model achieved the top rank on a standard chest X-ray question-answering benchmark without access to any images. Third, when models were explicitly instructed to guess answers without image access, rather than being implicitly prompted to assume images were present, performance declined markedly. Explicit guessing appears to engage a more conservative response regime, in contrast to the mirage regime in which models behave as though images have been provided. These findings expose fundamental vulnerabilities in how visual-language models reason and are evaluated, pointing to an urgent need for private benchmarks that eliminate textual cues enabling non-visual inference, particularly in medical contexts where miscalibrated AI carries the greatest consequence. We introduce B-Clean as a principled solution for fair, vision-grounded evaluation of multimodal AI systems.
Authors: Yicai Xing
Abstract: As large language models (LLMs) and vision-language-action models (VLAs) become widely deployed, the tokens consumed by AI inference are evolving into a new type of commodity. This paper systematically analyzes the commodity attributes of tokens, arguing for their transition from intelligent service outputs to compute infrastructure raw materials, and draws comparisons with established commodities such as electricity, carbon emission allowances, and bandwidth. Building on the historical experience of electricity futures markets and the theory of commodity financialization, we propose a complete design for standardized token futures contracts, including the definition of a Standard Inference Token (SIT), contract specifications, settlement mechanisms, margin systems, and market-maker regimes. By constructing a mean-reverting jump-diffusion stochastic process model and conducting Monte Carlo simulations, we evaluate the hedging efficiency of the proposed futures contracts for application-layer enterprises. Simulation results show that, under an application-layer demand explosion scenario, token futures can reduce enterprise compute cost volatility by 62%-78%. We also explore the feasibility of GPU compute futures and discuss the regulatory framework for token futures markets, providing a theoretical foundation and practical roadmap for the financialization of compute resources.
Authors: Neelmani Vispute
Abstract: As AI agents transition from human-supervised copilots to autonomous platform infrastructure, the ability to analyze their reasoning behavior across populations of investigations becomes a pressing infrastructure requirement. Existing operational tooling addresses adjacent needs effectively: state checkpoint systems enable fault tolerance; observability platforms provide execution traces for debugging; telemetry standards ensure interoperability. What current systems do not natively provide as a first-class, schema-level primitive is structured reasoning provenance -- normalized, queryable records of why the agent chose each action, what it concluded from each observation, how each conclusion shaped its strategy, and which evidence supports its final verdict. This paper introduces the Agent Execution Record (AER), a structured reasoning provenance primitive that captures intent, observation, and inference as first-class queryable fields on every step, alongside versioned plans with revision rationale, evidence chains, structured verdicts with confidence scores, and delegation authority chains. We formalize the distinction between computational state persistence and reasoning provenance, argue that the latter cannot in general be faithfully reconstructed from the former, and show how AERs enable population-level behavioral analytics: reasoning pattern mining, confidence calibration, cross-agent comparison, and counterfactual regression testing via mock replay. We present a domain-agnostic model with extensible domain profiles, a reference implementation and SDK, and outline an evaluation methodology informed by preliminary deployment on a production platformized root cause analysis agent.
Authors: Mohammad Asadi, Tahoura Nedaee, Jack W. O'Sullivan, Euan Ashley, Ehsan Adeli
Abstract: Multimodal large language models (MLLMs) have shown strong potential for medical Visual Question Answering (VQA), yet they remain prone to hallucinations, defined as generating responses that contradict the input image, posing serious risks in clinical settings. Current hallucination detection methods, such as Semantic Entropy (SE) and Vision-Amplified Semantic Entropy (VASE), require 10 to 20 stochastic generations per sample together with an external natural language inference model for semantic clustering, making them computationally expensive and difficult to deploy in practice. We observe that hallucinated responses exhibit a distinctive signature directly in the model's own log-probabilities: inconsistent token-level confidence and weak sensitivity to visual evidence. Based on this observation, we propose Confidence-Evidence Bayesian Gain (CEBaG), a deterministic hallucination detection method that requires no stochastic sampling, no external models, and no task-specific hyperparameters. CEBaG combines two complementary signals: token-level predictive variance, which captures inconsistent confidence across response tokens, and evidence magnitude, which measures how much the image shifts per-token predictions relative to text-only inference. Evaluated across four medical MLLMs and three VQA benchmarks (16 experimental settings), CEBaG achieves the highest AUC in 13 of 16 settings and improves over VASE by 8 AUC points on average, while being fully deterministic and self-contained. The code will be made available upon acceptance.
Authors: Hunmin Do, Taejun Yoon, Kiyong Jung
Abstract: While Multi-Agent Debate (MAD) research has advanced, its efficacy in coordinating complex stakeholder interests such as travel planning remains largely unexplored. To bridge this gap, we propose MIND (Multi-agent Inference for Negotiation Dialogue), a framework designed to simulate realistic consensus-building among travelers with heterogeneous preferences. Grounded in the Theory of Mind (ToM), MIND introduces a Strategic Appraisal phase that infers opponent willingness (w) from linguistic nuances with 90.2% accuracy. Experimental results demonstrate that MIND outperforms traditional MAD frameworks, achieving a 20.5% improvement in High-w Hit and a 30.7% increase in Debate Hit-Rate, effectively prioritizing high-stakes constraints. Furthermore, qualitative evaluations via LLM-as-a-Judge confirm that MIND surpasses baselines in Rationality (68.8%) and Fluency (72.4%), securing an overall win rate of 68.3%. These findings validate that MIND effectively models human negotiation dynamics to derive persuasive consensus.
Authors: Jinhui Ren, Huaiming Li, Yabin Liu, Tao Li, Zhaokun Liu, Yujia Liang, Zengle Ge, Chufan Wu, Xiaomin Yuan, Danyu Liu, Annan Li, Jianmin Wu
Abstract: High-fidelity vehicle drag evaluation is constrained less by solver runtime than by workflow friction: geometry cleanup, meshing retries, queue contention, and reproducibility failures across teams. We present a contract-centric blueprint for self-evolving coding agents that discover executable surrogate pipelines for predicting drag coefficient $C_d$ under industrial constraints. The method formulates surrogate discovery as constrained optimization over programs, not static model instances, and combines Famou-Agent-style evaluator feedback with population-based island evolution, structured mutations (data, model, loss, and split policies), and multi-objective selection balancing ranking quality, stability, and cost. A hard evaluation contract enforces leakage prevention, deterministic replay, multi-seed robustness, and resource budgets before any candidate is admitted. Across eight anonymized evolutionary operators, the best system reaches a Combined Score of 0.9335 with sign-accuracy 0.9180, while trajectory and ablation analyses show that adaptive sampling and island migration are primary drivers of convergence quality. The deployment model is explicitly ``screen-and-escalate'': surrogates provide high-throughput ranking for design exploration, but low-confidence or out-of-distribution cases are automatically escalated to high-fidelity CFD. The resulting contribution is an auditable, reusable workflow for accelerating aerodynamic design iteration while preserving decision-grade reliability, governance traceability, and safety boundaries.
Authors: Xi Wang, Xu Yang, Donghao Sun, Cheng Deng
Abstract: Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting under continuously evolving and imbalanced data distributions. To tackle these issues, we exploit the informativeness and scalability of language knowledge. Specifically, we analyze the LT CIL data distribution to guide large language models (LLMs) in generating a stratified language tree that hierarchically organizes semantic information from coarse to fine grained granularity. Building upon this structure, we introduce stratified adaptive language guidance, which leverages learnable weights to merge multi-scale semantic representations, thereby enabling dynamic supervisory adjustment for tail classes and alleviating the impact of data imbalance. Furthermore, we introduce stratified alignment language guidance, which exploits the structural stability of the language tree to constrain optimization and reinforce semantic visual alignment, thereby alleviating catastrophic forgetting. Extensive experiments on multiple benchmarks demonstrate that our method achieves state of the art performance.
Authors: Shuo Wang, Ziyu Chen, Ming Tang
Abstract: Fine-tuning large language models (LLMs) with backpropagation achieves high performance but incurs substantial memory overhead, limiting scalability on resource-constrained hardware. Zeroth-order (ZO) optimization provides a memory-efficient alternative by relying solely on forward passes, yet it typically suffers from slow or unstable convergence due to high-variance gradient estimates. Sparse ZO updates partially address this issue by perturbing only a subset of parameters, but their effectiveness hinges on selecting informative parameters, which is challenging in ZO optimization because each query yields only scalar feedback. We propose \textbf{Adaptive Curvature-Guided Sparse Zeroth-Order Optimization (CurvZO)}, which tracks curvature signals online from scalar ZO feedback and leverages these signals to construct a parameter-wise sampling distribution for selecting coordinates at each update, reducing the variance of the sparse ZO gradient estimator. Moreover, CurvZO dynamically adapts the perturbation budget to the evolving curvature signal distribution, yielding sparse ZO updates that remain both focused and sufficiently exploratory. Extensive experiments on OPT and Llama across diverse NLP tasks show that CurvZO consistently improves fine-tuning performance and reduces training time over ZO baselines. It improves accuracy by up to 4.4 points and achieves up to a $2\times$ speedup, while preserving memory efficiency.
Authors: Andreas Sauter, Yuyue Zhao, Jacopo Urbani, Wenxiang Hu, Zaiqiao Meng, Lun Zhou, Xiaohui Yan, Yougang Lyu
Abstract: Scientific idea generation is a cornerstone of autonomous knowledge discovery, yet the iterative evolution required to transform initial concepts into high-quality research proposals remains a formidable challenge for Large Language Models (LLMs). Existing Reinforcement Learning (RL) paradigms often rely on rubric-based scalar rewards that provide global quality scores but lack actionable granularity. Conversely, language-based refinement methods are typically confined to inference-time prompting, targeting models that are not explicitly optimized to internalize such critiques. To bridge this gap, we propose \textbf{EvoIdeator}, a framework that facilitates the evolution of scientific ideas by aligning the RL training objective with \textbf{checklist-grounded feedback}. EvoIdeator leverages a structured judge model to generate two synergistic signals: (1) \emph{lexicographic rewards} for multi-dimensional optimization, and (2) \emph{fine-grained language feedback} that offers span-level critiques regarding grounding, feasibility, and methodological rigor. By integrating these signals into the RL loop, we condition the policy to systematically utilize precise feedback during both optimization and inference. Extensive experiments demonstrate that EvoIdeator, built on Qwen3-4B, significantly outperforms much larger frontier models across key scientific metrics. Crucially, the learned policy exhibits strong generalization to diverse external feedback sources without further fine-tuning, offering a scalable and rigorous path toward self-refining autonomous ideation.
Authors: Yiling Wu
Abstract: Different types of reasoning impose different structural demands on representational systems, yet no systematic account of these demands exists across psychology, AI, and philosophy of mind. I propose a framework identifying four structural properties of representational systems: operability, consistency, structural preservation, and compositionality. These properties are demanded to different degrees by different forms of reasoning, from induction through analogy and causal inference to deduction and formal logic. Each property excludes a distinct class of reasoning failure. The analysis reveals a principal structural boundary: reasoning types below it can operate on associative, probabilistic representations, while those above it require all four properties to be fully satisfied. Scaling statistical learning without structural reorganization is insufficient to cross this boundary, because the structural guarantees required by deductive reasoning cannot be approximated through probabilistic means. Converging evidence from AI evaluation, developmental psychology, and cognitive neuroscience supports the framework at different levels of directness. Three testable predictions are derived, including compounding degradation, selective vulnerability to targeted structural disruption, and irreducibility under scaling. The framework is a necessary-condition account, agnostic about representational format, that aims to reorganize existing debates rather than close them.
Authors: Yiling Wu
Abstract: Large language models are the first systems to achieve high cognitive performance without clearly undergoing representation genesis: the transition from a non-representing physical system to one whose states guide behavior in a content-sensitive way. Prior cognitive systems had already made this transition before we could examine it, and philosophy of mind treated genesis as a background condition rather than an explanatory target. LLMs provide a case that does not clearly involve this transition, making the genesis question newly urgent: if genesis did not occur, which cognitive capacities are affected, and why? We currently lack the conceptual resources to answer this. The reason, this paper argues, is structural. Major frameworks in philosophy of mind, including the Language of Thought hypothesis, teleosemantics, predictive processing, enactivism, and genetic phenomenology, share a common feature when applied to the genesis question: at some explanatory step, each deploys concepts whose explanatory purchase depends on the system already being organized as a representer. This pattern, which we call the Representation Presupposition structure, generates systematic explanatory deferral. Attempts to explain the first acquisition of content-manipulable representation within the existing categorical vocabulary import resources from the representational side of the transition itself. We call this the Representation Regress. The paper offers a conceptual diagnosis rather than a new theory, establishing the structure of the problem and deriving two minimum adequacy conditions for any account that avoids this pattern. LLMs make the absence of such a theory consequential rather than merely theoretical.
Authors: Susana Nunes, Tiago Guerreiro, Catia Pesquita
Abstract: AI explanation methods often assume a static user model, producing non-adaptive explanations regardless of expert goals, reasoning strategies, or decision contexts. Knowledge graph-based explanations, despite their capacity for grounded, path-based reasoning, inherit this limitation. In complex domains such as scientific discovery, this assumption fails to capture the diversity of cognitive strategies and epistemic stances among experts, preventing explanations that foster deeper understanding and informed decision-making. However, the scarcity of human experts limits the use of direct human feedback to produce adaptive explanations. We present a reinforcement learning approach for scientific explanation generation that incorporates agentic personas, structured representations of expert reasoning strategies, that guide the explanation agent towards specific epistemic preferences. In an evaluation of knowledge graph-based explanations for drug discovery, we tested two personas that capture distinct epistemic stances derived from expert feedback. Results show that persona-driven explanations match state-of-the-art predictive performance while persona preferences closely align with those of their corresponding experts. Adaptive explanations were consistently preferred over non-adaptive baselines (n = 22), and persona-based training reduces feedback requirements by two orders of magnitude. These findings demonstrate how agentic personas enable scalable adaptive explainability for AI systems in complex and high-stakes domains.
Authors: Aryan Kasat, Smriti Singh, Aman Chadha, Vinija Jain
Abstract: Do large language models reason morally, or do they merely sound like they do? We investigate whether LLM responses to moral dilemmas exhibit genuine developmental progression through Kohlberg's stages of moral development, or whether alignment training instead produces reasoning-like outputs that superficially resemble mature moral judgment without the underlying developmental trajectory. Using an LLM-as-judge scoring pipeline validated across three judge models, we classify more than 600 responses from 13 LLMs spanning a range of architectures, parameter scales, and training regimes across six classical moral dilemmas, and conduct ten complementary analyses to characterize the nature and internal coherence of the resulting patterns. Our results reveal a striking inversion: responses overwhelmingly correspond to post-conventional reasoning (Stages 5-6) regardless of model size, architecture, or prompting strategy, the effective inverse of human developmental norms, where Stage 4 dominates. Most strikingly, a subset of models exhibit moral decoupling: systematic inconsistency between stated moral justification and action choice, a form of logical incoherence that persists across scale and prompting strategy and represents a direct reasoning consistency failure independent of rhetorical sophistication. Model scale carries a statistically significant but practically small effect; training type has no significant independent main effect; and models exhibit near-robotic cross-dilemma consistency producing logically indistinguishable responses across semantically distinct moral problems. We posit that these patterns constitute evidence for moral ventriloquism: the acquisition, through alignment training, of the rhetorical conventions of mature moral reasoning without the underlying developmental trajectory those conventions are meant to represent.
Authors: Naoshi Uchihira
Abstract: The emergence of generative AI is bringing about a significant transformation in knowledge management. Generative AI has the potential to address the limitations of conventional knowledge management systems, and it is increasingly being deployed in real-world settings with promising results. Related research is also expanding rapidly. However, much of this work focuses on research and practice related to the management of explicit knowledge. While fragmentary efforts have been made regarding the management of tacit knowledge using generative AI, the modeling and systematization that handle both tacit and explicit knowledge in an integrated manner remain insufficient. In this paper, we propose the "GenAI SECI" model as an updated version of the knowledge creation process (SECI) model, redesigned to leverage the capabilities of generative AI. A defining feature of the "GenAI SECI" model is the introduction of "Digital Fragmented Knowledge", a new concept that integrates explicit and tacit knowledge within cyberspace. Furthermore, a concrete system architecture for the proposed model is presented, along with a comparison with prior research models that share a similar problem awareness and objectives.
Authors: Shuying Chen, Sen Cui, Zhong Cao
Abstract: In this work, we propose Oph-Guid-RAG, a multimodal visual RAG system for ophthalmology clinical question answering and decision support. We treat each guideline page as an independent evidence unit and directly retrieve page images, preserving tables, flowcharts, and layout information. We further design a controllable retrieval framework with routing and filtering, which selectively introduces external evidence and reduces noise. The system integrates query decomposition, query rewriting, retrieval, reranking, and multimodal reasoning, and provides traceable outputs with guideline page references. We evaluate our method on HealthBench using a doctor-based scoring protocol. On the hard subset, our approach improves the overall score from 0.2969 to 0.3861 (+0.0892, +30.0%) compared to GPT-5.2, and achieves higher accuracy, improving from 0.5956 to 0.6576 (+0.0620, +10.4%). Compared to GPT-5.4, our method achieves a larger accuracy gain of +0.1289 (+24.4%). These results show that our method is more effective on challenging cases that require precise, evidence-based reasoning. Ablation studies further show that reranking, routing, and retrieval design are critical for stable performance, especially under difficult settings. Overall, we show how combining visionbased retrieval with controllable reasoning can improve evidence grounding and robustness in clinical AI applications,while pointing out that further work is needed to be more complete.
Authors: Caio Azevedo, Stefano Sabatini, Sascha Hornauer, Fabien Moutarde
Abstract: To safely operate, an autonomous vehicle must know the future behavior of a potentially high number of interacting agents around it, a task often posed as multi-agent trajectory prediction. Many previous attempts to model social interactions and solve the joint prediction task either add extensive computational requirements or rely on heuristics to label multi-agent behavior types. Braid theory, in contrast, provides a powerful exact descriptor of multi-agent behavior by projecting future trajectories into braids that express how trajectories cross with each other over time; a braid then corresponds to a specific mode of coordination between the multiple agents in the future. In past work, braids have been used lightly to reason about interacting agents and restrict the attention window of predicted agents. We show that leveraging more fully the expressivity of the braid representation and using it to condition the trajectories themselves leads to even further gains in joint prediction performance, with negligible added complexity either in training or at inference time. We do so by proposing a novel auxiliary task, braid prediction, done in parallel with the trajectory prediction task. By classifying edges between agents into their correct crossing types in the braid representation, the braid prediction task is able to imbue the model with improved social awareness, which is reflected in joint predictions that more closely adhere to the actual multi-agent behavior. This simple auxiliary task allowed us to obtain significant improvements in joint metrics on three separate datasets. We show how the braid prediction task infuses the model with future intention awareness, leading to more accurate joint predictions. Code is available at github.com/caiocj1/traj-pred-braid-theory.
Authors: Xi Yang, Aurelie Lozano, Naoki Abe, Bhavya, Saurabh Jha, Noah Zheutlin, Rohan R. Arora, Yu Deng, Daby M. Sow
Abstract: Despite rapid progress in AI agents for enterprise automation and decision-making, their real-world deployment and further performance gains remain constrained by limited data quality and quantity, complex real-world reasoning demands, difficulties with self-play, and the lack of reliable feedback signals. To address these challenges, we propose a lightweight, model-agnostic framework for improving LLM-based enterprise agents via offline reinforcement learning (RL). The proposed Context Engineering via DT-MDP (DT-MDP-CE) framework comprises three key components: (1) A Digital-Twin Markov Decision Process (DT-MDP), which abstracts the agent's reasoning behavior as a finite MDP; (2) A robust contrastive inverse RL, which, armed with the DT-MDP, to efficiently estimate a well-founded reward function and induces policies from mixed-quality offline trajectories; and (3) RL-guided context engineering, which uses the policy obtained from the integrated process of (1) and (2), to improve the agent's decision-making behavior. As a case study, we apply the framework to a representative task in the enterprise-oriented domain of IT automation. Extensive experimental results demonstrate consistent and significant improvements over baseline agents across a wide range of evaluation settings, suggesting that the framework can generalize to other agents sharing similar characteristics in enterprise environments.
Authors: Xiao Han, Yuzheng Fan, Sendong Zhao, Haochun Wang, Bing Qin
Abstract: Clinical decision-making agents can benefit from reusing prior decision experience. However, many memory-augmented methods store experiences as independent records without explicit relational structure, which may introduce noisy retrieval, unreliable reuse, and in some cases even hurt performance compared to direct LLM inference. We propose GSEM (Graph-based Self-Evolving Memory), a clinical memory framework that organizes clinical experiences into a dual-layer memory graph, capturing both the decision structure within each experience and the relational dependencies across experiences, and supporting applicability-aware retrieval and online feedback-driven calibration of node quality and edge weights. Across MedR-Bench and MedAgentsBench with two LLM backbones, GSEM achieves the highest average accuracy among all baselines, reaching 70.90\% and 69.24\% with DeepSeek-V3.2 and Qwen3.5-35B, respectively. Code is available at https://github.com/xhan1022/gsem.
Authors: Syed Usama Imtiaz, Mitra Nasr Azadani, Nasrin Alamdari
Abstract: Foundation models are now increasingly being developed for Earth observation (EO), yet they often rely on stochastic masking that do not explicitly enforce physics constraints; a critical trustworthiness limitation, in particular for predictive models that guide public health decisions. In this work, we propose SpecTM (Spectral Targeted Masking), a physics-informed masking design that encourages the reconstruction of targeted bands from cross-spectral context during pretraining. To achieve this, we developed an adaptable multi-task (band reconstruction, bio-optical index inference, and 8-day-ahead temporal prediction) self-supervised learning (SSL) framework that encodes spectrally intrinsic representations via joint optimization, and evaluated it on a downstream microcystin concentration regression model using NASA PACE hyperspectral imagery over Lake Erie. SpecTM achieves R^2 = 0.695 (current week) and R^2 = 0.620 (8-day-ahead) predictions surpassing all baseline models by (+34% (0.51 Ridge) and +99% (SVR 0.31)) respectively. Our ablation experiments show targeted masking improves predictions by +0.037 R^2 over random masking. Furthermore, it outperforms strong baselines with 2.2x superior label efficiency under extreme scarcity. SpecTM enables physics-informed representation learning across EO domains and improves the interpretability of foundation models.
Authors: Jack W O'Sullivan, Mohammad Asadi, Lennart Elbe, Akshay Chaudhari, Tahoura Nedaee, Francois Haddad, Michael Salerno, Li Fe-Fei, Ehsan Adeli, Rima Arnaout, Euan A Ashley
Abstract: Cardiovascular disease remains the leading cause of global mortality, with progress hindered by human interpretation of complex cardiac tests. Current AI vision-language models are limited to single-modality inputs and are non-interactive. We present MARCUS (Multimodal Autonomous Reasoning and Chat for Ultrasound and Signals), an agentic vision-language system for end-to-end interpretation of electrocardiograms (ECGs), echocardiograms, and cardiac magnetic resonance imaging (CMR) independently and as multimodal input. MARCUS employs a hierarchical agentic architecture comprising modality-specific vision-language expert models, each integrating domain-trained visual encoders with multi-stage language model optimization, coordinated by a multimodal orchestrator. Trained on 13.5 million images (0.25M ECGs, 1.3M echocardiogram images, 12M CMR images) and our novel expert-curated dataset spanning 1.6 million questions, MARCUS achieves state-of-the-art performance surpassing frontier models (GPT-5 Thinking, Gemini 2.5 Pro Deep Think). Across internal (Stanford) and external (UCSF) test cohorts, MARCUS achieves accuracies of 87-91% for ECG, 67-86% for echocardiography, and 85-88% for CMR, outperforming frontier models by 34-45% (P<0.001). On multimodal cases, MARCUS achieved 70% accuracy, nearly triple that of frontier models (22-28%), with 1.7-3.0x higher free-text quality scores. Our agentic architecture also confers resistance to mirage reasoning, whereby vision-language models derive reasoning from unintended textual signals or hallucinated visual content. MARCUS demonstrates that domain-specific visual encoders with an agentic orchestrator enable multimodal cardiac interpretation. We release our models, code, and benchmark open-source.
Authors: Zhaoze Wang, Genela Morris, Dori Derdikman, Pratik Chaudhari, Vijay Balasubramanian
Abstract: Grid cells in the medial entorhinal cortex (MEC) and place cells in the hippocampus (HC) both form spatial representations. Grid cells fire in triangular grid patterns, while place cells fire at specific locations and respond to contextual cues. How do these interacting systems support not only spatial encoding but also internally driven path planning, such as navigating to locations recalled from cues? Here, we propose a system-level theory of MEC-HC wiring that explains how grid and place cell patterns could be connected to enable cue-triggered goal retrieval, path planning, and reconstruction of sensory experience along planned routes. We suggest that place cells autoassociate sensory inputs with grid cell patterns, allowing sensory cues to trigger recall of goal-location grid patterns. We show analytically that grid-based planning permits shortcuts through unvisited locations and generalizes local transitions to long-range paths. During planning, intermediate grid states trigger place cell pattern completion, reconstructing sensory experiences along the route. Using a single-layer RNN modeling the HC-MEC loop with a planning subnetwork, we demonstrate these effects in both biologically grounded navigation simulations using RatatouGym and visually realistic navigation tasks using Habitat Sim.
Authors: Angelica Lim, \"O. Nilay Yal\c{c}in
Abstract: The fields of human-robot interaction (HRI) and embodied conversational agents (ECAs) have long studied how empathy could be implemented in machines. One of the major drivers has been the goal of giving multimodal social and emotional intelligence to these artificially intelligent agents, which interact with people through facial expressions, body, gesture, and speech. What empathic behaviors and models have these fields implemented by mimicking human and animal behavior? In what ways have they explored creating machine-specific analogies? This chapter aims to review the knowledge from these studies, towards applying the lessons learned to today's ubiquitous, language-based agents such as ChatGPT.
Authors: Wenwen Li, Yuanyuan Tian, Sizhe Wang, Amber Wutich, Paul Westerhoff, Sarah Porter, Anais Roque, Jobayer Hossain, Patrick Thomson, Rhett Larson, Michael Hanemann
Abstract: Understanding how interdisciplinary research teams converge on shared knowledge is a persistent challenge. This paper presents a novel, multi-layer, AI-driven analytical framework for mapping research convergence in interdisciplinary teams. The framework integrates large language models (LLMs), graph-based visualization and analytics, and human-in-the-loop evaluation to examine how research viewpoints are shared, influenced, and integrated over time. LLMs are used to extract structured viewpoints aligned with the \emph{Needs-Approach-Benefits-Competition (NABC)} framework and to infer potential viewpoint flows across presenters, forming a common semantic foundation for three complementary analyses: (1) similarity-based qualitative analysis to identify two key types of viewpoints, popular and unique, for building convergence, (2) quantitative cross-domain influence analysis using network centrality measures, and (3) temporal viewpoint flow analysis to capture convergence dynamics. To address uncertainty in LLM-based inference, the framework incorporates expert validation through structured surveys and cross-layer consistency checks. A case study on water insecurity in underserved communities as part of the Arizona Water Innovation Initiatives demonstrates increasing viewpoint convergence and domain-specific influence patterns, illustrating the value of the proposed AI-enabled approach for research convergence analysis.
Authors: Xu Zhao, Xiting Wang, Weiran Shen
Abstract: Large language models (LLMs) have achieved impressive capabilities, yet ensuring their safety against harmful prompts remains a critical challenge. Recent work has revealed that the latent representations (embeddings) of harmful and safe queries in LLMs typically exhibit linear separability, a property that has been exploited to construct attacks by perturbing the embeddings of harmful queries towards the safe subspace. Motivated by this observation, we propose a representation-level fine-tuning approach, named Embedding Space Separation (ES2), which improves LLM safety by explicitly enlarging the distance between harmful and safe representations in the embedding space. To prevent degradation of model's general capabilities, we introduce a Kullback-Leibler (KL) divergence regularization term into the loss function, which constrains the logits of the fine-tuned model to align with those of the original base model on harmless inputs. We evaluate our method on several open-source LLMs using standard safety benchmarks. Extensive experimental results demonstrate that our approach substantially improves model safety while maintaining comparable general capabilities.
Authors: Hyunjun Jeon, Kyuyoung Kim, Jinwoo Shin
Abstract: Modern language models can readily extract sensitive information from unstructured text, making redaction -- the selective removal of such information -- critical for data security. However, existing benchmarks for redaction typically focus on predefined categories of data such as personally identifiable information (PII) or evaluate specific techniques like masking. To address this limitation, we introduce RedacBench, a comprehensive benchmark for evaluating policy-conditioned redaction across domains and strategies. Constructed from 514 human-authored texts spanning individual, corporate, and government sources, paired with 187 security policies, RedacBench measures a model's ability to selectively remove policy-violating information while preserving the original semantics. We quantify performance using 8,053 annotated propositions that capture all inferable information in each text. This enables assessment of both security -- the removal of sensitive propositions -- and utility -- the preservation of non-sensitive propositions. Experiments across multiple redaction strategies and state-of-the-art language models show that while more advanced models can improve security, preserving utility remains a challenge. To facilitate future research, we release RedacBench along with a web-based playground for dataset customization and evaluation. Available at https://hyunjunian.github.io/redaction-playground/.
Authors: Hengwei Ye, Yuanting Guan, Yuxuan Ge, Tianying Zhu, Zhenhan Guan, Yijia Zhong, Yijing Zhang, Han Zhang, Yingna Wu, Zheng Tian
Abstract: Multimodal Large Language Models (MLLMs) combine the linguistic strengths of LLMs with the ability to process multimodal data, enbaling them to address a broader range of visual tasks. Because MLLMs aim at more general, human-like competence than language-only models, we take inspiration from the Wechsler Intelligence Scales - an established battery for evaluating children by decomposing intelligence into interpretable, testable abilities. We introduce KidGym, a comprehensive 2D grid-based benchmark for assessing five essential capabilities of MLLMs: Execution, Perception Reasoning, Learning, Memory and Planning. The benchmark comprises 12 unique tasks, each targeting at least one core capability, specifically designed to guage MLLMs' adaptability and developmental potential, mirroring the stages of children's cognitive growth. Additionally, our tasks encompass diverse scenarios and objects with randomly generated layouts, ensuring a more accurate and robust evluation of MLLM capabilities. KidGym is designed to be fully user-customizable and extensible, allowing researchers to create new evaluation scenarios and adjust difficuly levels to accommodate the rapidly growing MLLM community. Through the evaluation of state-of-the-art MLLMs using KidGym, we identified significant insights into model capabilities and revealed several limitations of current models. We release our benchmark at: https://bobo-ye.github.io/KidGym/.
Authors: Roy Uziel, Omer Belhasin, Itay Levi, Akhiad Bercovich, Ran El-Yaniv, Ran Zilberstein, Michael Elad
Abstract: Masked Diffusion Models (MDMs) provide an efficient non-causal alternative to autoregressive generation but often struggle with token dependencies and semantic incoherence due to their reliance on discrete marginal distributions. We address these limitations by shifting the diffusion process into a continuous sentence-level semantic space. We propose CRoCoDiL (Continuous and Robust Conditioned Diffusion for Language), a unified fine-tuning approach that jointly trains an encoder-demasker architecture, grounding the MDM demasking in continuous latent representations. This leads to the formation of a novel autoencoder in which decoding is obtained by an MDM algorithm. Relying on the same framework, we introduce two unconditional text synthesis algorithms: Continuous-Then-Discrete (ConThenDisc), a hybrid-diffusion approach that first generates latent representations in continuous space and then decodes these to tokens via an MDM, and Continuous-Within-Discrete (ConWithinDisc), a multi-diffusion strategy that refines latent representations throughout the discrete sampling process. Experiments using LLaDA show that our methods achieve superior generation quality and more than 10x faster sampling speeds in an unconditional setting.
Authors: Bahare Riahi, Ally Limke, Xiaoyi Tian, Viktoriia Storozhevykh, Sayali Patukale, Tahreem Yasir, Khushbu Singh, Jennifer Chiu, Nicholas lytle, Tiffany Barnes, Veronica Catete
Abstract: AI-based chatbots have the potential to accelerate learning and teaching, but may also have counterproductive consequences without thoughtful design and scaffolding. To better understand teachers' perspectives on large language model (LLM)-based chatbots, we conducted a study with 11 teams of middle school teachers using chatbots for a science and computational thinking activity within a block-based programming environment. Based on a qualitative analysis of audio transcripts and chatbot interactions, we propose three profiles: explorer, frustrated, and mixed, that reflect diverse scaffolding needs. In their discussions, we found that teachers perceived chatbot benefits such as building prompting skills and self-confidence alongside risks including potential declines in learning and critical thinking. Key design recommendations include scaffolding the introduction to chatbots, facilitating teacher control of chatbot features, and suggesting when and how chatbots should be used. Our contribution informs the design of chatbots to support teachers and learners in middle school coding activities.
Authors: Tatiana Chakravorti, Pranav Narayanan Venkit, Sourojit Ghosh, Sarah Rajtmajer
Abstract: Generative AI tools are increasingly entering academic peer review workflows, raising questions about fairness, accountability, and the legitimacy of evaluative judgment. While these systems promise efficiency gains amid growing reviewer overload, their use introduces new sociotechnical risks. This paper presents a convergent mixed-method study combining discourse analysis of 448 social media posts with interviews with 14 area chairs and program chairs from leading AI and HCI conferences to examine how GenAI is discussed and experienced in peer review. Across both datasets, we find broad agreement that GenAI may be acceptable for limited supportive tasks, such as improving clarity or structuring feedback, but that core evaluative judgments, assessing novelty, contribution, and acceptance, should remain human responsibilities. At the same time, participants highlight concerns about epistemic harm, over-standardization, unclear responsibility, and adversarial risks such as prompt injection. User interviews reveal how structural strain and institutional policy ambiguity shift interpretive and enforcement burdens onto individual scholars, disproportionately affecting junior authors and reviewers. By triangulating public governance discourse with lived review practices, this work reframes AI mediated peer review as a sociotechnical governance challenge and offers recommendations for preserving accountability, trust, and meaningful human oversight. Overall, we argue that AI-assisted peer review is best governed not by blanket bans or detection alone, but by explicitly reserving evaluative judgment for humans while instituting enforceable, role-specific controls that preserve accountability. We conclude with role specific recommendations that formalize the support judgment boundary.
Authors: Michael Hersche, Nicolas Menet, Ronan Tanios, Abbas Rahimi
Abstract: Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models, offering sub-linear generation latency and bidirectional capabilities that are particularly appealing for code generation and editing. Achieving sub-linear latency in discrete DLMs requires predicting multiple tokens in parallel. However, standard DLMs sample tokens independently from conditional marginal distributions, failing to capture the joint dependencies among concurrently generated tokens. As a result, they often lead to syntactic inconsistencies and break multi-token structures. In this work, we introduce CoDiLA (Coherent Diffusion with Local Autoregression), a method that reconciles parallel sampling with local dependency modeling. Rather than forcing the DLM to resolve fine-grained syntax, CoDiLA delegates local decoding to a small, auxiliary AR model operating on the diffusion latents. This design allows for parallel block generation while ensuring sequential validity within each block and maintaining core DLM capabilities, including bidirectional modeling across blocks. We demonstrate that using a highly compact auxiliary AR model (e.g., 0.6B parameters) effectively eliminates coherence artifacts, establishing a new Pareto frontier for accuracy and speed in code generation benchmarks.
Authors: Kushal Khemani
Abstract: Immediate feedback is a foundational requirement of effective AI-mediated learning, yet the energy and latency costs of delivering it remain largely unexamined. This study investigates the latency-energy-learning trade-off in AI tutoring through an empirical comparison of two on-device inference configurations of Microsoft Phi-3 Mini (4k-instruct) on an NVIDIA T4 GPU: full-precision FP16 and 4-bit NormalFloat (NF4) quantisation. Both were evaluated under KV-cache-enabled inference across 500 educational prompts spanning five secondary school subject domains. Pedagogical quality was assessed for each of the 1000 generated responses by a hybrid panel of 10 Cambridge International teachers and three frontier AI systems using a four-dimension rubric. We introduce Learning-per-Watt (LpW), a novel metric quantifying pedagogical value per unit of energy over the learner's waiting window. Under realistic deployment, NF4 achieves lower per-inference energy than FP16 (329 J vs. 369 J) but higher latency (13.4 s vs. 9.2 s), yielding a modest FP16 advantage in LpW of 1.33x at a quality difference of 0.19 points. Under cache-disabled inference -- used in offline evaluation but absent from real deployments -- the gap widens to 7.4x, overstating the FP16 advantage by more than fivefold. Quantisation efficiency is hardware-dependent and inference-regime dependent, with significant implications for equitable AI tutoring deployment in low-resource settings.
Authors: Drake Mullens, Stella Shen
Abstract: Do expert personas improve language model performance? The Wharton Generative AI Lab reports that they do not, broadcasting to millions via social media the recommendation that practitioners abandon a technique recommended by Anthropic, Google, and OpenAI. We demonstrate that this null finding was structurally predictable. Five core mechanisms precluded detection before data collection began: baseline contamination elevating the starting point to near-ceiling, system prompt hierarchy subordinating experimental manipulation, impossible expert specifications collapsing to generic competence, format constraints suppressing reasoning processes, and provider exclusion limiting generalizability. Controlled trials correcting these limitations reveal what the original design obscured. To test this, we selected the GPQA Diamond hardest questions to prevent baseline pattern matching, forcing reliance on genuine expert reasoning. On items with valid key answers, expert personas achieve ceiling accuracy. They eliminated all baseline errors through confidence amplification. Furthermore, forensic examination of model divergence identified that half of the hardest GPQA items contain chemically or logically indefensible answers. The model's CoT revealed reasoning away from impossible answers, yielding penalization for accurate chemistry. These findings recontextualize the original null results. Methodologically sound persona research faces measurement constraints imposed by benchmark validity limitations. Answering the persona question requires evaluation infrastructure the field does not yet possess.
Authors: Eric Gong, Nathan E. Sanders, Bruce Schneier
Abstract: Traditional survey-based political issue polling is becoming less tractable due to increasing costs and risk of bias associated with growing non-response rates and declining coverage of key demographic groups. With researchers and pollsters seeking alternatives, Large Language Models have drawn attention for their potential to augment human population studies in polling contexts. We propose and implement a new framework for anticipating human responses on multiple-choice political issue polling questions by directly prompting an LLM to predict a distribution of responses. By comparison to a large and high quality issue poll of the US population, the Cooperative Election Study, we evaluate how the accuracy of this framework varies across a range of demographics and questions on a variety of topics, as well as how this framework compares to previously proposed frameworks where LLMs are repeatedly queried to simulate individual respondents. We find the proposed framework consistently exhibits more accurate predictions than individual querying at significantly lower cost. In addition, we find the performance of the proposed framework varies much more systematically and predictably across demographics and questions, making it possible for those performing AI polling to better anticipate model performance using only information available before a query is issued.
Authors: Ahmed Abouelazm, Jonas Michel, Daniel Bogdoll, Philip Sch\"orner, J. Marius Z\"ollner
Abstract: Autonomous driving involves multiple, often conflicting objectives such as safety, efficiency, and comfort. In reinforcement learning (RL), these objectives are typically combined through weighted summation, which collapses their relative priorities and often yields policies that violate safety-critical constraints. To overcome this limitation, we introduce the Preordered Multi-Objective MDP (Pr-MOMDP), which augments standard MOMDPs with a preorder over reward components. This structure enables reasoning about actions with respect to a hierarchy of objectives rather than a scalar signal. To make this structure actionable, we extend distributional RL with a novel pairwise comparison metric, Quantile Dominance (QD), that evaluates action return distributions without reducing them into a single statistic. Building on QD, we propose an algorithm for extracting optimal subsets, the subset of actions that remain non-dominated under each objective, which allows precedence information to shape both decision-making and training targets. Our framework is instantiated with Implicit Quantile Networks (IQN), establishing a concrete implementation while preserving compatibility with a broad class of distributional RL methods. Experiments in Carla show improved success rates, fewer collisions and off-road events, and deliver statistically more robust policies than IQN and ensemble-IQN baselines. By ensuring policies respect rewards preorder, our work advances safer, more reliable autonomous driving systems.
Authors: Dang Nguyen, Harvey Yiyun Fu, Peter West, Chenhao Tan, Ari Holtzman
Abstract: Email communication increasingly involves large language models (LLMs), but we lack intuition on how they will read, write, and optimize for nuanced social goals. We introduce HR Simulator, a game where communication is the core mechanic: players play as a Human Resources officer and write emails to solve socially challenging workplace scenarios. An analysis of 600+ human and LLM emails with LLMs-as-judge reveals evidence for larger LLMs becoming more homogenous in their email quality judgments. Under LLM judges, humans underperform LLMs (e.g., 23.5% vs. 48-54% success rate), but a human+LLM approach can outperform LLM-only (e.g., from 40% to nearly 100% in one scenario). In cases where models' email preferences disagree, emergent tact is a plausible explanation: weaker models prefer less tactful strategies while stronger models prefer more tactful ones. Regarding tone, LLM emails are more formal and empathetic while human emails are more varied. LLM rewrites make human emails more formal and empathetic, but models still struggle to imitate human emails in the low empathy, low formality quadrant, which highlights a limitation of current post-training approaches. Our results demonstrate the efficacy of communication games as instruments to measure communication in the era of LLMs, and posit human-LLM co-writing as an effective form of communication in that future.
Authors: Chen Xiong, Ziwen Wang, Deqi Wang, Cheng Wang, Yiyang Chen, He Zhang, Chao Gou
Abstract: Autonomous driving testing increasingly relies on mining safety critical scenarios from large scale naturalistic driving data, yet existing screening pipelines still depend on manual risk annotation and expensive frame by frame risk evaluation, resulting in low efficiency and weakly grounded risk quantification. To address this issue, we propose a driver risk fusion based hazardous scenario screening method for autonomous driving. During training, the method combines an improved Driver Risk Field with a dynamic cost model to generate high quality risk supervision signals, while during inference it directly predicts scenario level risk scores through fast forward passes, avoiding per frame risk computation and enabling efficient large scale ranking and retrieval. The improved Driver Risk Field introduces a new risk height function and a speed adaptive look ahead mechanism, and the dynamic cost model integrates kinetic energy, oriented bounding box constraints, and Gaussian kernel diffusion smoothing for more accurate interaction modeling. We further design a risk trajectory cross attention decoder to jointly decode risk and trajectories. Experiments on the INTERACTION and FLUID datasets show that the proposed method produces smoother and more discriminative risk estimates. On FLUID, it achieves an AUC of 0.792 and an AP of 0.825, outperforming PODAR by 9.1 percent and 5.1 percent, respectively, demonstrating its effectiveness for scalable risk labeling and hazardous scenario screening.
Authors: Chen Xiong, Cheng Wang, Yuhang Liu, Zirui Wu, Ye Tian
Abstract: In contemporary autonomous driving testing, virtual simulation has become an important approach due to its efficiency and cost effectiveness. However, existing methods usually rely on reinforcement learning to generate risky scenarios, making it difficult to efficiently learn realistic emergency behaviors. To address this issue, we propose a behavior guided method for generating high risk lane change scenarios. First, a behavior learning module based on an optimized sequence generative adversarial network is developed to learn emergency lane change behaviors from an extracted dataset. This design alleviates the limitations of existing datasets and improves learning from relatively few samples. Then, the opposing vehicle is modeled as an agent, and the road environment together with surrounding vehicles is incorporated into the operating environment. Based on the Recursive Proximal Policy Optimization strategy, the generated trajectories are used to guide the vehicle toward dangerous behaviors for more effective risk scenario exploration. Finally, the reference trajectory is combined with model predictive control as physical constraints to continuously optimize the strategy and ensure physical authenticity. Experimental results show that the proposed method can effectively learn high risk trajectory behaviors from limited data and generate high risk collision scenarios with better efficiency than traditional methods such as grid search and manual design.
Authors: Saadi Lahlou (London School of Economics and Political Science, Paris Institute for Advanced Study), Annabelle Gouttebroze (London School of Economics and Political Science), Atrina Oraee (London School of Economics and Political Science), Julian Madera (London School of Economics and Political Science)
Abstract: We qualitatively compared literature reviews produced with varying degrees of AI assistance. The same LLM, given the same corpus of 280 papers but different selections, produced dramatically different reviews, from mainstream and politically neutral to critical and post-colonial, though neither orientation was intended. LLM outputs always appear at first glance to be well written, well informed and thought out, but closer reading reveals gaps, biases and lack of depth. Our comparison of six versions shows a series of pitfalls and suggests precautions necessary when using AI assistance to make a literature review. Main issues are: (1) The bias of ignorance (you do not know what you do not get) in the selection of relevant papers. (2) Alignment and digital sycophancy: commercial AI models slavishly take you further in the direction they understand you give them, reinforcing biases. (3) Mainstreaming: because of their statistical nature, LLM productions tend to favor mainstream perspectives and content; in our case there was only 20% overlap between paper selections by humans and the LLM. (4) Limited capacity for creative restructuring, with vague and ambiguous statements. (5) Lack of critical perspective, coming from distant reading and political correctness. Most pitfalls can be addressed by prompting, but only if the user knows the domain well enough to detect them. There is a paradox: producing a good AI-assisted review requires expertise that comes from reading the literature, which is precisely what AI was meant to reduce. Overall, AI can improve the span and quality of the review, but the gain of time is not as massive as one would expect, and a press-button strategy leaving AI to do the work is a recipe for disaster. We conclude with recommendations for those who write, or assess, such LLM-augmented reviews.
Authors: Michal Olak, Tommaso Boccato, Matteo Ferrante
Abstract: Speech brain--computer interfaces require decoders that translate intracortical activity into linguistic output while remaining robust to limited data and day-to-day variability. While prior high-performing systems have largely relied on framewise phoneme decoding combined with downstream language models, it remains unclear what contextual sequence-to-sequence decoding contributes to sublexical neural readout, robustness, and interpretability. We evaluated a multitask Transformer-based sequence-to-sequence model for attempted speech decoding from area 6v intracortical recordings. The model jointly predicts phoneme sequences, word sequences, and auxiliary acoustic features. To address day-to-day nonstationarity, we introduced the Neural Hammer Scalpel (NHS) calibration module, which combines global alignment with feature-wise modulation. We further analyzed held-out-day generalization and attention patterns in the encoder and decoders. On the Willett et al. dataset, the proposed model achieved a state-of-the-art phoneme error rate of 14.3%. Word decoding reached 25.6% WER with direct decoding and 19.4% WER with candidate generation and rescoring. NHS substantially improved both phoneme and word decoding relative to linear or no day-specific transform, while held-out-day experiments showed increasing degradation on unseen days with temporal distance. Attention visualizations revealed recurring temporal chunking in encoder representations and distinct use of these segments by phoneme and word decoders. These results indicate that contextual sequence-to-sequence modeling can improve the fidelity of neural-to-phoneme readout from intracortical speech signals and suggest that attention-based analyses can generate useful hypotheses about how neural speech evidence is segmented and accumulated over time.
Authors: Jiaqi Lai, Hou Liang, Weihong Huang
Abstract: As artificial intelligence (AI) is increasingly deployed in high-stakes public decision-making (from resource allocation to welfare distribution), public trust in these systems has become a critical determinant of their legitimacy and sustainability. Yet existing AI governance research remains largely qualitative, lacking formal mathematical frameworks to characterize the precise conditions under which public trust collapses. This paper addresses that gap by proposing a rigorous coupled dynamics model that integrates a discrete-time Hawkes process -- capturing the self-exciting generation of AI controversy events such as perceived algorithmic unfairness or accountability failures -- with a Friedkin-Johnsen opinion dynamics model that governs the evolution of institutional trust across social networks. A key innovation is the bidirectional feedback mechanism: declining trust amplifies the intensity of subsequent controversy events, which in turn further erode trust, forming a self-reinforcing collapse loop. We derive closed-form equilibrium solutions and perform formal stability analysis, establishing the critical spectral condition rho(J_{2nt}) < 1 that delineates the boundary between trust resilience and systemic collapse. Numerical experiments further reveal how echo chamber network structures and media amplification accelerate governance failure. Our core contribution to the AI governance field is a baseline collapse model: a formal stability analysis framework demonstrating that, absent strong institutional intervention, even minor algorithmic biases can propagate through social networks to trigger irreversible trust breakdown in AI governance systems.
Authors: Montgomery Flora, Samuel Varga, Corey Potvin, Noah Lang
Abstract: While machine learning (ML) post-processing of convection-allowing model (CAM) output for severe weather hazards (large hail, damaging winds, and/or tornadoes) has shown promise for very short lead times (0-3 hours), its application to slightly longer forecast windows remains relatively underexplored. In this study, we develop and evaluate a grid-based ML framework to predict the probability of severe weather hazards over the next 2-6 hours using forecast output from the Warn-on-Forecast System (WoFS). Our dataset includes WoFS ensemble forecasts valid every 5 minutes out to 6 hours from 108 days during the 2019--2023 NOAA Hazardous Weather Testbed Spring Forecasting Experiments. We train ML models to generate probabilistic forecasts of severe weather akin to Storm Prediction Center outlooks (i.e., likelihood of a tornado, severe wind, or severe hail event within 36 km of each point). We compare a histogram gradient-boosted tree (HGBT) model and a deep learning U-Net approach against a carefully calibrated baseline generated from 2-5 km updraft helicity. Results indicate that the HGBT and U-Net outperform the baseline, particularly at higher probability thresholds. The HGBT achieves the best performance metrics, but predicted probabilities cap at 60% while the U-net forecasts extend to 100%. Similar to previous studies, the U-Net produces spatially smoother guidance than the tree-based method. These findings add to the growing evidence of the effectiveness of ML-based CAM post-processing for providing short-term severe weather guidance.
Authors: Nathan Garland
Abstract: Student experiences and empirical studies report that "black box" AI text detectors produce high false positive rates with disproportionate errors against certain student populations, yet typically theoretical analyses model detection as a test between two known distributions for human and AI prose. This framing omits the structural feature of university assessment whereby an assessor generally does not know the individual student's writing distribution, making the null hypothesis composite. Standard application of the variational characterisation of total variation distance to this composite null shows trade-off bounds that any text-only, one-shot detector with useful power must produce false accusations at a rate governed by the distributional overlap between student writing and AI output. This is a constraint arising from population diversity that is logically independent of AI model quality and cannot be overcome by better detector engineering or technology. A subgroup mixture bound connects these quantities to observable demographic groups, providing a theoretical basis for the disparate impact patterns documented empirically. We propose suggestions to improve policy and practice, and argue that detection scores should not serve as sole evidence in misconduct proceedings.
Authors: Tianshu Zhang, Huan Sun
Abstract: Autonomous science agents built on large language models (LLMs) are increasingly used to generate hypotheses, design experiments, and produce reports. However, prior work mainly targets open-ended scientific problems with subjective outputs that are difficult to evaluate. Scientific coding benchmarks, by contrast, provide executable outputs for objective assessment. Existing approaches remain engineering-driven pipelines, revealing the need for structured, end-to-end science agent frameworks for scientific coding tasks. We address this gap by focusing on scientific coding tasks, where evaluation can be made rigorously, and introducing an agent framework SciNav (Scientific Navigator) that enables more effective solution exploration. Our framework is designed to operate under constrained search budgets, moving beyond reliance on pre-defined success metrics and prolonged search cycles. Inspired by findings that comparative judgments often reveal finer-grained quality differences and therefore provide greater discriminative power than absolute scoring, our framework leverages pairwise relative judgments within a tree search process to select top-K promising solution branches, prune low-potential ones, and progressively narrow down the solution candidates on the selected branches guided by relative comparisons. We demonstrate our agent's effectiveness across different types of tasks on two benchmarks. Experiments show that SciNav significantly outperforms direct prompting and prior agents like OpenHands and Self-Debug across different base models, task types, and difficulty levels, and exceeds different frontier comparators such as random selection and LLM absolute scoring. These results confirm the strength of our agent design and highlight the effectiveness of relative judgment-guided top-K search for high-quality scientific coding, marking a step toward more practical science agents.
Authors: Marek Zylinski, Bartosz Tomasz Smigielski, Gerard Cybulski
Abstract: Reliable detection of event-related potentials (ERPs) at the single-trial level remains a major challenge due to the low signal-to-noise ratio EEG recordings. In this work, we investigate whether incorporating prior knowledge about ERP templates into deep learning models can improve detection performance. We employ the Deep-Match framework for ERP detection using multi-channel EEG signals. The model is trained in two stages. First, an encoder-decoder architecture is trained to reconstruct input EEG signals, enabling the network to learn compact signal representations. In the second stage, the decoder is replaced with a detection module, and the network is fine-tuned for ERP identification. Two model variants are evaluated: a standard model with randomly initialized filters and a Deep-MF model in which input kernels are initialized using ERP templates. Model performance is assessed on a single-trial ERP detection task using leave-one-subject-out validation. The proposed Deep-MF model slightly outperforms the detector with standard kernel initialization for most held-out subjects. Despite substantial inter-subject variability, Deep-MF achieves a higher average F1-score (0.37) compared to the standard network (0.34), indicating improved robustness to cross-subject differences. The best performance obtained by Deep-MF reaches an F1-score of 0.71, exceeding the maximum score achieved by the standard model (0.59). These results demonstrate that ERP-informed kernel initialization can provide consistent improvements in subject-independent single-trial ERP detection. Overall, the findings highlight the potential of integrating domain knowledge with deep learning architectures for EEG analysis. The proposed approach represents a step toward practical wearable EEG and passive brain-computer interface systems capable of real-time monitoring of cognitive processes.
Authors: Zequn Liu, Kehan Wu, Shufang Xie, Zekun Guo, Wei Zhang, Tao Qin, Renhe Liu, Yingce Xia
Abstract: Emerging reasoning models hold promise for automating scientific discovery. However, their training is hindered by a critical supervision gap: experimental outcomes are abundant, whereas intermediate reasoning steps are rarely documented at scale. To bridge this gap, we propose DESRO, a framework for deciphering scientific reasoning from outcomes. By analyzing shared patterns and key differences within grouped data, a large language model (LLM) can recover the underlying logic. We instantiate this framework in molecule optimization, a pivotal stage in drug discovery that traditionally relies on the iterative reasoning of medicinal chemists. Across 2.3 million molecular property records, our framework infers optimization rationales by grouping molecules with shared fragments, then using an LLM to analyze how structural variations correlate with property differences. Based on the derived data, we train a model that conducts molecule optimization through an interpretable reasoning process. DESRO achieves the highest success rates on 15 out of 18 tasks, spanning both single- and multi-property optimization of bioactivity and ADMET properties. The reasoning process enables robust generalization to out-of-distribution scenarios, including novel property combinations, unseen biological targets, and unseen properties defined solely by natural language descriptions. In retrospective case studies under strict temporal splits, the model autonomously reconstructs expert-level lead optimization trajectories. Additionally, our framework extends beyond molecule optimization to reaction ligand selection. Our results establish deciphering reasoning steps from outcome data as a viable paradigm for enabling scientific reasoning, providing a scalable approach to accelerate scientific discovery.
Authors: Islam Guven, Mehmet Parlak
Abstract: Multi-UAV networks are increasingly deployed for large-scale inspection and monitoring missions, where operational performance depends on the coordination of sensing reliability, communication quality, and energy constraints. In particular, the rapid increase in overflowing waste bins and illegal dumping sites has created a need for efficient detection of waste hotspots. In this work, we introduce JCAS-MARL, a resource-aware multi-agent reinforcement learning (MARL) framework for joint communication and sensing (JCAS)-enabled UAV networks. Within this framework, multiple UAVs operate in a shared environment where each agent jointly controls its trajectory and the resource allocation of an OFDM waveform used simultaneously for sensing and communication. Battery consumption, charging behavior, and associated CO$_2$ emissions are incorporated into the system state to model realistic operational constraints. Information sharing occurs over a dynamic communication graph determined by UAV positions and wireless channel conditions. Waste hotspot detection requires consensus among multiple UAVs to improve reliability. Using this environment, we investigate how MARL policies exploit the sensing-communication-energy trade-off in JCAS-enabled UAV networks. Simulation results demonstrate that adaptive pilot-density control learned by the agents can outperform static configurations, particularly in scenarios where sensing accuracy and communication connectivity vary across the environment.
Authors: Stefan Hackmann
Abstract: Despite the rapid advancements in Artificial Intelligence (AI), Stochastic Differential Equations (SDEs) remain the gold-standard formalism for modeling systems under uncertainty. However, applying SDEs in practice is fraught with challenges: modeling risk is high, calibration is often brittle, and high-fidelity simulations are computationally expensive. This technical report introduces JointFM, a foundation model that inverts this paradigm. Instead of fitting SDEs to data, we sample an infinite stream of synthetic SDEs to train a generic model to predict future joint probability distributions directly. This approach establishes JointFM as the first foundation model for distributional predictions of coupled time series - requiring no task-specific calibration or finetuning. Despite operating in a purely zero-shot setting, JointFM reduces the energy loss by 14.2% relative to the strongest baseline when recovering oracle joint distributions generated by unseen synthetic SDEs.
Authors: Yesung Cho, Dongmyung Shin, Sujeong Hong, Jooyeon Lee, Seongmin Park, Geongyu Lee, Jongbae Park, Hong Koo Ha
Abstract: Prostate cancer is one of the most frequently diagnosed malignancies in men worldwide. However, precise prediction of biochemical recurrence (BCR) after radical prostatectomy remains challenging due to the multifocality of tumors distributed throughout the prostate gland. In this paper, we propose a novel AI framework that simultaneously processes a series of multi-section pathology slides to capture the comprehensive tumor landscape across the entire prostate gland. To develop this predictive AI model, we curated a large-scale dataset of 23,451 slides from 789 patients. The proposed framework demonstrated strong predictive performance for 1- and 2-year BCR prediction, substantially outperforming established clinical benchmarks. The AI-derived risk score was validated as the most potent independent prognostic factor in a multivariable Cox proportional hazards analysis, surpassing conventional clinical markers such as pre-operative PSA and Gleason score. Furthermore, we demonstrated that integrating patch and slide sub-sampling strategies significantly reduces computational cost during both training and inference without compromising predictive performance, and generalizability of AI was confirmed through external validation. Collectively, these results highlight the clinical feasibility and prognostic value of the proposed AI-based multi-section slide analysis as a scalable tool for post-operative management in prostate cancer.
Authors: Saeed Khaki, Nima Safaei, Kamal Ginotra
Abstract: Transformer-based vision-language models (VLMs) contain substantial depth redundancy, yet the effect of removing specific decoder layers remains poorly understood, especially for domains that require tight coupling between perception and multi-step reasoning. We study structured decoder layer pruning through the lens of domain-aware activation similarity, measuring how strongly each layer transforms representations for math versus non-math inputs. This yields simple math-aware, non-math-aware, and mixed ranking criteria that identify layers whose input-output activations change least within a target domain. Across two state-of-the-art VLMs and a broad suite of math and general multimodal benchmarks, we uncover a consistent three-regime structure: at low pruning budgets, performance is highly sensitive to which layers are removed; at moderate budgets, methods converge as structural damage accumulates; and at high budgets, structural continuity dominates, favoring spacing-aware strategies. Our domain-aware rankings achieve the strongest stability in the ranking-sensitive regime, while matching or exceeding structure-aware baselines at larger budgets. These results provide a clearer picture of how depth contributes to domain-specific behavior in VLMs and offer a practical, interpretable approach to reducing model depth without sacrificing essential mathematical or general vision-language capabilities.
Authors: Zhuofeng Li, Dongfu Jiang, Xueguang Ma, Haoxiang Zhang, Ping Nie, Yuyu Zhang, Kai Zou, Jianwen Xie, Yu Zhang, Wenhu Chen
Abstract: Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning. However, existing data collection pipelines typically rely on proprietary web APIs, making large-scale trajectory synthesis costly, unstable, and difficult to reproduce. We present OpenResearcher, a reproducible pipeline that decouples one-time corpus bootstrapping from multi-turn trajectory synthesis and executes the search-and-browse loop entirely offline using three explicit browser primitives: search, open, and find, over a 15M-document corpus. Using GPT-OSS-120B as the teacher model, we synthesize over 97K trajectories, including a substantial long-horizon tail with 100+ tool calls. Supervised fine-tuning a 30B-A3B backbone on these trajectories achieves 54.8\% accuracy on BrowseComp-Plus, a +34.0 point improvement over the base model, while remaining competitive on BrowseComp, GAIA, and xbench-DeepSearch. Because the environment is offline and fully instrumented, it also enables controlled analysis, where our study reveals practical insights into deep research pipeline design, including data filtering strategies, agent configuration choices, and how retrieval success relates to final answer accuracy. We release the pipeline, synthesized trajectories, model checkpoints, and the offline search environment at https://github.com/TIGER-AI-Lab/OpenResearcher.
Authors: Alex Popa, Adrian Taylor, Ranwa Al Mallah
Abstract: Reinforcement learning techniques are being explored as solutions to the threat of cyber attacks on enterprise networks. Recent research in the field of AI in cyber security has investigated the ability of homogeneous multi-agent reinforcement learning agents, capable of inter-agent communication, to respond to cyberattacks. This paper advances the study of learned communication in multi-agent systems by examining heterogeneous agent capabilities within a simulated network environment. To this end, we leverage CommFormer, a publicly available state-of-the-art communication algorithm, to train and evaluate agents within the Cyber Operations Research Gym (CybORG). Our results show that CommFormer agents with heterogeneous capabilities can outperform other algorithms deployed in the CybORG environment, by converging to an optimal policy up to four times faster while improving standard error by up 38%. The agents implemented in this project provide an additional avenue for exploration in the field of AI for cyber security, enabling further research involving realistic networks.
Authors: Jussi Keppo, Yuze Li, Gerry Tsoukalas, Nuo Yuan
Abstract: Recent work shows that pricing with symmetric LLM agents leads to algorithmic collusion. We show that collusion is fragile under the heterogeneity typical of real deployments. In a stylized repeated-pricing model, heterogeneity in patience or data access reduces the set of collusive equilibria. Experiments with open-source LLM agents (totaling over 2,000 compute hours) align with these predictions: patience heterogeneity reduces price lift from 22% to 10% above competitive levels; asymmetric data access, to 7%. Increasing the number of competing LLMs breaks up collusion; so does cross-algorithm heterogeneity, that is, setting LLMs against Q-learning agents. But model-size differences (e.g., 32B vs. 14B weights) do not; they generate leader-follower dynamics that stabilize collusion. We discuss antitrust implications, such as enforcement actions restricting data-sharing and policies promoting algorithmic diversity.
Authors: Songfeng Zhu
Abstract: In incremental classification tasks for hyperspectral images, catastrophic forgetting is an unavoidable challenge. While memory recall methods can mitigate this issue, they heavily rely on samples from old categories. This paper proposes a teacher-based knowledge retention method for incremental image classification. It alleviates model forgetting of old category samples by utilizing incremental category samples, without depending on old category samples. Additionally, this paper introduces a mask-based partial category knowledge distillation algorithm. By decoupling knowledge distillation, this approach filters out potentially misleading information that could misguide the student model, thereby enhancing overall accuracy. Comparative and ablation experiments demonstrate the proposed method's robust performance.
Authors: Dong Li, Zhengzhang Chen, Xujiang Zhao, Linlin Yu, Zhong Chen, Yi He, Haifeng Chen, Chen Zhao
Abstract: Uncovering causal structures from observational data is crucial for understanding complex systems and making informed decisions. While reinforcement learning (RL) has shown promise in identifying these structures in the form of a directed acyclic graph (DAG), existing methods often lack efficiency, making them unsuitable for online applications. In this paper, we propose MARLIN, an efficient multi agent RL based approach for incremental DAG learning. MARLIN uses a DAG generation policy that maps a continuous real valued space to the DAG space as an intra batch strategy, then incorporates two RL agents state specific and state invariant to uncover causal relationships and integrates these agents into an incremental learning framework. Furthermore, the framework leverages a factored action space to enhance parallelization efficiency. Extensive experiments on synthetic and real datasets demonstrate that MARLIN outperforms state of the art methods in terms of both efficiency and effectiveness.
Authors: Jing Liu, Zhenchao Ma, Han Yu, Bobo Ju, Wenliang Yang, Chengfang Li, Bo Hu, Liang Song
Abstract: Recent advances in collaborative knowledge distillation have demonstrated cutting-edge performance for resource-constrained distributed multimedia learning scenarios. However, achieving such competitiveness requires addressing a fundamental mismatch: high-dimensional teacher knowledge complexity versus heterogeneous client learning capacities, which currently prohibits deployment in edge-based visual analytics systems. Drawing inspiration from curriculum learning principles, we introduce Federated Adaptive Progressive Distillation (FAPD), a consensus-driven framework that orchestrates adaptive knowledge transfer. FAPD hierarchically decomposes teacher features via PCA-based structuring, extracting principal components ordered by variance contribution to establish a natural visual knowledge hierarchy. Clients progressively receive knowledge of increasing complexity through dimension-adaptive projection matrices. Meanwhile, the server monitors network-wide learning stability by tracking global accuracy fluctuations across a temporal consensus window, advancing curriculum dimensionality only when collective consensus emerges. Consequently, FAPD provably adapts knowledge transfer pace while achieving superior convergence over fixed-complexity approaches. Extensive experiments on three datasets validate FAPD's effectiveness: it attains 3.64% accuracy improvement over FedAvg on CIFAR-10, demonstrates 2x faster convergence, and maintains robust performance under extreme data heterogeneity ({\alpha}=0.1), outperforming baselines by over 4.5%.
Authors: Adithya Parthasarathy, Aswathnarayan Muthukrishnan Kirubakaran, Akshay Deshpande, Ram Sekhar Bodala, Suhas Malempati, Nachiappan Chockalingam, Vinoth Punniyamoorthy, Seema Gangaiah Aarella
Abstract: Accurate calibration is essential for instruments whose measurements must remain traceable, reliable, and compliant over long operating periods. Fixed-interval programs are easy to administer, but they ignore that instruments drift at different rates under different conditions. This paper studies calibration scheduling as a predictive maintenance problem: given recent sensor histories, estimate time-to-drift (TTD) and intervene before a violation occurs. We adapt the NASA C-MAPSS benchmark into a calibration setting by selecting drift-sensitive sensors, defining virtual calibration thresholds, and inserting synthetic reset events that emulate repeated recalibration. We then compare classical regressors, recurrent and convolutional sequence models, and a compact Transformer for TTD prediction. The Transformer provides the strongest point forecasts on the primary FD001 split and remains competitive on the harder FD002--FD004 splits, while a quantile-based uncertainty model supports conservative scheduling when drift behavior is noisier. Under a violation-aware cost model, predictive scheduling lowers cost relative to reactive and fixed policies, and uncertainty-aware triggers sharply reduce violations when point forecasts are less reliable. The results show that condition-based calibration can be framed as a joint forecasting and decision problem, and that combining sequence models with risk-aware policies is a practical route toward smarter calibration planning.
Authors: Yusen Wu, Xiaotie Deng
Abstract: Existing Retrieval-Augmented Generation (RAG) methods for code struggle to capture the high-level architectural patterns and cross-file dependencies inherent in complex, theory-driven codebases, such as those in algorithmic game theory (AGT), leading to a persistent semantic and structural gap between abstract concepts and executable implementations. To address this challenge, we propose Hierarchical Code/Architecture-guided Agent Generation (HCAG), a framework that reformulates repository-level code generation as a structured, planning-oriented process over hierarchical knowledge. HCAG adopts a two-phase design: an offline hierarchical abstraction phase that recursively parses code repositories and aligned theoretical texts to construct a multi-resolution semantic knowledge base explicitly linking theory, architecture, and implementation; and an online hierarchical retrieval and scaffolded generation phase that performs top-down, level-wise retrieval to guide LLMs in an architecture-then-module generation paradigm. To further improve robustness and consistency, HCAG integrates a multi-agent discussion inspired by cooperative game. We provide a theoretical analysis showing that hierarchical abstraction with adaptive node compression achieves cost-optimality compared to flat and iterative RAG baselines. Extensive experiments on diverse game-theoretic system generation tasks demonstrate that HCAG substantially outperforms representative repository-level methods in code quality, architectural coherence, and requirement pass rate. In addition, HCAG produces a large-scale, aligned theory-implementation dataset that effectively enhances domain-specific LLMs through post-training. Although demonstrated in AGT, HCAG paradigm also offers a general blueprint for mining, reusing, and generating complex systems from structured codebases in other domains.
Authors: Shaolin Wang, Yi Mei, Haoyang Che, He Jiang, Shui Yu, Ying Gu
Abstract: Software systems have traditionally been designed for human interaction, emphasizing graphical user interfaces, usability, and cognitive alignment with end users. However, recent advances in large language model (LLM)-based agents are changing the primary consumers of software systems. Increasingly, software is no longer only used by humans, but also invoked autonomously by AI agents through structured interfaces. In this paper, we argue that software engineering is undergoing a paradigm shift from human-oriented interfaces to agent-oriented invocation systems. We formalize the notion of agent interfaces, introduce invocable capabilities as the fundamental building blocks of AI-oriented software, and outline design principles for such systems, including machine interpretability, composability, and invocation reliability. We then discuss architectural and organizational implications of this shift, highlighting a transition from monolithic applications to capability-based systems that can be dynamically composed by AI agents. The paper aims to provide a conceptual foundation for the emerging paradigm of AI-native software design.
Authors: Mehtab Ur Rahman, Martha Larson, Cristian Tejedor-Garcia
Abstract: Voice privacy approaches that preserve the anonymity of speakers modify speech in an attempt to break the link with the true identity of the speaker. Current benchmarks measure speaker protection based on signal-to-signal comparisons. In this paper, we introduce an attribute-based perspective, where we measure privacy protection in terms of comparisons between sets of speaker attributes. First, we analyze privacy impact by calculating speaker uniqueness for ground truth attributes, attributes inferred on the original speech, and attributes inferred on speech protected with standard anonymization. Next, we examine a threat scenario involving only a single utterance per speaker and calculate attack error rates. Overall, we observe that inferred attributes still present a risk despite attribute inference errors. Our research points to the importance of considering both attribute-related threats and protection mechanisms in future voice privacy research.
Authors: Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li
Abstract: Flow Matching (FM) has recently emerged as a leading approach for high-fidelity visual generation, offering a robust continuous-time alternative to ordinary differential equation (ODE) based models. However, despite their success, FM models are highly sensitive to dataset biases, which cause severe semantic degradation when generating out-of-distribution or minority-class samples. In this paper, we provide a rigorous mathematical formalization of the ``Bias Manifold'' within the FM framework. We identify that this performance drop is driven by conditional expectation smoothing, a mechanism that inevitably leads to trajectory lock-in during inference. To resolve this, we introduce InjectFlow, a novel, training-free method by injecting orthogonal semantics during the initial velocity field computation, without requiring any changes to the random seeds. This design effectively prevents the latent drift toward majority modes while maintaining high generative quality. Extensive experiments demonstrate the effectiveness of our approach. Notably, on the GenEval dataset, InjectFlow successfully fixes 75% of the prompts that standard flow matching models fail to generate correctly. Ultimately, our theoretical analysis and algorithm provide a ready-to-use solution for building more fair and robust visual foundation models.
Authors: Yuzhe Weng, Haotian Wang, Yuanhong Yu, Jun Du, Shan He, Xiaoyan Wu, Haoran Xu
Abstract: Audio-driven talking head generation aims to create vivid and realistic videos from a static portrait and speech. Existing AR-based methods rely on intermediate facial representations, which limit their expressiveness and realism. Meanwhile, diffusion-based methods generate clip-by-clip, lacking fine-grained control and causing inherent latency due to overall denoising across the window. To address these limitations, we propose EARTalking, a novel end-to-end, GPT-style autoregressive model for interactive audio-driven talking head generation. Our method introduces a novel frame-by-frame, in-context, audio-driven streaming generation paradigm. For inherently supporting variable-length video generation with identity consistency, we propose the Sink Frame Window Attention (SFA) mechanism. Furthermore, to avoid the complex, separate networks that prior works required for diverse control signals, we propose a streaming Frame Condition In-Context (FCIC) scheme. This scheme efficiently injects diverse control signals in a streaming, in-context manner, enabling interactive control at every frame and at arbitrary moments. Experiments demonstrate that EARTalking outperforms existing autoregressive methods and achieves performance comparable to diffusion-based methods. Our work demonstrates the feasibility of in-context streaming autoregressive control, unlocking a scalable direction for flexible, efficient generation. The code will be released for reproducibility.
Authors: Aayam Bansal, Ishaan Gangwani
Abstract: Cooperative perception among autonomous agents overcomes the limitations of single-agent sensing, but bandwidth constraints in vehicle-to-everything (V2X) networks require efficient communication policies. Existing approaches rely on reactive mechanisms, such as confidence maps, learned gating, or sparse masks, to decide what to transmit, without reasoning about why a message benefits the receiver. We introduce Reason-to-Transmit (R2T), a framework that equips each agent with a lightweight transformer-based module that reasons over local scene context, estimated neighbor information gaps, and bandwidth budget to make per-region transmission decisions. Trained end-to-end with a bandwidth-aware objective, R2T is evaluated against nine baselines in a multi-agent bird's-eye-view perception environment. Any communication improves performance by about 58% AP over no communication. At low bandwidth, all selective methods perform similarly, but R2T shows clear gains under high occlusion, where information asymmetry is greatest, approaching oracle performance. All methods degrade gracefully under packet drops up to 50%, showing robustness to communication failures. These results indicate that while fusion design dominates performance, deliberative communication provides additional gains in challenging scenarios. R2T introduces a reasoning-based approach to communication, enabling more efficient and context-aware information sharing in cooperative perception.
Authors: Rohan Siva, Kai Cheung, Lichi Li, Ganesh Sundaram
Abstract: Modern machine learning systems rely on complex data engineering workflows to extract, transform, and load (ELT) data into production pipelines. However, constructing these pipelines remains time-consuming and requires substantial expertise in data infrastructure and orchestration frameworks. Recent advances in large language model (LLM) agents offer a potential path toward automating these workflows, but existing approaches struggle with under-specified user intent, unreliable tool generation, and limited guarantees of executable outputs. We introduce kRAIG, an AI agent that translates natural language specifications into production-ready Kubeflow Pipelines (KFP). To resolve ambiguity in user intent, we propose ReQuesAct (Reason, Question, Act), an interaction framework that explicitly clarifies intent prior to pipeline synthesis. The system orchestrates end-to-end data movement from diverse sources and generates task-specific transformation components through a retrieval-augmented tool synthesis process. To ensure data quality and safety, kRAIG incorporates LLM-based validation stages that verify pipeline integrity prior to execution. Our framework achieves a 3x improvement in extraction and loading success and a 25 percent increase in transformation accuracy compared to state-of-the-art agentic baselines. These improvements demonstrate that structured agent workflows with explicit intent clarification and validation significantly enhance the reliability and executability of automated data engineering pipelines.
Authors: Sarat Mudunuri, Jian Wan, Ally Qin, Srinivasan Manoharan
Abstract: Large Language Models (LLMs) with tool-calling capabilities have demonstrated remarkable potential in executing complex tasks through external tool integration. The Model Context Protocol (MCP) has emerged as a standardized framework for connecting LLMs to diverse toolsets, with individual MCP servers potentially exposing dozens to hundreds of tools. However, current implementations face a critical scalability challenge: providing all available tools to the LLM context results in substantial token overhead, increased costs, reduced accuracy, and context window constraints. We present a semantic tool discovery architecture that addresses these challenges through vector-based retrieval. Our approach indexes MCP tools using dense embeddings that capture semantic relationships between tool capabilities and user intent, dynamically selecting only the most relevant tools (typically 3-5) rather than exposing the entire tool catalog (50-100+). Experimental results demonstrate a 99.6% reduction in tool-related token consumption with a hit rate of 97.1% at K=3 and an MRR of 0.91 on a benchmark of 140 queries across 121 tools from 5 MCP servers, with sub-100ms retrieval latency. Contributions include: (1) a semantic indexing framework for MCP tools, (2) a dynamic tool selection algorithm based on query-tool similarity, (3) comprehensive evaluation demonstrating significant efficiency and accuracy improvements, and (4) extensibility to multi-agent and cross-organizational tool discovery.
Authors: Sasan Mansouri, Edoardo Pilla, Mark Wahrenburg, Fabian Woebbeking
Abstract: Answering financial questions is often treated as an information retrieval problem. In practice, however, much of the relevant information is already available in curated vendor systems, especially for quantitative analysis. We study whether, and under which conditions, Model Context Protocol (MCP) offers a more reliable alternative to standard retrieval-augmented generation (RAG) by allowing large language models (LLMs) to interact directly with data rather than relying on document ingestion and chunk retrieval. We test this by building a custom MCP server that exposes LSEG APIs as tools and evaluating it on the FinDER benchmark. The approach performs particularly well on the Financials subset, achieving up to 80.4% accuracy on multi-step numerical questions when relevant context is retrieved. The paper thus provides both a baseline for MCP-based financial question answering (QA) and evidence on where this approach breaks down, such as for questions requiring qualitative or document-specific context. Overall, direct access to curated data is a lightweight and effective alternative to document-centric RAG for quantitative financial QA, but not a substitute for all financial QA tasks.
Authors: Shasha Yu, Fiona Carroll, Barry L. Bentley
Abstract: Large language models (LLMs) are increasingly deployed as agents with access to executable tools, enabling direct interaction with external systems. However, most safety evaluations remain text-centric and assume that compliant language implies safe behavior, an assumption that becomes unreliable once models are allowed to act. In this work, we empirically examine how executable tool affordance alters safety alignment in LLM agents using a paired evaluation framework that compares text-only chatbot behavior with tool-enabled agent behavior under identical prompts and policies. Experiments are conducted in a deterministic financial transaction environment with binary safety constraints across 1,500 procedurally generated scenarios. To separate intent from outcome, we distinguish between attempted and realized violations using dual enforcement regimes that either block or permit unsafe actions. Both evaluated models maintain perfect compliance in text-only settings, yet exhibit sharp increases in violations after tool access is introduced, reaching rates up to 85% despite unchanged rules. We observe substantial gaps between attempted and executed violations, indicating that external guardrails can suppress visible harm while masking persistent misalignment. Agents also develop spontaneous constraint circumvention strategies without adversarial prompting. These results demonstrate that tool affordance acts as a primary driver of safety misalignment and that text-based evaluation alone is insufficient for assessing agentic systems.
Authors: Fujian Jia, Jiwen Gu, Cheng Lu, Dezhi Zhao, Mengjiang Huang, Yuanzhi Lu, Xin Liu, Kang Liu
Abstract: Understanding mechanistic relationships among genes and their impacts on biological pathways is essential for elucidating disease mechanisms and advancing precision medicine. Despite the availability of extensive molecular interaction and pathway data in public databases, integrating heterogeneous knowledge sources and enabling interpretable multi-step reasoning across biological networks remain challenging. We present GIP-RAG (Gene Interaction Prediction through Retrieval-Augmented Generation), a computational framework that combines biomedical knowledge graphs with large language models (LLMs) to infer and interpret gene interactions. The framework constructs a unified gene interaction knowledge graph by integrating curated data from KEGG, WikiPathways, SIGNOR, Pathway Commons, and PubChem. Given user-specified genes, a query-driven module retrieves relevant subgraphs, which are incorporated into structured prompts to guide LLM-based stepwise reasoning. This enables identification of direct and indirect regulatory relationships and generation of mechanistic explanations supported by biological evidence. Beyond pairwise interactions, GIP-RAG includes a pathway-level functional impact module that simulates propagation of gene perturbations through signaling networks and evaluates potential pathway state changes. Evaluation across diverse biological scenarios demonstrates that the framework generates consistent, interpretable, and evidence-supported insights into gene regulatory mechanisms. Overall, GIP-RAG provides a general and interpretable approach for integrating knowledge graphs with retrieval-augmented LLMs to support mechanistic reasoning in complex molecular systems.
Authors: Artem Maryanskyy
Abstract: Multi-agent LLM pipelines produce contradictory evidence on whether team diversity improves output quality: heterogeneous Mixture-of-Agents teams outperform single models, yet homogeneous Self-MoA teams consistently win under synthesis-based aggregation. We propose a resolution by identifying the selection bottleneck -- a crossover threshold in aggregation quality that determines whether diversity helps or hurts. Under this model, we obtain a closed-form crossover threshold $s^*$ (Proposition 1) that separates the regimes where diversity helps and hurts. In a targeted experiment spanning 42 tasks across 7 categories ($N=210$), a diverse team with judge-based selection achieves a win rate of 0.810 against a single-model baseline, while a homogeneous team scores 0.512 -- near chance (Glass's $\Delta = 2.07$). Judge-based selection outperforms MoA-style synthesis by $\Delta_{\mathrm{WR}} = +0.631$ -- the synthesis approach is preferred over the baseline in zero of 42 tasks by the judge panel. A decoupled evaluation with independent judges confirms all directional findings (Spearman $\rho = 0.90$). Exploratory evidence suggests that including a weaker model improves performance while reducing cost ($p < 10^{-4}$, not pre-registered). Our results suggest that selector quality may be a more impactful design lever than generator diversity in single-round generate-then-select pipelines.
Authors: Liu hung ming
Abstract: Video world models trained with Joint Embedding Predictive Architectures (JEPA) acquire rich spatiotemporal representations by predicting masked regions in latent space rather than reconstructing pixels. This removes the visual verification pathway of generative models, creating a structural interpretability gap: the encoder has learned physical structure inaccessible in any inspectable form. Existing probing methods either operate in continuous space without a structured intermediate layer, or attach generative components whose parameters confound attribution of behavior to the encoder. We propose the AI Mother Tongue (AIM) framework as a passive quantization probe: a lightweight, vocabulary-free probe that converts V-JEPA 2 continuous latent vectors into discrete symbol sequences without task-specific supervision or modifying the encoder. Because the encoder is kept completely frozen, any symbolic structure in the AIM codebook is attributable entirely to V-JEPA 2 pre-trained representations -- not to the probe. We evaluate through category-contrast experiments on Kinetics-mini along three physical dimensions: grasp angle, object geometry, and motion temporal structure. AIM symbol distributions differ significantly across all three experiments (chi^2 p < 10^{-4}; MI 0.036--0.117 bits, NMI 1.2--3.9% of the 3-bit maximum; JSD up to 0.342; codebook active ratio 62.5%). The experiments reveal that V-JEPA 2 latent space is markedly compact: diverse action categories share a common representational core, with semantic differences encoded as graded distributional variations rather than categorical boundaries. These results establish Stage 1 of a four-stage roadmap toward an action-conditioned symbolic world model, demonstrating that structured symbolic manifolds are discoverable properties of frozen JEPA latent spaces.
Authors: Oleksii Bychkov
Abstract: Modern autonomous multi-agent systems combine heterogeneous learning mechanisms operating at different timescales. An open question remains: can one formally guarantee that coupled dynamics of such mechanisms stay within the admissible operational regime? This paper studies a tri-hierarchical swarm learning system where three mechanisms act simultaneously: (1) local Hebbian online learning at individual agent level (fast timescale, 10-100 ms); (2) multi-agent reinforcement learning (MARL) for tactical group coordination (medium timescale, 1-10 s); (3) meta-learning (MAML) for strategic adaptation (slow timescale, 10-100 s). Four results are established. The Bounded Total Error Theorem shows that under contractual constraints on learning rates, Lipschitz continuity of inter-level mappings, and weight stabilization, total suboptimality admits a component-wise upper bound uniform in time. The Bounded Representation Drift Theorem gives a worst-case estimate of how Hebbian updates affect coordination-level embeddings during one MARL cycle. The Meta-Level Compatibility Theorem provides sufficient conditions under which strategic adaptation preserves lower-level invariants. The Non-Accumulation Theorem proves that error does not grow unboundedly over time.
Authors: Yu-Ning Qiu, Lin-Feng Zou, Jiong-Da Wang, Xue-Rong Yuan, Wang-Zhou Dai
Abstract: In complex code-generation tasks, conversation-based LLM code repair exhibits limited ability to recover from first-pass programming errors, as such code revisions are usually driven by LLMs' "plausible reasoning" rather than a formal, algorithmic debugging procedure. However, a formal foundation for such debugging exists in Udi Shapiro's theory of algorithmic program debugging (APD), which frames program repair as an explicit, stepwise procedural refinement process. In this paper, we propose a neuro-symbolic procedural refinement approach, Abduction-Based Procedural Refinement (ABPR), which couples an LLM with a meta-interpreter that materialises program execution into compact, declarative tree-structured traces, following the principles of APD. We evaluate ABPR on ARC-AGI-2, a benchmark requiring strong abstraction and debugging capabilities, and adopt Prolog as the target language due to its declarative semantics, which are well-suited to algorithmic program debugging. Our experiments show that ABPR paired with Gemini-3-Flash achieves a Pass@2 score of 56.67\% even in a language in which contemporary LLMs typically underperform. These results point towards a more auditable paradigm for program repair by integrating LLMs with classical formal methods.
Authors: Yao Tian, Zhoujin Tian, Xi Zhao, Ruiyuan Zhang, Xiaofang Zhou
Abstract: In multi-vector retrieval, both queries and data are represented as sets of high-dimensional vectors, enabling finer-grained semantic matching and improving retrieval quality over single-vector approaches. However, its practical adoption is held back by the lack of effective indexing algorithms. Existing work, attempting to reuse standard single-vector indexes, often fails to preserve multi-vector semantics or remains slow. In this work, we present GEM, a native indexing framework for multi-vector representations. The core idea is to construct a proximity graph directly over vector sets, preserving their fine-grained semantics while enabling efficient navigation. First, GEM designs a set-level clustering scheme. It associates each vector set with only its most informative clusters, effectively reducing redundancy without hurting semantic coverage. Then, it builds local proximity graphs within clusters and bridges them into a globally navigable structure. To handle the non-metric nature of multi-vector similarity, GEM decouples the graph construction metric from the final relevance score and injects semantic shortcuts to guide efficient navigation toward relevant regions. At query time, GEM launches beam search from multiple entry points and prunes paths early using cluster cues. To further enhance efficiency, a quantized distance estimation technique is used for both indexing and search. Across in-domain, out-of-domain, and multi-modal benchmarks, GEM achieves up to 16x speedup over state-of-the-art methods while matching or improving accuracy.
Authors: Wooseok Sim, Hogun Park
Abstract: Federated Recommender Systems (FRS) preserve privacy by training decentralized models on client-specific user-item subgraphs without sharing raw data. However, FRS faces a unique challenge: subgraph structural imbalance, where drastic variations in subgraph scale (user/item counts) and connectivity (item degree) misalign client representations, making it challenging to train a robust model that respects each client's unique structural characteristics. To address this, we propose a Low-pass Personalized Subgraph Federated recommender system (LPSFed). LPSFed leverages graph Fourier transforms and low-pass spectral filtering to extract low-frequency structural signals that remain stable across subgraphs of varying size and degree, allowing robust personalized parameter updates guided by similarity to a neutral structural anchor. Additionally, we leverage a localized popularity bias-aware margin that captures item-degree imbalance within each subgraph and incorporates it into a personalized bias correction term to mitigate recommendation bias. Supported by theoretical analysis and validated on five real-world datasets, LPSFed achieves superior recommendation accuracy and enhances model robustness.
Authors: Zijian Lu, Yiping Zuo, Yupeng Nie, Xin He, Weibei Fan, Chen Dai
Abstract: Despite rapid progress in multimodal GUI agents, reusable skill acquisition remains difficult because on-demand generated skills often leave action semantics, state assumptions, and success criteria implicit. This makes them brittle to execution errors, hard to verify, and difficult to repair. We present ContractSkill, a framework that converts a draft skill into a contracted executable artifact with explicit preconditions, step specifications, postconditions, recovery rules, and termination checks. This representation enables deterministic verification, step-level fault localization, and minimal patch-based repair, turning skill refinement into localized editing rather than full regeneration. Experiments on VisualWebArena and MiniWoB with GLM-4.6V and Qwen3.5-Plus show that ContractSkill improves self-generated skills from 9.4% and 10.9% to 28.1% and 37.5% on VisualWebArena, and from 66.5% and 60.5% to 77.5% and 81.0% on MiniWoB. Repaired artifacts also transfer across models, improving the target model's self-generated-skill baseline by up to 47.8 points and 12.8 points on the two benchmarks, respectively. These results suggest that agent skills are better treated as explicit procedural artifacts that can be verified, repaired, and shared across models.
Authors: Yizhe Zhao, Yongjian Fu, Zihao Feng, Hao Pan, Yongheng Deng, Yaoxue Zhang, Ju Ren
Abstract: Mobile advertising dominates app monetization but introduces risks ranging from intrusive user experience to malware delivery. Existing detection methods rely either on static analysis, which misses runtime behaviors, or on heuristic UI exploration, which struggles with sparse and obfuscated ads. In this paper, we present MANA, the first agentic multimodal reasoning framework for mobile ad detection. MANA integrates static, visual, temporal, and experiential signals into a reasoning-guided navigation strategy that determines not only how to traverse interfaces but also where to focus, enabling efficient and robust exploration. We implement and evaluate MANA on commercial smartphones over 200 apps, achieving state-of-the-art accuracy and efficiency. Compared to baselines, it improves detection accuracy by 30.5%-56.3% and reduces exploration steps by 29.7%-63.3%. Case studies further demonstrate its ability to uncover obfuscated and malicious ads, underscoring its practicality for mobile ad auditing and its potential for broader runtime UI analysis (e.g., permission abuse). Code and dataset are available at https://github.com/MANA-2026/MANA.
Authors: Yuxuan He, Chaiming Huang, Yifan Wu, Hongjun Wang, Chenkui Shen, Jifan Zhang, Long Li
Abstract: A short video succeeds not simply because of what it shows, but because of how it schedules attention -- yet current multimodal models lack the structural grammar to parse or produce this organization. Existing models can describe scenes, answer event-centric questions, and read on-screen text, but they are far less reliable at identifying timeline-grounded units such as hooks, cut rationales, shot-induced tension, and platform-facing packaging cues. We propose SV6D (Structured Video in Six Dimensions), inspired by professional storyboard practice in film and television production, a representation framework that decomposes internet-native video into six complementary structural dimensions -- subject, aesthetics, camera language, editing, narrative, and dissemination -- with each label tied to physically observable evidence on the timeline. We formalize a unified optimization objective over SV6D that combines Hungarian-matched temporal alignment, dimension-wise semantic label distance, and quality regularization. Building on this framework, we present Leum-VL-8B, an 8B video-language model that realizes the SV6D objective through an expert-driven post-training pipeline, further refined through verifiable reinforcement learning on perception-oriented tasks. Leum-VL-8B achieves 70.8 on VideoMME (w/o subtitles), 70.0 on MVBench, and 61.6 on MotionBench, while remaining competitive on general multimodal evaluations such as MMBench-EN. We also construct FeedBench, a benchmark for structure-sensitive short-video understanding. Our results indicate that the missing layer in video AI is not pixel generation but structural representation: grounded on the timeline, linked to visible evidence, and directly consumable by downstream workflows such as editing, retrieval, recommendation, and generation control, including text-heavy internet video formats with overlays and image-text layouts.
Authors: Vicen\c{c} Torra, Maria Bras-Amor\'os
Abstract: Memory poisoning attacks for Agentic AI and multi-agent systems (MAS) have recently caught attention. It is partially due to the fact that Large Language Models (LLMs) facilitate the construction and deployment of agents. Different memory systems are being used nowadays in this context, including semantic, episodic, and short-term memory. This distinction between the different types of memory systems focuses mostly on their duration but also on their origin and their localization. It ranges from the short-term memory originated at the user's end localized in the different agents to the long-term consolidated memory localized in well established knowledge databases. In this paper, we first present the main types of memory systems, we then discuss the feasibility of memory poisoning attacks in these different types of memory systems, and we propose mitigation strategies. We review the already existing security solutions to mitigate some of the alleged attacks, and we discuss adapted solutions based on cryptography. We propose to implement local inference based on private knowledge retrieval as an example of mitigation strategy for memory poisoning for semantic memory. We also emphasize actual risks in relation to interactions between agents, which can cause memory poisoning. These latter risks are not so much studied in the literature and are difficult to formalize and solve. Thus, we contribute to the construction of agents that are secure by design.
Authors: Ali Darijani, J\"urgen Beyerer, Zahra Sadat Hajseyed Nasrollah, Luisa Hoffmann, Michael Heizmann
Abstract: Probability theory has become the predominant framework for quantifying uncertainty across scientific and engineering disciplines, with a particular focus on measurement and control systems. However, the widespread reliance on simple Gaussian assumptions--particularly in control theory, manufacturing, and measurement systems--can result in incomplete representations and multistage lossy approximations of complex phenomena, including inaccurate propagation of uncertainty through multi stage processes. This work proposes a comprehensive yet computationally tractable framework for representing and propagating quantitative attributes arising in measurement systems using Probability Density Functions (PDFs). Recognizing the constraints imposed by finite memory in software systems, we advocate for the use of Gaussian Mixture Models (GMMs), a principled extension of the familiar Gaussian framework, as they are universal approximators of PDFs whose complexity can be tuned to trade off approximation accuracy against memory and computation. From both mathematical and computational perspectives, GMMs enable high performance and, in many cases, closed form solutions of essential operations in control and measurement. The paper presents practical applications within manufacturing and measurement contexts especially circular factory, demonstrating how the GMMs framework supports accurate representation and propagation of measurement uncertainty and offers improved accuracy--compared to the traditional Gaussian framework--while keeping the computations tractable.
Authors: Xuanwang Zhang, Yuteng Han, Jinnan Qi, Mulong Xie, Zhen Wu, Xinyu Dai
Abstract: Despite significant advances in autonomous web navigation, current methods remain far from human-level performance in complex web environments. We argue that this limitation stems from Topological Blindness, where agents are forced to explore via trial-and-error without access to the global topological structure of the environment. To overcome this limitation, we introduce WebNavigator, which reframes web navigation from probabilistic exploration into deterministic retrieval and pathfinding. WebNavigator constructs Interaction Graphs via zero-token cost heuristic exploration offline and implements a Retrieve-Reason-Teleport workflow for global navigation online. WebNavigator achieves state-of-the-art performance on WebArena and OnlineMind2Web. On WebArena multi-site tasks, WebNavigator achieves a 72.9\% success rate, more than doubling the performance of enterprise-level agents. This work reveals that Topological Blindness, rather than model reasoning capabilities alone, is an underestimated bottleneck in autonomous web navigation.
Authors: Christopher J. Agostino, Nayan D'Souza
Abstract: Industry practitioners and academic researchers regularly use multi-agent systems to accelerate their work, yet the frameworks through which these systems operate do not provide a simple, unified mechanism for scalably managing the critical aspects of the agent harness, impacting both the quality of individual human-agent interactions and the capacity for practitioners to coordinate toward common goals through shared agent infrastructure. Agent frameworks have enabled increasingly sophisticated multi-agent systems, but the behavioral specifications that define what these agents can do remain fragmented across prose instruction files, framework-internal configuration, and mechanisms like MCP servers that operate separately from individual agent definitions, making these specifications difficult to share, version, or collaboratively maintain across teams and projects. Applying the ALARA principle from radiation safety (exposures kept as low as reasonably achievable) to agent context, we introduce a declarative context-agent-tool (CAT) data layer expressed through interrelated files that scope each agent's tool access and context to the minimum its role requires, and \texttt{npcsh}, a command-line shell for executing it. Because the system parses and enforces these files structurally, modifying an agent's tool list produces a guaranteed behavioral change rather than a suggestion the model may or may not follow. We evaluate 22 locally-hosted models from 0.6B to 35B parameters across 115 practical tasks spanning file operations, web search, multi-step scripting, tool chaining, and multi-agent delegation, characterizing which model families succeed at which task categories and where they break down across $\sim$2500 total executions.
Authors: Christopher J. Agostino, Quan Le Thien, Nayan D'Souza, Louis van der Elst
Abstract: Understanding the fundamental mechanisms governing the production of meaning in the processing of natural language is critical for designing safe, thoughtful, engaging, and empowering human-agent interactions. Experiments in cognitive science and social psychology have demonstrated that human semantic processing exhibits contextuality more consistent with quantum logical mechanisms than classical Boolean theories, and recent works have found similar results in large language models -- in particular, clear violations of the Bell inequality in experiments of contextuality during interpretation of ambiguous expressions. We explore the CHSH $|S|$ parameter -- the metric associated with the inequality -- across the inference parameter space of models spanning four orders of magnitude in scale, cross-referencing it with MMLU, hallucination rate, and nonsense detection benchmarks. We find that the interquartile range of the $|S|$ distribution -- the statistic that most sharply differentiates models from one another -- is completely orthogonal to all external benchmarks, while violation rate shows weak anticorrelation with all three benchmarks that does not reach significance. We investigate how $|S|$ varies with sampling parameters and word order, and discuss the information-theoretic constraints that genuine contextuality imposes on prompt injection defenses and its human analogue, whereby careful construction and maintenance of social contextuality can be carried out at scale -- manufacturing not consent but contextuality itself, a subtler and more fundamental form of manipulation that shapes the space of possible interpretations before any particular one is reached.
Authors: Men Niu, Xinxin Fan, Quanliang Jing, Shaoye Luo, Yunfeng Lu
Abstract: Cooperative multi-agent reinforcement learning (c-MARL) has been widely deployed in real-world applications, such as social robots, embodied intelligence, UAV swarms, etc. Nevertheless, many adversarial attacks still exist to threaten various c-MARL systems. At present, the studies mainly focus on single-adversary perturbation attacks and white-box adversarial attacks that manipulate agents' internal observations or actions. To address these limitations, we in this paper attempt to study collusive adversarial attacks through strategically organizing a set of malicious agents into three collusive attack modes: Collective Malicious Agents, Disguised Malicious Agents, and Spied Malicious Agents. Three novelties are involved: i) three collusive adversarial attacks are creatively proposed for the first time, and a unified framework CAMA for policy-level collusive attacks is designed; ii) the attack effectiveness is theoretically analyzed from the perspectives of disruptiveness, stealthiness, and attack cost; and iii) the three collusive adversarial attacks are technically realized through agent's observation information fusion, attack-trigger control. Finally, multi-facet experiments on four SMAC II maps are performed, and experimental results showcase the three collusive attacks have an additive adversarial synergy, strengthening attack outcome while maintaining high stealthiness and stability over long horizons. Our work fills the gap for collusive adversarial learning in c-MARL.
Authors: Y. Sungtaek Ju
Abstract: Probabilistic circuit (PC) structure learning is hampered by greedy algorithms that make irreversible, locally optimal decisions. We propose SymCircuit, which replaces greedy search with a learned generative policy trained via entropy-regularized reinforcement learning. Instantiating the RL-as-inference framework in the PC domain, we show the optimal policy is a tempered Bayesian posterior, recovering the exact posterior when the regularization temperature is set inversely proportional to the dataset size. The policy is implemented as SymFormer, a grammar-constrained autoregressive Transformer with tree-relative self-attention that guarantees valid circuits at every generation step. We introduce option-level REINFORCE, restricting gradient updates to structural decisions rather than all tokens, yielding an SNR (signal to noise ratio) improvement and >10 times sample efficiency gain on the NLTCS dataset. A three-layer uncertainty decomposition (structural via model averaging, parametric via the delta method, leaf via conjugate Dirichlet-Categorical propagation) is grounded in the multilinear polynomial structure of PC outputs. On NLTCS, SymCircuit closes 93% of the gap to LearnSPN; preliminary results on Plants (69 variables) suggest scalability.
Authors: Yichun Xu, Navjot K. Khaira, Tejinder Singh
Abstract: The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint scales linearly with context length, imposing critical bottlenecks on GPU memory capacity, memory bandwidth, and inference throughput as production LLMs push context windows from thousands to millions of tokens. Efficient KV cache management has thus become a first-order challenge for scalable LLM deployment. This paper provides a systematic review of recent KV cache optimization techniques, organizing them into five principal directions: cache eviction, cache compression, hybrid memory solutions, novel attention mechanisms, and combination strategies. For each category we analyze the underlying mechanisms, deployment trade-offs, and empirical performance across memory reduction, throughput, and model accuracy metrics. We further map techniques to seven practical deployment scenarios, including long-context single requests, high-throughput datacenter serving, edge devices, multi-turn conversations, and accuracy-critical reasoning, providing actionable guidance for practitioners selecting among competing approaches. Our analysis reveals that no single technique dominates across all settings; instead, the optimal strategy depends on context length, hardware constraints, and workload characteristics, pointing toward adaptive, multi-stage optimization pipelines as a promising direction for future research.
Authors: Marcus Armstrong, Navid Ayoobi, Arjun Mukherjee
Abstract: We investigate whether independently trained language models converge to geometrically compatible latent representations, and whether this compatibility can be exploited to correct model behavior at inference time without any weight updates. We learn a linear projection matrix that maps activation vectors from a large teacher model into the coordinate system of a smaller student model, then intervene on the student's residual stream during generation by substituting its internal state with the translated teacher representation. Across a fully crossed experimental matrix of 20 heterogeneous teacher-student pairings spanning mixture-of-experts, dense, code-specialized, and synthetically trained architectures, the Ridge projection consistently achieves R^2 = 0.50 on verbal reasoning and R^2 = 0.40 on mathematical reasoning, collapsing to R^2 = -0.22 under permutation control and R^2 = 0.01 under L_1 regularization. Behavioral correction rates range from 14.0% to 50.0% on TruthfulQA (mean 25.2%) and from 8.5% to 43.3% on GSM8K arithmetic reasoning (mean 25.5%), demonstrating that the method generalizes across fundamentally different reasoning domains. We report a near-zero correlation between geometric alignment quality and behavioral correction rate (r = -0.07), revealing a dissociation between representation space fidelity and output space impact. Intervention strength is architecture-specific: student models exhibit characteristic sensitivity profiles that invert across domains, with the most steerable verbal student becoming the least steerable mathematical student. Finally, a double dissociation experiment conducted across all 20 model pairings confirms without exception that projection matrices collapse catastrophically when transferred across reasoning domains (mean R^2 = -3.83 in both transfer directions), establishing domain-specific subspace geometry as a universal property of LMs.
Authors: Ata Poyraz Turna, Asrin Efe Yorulmaz, Tamer Ba\c{s}ar
Abstract: Classical Bayesian persuasion studies how a sender influences receivers through carefully designed signaling policies within a single strategic interaction. In many real-world environments, such interactions are repeated across multiple games, creating opportunities to exploit structural similarity across tasks. In this work, we introduce Meta-Persuasion algorithms, establishing the first line of theoretical results for both full-feedback and bandit-feedback settings in the Online Bayesian Persuasion (OBP) and Markov Persuasion Process (MPP) frameworks. We show that our proposed meta-persuasion algorithms achieve provably sharper regret rates under natural notions of task similarity, improving upon the best-known convergence rates for both OBP and MPP. At the same time, they recover the standard single-game guarantees when the sequence of games is picked arbitrarily. Finally, we complement our theoretical analysis with numerical experiments that highlight our regret improvements and the benefits of meta-learning in repeated persuasion environments.
Authors: Yuanhong Zheng, Ruichuan An, Xiaopeng Lin, Yuxing Liu, Sihan Yang, Huanyu Zhang, Haodong Li, Qintong Zhang, Renrui Zhang, Guopeng Li, Yifan Zhang, Yuheng Li, Wentao Zhang
Abstract: Human cognition of new concepts is inherently a streaming process: we continuously recognize new objects or identities and update our memories over time. However, current multimodal personalization methods are largely limited to static images or offline videos. This disconnects continuous visual input from instant real-world feedback, limiting their ability to provide the real-time, interactive personalized responses essential for future AI assistants. To bridge this gap, we first propose and formally define the novel task of Personalized Streaming Video Understanding (PSVU). To facilitate research in this new direction, we introduce PEARL-Bench, the first comprehensive benchmark designed specifically to evaluate this challenging setting. It evaluates a model's ability to respond to personalized concepts at exact timestamps under two modes: (1) Frame-level, focusing on a specific person or object in discrete frames, and (2) a novel Video-level, focusing on personalized actions unfolding across continuous frames. PEARL-Bench comprises 132 unique videos and 2,173 fine-grained annotations with precise timestamps. Concept diversity and annotation quality are strictly ensured through a combined pipeline of automated generation and human verification. To tackle this challenging new setting, we further propose PEARL, a plug-and-play, training-free strategy that serves as a strong baseline. Extensive evaluations across 8 offline and online models demonstrate that PEARL achieves state-of-the-art performance. Notably, it brings consistent PSVU improvements when applied to 3 distinct architectures, proving to be a highly effective and robust strategy. We hope this work advances vision-language model (VLM) personalization and inspires further research into streaming personalized AI assistants. Code is available at https://github.com/Yuanhong-Zheng/PEARL.
Authors: Weili Cao, Xunjian Yin, Bhuwan Dhingra, Shuyan Zhou
Abstract: Large Language Models (LLMs) have demonstrated remarkable progress in scaling to access massive contexts. However, the access is via the latent and uninterpretable attention mechanisms, and LLMs fail to effective process long context, exhibiting significant performance degradation as context length increases. In this work, we study whether long-context processing can be externalized from latent attention into explicit, executable interactions, by allowing coding agents to organize text in file systems and manipulate it using its native tools. We evaluate off-the-shelf frontier coding agents as the general interface for tasks that require processing long contexts, including long-context reasoning, retrieval-augmented generation, and open-domain question answering with large-scale corpus contains up to three trillion tokens. Across multiple benchmarks, these agents outperform published state-of-the-art by 17.3% on average. We attribute this efficacy to two key factors: native tool proficiency, which enables agents to leverage executable code and terminal commands rather than passive semantic queries, and file system familiarity, which allows them to navigate massive text corpora as directory structures. These findings suggest that delegating long-context processing to coding agents offers an effective alternative to semantic search or context window scaling, opening new directions for long-context processing in LLMs.
Authors: Yen-Ting Piao, Jay Chiehen Liao, Wei-Tang Chien, Toshiki Ogimoto, Shang-Tse Chen, Yun-Nung Chen, Chun-Yi Lee, Shao-Yuan Lo
Abstract: While Large Audio-Language Models (LALMs) have been shown to exhibit degraded instruction-following capabilities, their ability to infer task patterns from in-context examples under audio conditioning remains unstudied. To address this gap, we present ALICE, a three-stage framework that progressively reduces textual guidance to systematically evaluate LALMs' in-context learning ability under audio conditioning. Evaluating six LALMs across four audio understanding tasks under two output constraint categories, we uncover a consistent asymmetry across all stages and LALMs: in-context demonstrations reliably improve format compliance but fail to improve, and often degrade, the core task performance. This suggests that LALMs can glean surface-level formatting patterns from demonstrations but may struggle to leverage cross-modal semantic grounding to reliably infer task objectives from audio-conditioned examples, highlighting potential limitations in current cross-modal integration.
Authors: Truong Quynh Hoa, Hoang Dinh Cuong, Truong Xuan Khanh
Abstract: We propose Melaguard, a multimodal ML framework (Transformer-lite, 1.2M parameters, 4-head self-attention) for detecting neurovascular instability (NVI) from wearable-compatible physiological signals prior to structural stroke pathology. The model fuses heart rate variability (HRV), peripheral perfusion index, SpO2, and bilateral phase coherence into a composite NVI Score, designed for edge inference (WCET <=4 ms on Cortex-M4). NVI - the pre-structural dysregulation of cerebrovascular autoregulation preceding overt stroke - remains undetectable by existing single-modality wearables. With 12.2 million incident strokes annually, continuous multimodal physiological monitoring offers a practical path to community-scale screening. Three-stage independent validation: (1) synthetic benchmark (n=10,000), AUC=0.88 [0.83-0.92]; (2) clinical cohort PhysioNet CVES (n=172; 84 stroke, 88 control) - Transformer-lite achieves AUC=0.755 [0.630-0.778], outperforming LSTM (0.643), Random Forest (0.665), SVM (0.472); HRV-SDNN discriminates stroke (p=0.011); (3) PPG pipeline PhysioNet BIDMC (n=53) -- pulse rate r=0.748 and HRV surrogate r=0.690 vs. ECG ground truth. Cross-modality validation on PPG-BP (n=219) confirms PPG morphology classifies cerebrovascular disease at AUC=0.923 [0.869-0.968]. Multimodal fusion consistently outperforms single-modality baselines. Code: https://github.com/ClevixLab/Melaguard
Authors: Cailin Winston, Claris Winston, Ren\'e Just
Abstract: Tool-augmented Large Language Models (TaLLMs) extend LLMs with the ability to invoke external tools, enabling them to interact with real-world environments. However, a major limitation in deploying TaLLMs in sensitive applications such as customer service and business process automation is a lack of reliable compliance with domain-specific operational policies regarding tool-use and agent behavior. Current approaches merely steer LLMs to adhere to policies by including policy descriptions in the LLM context, but these provide no guarantees that policy violations will be prevented. In this paper, we introduce an SMT solver-aided framework to enforce tool-use policy compliance in TaLLM agents. Specifically, we use an LLM-assisted, human-guided approach to translate natural-language-specified tool-use policies into formal logic (SMT-LIB-2.0) constraints over agent-observable state and tool arguments. At runtime, planned tool calls are intercepted and checked against the constraints using the Z3 solver as a pre-condition to the tool call. Tool invocations that violate the policy are blocked. We evaluated on the TauBench benchmark and demonstrate that solver-aided policy checking reduces policy violations while maintaining overall task accuracy. These results suggest that integrating formal reasoning into TaLLM execution can improve tool-call policy compliance and overall reliability.
Authors: Rounak Saha, Gurusha Juneja, Dayita Chaudhuri, Naveeja Sajeevan, Nihar B Shah, Danish Pruthi
Abstract: A number of scientific conferences and journals have recently enacted policies that prohibit LLM usage by peer reviewers, except for polishing, paraphrasing, and grammar correction of otherwise human-written reviews. But, are these policies enforceable? To answer this question, we assemble a dataset of peer reviews simulating multiple levels of human-AI collaboration, and evaluate five state-of-the-art detectors, including two commercial systems. Our analysis shows that all detectors misclassify a non-trivial fraction of LLM-polished reviews as AI-generated, thereby risking false accusations of academic misconduct. We further investigate whether peer-review-specific signals, including access to the paper manuscript and the constrained domain of scientific writing, can be leveraged to improve detection. While incorporating such signals yields measurable gains in some settings, we identify limitations in each approach and find that none meets the accuracy standards required for identifying AI use in peer reviews. Importantly, our results suggest that recent public estimates of AI use in peer reviews through the use of AI-text detectors should be interpreted with caution, as current detectors misclassify mixed reviews (collaborative human-AI outputs) as fully AI generated, potentially overstating the extent of policy violations.
Authors: Yalemzerf Getnet, Abiy Tasissa, Waltenegus Dargie
Abstract: Assigning relevance scores to the input features of a machine learning model enables to measure the contributions of the features in achieving a correct outcome. It is regarded as one of the approaches towards developing explainable models. For biomedical assignments, this is very useful for medical experts to comprehend machine-based decisions. In the analysis of electro cardiogram (ECG) signals, in particular, understanding which of the electrocardiogram samples or features contributed most for a given decision amounts to understanding the underlying cardiac phases or conditions the machine tries to explain. For the computation of relevance scores, determining the proper baseline is important. Moreover, the scores should have a distribution which is at once intuitive to interpret and easy to associate with the underline cardiac reality. The purpose of this work is to achieve these goals. Specifically, we propose a shift-invariant baseline which has a physical significance in the analysis as well as interpretation of electrocardiogram measurements. Moreover, we aggregate significance scores in such a way that they can be mapped to cardiac phases. We demonstrate our approach by inferring physical exertion from cardiac exertion using a residual network. We show that the ECG samples which achieved the highest relevance scores (and, therefore, which contributed most to the accurate recognition of the physical exertion) are those associated with the P and T waves. Index Terms Attribution, baseline, cardiovascular diseases, electrocardiogram, activity recognition, machine learning
Authors: \c{S}uayp Talha Kocabay, Talha R\"uzgar Akku\c{s}
Abstract: Masked Diffusion Language Models (MDLMs) have emerged as a compelling non-autoregressive alternative to standard large language models; however, their application to morphologically rich languages remains limited. In this paper, we introduce $\textit{Diffutron}$, a masked diffusion language model specifically designed for Turkish. Our approach leverages a resource-efficient training pipeline, starting with LoRA-based continual pre-training of a multilingual encoder on a large-scale corpus. To enable generative capabilities, we employ a progressive instruction-tuning strategy, sequentially adapting the model on general and task-specific instruction sets. Experimental results across comprehensive benchmarks demonstrate that, despite its compact size, our model achieves competitive performance compared to existing multi-billion-parameter baselines. These findings validate the effectiveness of masked diffusion modeling combined with multi-stage tuning for non-autoregressive text generation in Turkish.
Authors: Robert Godwin-Jones
Abstract: Learning another language can be a highly emotional process, typically characterized by numerous frustrations and triumphs, big and small. For most learners, language learning does not follow a linear, predictable path, its zigzag course shaped by motivational (or demotivating) variables such as personal characteristics, teacher/peer relationships, learning materials, and dreams of a future L2 (second language) self. While some aspects of language learning (reading, grammar) are relatively mechanical, others can be stressful and unpredictable, especially conversing in the target language. That experience necessitates not only knowledge of structure and lexis, but also the ability to use the language in ways that are appropriate to the social and cultural context. A new opportunity to practice conversational abilities has arrived through the availability of AI chatbots, with both advantages (responsive, non-judgmental) and drawbacks (emotionally void, culturally biased). This column explores aspects of emotion as they arise in technology use and in particular how automatic emotion recognition and simulated human responsiveness in AI systems interface with language learning and the development of pragmatic and interactional competence. Emotion AI, the algorithmically driven interpretation of users' affective signals, has been seen as enabling greater personalized learning, adapting to perceived learner cognitive and emotional states. Others warn of emotional manipulation and inappropriate and ineffective user profiling
Authors: Bernardo Magri, Benjamin Marsh, Paul Gebheim
Abstract: Modern cloud inference creates a two sided privacy problem where users reveal sensitive inputs to providers, while providers must execute proprietary model weights inside potentially leaky execution environments. Fully homomorphic encryption (FHE) offers cryptographic guarantees but remains prohibitively expensive for modern architectures. We argue that progress requires co-design where specializing FHE schemes/compilers for the static structure of inference circuits, while simultaneously constraining inference architectures to reduce dominant homomorphic cost drivers. We outline a meet in the middle agenda and concrete optimization targets on both axes.
Authors: Dani Roytburg, Shreya Sridhar, Daphne Ippolito
Abstract: Language models are increasingly being trained to "reason" before answering users' queries, outputting hundreds or even thousands of tokens worth of deliberation before their final answer. While the main intention of reasoning is to improve models' ability to arrive at a correct answer, we argue that these models should be assessed for the legibility of their reasoning traces in addition to the correctness of their final answers. In this paper, we evaluate 90k traces from 12 Reasoning Language Models (RLMs) for the quality of their reasoning traces. We introduce the concept of transfer utility, which assesses how useful an RLM's reasoning traces are for guiding a weaker, non-reasoning model toward arriving at the correct answer. We find that the reasoning traces of the highest-performing models rank among the lowest for legibility. Furthermore, we uncover tensions between efficiency-based measurements of legibility (such as trace length) and transfer utility. These tensions establish a legibility Pareto frontier, and we demonstrate that an RLM's ability to output highly legible traces can be a task- and audience-dependent goal. Crucially, we find that reward models used to train RLMs do not intrinsically reward legibility. Together, these metrics and the findings they surface chart a path towards scaffolding reasoning traces for a multi-agent future.
Authors: Anton Korikov, Scott Sanner
Abstract: LLM-reranking is limited by the top-k documents retrieved by vector similarity, which neither enables contextual query-document token interactions nor captures multimodal relevance distributions. While LLM query reformulation attempts to improve recall by generating improved or additional queries, it is still followed by vector similarity retrieval. We thus propose to address these top-k retrieval stage failures by introducing ReBOL, which 1) uses LLM query reformulations to initialize a multimodal Bayesian Optimization (BO) posterior over document relevance, and 2) iteratively acquires document batches for LLM query-document relevance scoring followed by posterior updates to optimize relevance. After exploring query reformulation and document batch diversification techniques, we evaluate ReBOL against LLM reranker baselines on five BEIR datasets and using two LLMs (Gemini-2.5-Flash-Lite, GPT-5.2). ReBOL consistently achieves higher recall and competitive rankings, for example compared to the best LLM reranker on the Robust04 dataset with 46.5% vs. 35.0% recall@100 and 63.6% vs. 61.2% NDCG@10. We also show that ReBOL can achieve comparable latency to LLM rerankers.
Authors: Mohammed Rakibul Hasan
Abstract: Large Language Models (LLMs) offer significant potential for delivering health information. However, their reliability in low-resource contexts remains uncertain. This study evaluates GPT-4, Gemini Pro, Llama~3, and Mistral-7B on health crisis-related enquiries concerning COVID-19, dengue, the Nipah virus, and Chikungunya in the low-resource context of Bangladesh. We constructed a question--answer dataset from authoritative sources and assessed model outputs through semantic similarity, expert-model cross-evaluation, and Natural Language Inference (NLI). Findings highlight both the strengths and limitations of LLMs in representing epidemiological history and health crisis knowledge, underscoring their promise and risks for informing policy in resource-constrained environments.
Authors: Ian Osband
Abstract: Distributed reinforcement learning trains on data from stale, buggy, or mismatched actors, producing actions with high surprisal (negative log-probability) under the learner's policy. The core difficulty is not surprising data per se, but \emph{negative learning from surprising data}. High-surprisal failures can dominate the update direction despite carrying little useful signal, while high-surprisal successes reveal opportunities the current policy would otherwise miss. The \textit{Delightful Policy Gradient} (DG) separates these cases by gating each update with delight, the product of advantage and surprisal, suppressing rare failures and amplifying rare successes without behavior probabilities. Under contaminated sampling, the cosine similarity between the standard policy gradient and the true gradient collapses, while DG's grows as the policy improves. No sign-blind reweighting, including exact importance sampling, can reproduce this effect. On MNIST with simulated staleness, DG without off-policy correction outperforms importance-weighted PG with exact behavior probabilities. On a transformer sequence task with staleness, actor bugs, reward corruption, and rare discovery, DG achieves roughly $10{\times}$ lower error. When all four frictions act simultaneously, its compute advantage is order-of-magnitude and grows with task complexity.
Authors: Ian Osband
Abstract: Policy gradient computes a backward pass for every sample, even though the backward pass is expensive and most samples carry little learning value. The Delightful Policy Gradient (DG) provides a forward-pass signal of learning value: \emph{delight}, the product of advantage and surprisal (negative log-probability). We introduce the \emph{Kondo gate}, which compares delight against a compute price and pays for a backward pass only when the sample is worth it, thereby tracing a quality--cost Pareto frontier. In bandits, zero-price gating preserves useful gradient signal while removing perpendicular noise, and delight is a more reliable screening signal than additive combinations of value and surprise. On MNIST and transformer token reversal, the Kondo gate skips most backward passes while retaining nearly all of DG's learning quality, with gains that grow as problems get harder and backward passes become more expensive. Because the gate tolerates approximate delight, a cheap forward pass can screen samples before expensive backpropagation, suggesting a speculative-decoding-for-training paradigm.
Authors: Tony Mason
Abstract: We find that models report highest confidence precisely when they are fabricating. Across four model families (OLMo-3, Llama-3.1, Qwen3, Mistral), self-reported confidence inversely correlates with accuracy, with AUC ranging from 0.28 to 0.36 where 0.5 is random guessing. We prove, under explicit formal assumptions, that this is not a capability gap but an observational one. Under text-only observation, where a supervisor sees only the model's output text, no monitoring system can reliably distinguish honest model outputs from plausible fabrications. We prove two results: first, that any policy conditioning only on the query cannot satisfy epistemic honesty across ambiguous world states; second, that no learning algorithm optimizing reward from a text-only supervisor can converge to honest behavior when the supervisor's observations are identical for both grounded and fabricated responses. Within our formal model, these impossibilities hold regardless of model scale or training procedure, including RLHF and instruction tuning. We construct a tensor interface that escapes the impossibility by exporting computational byproducts (per-token entropy and log-probability distributions) that are structurally coupled to correctness under standard training. Per-token entropy achieves pooled AUC 0.757, outperforming all text baselines by 2.5--3.9 percentage points at every budget level tested (10\%, 20\%, 30\%). The entropy signal generalizes across architectures (Spearman $\rho = 0.762$). The core contribution is a cost surface where the empirical mapping from verification budget (fraction of queries receiving expensive checks) to detection accuracy for each judge strategy is a practical lookup for system builders deciding how to allocate verification resources. The contribution is the map. The territory is the system you are building.
Authors: Ghislain Dorian Tchuente Mondjo
Abstract: Generative AI platforms (Google AI Studio, OpenAI, Anthropic) provide infrastructures (APIs, models) that are transforming the application development ecosystem. Recent literature distinguishes three generations of business models: a first generation modeled on cloud computing (pay-per-use), a second characterized by diversification (freemium, subscriptions), and a third, emerging generation exploring multi-layer market architectures with revenue-sharing mechanisms. Despite these advances, current models impose a financial barrier to entry for developers, limiting innovation and excluding actors from emerging economies. This paper proposes and analyzes an original model, "Revenue-Sharing as Infrastructure" (RSI), where the platform offers its AI infrastructure for free and takes a percentage of the revenues generated by developers applications. This model reverses the traditional upstream payment logic and mobilizes concepts of value co-creation, incentive mechanisms, and multi-layer market architecture to build an original theoretical framework. A detailed comparative analysis shows that the RSI model lowers entry barriers for developers, aligns stakeholder interests, and could stimulate innovation in the ecosystem. Beyond its economic relevance, RSI has a major societal dimension: by enabling developers without initial capital to participate in the digital economy, it could unlock the "latent jobs dividend" in low-income countries, where mobile penetration reaches 84%, and help address local challenges in health, agriculture, and services. Finally, we discuss the conditions of feasibility and strategic implications for platforms and developers.
Authors: Muhammad Khalid, Yilmaz Uygun
Abstract: Requirements engineering in Industry 4.0 faces critical challenges with heterogeneous, unstructured documentation spanning technical specifications, supplier lists, and compliance standards. While retrieval-augmented generation (RAG) shows promise for knowledge-intensive tasks, no prior work has evaluated RAG on authentic industrial RE workflows using comprehensive production-grade performance metrics. This paper presents a comprehensive empirical evaluation of RAG for industrial requirements engineering automation using authentic automotive manufacturing documentation comprising 669 requirements across four specification standards (MBN 9666-1, MBN 9666-2, BQF 9666-5, MBN 9666-9) spanning 2015-2023, plus 49 supplier qualifications with extensive supporting documentation. Through controlled comparisons with BERT-based and ungrounded LLM approaches, the framework achieves 98.2% extraction accuracy with complete traceability, outperforming baselines by 24.4% and 19.6%, respectively. Hybrid semantic-lexical retrieval achieves MRR of 0.847. Expert quality assessment averaged 4.32/5.0 across five dimensions. The evaluation demonstrates 83% reduction in manual analysis time and 47% cost savings through multi-provider LLM orchestration. Ablation studies quantify individual component contributions. Longitudinal analysis reveals a 55% reduction in requirement volume coupled with 1,800% increase in IT security focus, identifying 10 legacy suppliers (20.4%) requiring requalification, representing potential $2.3M in avoided contract penalties.
Authors: Tianyi Huang, Nathan Huang, Justin Tang, Wenqian Chen, Elsa Fan
Abstract: Large language models (LLMs) are now widely used as judges, yet their decisions can change under presentation choices that should be irrelevant. We study one such source of instability: candidate-order sensitivity in listwise factuality evaluation, where several answers can look similarly polished while differing sharply in hallucination risk. We introduce PCFJudge, an inference-time method that reruns the same factuality-first listwise prompt over multiple orderings of the same candidate set and aggregates the resulting scores, ranks, and uncertainty signals into a single consensus decision. On RewardBench 2 Factuality, PCFJudge improves over direct judging by up to 7 absolute points. Development ablations show that the dominant gain comes from permutation consensus itself rather than from heavier arbitration layers. These results suggest that a meaningful share of factuality-judging error arises from order instability, and that averaging over this nuisance variation is a simple and effective way to make LLM evaluation more reliable.
Authors: Dong Liu, Yanxuan Yu, Ben Lengerich, Ying Nian Wu
Abstract: As long-context language modeling becomes increasingly important, the cost of maintaining and attending to large Key/Value (KV) caches grows rapidly, becoming a major bottleneck in both training and inference. While prior works such as Multi-Query Attention (MQA) and Multi-Latent Attention (MLA) reduce memory by sharing or compressing KV features, they often trade off representation quality or incur runtime overhead. We propose Memory-Keyed Attention (MKA), a hierarchical attention mechanism that integrates multi-level KV caches (local, session, and long-term) and learns to route attention across them dynamically. We further introduce Route-Fused MKA (FastMKA), a broadcast-routed variant that fuses memory sources before attention computation for improved efficiency. Experiments on different sequence lengths show that FastMKA achieves a favorable accuracy-efficiency trade-off: comparable perplexity to MLA while achieving up to 5x faster training throughput and 1.8x lower evaluation latency. These results highlight MKA as a practical and extensible framework for efficient long-context attention.
Authors: Hao Xu, Yuntian Chen, Chongqing Kang, Dongxiao Zhang
Abstract: The global shift towards renewable energy necessitates the development of ultrahigh-voltage (UHV) AC transmission to bridge the gap between remote energy sources and urban demand. While UHV grids offer superior capacity and efficiency, their implementation is often hindered by corona-induced audible noise (AN) and radio interference (RI). Since these emissions must meet strict environmental compliance standards, accurate prediction is vital for the large-scale deployment of UHV infrastructure. Existing engineering practices often rely on empirical laws, in which fixed log-linear structures limit accuracy and extrapolation. Herein, we present a monotonicity-constrained graph symbolic discovery framework, Mono-GraphMD, which uncovers compact, interpretable laws for corona-induced AN and RI. The framework provides mechanistic insight into how nonlinear interactions among the surface gradient, bundle number and diameter govern high-field emissions and enables accurate predictions for both corona-cage data and multicountry real UHV lines with up to 16-bundle conductors. Unlike black-box models, the discovered closed-form laws are highly portable and interpretable, allowing for rapid predictions when applied to various scenarios, thereby facilitating the engineering design process.
Authors: Hang-Cheng Dong, Pengcheng Cheng, Shuhuan Li
Abstract: Solving ill-posed inverse problems necessitates effective regularization strategies to stabilize the inversion process against measurement noise. While classical methods like Tikhonov regularization require heuristic parameter tuning, and standard deep learning approaches often lack interpretability and generalization across resolutions, we propose SC-Net (Spectral Correction Network), a novel operator learning framework. SC-Net operates in the spectral domain of the forward operator, learning a pointwise adaptive filter function that reweights spectral coefficients based on the signal-to-noise ratio. We provide a theoretical analysis showing that SC-Net approximates the continuous inverse operator, guaranteeing discretization invariance. Numerical experiments on 1D integral equations demonstrate that SC-Net: (1) achieves the theoretical minimax optimal convergence rate ($O(\delta^{0.5})$ for $s=p=1.5$), matching theoretical lower bounds; (2) learns interpretable sharp-cutoff filters that outperform Oracle Tikhonov regularization; and (3) exhibits zero-shot super-resolution, maintaining stable reconstruction errors ($\approx 0.23$) when trained on coarse grids ($N=256$) and tested on significantly finer grids (up to $N=2048$). The proposed method bridges the gap between rigorous regularization theory and data-driven operator learning.
Authors: Chao Wang, Xuancheng Zhou, Ruilin Hou, Xiaoyu Cheng, Ruiyi Ding
Abstract: Accurately characterizing non-linear functional manifolds with singularities is a fundamental challenge in scientific computing. While Multi-Layer Perceptrons (MLPs) dominate, their spectral bias hinders resolving high-curvature features without excessive parameters. We introduce Continued Fraction Neural Networks (CFNNs), integrating continued fractions with gradient-based optimization to provide a ``rational inductive bias.'' This enables capturing complex asymptotics and discontinuities with extreme parameter frugality. We provide formal approximation bounds demonstrating exponential convergence and stability guarantees. To address recursive instability, we develop three implementations: CFNN-Boost, CFNN-MoE, and CFNN-Hybrid. Benchmarks show CFNNs consistently outperform MLPs in precision with one to two orders of magnitude fewer parameters, exhibiting up to a 47-fold improvement in noise robustness and physical consistency. By bridging black-box flexibility and white-box transparency, CFNNs establish a reliable ``grey-box'' paradigm for AI-driven scientific research.
Authors: Sen Fang, Weiyuan Ding, Zhezhen Cao, Zhou Yang, Bowen Xu
Abstract: Large Language Models (LLMs) are increasingly adopted for vulnerability detection, yet their reasoning remains fundamentally unsound. We identify a root cause shared by both major mitigation paradigms (agent-based debate and retrieval augmentation): reasoning in an ungrounded deliberative space that lacks a bounded, hypothesis-specific evidence base. Without such grounding, agents fabricate cross-function dependencies, and retrieval heuristics supply generic knowledge decoupled from the repository's data-flow topology. Consequently, the resulting conclusions are driven by rhetorical persuasiveness rather than verifiable facts. To ground this deliberation, we present AEGIS, a novel multi-agent framework that shifts detection from ungrounded speculation to forensic verification over a closed factual substrate. Guided by a "From Clue to Verdict" philosophy, AEGIS first identifies suspicious code anomalies (clues), then dynamically reconstructs per-variable dependency chains for each clue via on-demand slicing over a repository-level Code Property Graph. Within this closed evidence boundary, a Verifier Agent constructs competing dialectical arguments for and against exploitability, while an independent Audit Agent scrutinizes every claim against the trace, exercising veto power to prevent hallucinated verdicts. Evaluation on the rigorous PrimeVul dataset demonstrates that AEGIS establishes a new state-of-the-art, achieving 122 Pair-wise Correct Predictions. To our knowledge, this is the first approach to surpass 100 on this benchmark. It reduces the false positive rate by up to 54.40% compared to leading baselines, at an average cost of $0.09 per sample without any task-specific training.
Authors: Jon-Paul Cacioli
Abstract: How do transformer language models represent magnitude? Recent work disagrees: some find logarithmic spacing, others linear encoding, others per-digit circular representations. We apply the formal tools of psychophysics to resolve this. Using four converging paradigms (representational similarity analysis, behavioural discrimination, precision gradients, causal intervention) across three magnitude domains in three 7-9B instruction-tuned models spanning three architecture families (Llama, Mistral, Qwen), we report three findings. First, representational geometry is consistently log-compressive: RSA correlations with a Weber-law dissimilarity matrix ranged from .68 to .96 across all 96 model-domain-layer cells, with linear geometry never preferred. Second, this geometry is dissociated from behaviour: one model produces a human-range Weber fraction (WF = 0.20) while the other does not, and both models perform at chance on temporal and spatial discrimination despite possessing logarithmic geometry. Third, causal intervention reveals a layer dissociation: early layers are functionally implicated in magnitude processing (4.1x specificity) while later layers where geometry is strongest are not causally engaged (1.2x). Corpus analysis confirms the efficient coding precondition (alpha = 0.77). These results suggest that training data statistics alone are sufficient to produce log-compressive magnitude geometry, but geometry alone does not guarantee behavioural competence.
Authors: Ling Xiao, Toshihiko Yamasaki
Abstract: Most fine-grained fashion image retrieval (FIR) methods assume a static setting, requiring full retraining when new attributes appear, which is costly and impractical for dynamic scenarios. Although pretrained models support zero-shot inference, their accuracy drops without supervision, and no prior work explores class-incremental learning (CIL) for fine-grained FIR. We propose a multihead continual learning framework for fine-grained fashion image retrieval with contrastive learning and exponential moving average (EMA) distillation (MCL-FIR). MCL-FIR adopts a multi-head design to accommodate evolving classes across increments, reformulates triplet inputs into doublets with InfoNCE for simpler and more effective training, and employs EMA distillation for efficient knowledge transfer. Experiments across four datasets demonstrate that, beyond its scalability, MCL-FIR achieves a strong balance between efficiency and accuracy. It significantly outperforms CIL baselines under similar training cost, and compared with static methods, it delivers comparable performance while using only about 30% of the training cost. The source code is publicly available in https://github.com/Dr-LingXiao/MCL-FIR.
Authors: Chien-Ping Lu
Abstract: Classical Amdahl's Law assumes a fixed decomposition between serial and parallel work and homogeneous replication; historically, it bounds how much parallel speedup is attainable. Modern systems instead combine specialized accelerators with programmable compute, tensor datapaths, and evolving pipelines, while empirical scaling laws shift which stages absorb marginal compute. The central tension is therefore not the serial-versus-parallel split alone, but resource allocation across heterogeneous hardware, given efficiency differences, and workload structures that determine how effectively additional compute can be converted into value. We reformulate Amdahl's Law for modern heterogeneous systems with scalable workloads. The analysis yields a finite collapse threshold: beyond a critical scalable fraction, specialization becomes suboptimal for any efficiency advantage of specialized hardware over programmable compute, and optimal specialized investment falls to zero, a phase transition rather than an asymptotic tail. We use this framework to interpret increasing GPU programmability and why domain-specific AI accelerators have not displaced GPUs.
Authors: Aratrika Mustafi, Soumya Mukherjee
Abstract: We propose a dense associative memory for empirical measures (weighted point clouds). Stored patterns and queries are finitely supported probability measures, and retrieval is defined by minimizing a Hopfield-style log-sum-exp energy built from the debiased Sinkhorn divergence. We derive retrieval dynamics as a spherical Hellinger Kantorovich (SHK) gradient flow, which updates both support locations and weights. Discretizing the flow yields a deterministic algorithm that uses Sinkhorn potentials to compute barycentric transport steps and a multiplicative simplex reweighting. Under local separation and PL-type conditions we prove basin invariance, geometric convergence to a local minimizer, and a bound showing the minimizer remains close to the corresponding stored pattern. Under a random pattern model, we further show that these Sinkhorn basins are disjoint with high probability, implying exponential capacity in the ambient dimension. Experiments on synthetic Gaussian point-cloud memories demonstrate robust recovery from perturbed queries versus a Euclidean Hopfield-type baseline.
Authors: Balaji Dinesh Gangireddi, Aniketh Garikaparthi, Manasi Patwardhan, Arman Cohan
Abstract: Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured merges, resulting in knowledge loss. These limitations are magnified in research-coding workflows, which involve heterogeneous repositories, underspecified environments, and weak feedback, where reproducing results from public codebases is an established evaluation regime. We introduce Reflective Evolving Research Engineer (REVERE), a framework that continuously learns from Global Training Context, recognizes recurring failure modes in cross-repository execution trajectories, distills them into reusable heuristics, and performs targeted edits across three configurable fields: the system prompt, a task-prompt template, and a cumulative cheatsheet. REVERE, via this reflective optimization framework, improves performance over prior state-of-the-art expert-crafted instructions on research coding tasks by 4.50% on SUPER, 3.51% on ResearchCodeBench, and 4.89% on ScienceAgentBench across their respective metrics. These results demonstrate that agents equipped with mechanisms for continual learning and global memory consolidation can meaningfully evolve their capabilities over time.
Authors: Tianyi Huang, Caden Yang, Emily Yin, Eric Wang, Michael Zhang
Abstract: Retrieval-augmented language models can retrieve relevant evidence yet still commit to answers before explicitly checking whether the retrieved context supports the conclusion. We present PAVE (Premise-Grounded Answer Validation and Editing), an inference-time validation layer for evidence-grounded question answering. PAVE decomposes retrieved context into question-conditioned atomic facts, drafts an answer, scores how well that draft is supported by the extracted premises, and revises low-support outputs before finalization. The resulting trace makes answer commitment auditable at the level of explicit premises, support scores, and revision decisions. In controlled ablations with a fixed retriever and backbone, PAVE outperforms simpler post-retrieval baselines in two evidence-grounded QA settings, with the largest gain reaching 32.7 accuracy points on a span-grounded benchmark. We view these findings as proof-of-concept evidence that explicit premise extraction plus support-gated revision can strengthen evidence-grounded consistency in retrieval-augmented LLM systems.
Authors: Sudip Laudari
Abstract: Echo State Networks (ESNs) are a reservoir computing framework widely used for nonlinear time-series prediction. However, despite their effectiveness, the randomly initialized reservoir often contains redundant nodes, leading to unnecessary computational overhead and reduced efficiency. In this work, we propose a graph centrality-based pruning approach that interprets the reservoir as a weighted directed graph and removes structurally less important nodes using centrality measures. Experiments on Mackey-Glass time-series prediction and electric load forecasting demonstrate that the proposed method can significantly reduce reservoir size while maintaining, and in some cases improving, prediction accuracy, while preserving the essential reservoir dynamics.
Authors: Kyudan Jung, Jihwan Kim, Minwoo Lee, Soyoon Kim, Jeonghoon Kim, Jaegul Choo, Cheonbok Park
Abstract: Recent advancements in text-to-speech technologies enable generating high-fidelity synthetic speech nearly indistinguishable from real human voices. While recent studies show the efficacy of self-supervised learning-based speech encoders for deepfake detection, these models struggle to generalize across unseen speakers. Our quantitative analysis suggests these encoder representations are substantially influenced by speaker information, causing detectors to exploit speaker-specific correlations rather than artifact-related cues. We call this phenomenon speaker entanglement. To mitigate this reliance, we introduce SNAP, a speaker-nulling framework. We estimate a speaker subspace and apply orthogonal projection to suppress speaker-dependent components, isolating synthesis artifacts within the residual features. By reducing speaker entanglement, SNAP encourages detectors to focus on artifact-related patterns, leading to state-of-the-art performance.
Authors: Parisa Omidmand, Saeid Ataei
Abstract: Organizations increasingly adopt AI technologies to accelerate their performance and capacity to adapt to market dynamics. This study examines how organizations implement AI in experimental methodologies such as growth hacking, lean startup, design thinking, and agile methodology to enhance efficiency and effectiveness. We performed a systematic literature review following the PRISMA 2020 framework, analyzing 37 articles from Web of Science (WOS) and Scopus databases published between 2018 and 2024 to assess AI integration with experimental approaches. Our findings indicate that AI plays a pivotal role in enhancing these methodologies by offering advanced tools for data analysis, real-time feedback, automation, and process optimization. For instance, AI-driven analytics improves decision-making in growth hacking, streamlines iterative cycles in lean startups, enhances creativity in design thinking, and optimizes task prioritization in agile methodology. Furthermore, we identified several real-world cases that successfully utilized AI in experimental strategies and improved their performance across various industries. However, despite the clear advantages of AI integration, organizations face barriers such as skill gaps, ethical concerns, and data governance issues. Addressing these challenges requires a strategic approach to AI adoption, including workforce training, strict data management, and following ethical standards.
Authors: Jiarong Liang, Zhiheng Lyu, Zijie Liu, Xiangchao Chen, Ping Nie, Kai Zou, Wenhu Chen
Abstract: Executable software engineering data is valuable for training SWE agents, but scaling it remains difficult for two reasons: only a small fraction of real repository changes yield verifiable, high-signal task instances, and naively building repository-specific environments quickly becomes the dominant systems cost. We present SWE-Next, an execution-grounded framework for scalable SWE task and trajectory collection. On the data side, SWE-Next mines real merged pull requests, executes candidate base/merged commit pairs, and retains only those that produce strict test improvements without regressions, yielding self-verifying instances. It also applies strict submission gating so that collected trajectories remain evidence-driven rather than speculative. On the systems side, SWE-Next introduces reusable repo-quarter profiles, which reuse the same environment across nearby commits in time while keeping each task run separate and reproducible. Using only 30 hours and 639GB of environment storage, SWE-Next processes 3,971 seed repositories and 102,582 candidate commit pairs mined from real merged PRs to construct a dataset of 2,308 self-verifying instances. Experiments show that SWE-Next improves downstream pass@1 with fewer or comparable training trajectories, indicating that its gains come not from a stronger trajectory generator, but from higher-signal execution-grounded supervision and more efficient data collection.
Authors: Yifan Yang, Lei Zou, Wendy Jepson
Abstract: In the immediate aftermath of natural disasters, rapid situational awareness is critical. Traditionally, satellite observations are widely used to estimate damage extent. However, they lack the ground-level perspective essential for characterizing specific structural failures and impacts. Meanwhile, ground-level data (e.g., street-view imagery) remains largely inaccessible during time-sensitive events. This study investigates Satellite-to-Street View Synthesis to bridge this data gap. We introduce two generative strategies to synthesize post-disaster street views from satellite imagery: a Vision-Language Model (VLM)-guided approach and a damage-sensitive Mixture-of-Experts (MoE) method. We benchmark these against general-purpose baselines (Pix2Pix, ControlNet) using a proposed Structure-Aware Evaluation Framework. This multi-tier protocol integrates (1) pixel-level quality assessment, (2) ResNet-based semantic consistency verification, and (3) a novel VLM-as-a-Judge for perceptual alignment. Experiments on 300 disaster scenarios reveal a critical realism--fidelity trade-off: while diffusion-based approaches (e.g., ControlNet) achieve high perceptual realism, they often hallucinate structural details. Quantitative results show that standard ControlNet achieves the highest semantic accuracy, 0.71, whereas VLM-enhanced and MoE models excel in textural plausibility but struggle with semantic clarity. This work establishes a baseline for trustworthy cross-view synthesis, emphasizing that visually realistic generations may still fail to preserve critical structural information required for reliable disaster assessment.
Authors: Hongyu Wang, Yuhan Jing, Yibing Shi, Enjin Zhou, Haotian Zhang, Jialong Shi
Abstract: Proper parameter configuration is a prerequisite for the success of Evolutionary Algorithms (EAs). While various adaptive strategies have been proposed, it remains an open question whether all control dimensions contribute equally to algorithmic scalability. To investigate this, we categorize control variables into numerical parameters (e.g., crossover and mutation rates) and structural parameters (e.g., population size and operator switching), hypothesizing that they play distinct roles. This paper presents an empirical study utilizing a dual-level Deep Reinforcement Learning (DRL) framework to decouple and analyze the impact of these two dimensions on the Traveling Salesman Problem (TSP). We employ a Recurrent PPO agent to dynamically regulate these parameters, treating the DRL model as a probe to reveal evolutionary dynamics. Experimental results confirm the effectiveness of this approach: the learned policies outperform static baselines, reducing the optimality gap by approximately 45% on the largest tested instance (rl5915). Building on this validated framework, our ablation analysis reveals a fundamental insight: while numerical tuning offers local refinement, structural plasticity is the decisive factor in preventing stagnation and facilitating escape from local optima. These findings suggest that future automated algorithm design should prioritize dynamic structural reconfiguration over fine-grained probability adjustment. To facilitate reproducibility, the source code is available at https://github.com/StarDream1314/DRLGA-TSP
Authors: Jose Luis Lima de Jesus Silva
Abstract: Acoustic borehole images provide high-resolution borehole-wall structure, but large-scale interpretation remains difficult because dense expert annotations are rarely available and subsurface information is intrinsically multimodal. The challenge is developing weakly supervised methods combining two-dimensional image texture with depth-aligned one-dimensional well-logs. Here, we introduce a weakly supervised multimodal segmentation framework that refines threshold-guided pseudo-labels through learned models. This preserves the annotation-free character of classical thresholding and clustering workflows while extending them with denoising, confidence-aware pseudo-supervision, and physically structured fusion. We establish that threshold-guided learned refinement provides the most robust improvement over raw thresholding, denoised thresholding, and latent clustering baselines. Multimodal performance depends strongly on fusion strategy: direct concatenation provides limited gains, whereas depth-aware cross-attention, gated fusion, and confidence-aware modulation substantially improve agreement with the weak supervisory reference. The strongest model, confidence-gated depth-aware cross-attention (CG-DCA), consistently outperforms threshold-based, image-only, and earlier multimodal baselines. Targeted ablations show its advantage depends specifically on confidence-aware fusion and structured local depth interaction rather than model complexity alone. Cross-well analyses confirm this performance is broadly stable. These results establish a practical, scalable framework for annotation-free segmentation, showing multimodal improvement is maximized when auxiliary logs are incorporated selectively and depth-aware.
Authors: Fan Huang
Abstract: Existing prompting paradigms structure LLM reasoning in limited topologies: Chain-of-Thought (CoT) produces linear traces, while Tree-of-Thought (ToT) performs branching search. Yet complex reasoning often requires merging intermediate results, revisiting hypotheses, and integrating evidence from multiple sources. We propose Network-of-Thought (NoT), a framework that models reasoning as a directed graph with typed nodes and edges, guided by a heuristic-based controller policy. Across four benchmarks (GSM8K, Game of 24, HotpotQA, ProofWriter) and three models (GPT-4o-mini, Llama-3.3-70B-Instruct, Qwen2.5-72B-Instruct), we investigate when network topology outperforms chain or tree structures, whether LLM-generated heuristics can guide graph-based reasoning search, and the computation-accuracy tradeoff across topologies, evaluating each method on accuracy, topology simplicity, and token efficiency. Our results show that CoT remains effective for sequential tasks with GPT-4o-mini (89.5\% on GSM8K), while NoT surpasses ToT on multi-hop reasoning (91.0\% vs.\ 88.0\% on HotpotQA with LLM-as-Judge). With 72B open-source models, NoT achieves the highest accuracy on GSM8K (91.5\%), and Qwen2.5-72B achieves the best multi-hop QA result overall (91.7\% on HotpotQA). Self-generated controller heuristics outperform fixed and random strategies on logical reasoning, with uncertainty-only weighting achieving 57.0\% on ProofWriter. We also find that evaluation methodology significantly impacts method rankings: string-match underestimates all methods on open-ended QA, with the largest gap for NoT, a pattern consistent across all three models (14--18 percentage point gap on HotpotQA).
Authors: Sunghyun Park, Jeongho Kim, Hyoungwoo Park, Debasmit Das, Sungrack Yun, Munawar Hayat, Jaegul Choo, Fatih Porikli, Seokeon Choi
Abstract: Diffusion Transformers (DiTs) have significantly enhanced text-to-image (T2I) generation quality, enabling high-quality personalized content creation. However, fine-tuning these models requires substantial computational complexity and memory, limiting practical deployment under resource constraints. To tackle these challenges, we propose a memory-efficient fine-tuning framework called DiT-BlockSkip, integrating timestep-aware dynamic patch sampling and block skipping by precomputing residual features. Our dynamic patch sampling strategy adjusts patch sizes based on the diffusion timestep, then resizes the cropped patches to a fixed lower resolution. This approach reduces forward & backward memory usage while allowing the model to capture global structures at higher timesteps and fine-grained details at lower timesteps. The block skipping mechanism selectively fine-tunes essential transformer blocks and precomputes residual features for the skipped blocks, significantly reducing training memory. To identify vital blocks for personalization, we introduce a block selection strategy based on cross-attention masking. Evaluations demonstrate that our approach achieves competitive personalization performance qualitatively and quantitatively, while reducing memory usage substantially, moving toward on-device feasibility (e.g., smartphones, IoT devices) for large-scale diffusion transformers.
Authors: Aarush Aggarwal, Akshat Tomar, Amritanshu Tiwari, Sargam Goyal
Abstract: Robust semantic segmentation is crucial for safe autonomous driving, yet deployed models remain vulnerable to black-box adversarial attacks when target weights are unknown. Most existing approaches either craft image-wide perturbations or optimize patches for a single architecture, which limits their practicality and transferability. We introduce OmniPatch, a training framework for learning a universal adversarial patch that generalizes across images and both ViT and CNN architectures without requiring access to target model parameters.
Authors: Hanqiao Ye, Yuzhou Liu, Yangdong Liu, Shuhan Shen
Abstract: While structure-based relocalizers have long strived for point correspondences when establishing or regressing query-map associations, in this paper, we pioneer the use of planar primitives and 3D planar maps for lightweight 6-DoF camera relocalization in structured environments. Planar primitives, beyond being fundamental entities in projective geometry, also serve as region-based representations that encapsulate both structural and semantic richness. This motivates us to introduce PlanaReLoc, a streamlined plane-centric paradigm where a deep matcher associates planar primitives across the query image and the map within a learned unified embedding space, after which the 6-DoF pose is solved and refined under a robust framework. Through comprehensive experiments on the ScanNet and 12Scenes datasets across hundreds of scenes, our method demonstrates the superiority of planar primitives in facilitating reliable cross-modal structural correspondences and achieving effective camera relocalization without requiring realistically textured/colored maps, pose priors, or per-scene training. The code and data are available at https://github.com/3dv-casia/PlanaReLoc .
Authors: Milos Gravara, Juan Luis Herrera, Stefan Nastic
Abstract: Compound AI is a distributed intelligence approach that represents a unified system orchestrating specialized AI/ML models with engineered software components into AI workflows. Compound AI production deployments must satisfy accuracy, latency, and cost objectives under varying loads. However, many deployments operate on fixed infrastructure where horizontal scaling is not viable. Existing approaches optimize solely for accuracy and do not consider changes in workload conditions. We observe that compound AI systems can switch between configurations to fit infrastructure capacity, trading accuracy for latency based on current load. This requires discovering multiple Pareto-optimal configurations from a combinatorial search space and determining when to switch between them at runtime. We present Compass, a novel framework that enables dynamic configuration switching through offline optimization and online adaptation. Compass consists of three components: COMPASS-V algorithm for configuration discovery, Planner for switching policy derivation, and Elastico Controller for runtime adaptation. COMPASS-V discovers accuracy-feasible configurations using finite-difference guided search and a combination of hill-climbing and lateral expansion. Planner profiles these configurations on target hardware and derives switching policies using a queuing theory based model. Elastico monitors queue depth and switches configurations based on derived thresholds. Across two compound AI workflows, COMPASS-V achieves 100% recall while reducing configuration evaluations by 57.5% on average compared to exhaustive search, with efficiency gains reaching 95.3% at tight accuracy thresholds. Runtime adaptation achieves 90-98% SLO compliance under dynamic load patterns, improving SLO compliance by 71.6% over static high-accuracy baselines, while simultaneously improving accuracy by 3-5% over static fast baselines.
Authors: Wenjun Huang, Shenghao Fu, Yian Jin, Yang Ni, Ziteng Cui, Hanning Chen, Yirui He, Yezi Liu, Sanggeon Yun, SungHeon Jeong, Ryozo Masukawa, William Youngwoo Chung, Mohsen Imani
Abstract: RAW images captured by different camera sensors exhibit substantial domain shifts due to varying spectral responses, noise characteristics, and tone behaviors, complicating their direct use in downstream computer vision tasks. Prior methods address this problem by training domain-specific RAW-to-RAW translators for each source-target pair, but such approaches do not scale to real-world scenarios involving multiple types of commercial cameras. In this work, we introduce MERIT, the first unified framework for multi-domain RAW image translation, which leverages a single model to perform translations across arbitrary camera domains. To address domain-specific noise discrepancies, we propose a sensor-aware noise modeling loss that explicitly aligns the signal-dependent noise statistics of the generated images with those of the target domain. We further enhance the generator with a conditional multi-scale large kernel attention module for improved context and sensor-aware feature modeling. To facilitate standardized evaluation, we introduce MDRAW, the first dataset tailored for multi-domain RAW image translation, comprising both paired and unpaired RAW captures from five diverse camera sensors across a wide range of scenes. Extensive experiments demonstrate that MERIT outperforms prior models in both quality (5.56 dB improvement) and scalability (80% reduction in training iterations).
Authors: Yujin Park, Haejun Chung, Ikbeom Jang
Abstract: Pairwise comparison labeling is emerging as it yields higher inter-rater reliability than conventional classification labeling, but exhaustive comparisons require quadratic cost. We propose Dodgersort, which leverages CLIP-based hierarchical pre-ordering, a neural ranking head and probabilistic ensemble (Elo, BTL, GP), epistemic--aleatoric uncertainty decomposition, and information-theoretic pair selection. It reduces human comparisons while improving the reliability of the rankings. In visual ranking tasks in medical imaging, historical dating, and aesthetics, Dodgersort achieves a 11--16\% annotation reduction while improving inter-rater reliability. Cross-domain ablations across four datasets show that neural adaptation and ensemble uncertainty are key to this gain. In FG-NET with ground-truth ages, the framework extracts 5--20$\times$ more ranking information per comparison than baselines, yielding Pareto-optimal accuracy--efficiency trade-offs.
Authors: Xiangyu Zeng, Qi Xu, Yunke Wang, Chang Xu
Abstract: Long-context language modeling is commonly framed as a scalability challenge of token-level attention, yet local-to-global information structuring remains largely implicit in existing approaches. Drawing on cognitive theories of discourse comprehension, we propose HiCI (Hierarchical Construction--Integration), a hierarchical attention module that constructs segment-level representations, integrates them into a shared global context, and broadcasts both to condition segment-level attention. We validate HiCI through parameter-efficient adaptation of LLaMA-2 with only <5.5% additional parameters, extending context from 4K to 100K tokens (7B) and 64K tokens (13B). Across language modeling, retrieval, and instruction-following benchmarks, HiCI yields consistent improvements over strong baselines, including matching proprietary models on topic retrieval and surpassing GPT-3.5-Turbo-16K on code comprehension. These results demonstrate the effectiveness of explicit hierarchical structuring as an inductive bias for long-context modeling.
Authors: Shanshan Wang, Derek F. Wong, Jingming Yao, Lidia S. Chao
Abstract: ChatGPT has demonstrated remarkable capabilities on both poetry generation and translation, yet its ability to truly understand poetry remains unexplored. Previous poetry-related work merely analyzed experimental outcomes without addressing fundamental issues of comprehension. This paper introduces a comprehensive framework for evaluating ChatGPT's understanding of modern poetry. We collaborated with professional poets to evaluate ChatGPT's interpretation of modern Chinese poems by different poets along multiple dimensions. Evaluation results show that ChatGPT's interpretations align with the original poets' intents in over 73% of the cases. However, its understanding in certain dimensions, particularly in capturing poeticity, proved to be less satisfactory. These findings highlight the effectiveness and necessity of our proposed framework. This study not only evaluates ChatGPT's ability to understand modern poetry but also establishes a solid foundation for future research on LLMs and their application to poetry-related tasks.
Authors: Saken Tukenov
Abstract: Kazakh, a Turkic language spoken by over 22 million people, remains underserved by existing multilingual language models, which allocate minimal capacity to low-resource languages and employ tokenizers ill-suited to agglutinative morphology. We present SozKZ, a family of Llama-architecture language models (50M-600M parameters) trained entirely from scratch on 9 billion tokens of Kazakh text with a dedicated 50K BPE tokenizer. We evaluate all models on three Kazakh benchmarks -- multiple-choice cultural QA, reading comprehension (Belebele), and topic classification (SIB-200) -- alongside five multilingual baselines ranging from 500M to 3B parameters. Our 600M model achieves 30.3% accuracy on Kazakh cultural QA, approaching the 32.0% of Llama-3.2-1B (2x larger), and 25.5% on SIB-200 topic classification, surpassing all evaluated multilingual models up to 2B parameters. We observe consistent scaling from 50M to 600M, with MC QA accuracy rising from 22.8% to 30.3%, suggesting that further scaling remains beneficial. These results demonstrate that small, dedicated models trained from scratch with a language-appropriate tokenizer offer a viable path for low-resource language technology, achieving competitive performance at a fraction of the computational cost. All models and the tokenizer are released under open licenses.
Authors: Xander Coetzer, Arn\'e Schreuder, Anna Sergeevna Bosman
Abstract: Transfer learning with models pretrained on ImageNet has become a standard practice in computer vision. Transfer learning refers to fine-tuning pretrained weights of a neural network on a downstream task, typically unrelated to ImageNet. However, pretrained weights can become saturated and may yield insignificant gradients, failing to adapt to the downstream task. This hinders the ability of the model to train effectively, and is commonly referred to as loss of neural plasticity. Loss of plasticity may prevent the model from fully adapting to the target domain, especially when the downstream dataset is atypical in nature. While this issue has been widely explored in continual learning, it remains relatively understudied in the context of transfer learning. In this work, we propose the use of a targeted weight re-initialization strategy to restore neural plasticity prior to fine-tuning. Our experiments show that both convolutional neural networks (CNNs) and vision transformers (ViTs) benefit from this approach, yielding higher test accuracy with faster convergence on several image classification benchmarks. Our method introduces negligible computational overhead and is compatible with common transfer learning pipelines.
Authors: Hossein Javidnia
Abstract: Recent interpretability work often treats a feature as a single global direction, dictionary atom, or latent coordinate shared across contexts. We argue that this ontology can fail in obstructed representation spaces, where locally coherent meanings need not assemble into one globally consistent feature. We introduce an atlas-native replacement object, the semantic section: a transport-compatible family of local feature representatives defined over a context atlas. We formalize semantic sections, prove that tree-supported propagation is always pathwise realizable, and show that cycle consistency is the key criterion for genuine globalization. This yields a distinction between tree-local, globalizable, and twisted sections, with twisted sections capturing locally coherent but holonomy-obstructed meanings. We then develop a discovery-and-certification pipeline based on seeded propagation, synchronization across overlaps, defect-based pruning, cycle-aware taxonomy, and deduplication. Across layer-16 atlases for Llama 3.2 3B Instruct, Qwen 2.5 3B Instruct, and Gemma 2 2B IT, we find nontrivial populations of semantic sections, including cycle-supported globalizable and twisted regimes after deduplication. Most importantly, semantic identity is not recovered by raw global-vector similarity. Even certified globalizable sections show low cross-chart signed cosine similarity, and raw similarity baselines recover only a small fraction of true within-section pairs, often collapsing at moderate thresholds. By contrast, section-based identity recovery is perfect on certified supports. These results support semantic sections as a better feature ontology in obstructed regimes.
Authors: Kaustubh D. Dhole, Eugene Agichtein
Abstract: Large language models (LLMs) are increasingly evaluated and sometimes trained using automated graders such as LLM-as-judges that output scalar scores or preferences. While convenient, these approaches are often opaque: a single score rarely explains why an answer is good or bad, which requirements were missed, or how a system should be improved. This lack of interpretability limits their usefulness for model development, dataset curation, and high-stakes deployment. Query-specific rubric-based evaluation offers a more transparent alternative by decomposing quality into explicit, checkable criteria. However, manually designing high-quality, query-specific rubrics is labor-intensive and cognitively demanding and not feasible for deployment. While previous approaches have focused on generating intermediate rubrics for automated downstream evaluation, it is unclear if these rubrics are both interpretable and effective for human users. In this work, we investigate whether LLMs can generate useful, instance-specific rubrics as compared to human-authored rubrics, while also improving effectiveness for identifying good responses. Through our systematic study on two rubric benchmarks, and on multiple few-shot and post-training strategies, we find that off-the-shelf LLMs produce rubrics that are poorly aligned with human-authored ones. We introduce a simple strategy, RubricRAG, which retrieves domain knowledge via rubrics at inference time from related queries. We demonstrate that RubricRAG can generate more interpretable rubrics both for similarity to human-authored rubrics, and for improved downstream evaluation effectiveness. Our results highlight both the challenges and a promising approach of scalable, interpretable evaluation through automated rubric generation.
Authors: Kanishka Mitra, Frigyes Samuel Racz, Satyam Kumar, Ashish D. Deshpande, Jos\'e del R. Mill\'an
Abstract: Two distinct technologies have gained attention lately due to their prospects for motor rehabilitation: robotics and brain-machine interfaces (BMIs). Harnessing their combined efforts is a largely uncharted and promising direction that has immense clinical potential. However, a significant challenge is whether motor intentions from the user can be accurately detected using non-invasive BMIs in the presence of instrumental noise and passive movements induced by the rehabilitation exoskeleton. As an alternative to the straightforward continuous control approach, this study instead aims to characterize the onset and offset of motor imagery during passive arm movements induced by an upper-body exoskeleton to allow for the natural control (initiation and termination) of functional movements. Ten participants were recruited to perform kinesthetic motor imagery (MI) of the right arm while attached to the robot, simultaneously cued with LEDs indicating the initiation and termination of a goal-oriented reaching task. Using electroencephalogram signals, we built a decoder to detect the transition between i) rest and beginning MI and ii) maintaining and ending MI. Offline decoder evaluation achieved group average onset accuracy of 60.7% and 66.6% for offset accuracy, revealing that the start and stop of MI could be identified while attached to the robot. Furthermore, pseudo-online evaluation could replicate this performance, forecasting reliable online exoskeleton control in the future. Our approach showed that participants could produce quality and reliable sensorimotor rhythms regardless of noise or passive arm movements induced by wearing the exoskeleton, which opens new possibilities for BMI control of assistive devices.
Authors: Zhaoyi Liu, Haichuan Zhang, Ang Li
Abstract: Hyper-Connections (HC) generalize residual connections into multiple streams, employing residual matrices for cross-stream feature mixing to enrich model expressivity. However, unconstrained mixing disrupts the identity mapping property intrinsic to the residual connection, causing unstable training. To address this, Manifold-Constrained Hyper-Connections (mHC) and its variant restrict these matrices to the Birkhoff polytope (doubly stochastic matrices) via Sinkhorn iterations or permutation-based parameterizations. We reveal three limitations of this polytope constraint: (1) identity degeneration, where learned matrices collapse around the identity and diminish cross-stream interactions, (2) an expressivity bottleneck, as the non-negativity constraint prevents subtractive feature disentanglement, and (3) parameterization inefficiencies, manifesting as unstable Sinkhorn iterations or the factorial-scaling overhead of permutation-based parameterizations. To overcome these flaws, we propose Spectral-Sphere-Constrained Hyper-Connections (sHC). By geometrically shifting the feasible set from a rigid polytope to a spectral norm sphere, sHC allows negative entries, unlocking subtractive interactions for selective feature diversification. This shift eliminates unstable Sinkhorn projections and factorial parameterization, enabling expressive, non-degenerate residual matrices while preserving training stability.
Authors: Andrea Marinoni, Pietro Lio', Erik Cambria, Luca Dal Zilio, Weisi Lin, Mauro Dalla Mura, Jocelyn Chanussot, Edoardo Ragusa, Gianmarco Mengaldo, Chi Yan Tso, Yihao Zhu, Benjamin Horton
Abstract: The strong and continuous increase of AI-based services leads to the steady proliferation of AI data centres worldwide with the unavoidable escalation of their power consumption. It is unknown how this energy demand for computational purposes will impact the surrounding environment. Here, we focus our attention on the heat dissipation of AI hyperscalers. Taking advantage of land surface temperature measurements acquired by remote sensing platforms over the last decades, we are able to obtain a robust assessment of the temperature increase recorded in the areas surrounding AI data centres globally. We estimate that the land surface temperature increases by 2{\deg}C on average after the start of operations of an AI data centre, inducing local microclimate zones, which we call the data heat island effect. We assess the impact on the communities, quantifying that more than 340 million people could be affected by this temperature increase. Our results show that the data heat island effect could have a remarkable influence on communities and regional welfare in the future, hence becoming part of the conversation around environmentally sustainable AI worldwide.
Authors: Joe Khawand, David Colliaux
Abstract: Online Continual Learning (OCL) for image classification represents a challenging subset of Continual Learning, focusing on classifying images from a stream without assuming data independence and identical distribution (i.i.d). The primary challenge in this context is to prevent catastrophic forgetting, where the model's performance on previous tasks deteriorates as it learns new ones. Although various strategies have been proposed to address this issue, achieving rapid convergence remains a significant challenge in the online setting. In this work, we introduce a novel approach to training OCL models that utilizes the Natural Gradient Descent optimizer, incorporating an approximation of the Fisher Information Matrix (FIM) through Kronecker Factored Approximate Curvature (KFAC). This method demonstrates substantial improvements in performance across all OCL methods, particularly when combined with existing OCL tricks, on datasets such as Split CIFAR-100, CORE50, and Split miniImageNet.
Authors: Hongyu Cao, Kunpeng Liu, Dongjie Wang, Yanjie Fu
Abstract: Large language models exhibit strong reasoning capabilities, yet often rely on shortcuts such as surface pattern matching and answer memorization rather than genuine logical inference. We propose Shortcut-Aware Reasoning Training (SART), a gradient-aware framework that detects and mitigates shortcut-promoting samples via ShortcutScore and gradient surgery. Our method identifies shortcut signals through gradient misalignment with validation objectives and answer-token concentration, and modifies training dynamics accordingly. Experiments on controlled reasoning benchmarks show that SART achieves +16.5% accuracy and +40.2% robustness over the strongest baseline, significantly improving generalization under distribution shifts. Code is available at: https://github.com/fuyanjie/short-cut-aware-data-centric-reasoning.
URLs: https://github.com/fuyanjie/short-cut-aware-data-centric-reasoning.
Authors: Mohamed Aymen Bouyahia, Argyris Kalogeratos
Abstract: Interpreting complex machine learning models is a critical challenge, especially for tabular data where model transparency is paramount. Local Interpretable Model-Agnostic Explanations (LIME) has been a very popular framework for interpretable machine learning, also inspiring many extensions. While traditional surrogate models used in LIME variants (e.g. linear regression and decision trees) offer a degree of stability, they can struggle to faithfully capture the complex non-linear decision boundaries that are inherent in many sophisticated black-box models. This work contributes toward bridging the gap between high predictive performance and interpretable decision-making. Specifically, we propose the NDT-LIME variant that integrates Neural Decision Trees (NDTs) as surrogate models. By leveraging the structured, hierarchical nature of NDTs, our approach aims at providing more accurate and meaningful local explanations. We evaluate its effectiveness on several benchmark tabular datasets, showing consistent improvements in explanation fidelity over traditional LIME surrogates.
Authors: Lisan Al Amin, Md Ismail Hossain, Rupak Kumar Das, Mahbubul Islam, Saddam Mukta, Abdulaziz Tabbakh
Abstract: The exponential growth in data has intensified the demand for computational power to train large-scale deep learning models. However, the rapid growth in model size and complexity raises concerns about equal and fair access to computational resources, particularly under increasing energy and infrastructure constraints. GPUs have emerged as essential for accelerating such workloads. This study benchmarks four deep learning models (Conv6, VGG16, ResNet18, CycleGAN) using TensorFlow and PyTorch on Intel Xeon CPUs and NVIDIA Tesla T4 GPUs. Our experiments demonstrate that, on average, GPU training achieves speedups ranging from 11x to 246x depending on model complexity, with lightweight models (Conv6) showing the highest acceleration (246x), mid-sized models (VGG16, ResNet18) achieving 51-116x speedups, and complex generative models (CycleGAN) reaching 11x improvements compared to CPU training. Additionally, in our PyTorch vs. TensorFlow comparison, we observed that TensorFlow's kernel-fusion optimizations reduce inference latency by approximately 15%. We also analyze GPU memory usage trends and projecting requirements through 2025 using polynomial regression. Our findings highlight that while GPUs are essential for sustaining AI's growth, democratized and shared access to GPU resources is critical for enabling research innovation across institutions with limited computational budgets.
Authors: Arun Vignesh Malarkkan, Xinyuan Wang, Kunpeng Liu, Denghui Zhang, Yanjie Fu
Abstract: Feature selection is fundamental to robust data-centric AI, but most existing methods optimize predictive performance under a single data distribution. This often selects spurious features that fail under distribution shifts. Motivated by principles from causal invariance, we study feature selection from a stability perspective and introduce Causally-Guided Diffusion for Stable Feature Selection (CGDFS). In CGDFS, we formalized feature selection as approximate posterior inference over feature subsets, whose posterior mass favors low prediction error and low cross-environment variance. Our framework combines three key insights: First, we formulate feature selection as stability-aware posterior sampling. Here, causal invariance serves as a soft inductive bias rather than explicit causal discovery. Second, we train a diffusion model as a learned prior over plausible continuous selection masks, combined with a stability-aware likelihood that rewards invariance across environments. This diffusion prior captures structural dependencies among features and enables scalable exploration of the combinatorially large selection space. Third, we perform guided annealed Langevin sampling that combines the diffusion prior with the stability objective, which yields a tractable, uncertainty-aware posterior inference that avoids discrete optimization and produces robust feature selections. We evaluate CGDFS on open-source real-world datasets exhibiting distribution shifts. Across both classification and regression tasks, CGDFS consistently selects more stable and transferable feature subsets, which leads to improved out-of-distribution performance and greater selection robustness compared to sparsity-based, tree-based, and stability-selection baselines.
Authors: Reshabh K Sharma, Dan Grossman
Abstract: Large Language Model (LLM) agents combine the chat interaction capabilities of LLMs with the power to interact with external tools and APIs. This enables them to perform complex tasks and act autonomously to achieve user goals. However, current agent systems operate on an all-or-nothing basis: an agent either has full access to an API's capabilities and a web page's content, or it has no access at all. This coarse-grained approach forces users to trust agents with more capabilities than they actually need for a given task. In this paper, we introduce AC4A, an access control framework for agents. As agents become more capable and autonomous, users need a way to limit what APIs or portions of web pages these agents can access, eliminating the need to trust them with everything an API or web page allows. Our goal with AC4A is to provide a framework for defining permissions that lets agents access only the resources they are authorized to access. AC4A works across both API-based and browser-based agents. It does not prescribe what permissions should be, but offers a flexible way to define and enforce them, making it practical for real-world systems. AC4A works by creating permissions granting access to resources, drawing inspiration from established access control frameworks like the one for the Unix file system. Applications define their resources as hierarchies and provide a way to compute the necessary permissions at runtime needed for successful resource access. We demonstrate the usefulness of AC4A in enforcing permissions over real-world APIs and web pages through case studies. The source code of AC4A is available at https://github.com/reSHARMA/AC4A
Authors: Yuren Hao, Shuhaib Mehri, ChengXiang Zhai, Dilek Hakkani-T\"ur
Abstract: Large language models are increasingly used as personal assistants, yet most lack a persistent user model, forcing users to repeatedly restate preferences across sessions. We propose Vector-Adapted Retrieval Scoring (VARS), a pipeline-agnostic, frozen-backbone framework that represents each user with long-term and short-term vectors in a shared preference space and uses these vectors to bias retrieval scoring over structured preference memory. The vectors are updated online from weak scalar rewards from users' feedback, enabling personalization without per-user fine-tuning. We evaluate on \textsc{MultiSessionCollab}, an online multi-session collaboration benchmark with rich user preference profiles, across math and code tasks. Under frozen backbones, the main benefit of user-aware retrieval is improved interaction efficiency rather than large gains in raw task accuracy: our full VARS agent achieves the strongest overall performance, matches a strong Reflection baseline in task success, and reduces timeout rate and user effort. The learned long-term vectors also align with cross-user preference overlap, while short-term vectors capture session-specific adaptation, supporting the interpretability of the dual-vector design. Code, model, and data are available at https://github.com/YurenHao0426/VARS.
Authors: Uchi Uchibeke
Abstract: AI agents today have passwords but no permission slips. They execute tool calls (fund transfers, database queries, shell commands, sub-agent delegation) with no standard mechanism to enforce authorization before the action executes. Current safety architectures rely on model alignment (probabilistic, training-time) and post-hoc evaluation (retrospective, batch). Neither provides deterministic, policy-based enforcement at the individual tool call level. We characterize this gap as the pre-action authorization problem and present the Open Agent Passport (OAP), an open specification and reference implementation that intercepts tool calls synchronously before execution, evaluates them against a declarative policy, and produces a cryptographically signed audit record. OAP enforces authorization decisions in a measured median of 53 ms (N=1,000). In a live adversarial testbed (4,437 authorization decisions across 1,151 sessions, $5,000 bounty), social engineering succeeded against the model 74.6% of the time under a permissive policy; under a restrictive OAP policy, a comparable population of attackers achieved a 0% success rate across 879 attempts. We distinguish pre-action authorization from sandboxed execution (contains blast radius but does not prevent unauthorized actions) and model-based screening (probabilistic), and show they are complementary. The same infrastructure that enforces security constraints (spending limits, capability scoping) also enforces quality gates, operational contracts, and compliance controls. The specification is released under Apache 2.0 (DOI: 10.5281/zenodo.18901596).
Authors: Jason Dury
Abstract: The Predictive Associative Memory (PAM) framework posits that useful relationships often connect items that co-occur in shared contexts rather than items that appear similar in embedding space. A contrastive MLP trained on co-occurrence annotations--Contrastive Association Learning (CAL)--has improved multi-hop passage retrieval and discovered narrative function at corpus scale in text. We test whether this principle transfers to molecular biology, where protein-protein interactions provide functional associations distinct from gene expression similarity. Four experiments across two biological domains map the operating envelope. On gene perturbation data (Replogle K562 CRISPRi, 2,285 genes), CAL trained on STRING protein interactions achieves cross-boundary AUC of 0.908 where expression similarity scores 0.518. A second gene dataset (DepMap, 17,725 genes) confirms the result after negative sampling correction, reaching cross-boundary AUC of 0.947. Two drug sensitivity experiments produce informative negatives that sharpen boundary conditions. Three cross-domain findings emerge: (1) inductive transfer succeeds in biology--a node-disjoint split with unseen genes yields AUC 0.826 (Delta +0.127)--where it fails in text (+/-0.10), suggesting physically grounded associations are more transferable than contingent co-occurrences; (2) CAL scores anti-correlate with interaction degree (Spearman r = -0.590), with gains concentrating on understudied genes with focused interaction profiles; (3) tighter association quality outperforms larger but noisier training sets, reversing the text pattern. Results are stable across training seeds (SD < 0.001) and cross-boundary threshold choices.
Authors: Xinyue Liu, Niloofar Mireshghallah, Jane C. Ginsburg, Tuhin Chakrabarty
Abstract: Frontier LLM companies have repeatedly assured courts and regulators that their models do not store copies of training data. They further rely on safety alignment strategies via RLHF, system prompts, and output filters to block verbatim regurgitation of copyrighted works, and have cited the efficacy of these measures in their legal defenses against copyright infringement claims. We show that finetuning bypasses these protections: by training models to expand plot summaries into full text, a task naturally suited for commercial writing assistants, we cause GPT-4o, Gemini-2.5-Pro, and DeepSeek-V3.1 to reproduce up to 85-90% of held-out copyrighted books, with single verbatim spans exceeding 460 words, using only semantic descriptions as prompts and no actual book text. This extraction generalizes across authors: finetuning exclusively on Haruki Murakami's novels unlocks verbatim recall of copyrighted books from over 30 unrelated authors. The effect is not specific to any training author or corpus: random author pairs and public-domain finetuning data produce comparable extraction, while finetuning on synthetic text yields near-zero extraction, indicating that finetuning on individual authors' works reactivates latent memorization from pretraining. Three models from different providers memorize the same books in the same regions ($r \ge 0.90$), pointing to an industry-wide vulnerability. Our findings offer compelling evidence that model weights store copies of copyrighted works and that the security failures that manifest after finetuning on individual authors' works undermine a key premise of recent fair use rulings, where courts have conditioned favorable outcomes on the adequacy of measures preventing reproduction of protected expression.
Authors: Kemal Kirtac
Abstract: This paper studies whether a lightweight trained aggregator can combine diverse zero-shot large language model judgments into a stronger downstream signal for corporate disclosure classification. Zero-shot LLMs can read disclosures without task-specific fine-tuning, but their predictions often vary across prompts, reasoning styles, and model families. I address this problem with a multi-agent framework in which three zero-shot agents independently read each disclosure and output a sentiment label, a confidence score, and a short rationale. A logistic meta-classifier then aggregates these signals to predict next-day stock return direction. I use a sample of 18,420 U.S. corporate disclosures issued by Nasdaq and S&P 500 firms between 2018 and 2024, matched to next-day stock returns. Results show that the trained aggregator outperforms all single agents, majority vote, confidence-weighted voting, and a FinBERT baseline. Balanced accuracy rises from 0.561 for the best single agent to 0.612 for the trained aggregator, with the largest gains in disclosures combining strong current performance with weak guidance or elevated risk. The results suggest that zero-shot LLM agents capture complementary financial signals and that supervised aggregation can turn cross-agent disagreement into a more useful classification target.
Authors: Abed K. Musaffar, Ambuj Singh, Francesco Bullo
Abstract: Large language models (LLMs) are increasingly deployed in human-AI teams as support agents for complex tasks such as information retrieval, programming, and decision-making assistance. While these agents' autonomy and contextual knowledge enables them to be useful, it also exposes them to a broad range of attacks, including data poisoning, prompt injection, and even prompt engineering. Through these attack vectors, malicious actors can manipulate an LLM agent to provide harmful information, potentially manipulating human agents to make harmful decisions. While prior work has focused on LLMs as attack targets or adversarial actors, this paper studies their potential role as defensive supervisors within mixed human-AI teams. Using a dataset consisting of multi-party conversations and decisions for a real human-AI team over a 25 round horizon, we formulate the problem of malicious behavior detection from interaction traces. We find that LLMs are capable of identifying malicious behavior in real-time, and without task-specific information, indicating the potential for task-agnostic defense. Moreover, we find that the malicious behavior of interest is not easily identified using simple heuristics, further suggesting the introduction of LLM defenders could render human teams more robust to certain classes of attack.
Authors: Valentina Kuskova, Dmitry Zaytsev, Michael Coppedge
Abstract: Time-varying causal models provide a powerful framework for studying dynamic scientific systems, yet most existing approaches assume that the underlying causal network is known a priori - an assumption rarely satisfied in real-world domains where causal structure is uncertain, evolving, or only indirectly observable. This limits the applicability of dynamic causal inference in many scientific settings. We propose Dynamic Causal Network Autoregression (DCNAR), a two-stage neural causal modeling framework that integrates data-driven causal discovery with time-varying causal inference. In the first stage, a neural autoregressive causal discovery model learns a sparse directed causal network from multivariate time series. In the second stage, this learned structure is used as a structural prior for a time-varying neural network autoregression, enabling dynamic estimation of causal influence without requiring pre-specified network structure. We evaluate the scientific validity of DCNAR using behavioral diagnostics that assess causal necessity, temporal stability, and sensitivity to structural change, rather than predictive accuracy alone. Experiments on multi-country panel time-series data demonstrate that learned causal networks yield more stable and behaviorally meaningful dynamic causal inferences than coefficient-based or structure-free alternatives, even when forecasting performance is comparable. These results position DCNAR as a general framework for using AI as a scientific instrument for dynamic causal reasoning under structural uncertainty.
Authors: Zelin Wan, Jin-Hee Cho, Mu Zhu, Ahmed H. Anwar, Charles Kamhoua, Munindar P. Singh
Abstract: Unmanned Aerial Vehicles (UAVs) are valuable for mission-critical systems like surveillance, rescue, or delivery. Not surprisingly, such systems attract cyberattacks, including Denial-of-Service (DoS) attacks to overwhelm the resources of mission drones (MDs). How can we defend UAV mission systems against DoS attacks? We adopt cyber deception as a defense strategy, in which honey drones (HDs) are proposed to bait and divert attacks. The attack and deceptive defense hinge upon radio signal strength: The attacker selects victim MDs based on their signals, and HDs attract the attacker from afar by emitting stronger signals, despite this reducing battery life. We formulate an optimization problem for the attacker and defender to identify their respective strategies for maximizing mission performance while minimizing energy consumption. To address this problem, we propose a novel approach, called HT-DRL. HT-DRL identifies optimal solutions without a long learning convergence time by taking the solutions of hypergame theory into the neural network of deep reinforcement learning. This achieves a systematic way to intelligently deceive attackers. We analyze the performance of diverse defense mechanisms under different attack strategies. Further, the HT-DRL-based HD approach outperforms existing non-HD counterparts up to two times better in mission performance while incurring low energy consumption.
Authors: Aarush Sinha, Rahul Seetharaman, Aman Bansal
Abstract: Hard negatives play a critical role in training and fine-tuning dense retrieval models, as they are semantically similar to positive documents yet non-relevant, and correctly distinguishing them is essential for improving retrieval accuracy. However, identifying effective hard negatives typically requires extensive ablation studies involving repeated fine-tuning with different negative sampling strategies and hyperparameters, resulting in substantial computational cost. In this paper, we introduce ECI: Effective Contrastive Information , a theoretically grounded metric grounded in Information Theory and Information Retrieval principles that enables practitioners to assess the quality of hard negatives prior to model fine-tuning. ECI evaluates negatives by optimizing the trade-off between Information Capacity the logarithmic bound on mutual information determined by set size and Discriminative Efficiency, a harmonic balance of Signal Magnitude (Hardness) and Safety (Max-Margin). Unlike heuristic approaches, ECI strictly penalizes unsafe, false-positive negatives prevalent in generative methods. We evaluate ECI across hard-negative sets mined or generated using BM25, cross-encoders, and large language models. Our results demonstrate that ECI accurately predicts downstream retrieval performance, identifying that hybrid strategies (BM25+Cross-Encoder) offer the optimal balance of volume and reliability, significantly reducing the need for costly end-to-end ablation studies.
Authors: Abhinaba Basu
Abstract: A single matrix out of 468 in GPT-2 Small can increase perplexity by 20,000x when compressed, revealing that transformer compression sensitivity spans five orders of magnitude. We map this sensitivity landscape across five architectures (117M-8B parameters), finding a consistent hierarchy: early-layer MLP up-projections are catastrophically sensitive while value projections compress nearly for free. This hierarchy is stable across compression levels, evaluation scales (2K-51K tokens), and datasets (WikiText-103, C4). Using Lyapunov stability theory, we show that residual connections contract compression errors by growing the hidden state faster than the error. Error contraction is necessary but not sufficient for compression tolerance: architecture-specific redundancy plays an equally important role, as demonstrated by the hybrid LFM2-2.6B degrading only 7x despite higher amplification than the fully-contracting GPT-2 Small (120x). Ten machine-checked Lean 4 theorems formalize per-matrix error bounds with no sorry markers; all bounds produce zero violations across 14,040+ configurations. We validate with downstream task evaluation (HellaSwag, ARC-Easy, Winogrande), activation-aware pruning on two architectures, and a Compression Fragility Index that rank-orders model robustness.
Authors: Yuma Aoki, Joon Park, Koh Takeuchi, Hisashi Kashima, Shinya Akimoto, Ryuichi Hashimoto, Takahiro Adachi, Takeshi Kishikawa, Takamitsu Sasaki
Abstract: This study addresses an important gap in time series outlier detection by proposing a novel problem setting: long-term outlier prediction. Conventional methods primarily focus on immediate detection by identifying deviations from normal patterns. As a result, their applicability is limited when forecasting outlier events far into the future. To overcome this limitation, we propose a simple and unsupervised two-layer method that is independent of specific models. The first layer performs standard outlier detection, and the second layer predicts future outlier scores based on the temporal structure of previously observed outliers. This framework enables not only pointwise detection but also long-term forecasting of outlier likelihoods. Experiments on synthetic datasets show that the proposed method performs well in both detection and prediction tasks. These findings suggest that the method can serve as a strong baseline for future work in outlier detection and forecasting.
Authors: Daniel Autenrieth
Abstract: This paper presents the first systematic measurement of educational alignment in Large Language Models. Using a Delphi-validated instrument comprising 48 items across eight educational-theoretical dimensions, the study reveals that GPT-5.1 exhibits highly coherent preference patterns (99.78% transitivity; 92.79% model accuracy) that largely align with humanistic educational principles where expert consensus exists. Crucially, divergences from expert opinion occur precisely in domains of normative disagreement among human experts themselves, particularly emotional dimensions and epistemic normativity. This raises a fundamental question for alignment research: When human values are contested, what should models be aligned to? The findings demonstrate that GPT-5.1 does not remain neutral in contested domains but adopts coherent positions, prioritizing emotional responsiveness and rejecting false balance. The methodology, combining Delphi consensus-building with Structured Preference Elicitation and Thurstonian Utility modeling, provides a replicable framework for domain-specific alignment evaluation beyond generic value benchmarks.
Authors: Rushikesh Deotale, Adithya Srinivasan, Yuan Tian, Tianyi Zhang, Pavlos Vlachos, Hector Gomez
Abstract: Finite element (FE) analysis guides the design and verification of nearly all manufactured objects. It is at the core of computational engineering, enabling simulation of complex physical systems, from fluids and solids to multiphysics systems. However, implementing FE codes and analyzing simulation results demands expertise across numerical analysis, continuum mechanics, and programming. Conventional Large Language Models (LLMs) can generate FE code, but they hallucinate, lack awareness of variational structures, and cannot close the loop from problem statement to a verified solution. Here, we propose ALL-FEM, an autonomous simulation system that integrates agentic AI with domain-specific, fine-tuned LLMs for FEniCS code generation across solid, fluid, and multiphysics applications. We construct a corpus of 1000+ verified FEniCS scripts by combining 500+ curated expert codes with a retrieval-augmented, multi-LLM pipeline that generates and filters codes for diverse PDEs, geometries, and boundary conditions. We used the corpus to fine-tune LLMs with 3B to 120B parameters. Our agentic framework orchestrates specialized agents, powered by fine-tuned LLMs, to formulate problems as PDEs, generate and debug code and visualize the results. We evaluated the system on 39 benchmarks that include problems of linear/nonlinear elasticity, plasticity, Newtonian/non-Newtonian flow, thermofluids, fluid-structure interaction, phase separation, and transport on moving domains. Embedded in a multi-agent workflow with runtime feedback, the best fine-tuned model (GPT OSS 120B) achieves code-level success of 71.79%, outperforming a non-agentic deployment of GPT 5 Thinking. By showing that relatively small, fine-tuned LLMs, orchestrated through agentic frameworks, can automate FE workflows, ALL-FEM offers a blueprint for autonomous simulation systems in computational science and engineering.
Authors: Jinquan Zheng, Jia Yuan, Jiacheng Yao, Chenyang Gu, Pujun Zheng, Guoxiu He
Abstract: Large language models (LLMs) used for multiple-choice and pairwise evaluation tasks often exhibit selection bias due to non-semantic factors like option positions and label symbols. Existing inference-time debiasing is costly and may harm reasoning, while pointwise training ignores that the same question should yield consistent answers across permutations. To address this issue, we propose Permutation-Aware Group Relative Policy Optimization (PA-GRPO), which mitigates selection bias by enforcing permutation-consistent semantic reasoning. PA-GRPO constructs a permutation group for each instance by generating multiple candidate permutations, and optimizes the model using two complementary mechanisms: (1) cross-permutation advantage, which computes advantages relative to the mean reward over all permutations of the same instance, and (2) consistency-aware reward, which encourages the model to produce consistent decisions across different permutations. Experimental results demonstrate that PA-GRPO outperforms strong baselines across seven benchmarks, substantially reducing selection bias while maintaining high overall performance. The code will be made available on Github (https://github.com/ECNU-Text-Computing/PA-GRPO).
Authors: Yunhai Hu, Junwei Zhou, Yumo Cao, Yitao Long, Yiwei Xu, Qiyi Jiang, Weiyao Wang, Xiaoyu Cao, Zhen Sun, Yiran Zou, Nan Du
Abstract: Effective retrieval in complex domains requires bridging the gap between structured metadata and unstructured content. Existing systems typically isolate these capabilities, relying on either symbolic filtering or vector similarity, failing to capture their interplay. In this work, we propose DSL-R1, a unified framework that synergizes logical reasoning with semantic matching via a novel Domain-Specific Language (DSL). By embedding vector primitives within SQL-style operators, our approach leverages the complementary strengths of symbolic precision and semantic coverage. We further introduce a reinforcement learning mechanism where rule-based execution feedback and retrieval quality rewards jointly optimize the DSL generation, balancing structural correctness and semantic alignment. Evaluations on a large-scale industrial email benchmark demonstrate that DSL-R1 achieves a +12.3% improvement in Hit@1/3, consistently outperforming decoupled baselines and establishing a robust paradigm for hybrid retrieval.
Authors: Shuwei Huang, Shizhuo Liu, Zijun Wei
Abstract: Diffusion-based image super-resolution (SR), which aims to reconstruct high-resolution (HR) images from corresponding low-resolution (LR) observations, faces a fundamental trade-off between inference efficiency and reconstruction quality. The state-of-the-art residual-shifting diffusion framework achieves efficient 4-step inference, yet suffers from severe performance degradation in compact sampling trajectories. This is mainly attributed to two core limitations: the inherent suboptimality of unconstrained random Gaussian noise in intermediate steps, which leads to error accumulation and insufficient LR prior guidance, and the initialization bias caused by naive bicubic upsampling. In this paper, we propose LPNSR, a prior-enhanced efficient diffusion framework to address these issues. We first mathematically derive the closed-form analytical solution of the optimal intermediate noise for the residual-shifting diffusion paradigm, and accordingly design an LR-guided multi-input-aware noise predictor to replace random Gaussian noise, embedding LR structural priors into the reverse process while fully preserving the framework's core efficient residual-shifting mechanism. We further mitigate initial bias with a high-quality pre-upsampling network to optimize the diffusion starting point. With a compact 4-step trajectory, LPNSR can be optimized in an end-to-end manner. Extensive experiments demonstrate that LPNSR achieves state-of-the-art perceptual performance on both synthetic and real-world datasets, without relying on any large-scale text-to-image priors. The source code of our method can be found at https://github.com/Faze-Hsw/LPNSR.
Authors: Wen Jiang, Kangyao Huang, Li Wang, Wang Xu, Wei Fan, Jinyuan Liu, Shaoyu Liu, Hanfang Liang, Hongwei Duan, Bin Xu, Xiangyang Ji
Abstract: UAVs play an important role in applications such as autonomous exploration, disaster response, and infrastructure inspection. However, UAV VLN in complex 3D environments remains challenging. A key difficulty is the structural representation mismatch between 2D visual perception and the 3D trajectory decision space, which limits spatial reasoning. To this end, we propose SpatialFly, a geometry-guided spatial representation framework for UAV VLN. Operating on RGB observations without explicit 3D reconstruction, SpatialFly introduces a geometry-guided 2D representation alignment mechanism. Specifically, the geometric prior injection module injects global structural cues into 2D semantic tokens to provide scene-level geometric guidance. The geometry-aware reparameterization module then aligns 2D semantic tokens with 3D geometric tokens through cross-modal attention, followed by gated residual fusion to preserve semantic discrimination. Experimental results show that SpatialFly consistently outperforms state-of-the-art UAV VLN baselines across both seen and unseen environments, reducing NE by 4.03m and improving SR by 1.27% over the strongest baseline on the unseen Full split. Additional trajectory-level analysis shows that SpatialFly produces trajectories with better path alignment and smoother, more stable motion.
Authors: Gia-Bao Doan, Nam-Khoa Huynh, Minh-Nhat-Huy Ho, Khanh-Thanh-Khoa Nguyen, Thanh-Hai Le
Abstract: The identification of hazardous driving behaviors from in-cabin video streams is essential for enhancing road safety and supporting the detection of traffic violations and unsafe driver actions. However, current temporal action localization techniques often struggle to balance accuracy with computational efficiency. In this work, we develop and evaluate a temporal action localization framework tailored for driver monitoring scenarios, particularly suitable for periodic inspection settings such as transportation safety checkpoints or fleet management assessment systems. Our approach follows a two-stage pipeline that combines VideoMAE-based feature extraction with an Augmented Self-Mask Attention (AMA) detector, enhanced by a Spatial Pyramid Pooling-Fast (SPPF) module to capture multi-scale temporal features. Experimental results reveal a distinct trade-off between model capacity and efficiency. At the feature extraction stage, the ViT-Giant backbone delivers higher representations with 88.09% Top-1 test accuracy, while the ViT-based variant proves to be a practical alternative, achieving 82.55% accuracy with significantly lower computational fine-tuning costs (101.85 GFLOPs/segment compared to 1584.06 GFLOPs/segment for Giant). In the downstream localization task, the integration of SPPF consistently improves performance across all configurations. Notably, the ViT-Giant + SPPF model achieves a peak mAP of 92.67%, while the lightweight ViT-based configuration maintains robust results.
Authors: Bing Wang, Ximing Li, Changchun Li, Jinjin Chi, Tianze Li, Renchu Guan, Shengsheng Wang
Abstract: Nowadays, the widespread dissemination of misinformation across numerous social media platforms has led to severe negative effects on society. To address this challenge, the automatic detection of misinformation, particularly under multimedia scenarios, has gained significant attention from both academic and industrial communities, leading to the emergence of a research task known as Multimodal Misinformation Detection (MMD). Typically, current MMD approaches focus on capturing the semantic relationships and inconsistency between various modalities but often overlook certain critical indicators within multimodal content. Recent research has shown that manipulated features within visual content in social media articles serve as valuable clues for MMD. Meanwhile, we argue that the potential intentions behind the manipulation, e.g., harmful and harmless, also matter in MMD. Therefore, in this study, we aim to identify such multimodal misinformation by capturing two types of features: manipulation features, which represent if visual content has been manipulated, and intention features, which assess the nature of these manipulations, distinguishing between harmful and harmless intentions. Unfortunately, the manipulation and intention labels that supervise these features to be discriminative are unknown. To address this, we introduce two weakly supervised indicators as substitutes by incorporating supplementary datasets focused on image manipulation detection and framing two different classification tasks as positive and unlabeled learning issues. With this framework, we introduce an innovative MMD approach, titled Harmful Visual Content Manipulation Matters in MMD (HAVC-M4 D). Comprehensive experiments conducted on four prevalent MMD datasets indicate that HAVC-M4 D significantly and consistently enhances the performance of existing MMD methods.
Authors: Ping Guo, Chengzhou Li, Guanchen Meng, Qi Jia, Jinyuan Liu, Zhu Liu, Yu Liu, Zhongxuan Luo, Xin Fan
Abstract: As one of the most important underwater sensing technologies, forward-looking sonar exhibits unique imaging characteristics. Sonar images are often affected by severe speckle noise, low texture contrast, acoustic shadows, and geometric distortions. These factors make it difficult for traditional teacher-student frameworks to achieve satisfactory performance in sonar semantic segmentation tasks under extremely limited labeled data conditions. To address this issue, we propose a Collaborative Teacher Semantic Segmentation Framework for forward-looking sonar images. This framework introduces a multi-teacher collaborative mechanism composed of one general teacher and multiple sonar-specific teachers. By adopting a multi-teacher alternating guidance strategy, the student model can learn general semantic representations while simultaneously capturing the unique characteristics of sonar images, thereby achieving more comprehensive and robust feature modeling. Considering the challenges of sonar images, which can lead teachers to generate a large number of noisy pseudo-labels, we further design a cross-teacher reliability assessment mechanism. This mechanism dynamically quantifies the reliability of pseudo-labels by evaluating the consistency and stability of predictions across multiple views and multiple teachers, thereby mitigating the negative impact caused by noisy pseudo-labels. Notably, on the FLSMD dataset, when only 2% of the data is labeled, our method achieves a 5.08% improvement in mIoU compared to other state-of-the-art approaches.
Authors: Tianle Yang, Chengzhe Sun, Phil Rose, Cassandra L. Jacobs, Siwei Lyu
Abstract: This study proposes a segmental-level prosodic probing framework to evaluate neural TTS models' ability to reproduce consonant-induced f0 perturbation, a fine-grained segmental-prosodic effect that reflects local articulatory mechanisms. We compare synthetic and natural speech realizations for thousands of words, stratified by lexical frequency, using Tacotron 2 and FastSpeech 2 trained on the same speech corpus (LJ Speech). These controlled analyses are then complemented by a large-scale evaluation spanning multiple advanced TTS systems. Results show accurate reproduction for high-frequency words but poor generalization to low-frequency items, suggesting that the examined TTS architectures rely more on lexical-level memorization than on abstract segmental-prosodic encoding. This finding highlights a limitation in such TTS systems' ability to generalize prosodic detail beyond seen data. The proposed probe offers a linguistically informed diagnostic framework that may inform future TTS evaluation methods, and has implications for interpretability and authenticity assessment in synthetic speech.
Authors: Tin Van Huynh, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen
Abstract: High-quality text representations are crucial for natural language understanding (NLU), but low-resource languages like Vietnamese face challenges due to limited annotated data. While pre-trained models like PhoBERT and CafeBERT perform well, their effectiveness is constrained by data scarcity. Contrastive learning (CL) has recently emerged as a promising approach for improving sentence representations, enabling models to effectively distinguish between semantically similar and dissimilar sentences. We propose ViCLSR (Vietnamese Contrastive Learning for Sentence Representations), a novel supervised contrastive learning framework specifically designed to optimize sentence embeddings for Vietnamese, leveraging existing natural language inference (NLI) datasets. Additionally, we propose a process to adapt existing Vietnamese datasets for supervised learning, ensuring compatibility with CL methods. Our experiments demonstrate that ViCLSR significantly outperforms the powerful monolingual pre-trained model PhoBERT on five benchmark NLU datasets such as ViNLI (+6.97% F1), ViWikiFC (+4.97% F1), ViFactCheck (+9.02% F1), UIT-ViCTSD (+5.36% F1), and ViMMRC2.0 (+4.33% Accuracy). ViCLSR shows that supervised contrastive learning can effectively address resource limitations in Vietnamese NLU tasks and improve sentence representation learning for low-resource languages. Furthermore, we conduct an in-depth analysis of the experimental results to uncover the factors contributing to the superior performance of contrastive learning models. ViCLSR is released for research purposes in advancing natural language processing tasks.
Authors: Dina Salama, Mohamed Mahmoud, Nourhan Bayasi, David Liu, Ilker Hacihaliloglu
Abstract: Thyroid ultrasound is the first-line exam for assessing thyroid nodules and determining whether biopsy is warranted. In routine reporting, radiologists produce two coupled outputs: a nodule contour for measurement and a TI-RADS risk category based on sonographic criteria. Yet both contouring style and risk grading vary across readers, creating inconsistent supervision that can degrade standard learning pipelines. In this paper, we address this workflow with a clinically guided multitask framework that jointly predicts the nodule mask and TI-RADS category within a single model. To ground risk prediction in clinically meaningful evidence, we guide the classification embedding using a compact TI-RADS aligned radiomics target during training, while preserving complementary deep features for discriminative performance. However, under annotator variability, naive multitask optimization often fails not because the tasks are unrelated, but because their gradients compete within the shared representation. To make this competition explicit and controllable, we introduce RLAR, a representation-level adversarial gradient regularizer. Rather than performing parameter-level gradient surgery, RLAR uses each task's normalized adversarial direction in latent space as a geometric probe of task sensitivity and penalizes excessive angular alignment between task-specific adversarial directions. On a public TI-RADS dataset, our clinically guided multitask model with RLAR consistently improves risk stratification while maintaining segmentation quality compared to single-task training and conventional multitask baselines. Code and pretrained models will be released.
Authors: Tasmay Pankaj Tibrewal, Pritish Saha, Ankit Meda, Kunal Singh, Pradeep Moturi
Abstract: Transformers lack an explicit architectural mechanism for storing and organizing knowledge acquired during training. We introduce learnable sparse memory banks: a set of latent tokens, randomly initialized and trained end-to-end, that transformer layers query via cross-attention to retrieve stored knowledge. To scale memory capacity without prohibitive attention costs, we propose chapter-based routing inspired by Mixture-of-Experts architectures, partitioning the memory bank into chapters and training a router to select relevant subsets per input. This enables scaling to 262K memory tokens while maintaining tractable computation. We evaluate our approach against standard transformers (in iso-FLOP settings) on pre-training and instruction fine-tuning across relevant benchmarks. Our models surpass iso-FLOP baselines suggesting scope for a new axis of scaling, demonstrating that explicit associative memory provides complementary capacity to what is captured implicitly in model parameters. Additionally, we observe improved knowledge retention under continued training, with robustness to forgetting when transitioning between training phases (e.g., pretraining to instruction fine-tuning).
Authors: He Wang, Tianyang Xu, Zhangyong Tang, Xiao-Jun Wu, Josef Kittler
Abstract: Due to the limited availability of paired multi-modal data, multi-modal trackers are typically built by adopting pre-trained RGB models with parameter-efficient fine-tuning modules. However, these fine-tuning methods overlook advanced adaptations for applying RGB pre-trained models and fail to modulate a single specific modality, cross-modal interactions, and the prediction head. To address the issues, we propose to perform Progressive Adaptation for Multi-Modal Tracking (PATrack). This innovative approach incorporates modality-dependent, modality-entangled, and task-level adapters, effectively bridging the gap in adapting RGB pre-trained networks to multi-modal data through a progressive strategy. Specifically, modality-specific information is enhanced through the modality-dependent adapter, decomposing the high- and low-frequency components, which ensures a more robust feature representation within each modality. The inter-modal interactions are introduced in the modality-entangled adapter, which implements a cross-attention operation guided by inter-modal shared information, ensuring the reliability of features conveyed between modalities. Additionally, recognising that the strong inductive bias of the prediction head does not adapt to the fused information, a task-level adapter specific to the prediction head is introduced. In summary, our design integrates intra-modal, inter-modal, and task-level adapters into a unified framework. Extensive experiments on RGB+Thermal, RGB+Depth, and RGB+Event tracking tasks demonstrate that our method shows impressive performance against state-of-the-art methods. Code is available at https://github.com/ouha1998/Learning-Progressive-Adaptation-for-Multi-Modal-Tracking.
URLs: https://github.com/ouha1998/Learning-Progressive-Adaptation-for-Multi-Modal-Tracking.
Authors: Long Xu, Junping Guo, Jianbo Zhao, Jianbo Lu, Yuzhong Peng
Abstract: Molecular property prediction constitutes a cornerstone of drug discovery and materials science, necessitating models capable of disentangling complex structure-property relationships across diverse molecular modalities. Existing approaches frequently exhibit entangled representations--conflating structural, chemical, and functional factors--thereby limiting interpretability and transferability. Furthermore, conventional methods inadequately exploit complementary information from graphs, sequences, and geometries, often relying on naive concatenation that neglects inter-modal dependencies. In this work, we propose DMMRL, which employs variational autoencoders to disentangle molecular representations into shared (structure-relevant) and private (modality-specific) latent spaces, enhancing both interpretability and predictive performance. The proposed variational disentanglement mechanism effectively isolates the most informative features for property prediction, while orthogonality and alignment regularizations promote statistical independence and cross-modal consistency. Additionally, a gated attention fusion module adaptively integrates shared representations, capturing complex inter-modal relationships. Experimental validation across seven benchmark datasets demonstrates DMMRL's superior performance relative to state-of-the-art approaches. The code and data underlying this article are freely available at https://github.com/xulong0826/DMMRL.
Authors: Yu-Wen Tseng, Xingyi Zheng, Ya-Chen Wu, I-Bin Liao, Yung-Hui Li, Hong-Han Shuai, Wen-Huang Cheng
Abstract: Test-time adaptation (TTA) adapts pre-trained models to distribution shifts at inference using only unlabeled test data. Under the Practical TTA (PTTA) setting, where test streams are temporally correlated and non-i.i.d., memory has become an indispensable component for stable adaptation, yet existing methods universally store amples in a single unstructured pool. We show that this single-cluster design is fundamentally mismatched to PTTA: a stream clusterability analysis reveals that test streams are inherently multi-modal, with the optimal number of mixture components consistently far exceeding one. To close this structural gap, we propose Multi-Cluster Memory (MCM), a plug-and-play framework that organizes stored samples into multiple clusters using lightweight pixel-level statistical descriptors. MCM introduces three complementary mechanisms: descriptor-based cluster assignment to capture distinct distributional modes, Adjacent Cluster Consolidation (ACC) to bound memory usage by merging the most similar temporally adjacent clusters, and Uniform Cluster Retrieval (UCR) to ensure balanced supervision across all modes during adaptation. Integrated with three contemporary TTA methods on CIFAR-10-C, CIFAR-100-C, ImageNet-C, and DomainNet, MCM achieves consistent improvements across all 12 configurations, with gains up to 5.00% on ImageNet-C and 12.13% on DomainNet. Notably, these gains scale with distributional complexity: larger label spaces with greater multi-modality benefit most from multi-cluster organization. GMM-based memory diagnostics further confirm that MCM maintains near-optimal distributional balance, entropy, and mode coverage, whereas single-cluster memory exhibits persistent imbalance and progressive mode loss. These results establish memory organization as a key design axis for practical test-time adaptation.
Authors: Peihan Ye, Alfreds Lapkovskis, Alaa Saleh, Qiyang Zhang, Praveen Kumar Donta
Abstract: The computational demands of modern AI services are increasingly shifting execution beyond centralized clouds toward a computing continuum spanning edge and end devices. However, the scale, heterogeneity, and cross-layer dependencies of these environments make resilience difficult to maintain. Existing fault-management methods are often too static, fragmented, or heavy to support timely self-healing, especially under noisy logs and edge resource constraints. To address these limitations, this paper presents NeSy-Edge, a neuro-symbolic framework for trustworthy self-healing in the computing continuum. The framework follows an edge-first design, where a resource-constrained edge node performs local perception and reasoning, while a cloud model is invoked only at the final diagnosis stage. Specifically, NeSy-Edge converts raw runtime logs into structured event representations, builds a prior-constrained sparse symbolic causal graph, and integrates causal evidence with historical troubleshooting knowledge for root-cause analysis and recovery recommendation. We evaluate our work on representative Loghub datasets under multiple levels of semantic noise, considering parsing quality, causal reasoning, end-to-end diagnosis, and edge-side resource usage. The results show that NeSy-Edge remains robust even at the highest noise level, achieving up to 75% root-cause analysis accuracy and 65% end-to-end accuracy while operating within about 1500 MB of local memory.
Authors: Octavian Untila
Abstract: An autonomous AI ecosystem (SUBSTRATE S3), generating product specifications without explicit instructions about formal methods, independently proposed the use of Z3 SMT solver across six distinct domains of AI safety: verification of LLM-generated code, tool API safety for AI agents, post-distillation reasoning correctness, CLI command validation, hardware assembly verification, and smart contract safety. These convergent discoveries, occurring across 8 products over 13 days with Jaccard similarity below 15% between variants, suggest that formal verification is not merely a useful technique for AI safety but an emergent property of any sufficiently complex system reasoning about its own safety. We propose a unified framework (substrate-guard) that applies Z3-based verification across all six output classes through a common API, and evaluate it on 181 test cases across five implemented domains, achieving 100% classification accuracy with zero false positives and zero false negatives. Our framework detected real bugs that empirical testing would miss, including an INT_MIN overflow in branchless RISC-V assembly and mathematically proved that unconstrained string parameters in tool APIs are formally unverifiable.
Authors: Feng Liu, Jian Xu, Xin Cui, Xinghao Wang, Zijie Guo, Jiong Wang, S. Mostafa Mousavi, Xinyu Gu, Hao Chen, Ben Fei, Lihua Fang, Fenghua Ling, Zefeng Li, Lei Bai
Abstract: Inferring the physical mechanisms that govern earthquake sequences from indirect geophysical observations remains difficult, particularly across tectonically distinct environments where similar seismic patterns can reflect different underlying processes. Current interpretations rely heavily on the expert synthesis of catalogs, spatiotemporal statistics, and candidate physical models, limiting reproducibility and the systematic transfer of insight across settings. Here we present TRACE (Trans-perspective Reasoning and Automated Comprehensive Evaluator), a multi-agent system that combines large language model planning with formal seismological constraints to derive auditable, physically grounded mechanistic inference from raw observations. Applied to the 2019 Ridgecrest sequence, TRACE autonomously identifies stress-perturbation-induced delayed triggering, resolving the cascading interaction between the Mw 6.4 and Mw 7.1 mainshocks; in the Santorini-Kolumbo case, the system identifies a structurally guided intrusion model, distinguishing fault-channeled episodic migration from the continuous propagation expected in homogeneous crustal failure. By providing a generalizable logical infrastructure for interpreting heterogeneous seismic phenomena, TRACE advances the field from expert-dependent analysis toward knowledge-guided autonomous discovery in Earth sciences.
Authors: Zhiqiang He
Abstract: This paper investigates the fundamental mechanisms driving plasticity loss in deep reinforcement learning (RL), a critical challenge where neural networks lose their ability to adapt to non-stationary environments. While existing research often relies on descriptive metrics like dormant neurons or effective rank, these summaries fail to explain the underlying optimization dynamics. We propose the Optimization-Centric Plasticity (OCP) hypothesis, which posits that plasticity loss arises because optimal points from previous tasks become poor local optima for new tasks, trapping parameters during task transitions and hindering subsequent learning. We theoretically establish the equivalence between neuron dormancy and zero-gradient states, demonstrating that the absence of gradient signals is the primary driver of dormancy. Our experiments reveal that plasticity loss is highly task-specific; notably, networks with high dormancy rates in one task can achieve performance parity with randomly initialized networks when switched to a significantly different task, suggesting that the network's capacity remains intact but is inhibited by the specific optimization landscape. Furthermore, our hypothesis elucidates why parameter constraints mitigate plasticity loss by preventing deep entrenchment in local optima. Validated across diverse non-stationary scenarios, our findings provide a rigorous optimization-based framework for understanding and restoring network plasticity in complex RL domains.
Authors: Kwanyoung Kim, Byeongsu Sim
Abstract: Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models with human preferences, inspiring the development of reward-centric diffusion reinforcement learning (RDRL) to achieve similar alignment and controllability. While diffusion models can generate high-quality outputs, RDRL remains susceptible to reward hacking, where the reward score increases without corresponding improvements in perceptual quality. We demonstrate that this vulnerability arises from the non-robustness of reward model gradients, particularly when the reward landscape with respect to the input image is sharp. To mitigate this issue, we introduce methods that exploit gradients from a robustified reward model without requiring its retraining. Specifically, we employ gradients from a flattened reward model, obtained through parameter perturbations of the diffusion model and perturbations of its generated samples. Empirically, each method independently alleviates reward hacking and improves robustness, while their joint use amplifies these benefits. Our resulting framework, RSA-FT (Reward Sharpness-Aware Fine-Tuning), is simple, broadly compatible, and consistently enhances the reliability of RDRL.
Authors: Andrei Baroian, Rutger Berger
Abstract: Reinforcement learning with verifiable rewards (RLVR) plays a crucial role in expanding the capacities of LLM reasoning, but GRPO-style training is dominated by expensive rollouts and wastes compute on unusable prompts. We propose Prompt Replay, an overhead-free online data selection method for GRPO that reuses prompts only (not trajectories), to preserve on-policy optimization. After each step, we insert prompts with medium difficulty into a buffer, and prioritize prompts closer to a pass rate of 0.5 (half answers correct, half wrong) to maximize the advantage, thus learning signal. Training batches are formed by mixing reused prompts with fresh samples, with cooldown steps and max reuse times controlling aggressiveness vs risk of overfitting. Across multiple model families (Llama-3.2- 3B, Qwen3-8B) and training datasets (Dolci, Polaris), evaluated using average accuracy on six standard math benchmarks, Prompt Replay reduces zero-variance prompts, increases mean absolute advantage and shows faster initial accuracy gains. Yet, it plateaus and converges with the baseline, as too aggressive configuration was used. The method is most efficient when the rollouts are the primary bottleneck and the dataset is difficult for the model. We additionally observe that Qwen2.5-Math can exhibit spurious-reward effects that invalidates ablations, raising a warning signal for using it as a sole testbed for GRPO method research.
Authors: Miryala Sathvika, Rudra Dhar, Karthik Vaidhyanathan
Abstract: Architecture views are essential for software architecture documentation, yet their manual creation is labor intensive and often leads to outdated artifacts. As systems grow in complexity, the automated generation of views from source code becomes increasingly valuable. Goal: We empirically evaluate the ability of LLMs and agentic approaches to generate architecture views from source code. Method: We analyze 340 open-source repositories across 13 experimental configurations using 3 LLMs with 3 prompting techniques and 2 agentic approaches, yielding 4,137 generated views. We evaluate the generated views by comparing them with the ground-truth using a combination of automated metrics complemented by human evaluations. Results: Prompting strategies offer marginal improvements. Few-shot prompting reduces clarity failures by 9.2% compared to zero-shot baselines. The custom agentic approach consistently outperforms the general-purpose agent, achieving the best clarity (22.6% failure rate) and level-of-detail success (50%). Conclusions: LLM and agentic approaches demonstrate capabilities in generating syntactically valid architecture views. However, they consistently exhibit granularity mismatches, operating at the code level rather than architectural abstractions. This suggests that there is still a need for human expertise, positioning LLMs and agents as assistive tools rather than autonomous architects.
Authors: Sai Koneru, Jian Wu, Sarah Rajtmajer
Abstract: Extracting hypotheses and their supporting statistical evidence from full-text scientific articles is central to the synthesis of empirical findings, but remains difficult due to document length and the distribution of scientific arguments across sections of the paper. The work studies a sequential full-text extraction setting, where the statement of a primary finding in an article's abstract is linked to (i) a corresponding hypothesis statement in the paper body and (ii) the statistical evidence that supports or refutes that hypothesis. This formulation induces a challenging within-document retrieval setting in which many candidate paragraphs are topically related to the finding but differ in rhetorical role, creating hard negatives for retrieval and extraction. Using a two-stage retrieve-and-extract framework, we conduct a controlled study of retrieval design choices, varying context quantity, context quality (standard Retrieval Augmented Generation, reranking, and a fine-tuned retriever paired with reranking), as well as an oracle paragraph setting to separate retrieval failures from extraction limits across four Large Language Model extractors. We find that targeted context selection consistently improves hypothesis extraction relative to full-text prompting, with gains concentrated in configurations that optimize retrieval quality and context cleanliness. In contrast, statistical evidence extraction remains substantially harder. Even with oracle paragraphs, performance remains moderate, indicating persistent extractor limitations in handling hybrid numeric-textual statements rather than retrieval failures alone.
Authors: Qiuchi Xiang, Haoxuan Qu, Hossein Rahmani, Jun Liu
Abstract: Multi-agent discussions have been widely adopted, motivating growing efforts to develop attacks that expose their vulnerabilities. In this work, we study a practical yet largely unexplored attack scenario, the discussion-monitored scenario, where anomaly detectors continuously monitor inter-agent communications and block detected adversarial messages. Although existing attacks are effective without discussion monitoring, we show that they exhibit detectable patterns and largely fail under such monitoring constraints. But does this imply that monitoring alone is sufficient to secure multi-agent discussions? To answer this question, we develop a novel attack method explicitly tailored to the discussion-monitored scenario. Extensive experiments demonstrate that effective attacks remain possible even under continuous monitoring, indicating that monitoring alone does not eliminate adversarial risks.
Authors: Tian Xia, Matthew Sinclair, Andreas Schuh, Fabio De Sousa Ribeiro, Raghav Mehta, Rajat Rasal, Esther Puyol-Ant\'on, Samuel Gerber, Kersten Petersen, Michiel Schaap, Ben Glocker
Abstract: Counterfactual image generation enables controlled data augmentation, bias mitigation, and disease modeling. However, existing methods guided by external classifiers or regressors are limited to subject-level factors (e.g., age) and fail to produce localized structural changes, often resulting in global artifacts. Pixel-level guidance using segmentation masks has been explored, but requires user-defined counterfactual masks, which are tedious and impractical. Segmentor-guided Counterfactual Fine-Tuning (Seg-CFT) addressed this by using segmentation-derived measurements to supervise structure-specific variables, yet it remains restricted to global interventions. We propose Positional Seg-CFT, which subdivides each structure into regional segments and derives independent measurements per region, enabling spatially localized and anatomically coherent counterfactuals. Experiments on coronary CT angiography show that Pos-Seg-CFT generates realistic, region-specific modifications, providing finer spatial control for modeling disease progression.
Authors: Di Lu, Yongzhi Liao, Xutong Mu, Lele Zheng, Ke Cheng, Xuewen Dong, Yulong Shen, Jianfeng Ma
Abstract: Host-acting agents promise a convenient interaction model in which users specify goals and the system determines how to realize them. We argue that this convenience introduces a distinct security problem: semantic under-specification in goal specification. User instructions are typically goal-oriented, yet they often leave process constraints, safety boundaries, persistence, and exposure insufficiently specified. As a result, the agent must complete missing execution semantics before acting, and this completion can produce risky host-side plans even when the user-stated goal is benign. In this paper, we develop a semantic threat model, present a taxonomy of semantic-induced risky completion patterns, and study the phenomenon through an OpenClaw-centered case study and execution-trace analysis. We further derive defense design principles for making execution boundaries explicit and constraining risky completion. These findings suggest that securing host-acting agents requires governing not only which actions are allowed at execution time, but also how goal-only instructions are translated into executable plans.
Authors: Zhongyang Li, Yaqian Li, Faming Fang, Rinyoichi Takezoe, Zi-Hao Bo, Cheng Qian, Mo Guang, Guixu Zhang, Kaiwen Long
Abstract: Multimodal large language models suffer from severe computational and memory bottlenecks, as the number of visual tokens far exceeds that of textual tokens. While recent methods employ projector modules to align and compress visual tokens into text-aligned features, they typically depend on fixed heuristics that limit adaptability across diverse scenarios. In this paper, we first propose Query Guided Mixture-of-Projector (QMoP), a novel and flexible framework that adaptively compresses visual tokens via three collaborative branches: (1) a pooling-based branch for coarse-grained global semantics, (2) a resampler branch for extracting high-level semantic representations, and (3) a pruning-based branch for fine-grained token selection to preserve critical visual detail. To adaptively coordinate these branches, we introduce the Query Guided Router (QGR), which dynamically selects and weights the outputs from different branches based on both visual input and textual queries. A Mixture-of-Experts-style fusion mechanism is designed to aggregate the outputs, harnessing the strengths of each strategy while suppressing noise. To systematically evaluate the effects of Visual Token Compression, we also develop VTCBench, a dedicated benchmark for evaluating the information loss induced by visual token compression. Extensive experiments demonstrate that despite relying on fundamental compression modules, QMoP outperforms strong baselines and delivers significant savings in memory, computation, and inference time.
Authors: Osamu Hirose, Emanuele Rodola
Abstract: Nonrigid registration is conventionally divided into point set registration, which aligns sparse geometries, and image registration, which aligns continuous intensity fields on regular grids. However, this dichotomy creates a critical bottleneck for emerging scientific data, such as spatial transcriptomics, where high-dimensional vector-valued functions, e.g., gene expression, are defined on irregular, sparse manifolds. Consequently, researchers currently face a forced choice: either sacrifice single-cell resolution via voxelization to utilize image-based tools, or ignore the critical functional signal to utilize geometric tools. To resolve this dilemma, we propose Domain Elastic Transform (DET), a grid-free probabilistic framework that unifies geometric and functional alignment. By treating data as functions on irregular domains, DET registers high-dimensional signals directly without binning. We formulate the problem within a rigorous Bayesian framework, modeling domain deformation as an elastic motion guided by a joint spatial-functional likelihood. The method is fully unsupervised and scalable, utilizing feature-sensitive downsampling to handle massive atlases. We demonstrate that DET achieves 92\% topological preservation on MERFISH data where state-of-the-art optimal transport methods struggle ($<$5\%), and successfully registers whole-embryo Stereo-seq atlases across developmental stages -- a task involving massive scale and complex nonrigid growth. The implementation of DET is available on {https://github.com/ohirose/bcpd} (since Mar, 2025).
Authors: Zihan Fang, Qianru Wang, Haonan An, Zheng Lin, Yiqin Deng, Xianhao Chen, Yuguang Fang
Abstract: Large language models (LLMs) increasingly adopt Mixture-of-Experts (MoE) architectures to scale model capacity while reducing computation. Fine-tuning these MoE-based LLMs often requires access to distributed and privacy-sensitive data, making centralized fine-tuning impractical. Federated learning (FL) therefore provides a paradigm to collaboratively fine-tune MoE-based LLMs, enabling each client to integrate diverse knowledge without compromising data privacy. However, the integration of MoE-based LLM fine-tuning into FL encounters two critical aggregation challenges due to inherent data heterogeneity across clients: (i) divergent local data distributions drive clients to develop distinct gating preference for localized expert selection, causing direct parameter aggregation to produce a ``one-size-fits-none'' global gating network, and (ii) same-indexed experts develop disparate semantic roles across clients, leading to expert semantic blurring and the degradation of expert specialization. To address these challenges, we propose FedAlign-MoE, a federated aggregation alignment framework that jointly enforces routing consistency and expert semantic alignment. Specifically, FedAlign-MoE aggregates gating behaviors by aligning routing distributions through consistency weighting and optimizes local gating networks through distribution regularization, maintaining cross-client stability without overriding discriminative local preferences. Meanwhile, FedAlign-MoE explicitly quantifies semantic consistency among same-indexed experts across clients and selectively aggregates updates from semantically aligned clients, ensuring stable and specialized functional roles for global experts. Extensive experiments demonstrate that FedAlign-MoE outperforms state-of-the-art benchmarks, achieving faster convergence and superior accuracy in non-IID federated environments.
Authors: Pranav Hemanth, Sampriti Saha
Abstract: Large language models (LLMs) are increasingly deployed for extended, multi-topic conversations, yet the flat, append-only structure of current conversation interfaces introduces a fundamental limitation: all context accumulates in a single unbounded window, causing topically distinct threads to bleed into one another and progressively degrade response quality. We term this failure mode logical context poisoning. In this paper, we introduce the Conversation Tree Architecture (CTA), a hierarchical framework that organizes LLM conversations as trees of discrete, context-isolated nodes. Each node maintains its own local context window; structured mechanisms govern how context flows between parent and child nodes, downstream on branch creation and upstream on branch deletion. We additionally introduce volatile nodes, transient branches whose local context must be selectively merged upward or permanently discarded before purging. We formalize the architecture's primitives, characterize the open design problems in context flow, relate our framework to prior work in LLM memory management, and describe a working prototype implementation. The CTA provides a principled foundation for structured conversational context management and extends naturally to multi-agent settings.
Authors: Zongjie Li, Chaozheng Wang, Yuchong Xie, Pingchuan Ma, Shuai Wang
Abstract: Large Language Models are increasingly being considered for deployment in safety-critical military applications. However, current benchmarks suffer from structural blindspots that systematically overestimate model capabilities in real-world tactical scenarios. Existing frameworks typically ignore strict legal constraints based on International Humanitarian Law (IHL), omit edge computing limitations, lack robustness testing for fog of war, and inadequately evaluate explicit reasoning. To address these vulnerabilities, we present WARBENCH, a comprehensive evaluation framework establishing a foundational tactical baseline alongside four distinct stress testing dimensions. Through a large scale empirical evaluation of nine leading models on 136 high-fidelity historical scenarios, we reveal severe structural flaws. First, baseline tactical reasoning systematically collapses under complex terrain and high force asymmetry. Second, while state of the art closed source models maintain functional compliance, edge-optimized small models expose extreme operational risks with legal violation rates approaching 70 percent. Furthermore, models experience catastrophic performance degradation under 4-bit quantization and systematic information loss. Conversely, explicit reasoning mechanisms serve as highly effective structural safeguards against inadvertent violations. Ultimately, these findings demonstrate that current models remain fundamentally unready for autonomous deployment in high stakes tactical environments.
Authors: Soudeep Ghoshal, Sandipan Chakraborty, Pradipto Chowdhury, Himanshu Buckchash
Abstract: Machine learning techniques, such as Transformers and Long Short-Term Memory (LSTM) networks, play a crucial role in Symbolic Music Generation (SMG). Existing literature indicates a difference between LSTMs and Transformers regarding their ability to model local melodic continuity versus maintaining global structural coherence. However, their specific properties within the context of SMG have not been systematically studied. This paper addresses this gap by providing a fine-grained comparative analysis of LSTMs versus Transformers for SMG, examining local and global properties in detail using 17 musical quality metrics on the Deutschl dataset. We find that LSTM networks excel at capturing local patterns but fail to preserve long-range dependencies, while Transformers model global structure effectively but tend to produce irregular phrasing. Based on this analysis and leveraging their respective strengths, we propose a Hybrid architecture combining a Transformer Encoder with an LSTM Decoder and evaluate it against both baselines. We evaluated 1,000 generated melodies from each of the three architectures on the Deutschl dataset. The results show that the hybrid method achieves better local and global continuity and coherence compared to the baselines. Our work highlights the key characteristics of these models and demonstrates how their properties can be leveraged to design superior models. We also supported the experiments with ablation studies and human perceptual evaluations, which statistically support the findings and provide robust validation for this work.
Authors: Minjong Cheon
Abstract: Weather forecasting is a fundamental problem for protecting lives and infrastructure from high-impact atmospheric events. Recently, data-driven weather forecasting methods based on deep learning have demonstrated strong performance, often reaching accuracy levels competitive with operational numerical systems. However, many existing models rely on large-scale training regimes and compute-intensive architectures, which raises the practical barrier for academic groups with limited compute resources. Here we introduce Sonny, an efficient hierarchical transformer that achieves competitive medium-range forecasting performance while remaining feasible within reasonable compute budgets. At the core of Sonny is a two-stage StepsNet design: a narrow slow path first models large-scale atmospheric dynamics, and a subsequent full-width fast path integrates thermodynamic interactions. To stabilize medium-range rollout without an additional fine-tuning stage, we apply exponential moving average (EMA) during training. On WeatherBench2, Sonny yields robust medium-range forecast skill, remains competitive with operational baselines, and demonstrates clear advantages over FastNet, particularly at extended tropical lead times. In practice, Sonny can be trained to convergence on a single NVIDIA A40 GPU in approximately 5.5 days.
Authors: Zhengxian Wu, Kai Shi, Chuanrui Zhang, Zirui Liao, Jun Yang, Ni Yang, Qiuying Peng, Luyuan Zhang, Hangrui Xu, Tianhuang Su, Zhenyu Yang, Haonan Lu, Haoqian Wang
Abstract: Recent progress in multimodal large language models has led to strong performance on reasoning tasks, but these improvements largely rely on high-quality annotated data or teacher-model distillation, both of which are costly and difficult to scale. To address this, we propose an unsupervised self-evolution training framework for multimodal reasoning that achieves stable performance improvements without using human-annotated answers or external reward models. For each input, we sample multiple reasoning trajectories and jointly model their within group structure. We use the Actor's self-consistency signal as a training prior, and introduce a bounded Judge based modulation to continuously reweight trajectories of different quality. We further model the modulated scores as a group level distribution and convert absolute scores into relative advantages within each group, enabling more robust policy updates. Trained with Group Relative Policy Optimization (GRPO) on unlabeled data, our method consistently improves reasoning performance and generalization on five mathematical reasoning benchmarks, offering a scalable path toward self-evolving multimodal models. The code are available at https://github.com/OPPO-Mente-Lab/LLM-Self-Judge.
Authors: Trung V. Phan, Thomas Bauschert
Abstract: Advanced Persistent Threats (APTs) are stealthy, multi-stage attacks that require adaptive and timely defense. While deep reinforcement learning (DRL) enables autonomous cyber defense, its decisions are often opaque and difficult to trust in operational environments. This paper presents DeepXplain, an explainable DRL framework for stage-aware APT defense. Building on our prior DeepStage model, DeepXplain integrates provenance-based graph learning, temporal stage estimation, and a unified XAI pipeline that provides structural, temporal, and policy-level explanations. Unlike post-hoc methods, explanation signals are incorporated directly into policy optimization through evidence alignment and confidence-aware reward shaping. To the best of our knowledge, DeepXplain is the first framework to integrate explanation signals into reinforcement learning for APT defense. Experiments in a realistic enterprise testbed show improvements in stage-weighted F1-score (0.887 to 0.915) and success rate (84.7% to 89.6%), along with higher explanation confidence (0.86), improved fidelity (0.79), and more compact explanations (0.31). These results demonstrate enhanced effectiveness and trustworthiness of autonomous cyber defense.
Authors: Runze Sun, Yu Zheng, Zexuan Xiong, Zhongjin Qu, Lei Chen, Jiwen Lu, Jie Zhou
Abstract: Combating hate speech on social media is critical for securing cyberspace, yet relies heavily on the efficacy of automated detection systems. As content formats evolve, hate speech is transitioning from solely plain text to complex multimodal expressions, making implicit attacks harder to spot. Current systems, however, often falter on these subtle cases, as they struggle with multimodal content where the emergent meaning transcends the aggregation of individual modalities. To bridge this gap, we move beyond binary classification to characterize semantic intent shifts where modalities interact to construct implicit hate from benign cues or neutralize toxicity through semantic inversion. Guided by this fine-grained formulation, we curate the Hate via Vision-Language Interplay (H-VLI) benchmark where the true intent hinges on the intricate interplay of modalities rather than overt visual or textual slurs. To effectively decipher these complex cues, we further propose the Asymmetric Reasoning via Courtroom Agent DEbate (ARCADE) framework. By simulating a judicial process where agents actively argue for accusation and defense, ARCADE forces the model to scrutinize deep semantic cues before reaching a verdict. Extensive experiments demonstrate that ARCADE significantly outperforms state-of-the-art baselines on H-VLI, particularly for challenging implicit cases, while maintaining competitive performance on established benchmarks. Our code and data are available at: https://github.com/Sayur1n/H-VLI
Authors: Vinay Sharma, Manish Jain
Abstract: Large Language Models (LLMs) often exhibit strong linguistic abilities while remaining unreliable on multi-step reasoning tasks, particularly when deployed without additional training or fine-tuning. In this work, we study inference-time techniques to improve the reasoning accuracy of LLMs. We systematically evaluate three classes of inference-time strategies: (i) self-consistency via stochastic decoding, where the model is sampled multiple times using controlled temperature and nucleus sampling and the most frequent final answer is selected; (ii) dual-model reasoning agreement, where outputs from two independent models are compared and only consistent reasoning traces are trusted; and (iii) self-reflection, where the model critiques and revises its own reasoning. Across all evaluated methods, we employ Chain-of-Thought (CoT) [1] prompting to elicit explicit intermediate reasoning steps before generating final answers. In this work, we provide a controlled comparative evaluation across three inference-time strategies under identical prompting and verification settings. Our experiments on LLM [2] show that self-consistency with nucleus sampling and controlled temperature value yields the substantial gains, achieving a 9% to 15% absolute improvement in accuracy over greedy single-pass decoding, well-suited for low-risk domains, offering meaningful gains with minimal overhead. The dual-model approach provides additional confirmation for model reasoning steps thus more appropriate for moderate-risk domains, where higher reliability justifies additional compute. Self-reflection offers only marginal improvements, suggesting limited effectiveness for smaller non-reasoning models at inference time.
Authors: Diego F. Vasquez Plaza, Vidya Manian
Abstract: Jet flavor tagging plays an important role in precise Standard Model measurement enabling the extraction of mass dependence in jet-quark interaction and quark-gluon plasma (QGP) interactions. They also enable inferring the nature of particles produced in high-energy particle collisions that contain heavy quarks. The classification of bottom jets is vital for exploring new Physics scenarios in proton-proton collisions. In this research, we present a hybrid deep learning architecture that integrates edge convolutions with transformer self-attention mechanisms, into one single architecture called the Edge Convolution Transformer (ECT) model for bottom-quark jet tagging. ECT processes track-level features (impact parameters, momentum, and their significances) alongside jet-level observables (vertex information and kinematics) to achieve state-of-the-art performance. The study utilizes the ATLAS simulation dataset. We demonstrate that ECT achieves 0.9333 AUC for b-jet versus combined charm and light jet discrimination, surpassing ParticleNet (0.8904 AUC) and the pure transformer baseline (0.9216 AUC). The model maintains inference latency below 0.060 ms per jet on modern GPUs, meeting the stringent requirements for real-time event selection at the LHC. Our results demonstrate that hybrid architectures combining local and global features offer superior performance for challenging jet classification tasks. The proposed architecture achieves good results in b-jet tagging, particularly excelling in charm jet rejection (the most challenging task), while maintaining competitive light-jet discrimination comparable to pure transformer models.
Authors: Xiaozhe Li, Tianyi Lyu, Siyi Yang, Yizhao Yang, Yuxi Gong, Jinxuan Huang, Ligao Zhang, Zhuoyi Huang, Qingwen Liu
Abstract: Understanding human intent is a high-level cognitive challenge for Large Language Models (LLMs), requiring sophisticated reasoning over noisy, conflicting, and non-linear discourse. While LLMs excel at following individual instructions, their ability to distill Collective Intent - the process of extracting consensus, resolving contradictions, and inferring latent trends from multi-source public discussions - remains largely unexplored. To bridge this gap, we introduce COIN-BENCH, a dynamic, real-world, live-updating benchmark specifically designed to evaluate LLMs on collective intent understanding within the consumer domain. Unlike traditional benchmarks that focus on transactional outcomes, COIN-BENCH operationalizes intent as a hierarchical cognitive structure, ranging from explicit scenarios to deep causal reasoning. We implement a robust evaluation pipeline that combines a rule-based method with an LLM-as-the-Judge approach. This framework incorporates COIN-TREE for hierarchical cognitive structuring and retrieval-augmented verification (COIN-RAG) to ensure expert-level precision in analyzing raw, collective human discussions. An extensive evaluation of 20 state-of-the-art LLMs across four dimensions - depth, breadth, informativeness, and correctness - reveals that while current models can handle surface-level aggregation, they still struggle with the analytical depth required for complex intent synthesis. COIN-BENCH establishes a new standard for advancing LLMs from passive instruction followers to expert-level analytical agents capable of deciphering the collective voice of the real world. See our project page on COIN-BENCH.
Authors: Oussama Zekri, Th\'eo Uscidda, Nicolas Boull\'e, Anna Korba
Abstract: We introduce Generalized Discrete Diffusion from Snapshots (GDDS), a unified framework for discrete diffusion modeling that supports arbitrary noising processes over large discrete state spaces. Our formulation encompasses all existing discrete diffusion approaches, while allowing significantly greater flexibility in the choice of corruption dynamics. The forward noising process relies on uniformization and enables fast arbitrary corruption. For the reverse process, we derive a simple evidence lower bound (ELBO) based on snapshot latents, instead of the entire noising path, that allows efficient training of standard generative modeling architectures with clear probabilistic interpretation. Our experiments on large-vocabulary discrete generation tasks suggest that the proposed framework outperforms existing discrete diffusion methods in terms of training efficiency and generation quality, and beats autoregressive models for the first time at this scale. We provide the code along with a blog post on the project page : \href{https://oussamazekri.fr/gdds}{https://oussamazekri.fr/gdds}.
URLs: https://oussamazekri.fr/gdds, https://oussamazekri.fr/gdds
Authors: K. M. Jubair Sami, Dipto Sumit, Ariyan Hossain, Farig Sadeque
Abstract: Large language models (LLMs) frequently exhibit performance biases against regional dialects of low-resource languages. However, frameworks to quantify these disparities remain scarce. We propose a two-phase framework to evaluate dialectal bias in LLM question-answering across nine Bengali dialects. First, we translate and gold-label standard Bengali questions into dialectal variants adopting a retrieval-augmented generation (RAG) pipeline to prepare 4,000 question sets. Since traditional translation quality evaluation metrics fail on unstandardized dialects, we evaluate fidelity using an LLM-as-a-judge, which human correlation confirms outperforms legacy metrics. Second, we benchmark 19 LLMs across these gold-labeled sets, running 68,395 RLAIF evaluations validated through multi-judge agreement and human fallback. Our findings reveal severe performance drops linked to linguistic divergence. For instance, responses to the highly divergent Chittagong dialect score 5.44/10, compared to 7.68/10 for Tangail. Furthermore, increased model scale does not consistently mitigate this bias. We contribute a validated translation quality evaluation method, a rigorous benchmark dataset, and a Critical Bias Sensitivity (CBS) metric for safety-critical applications.
Authors: Yijia Song, Juliet Biggs, Alin Achim, Robert Popescu, Simon Orrego, Nantheera Anantrasirichai
Abstract: Phase unwrapping remains a critical and challenging problem in InSAR processing, particularly in scenarios involving complex deformation patterns. In earthquake-related deformation, shallow sources can generate surface-breaking faults and abrupt displacement discontinuities, which severely disrupt phase continuity and often cause conventional unwrapping algorithms to fail. Another limitation of existing learning-based unwrapping methods is their reliance on fixed and relatively small input sizes, while real InSAR interferograms are typically large-scale and spatially heterogeneous. This mismatch restricts the applicability of many neural network approaches to real-world data. In this work, we present a phase unwrapping framework based on a diffusion model, developed to process large-scale interferograms and to address phase discontinuities caused by deformation. By leveraging a diffusion model architecture, the proposed method can recover physically consistent unwrapped phase fields even in the presence of fault-related phase jumps. Experimental results on both synthetic and real datasets demonstrate that the method effectively addresses discontinuities associated with near-surface deformation and scales well to large InSAR images, offering a practical alternative to manual unwrapping in challenging scenarios.
Authors: Guang Yang, Ziye Geng, Yihang Chen, Changqing Luo
Abstract: Adversarial-example-based fingerprinting approaches, which leverage the decision boundary characteristics of deep neural networks (DNNs) to craft fingerprints, have proven effective for model ownership protection. However, a fundamental challenge remains unresolved: how far a fingerprint should be placed from the decision boundary to simultaneously satisfy two essential properties, i.e., robustness and uniqueness, for effective and reliable ownership protection. Despite the importance of the fingerprint-to-boundary distance, existing works lack a theoretical solution and instead rely on empirical heuristics, which may violate either robustness or uniqueness properties. We propose AnaFP, an analytical fingerprinting scheme that constructs fingerprints under theoretical guidance. Specifically, we formulate fingerprint generation as controlling the fingerprint-to-boundary distance through a tunable stretch factor. To ensure both robustness and uniqueness, we mathematically formalize these properties that determine the lower and upper bounds of the stretch factor. These bounds jointly define an admissible interval within which the stretch factor must lie, thereby establishing a theoretical connection between the two constraints and the fingerprint-to-boundary distance. To enable practical fingerprint generation, we approximate the original (infinite) sets of pirated and independently trained models using two finite surrogate model pools and employ a quantile-based relaxation strategy to relax the derived bounds. Due to the circular dependency between the lower bound and the stretch factor, we apply grid search over the admissible interval to determine the most feasible stretch factor. Extensive experimental results show that AnaFP consistently outperforms prior methods, achieving effective ownership verification across diverse model architectures and model modification attacks.
Authors: Mariela M. Nina, Caio Veloso Costa, Lilian Berton, Didier A. Vega-Oliveros
Abstract: Although large language models have transformed natural language processing, their computational costs create accessibility barriers for low-resource languages such as Brazilian Portuguese. This work presents a systematic evaluation of Parameter-Efficient Fine-Tuning (PEFT) and quantization techniques applied to BERTimbau for Question Answering on SQuAD-BR, the Brazilian Portuguese translation of SQuAD v1. We evaluate 40 configurations combining four PEFT methods (LoRA, DoRA, QLoRA, QDoRA) across two model sizes (Base: 110M, Large: 335M parameters). Our findings reveal three critical insights: (1) LoRA achieves 95.8\% of baseline performance on BERTimbau-Large while reducing training time by 73.5\% (F1=81.32 vs 84.86); (2) higher learning rates (2e-4) substantially improve PEFT performance, with F1 gains of up to +19.71 points over standard rates; and (3) larger models show twice the quantization resilience (loss of 4.83 vs 9.56 F1 points). These results demonstrate that encoder-based models can be efficiently fine-tuned for extractive Brazilian Portuguese QA with substantially lower computational cost than large generative LLMs, promoting more sustainable approaches aligned with \textit{Green AI} principles. An exploratory evaluation of Tucano and Sabi\'a on the same extractive QA benchmark shows that while generative models can reach competitive F1 scores with LoRA fine-tuning, they require up to 4.2$\times$ more GPU memory and 3$\times$ more training time than BERTimbau-Base, reinforcing the efficiency advantage of smaller encoder-based architectures for this task.
Authors: Shivani Kamtikar, Kendall Koe, Justin Wasserman, Samhita Marri, Benjamin Walt, Naveen Kumar Uppalapati, Girish Krishnan, Girish Chowdhary
Abstract: As robotic systems increasingly operate in unstructured, cluttered, and previously unseen environments, there is a growing need for manipulators that combine compliance, adaptability, and precise control. This work presents a real-time hybrid rigid-soft continuum manipulator system designed for robust open-world object reaching in such challenging environments. The system integrates vision-based perception and 3D scene reconstruction with shape-aware motion planning to generate safe trajectories. A learning-based controller drives the hybrid arm to arbitrary target poses, leveraging the flexibility of the soft segment while maintaining the precision of the rigid segment. The system operates without environment-specific retraining, enabling direct generalization to new scenes. Extensive real-world experiments demonstrate consistent reaching performance with errors below 2 cm across diverse cluttered setups, highlighting the potential of hybrid manipulators for adaptive and reliable operation in unstructured environments.
Authors: Shuai Wang, Yinan Yu, Earl Barr, Dhasarathy Parthasarathy
Abstract: Multidisciplinary Software Development (MSD) requires domain experts and developers to collaborate across incompatible formalisms and separate artifact sets. Today, even with AI coding assistants like GitHub Copilot, this process remains inefficient; individual coding tasks are semi-automated, but the workflow connecting domain knowledge to implementation is not. Developers and experts still lack a shared view, resulting in repeated coordination, clarification rounds, and error-prone handoffs. We address this gap through a graph-based workflow optimization approach that progressively replaces manual coordination with LLM-powered services, enabling incremental adoption without disrupting established practices. We evaluate our approach on \texttt{spapi}, a production in-vehicle API system at Volvo Group involving 192 endpoints, 420 properties, and 776 CAN signals across six functional domains. The automated workflow achieves 93.7\% F1 score while reducing per-API development time from approximately 5 hours to under 7 minutes, saving an estimated 979 engineering hours. In production, the system received high satisfaction from both domain experts and developers, with all participants reporting full satisfaction with communication efficiency.
Authors: Shuai Wang, Yinan Yu
Abstract: Large Language Models (LLMs) demonstrate impressive natural language capabilities but often struggle with knowledge-intensive reasoning tasks. Knowledge Base Question Answering (KBQA), which leverages structured Knowledge Graphs (KGs) exemplifies this challenge due to the need for accurate multi-hop reasoning. Existing approaches typically perform sequential reasoning steps guided by predefined pipelines, restricting flexibility and causing error cascades due to isolated reasoning at each step. To address these limitations, we propose KG-Hopper, a novel Reinforcement Learning (RL) framework that empowers compact open LLMs with the ability to perform integrated multi-hop KG reasoning within a single inference round. Rather than reasoning step-by-step, we train a Reasoning LLM that embeds the entire KG traversal and decision process into a unified ``thinking'' stage, enabling global reasoning over cross-step dependencies and dynamic path exploration with backtracking. Experimental results on eight KG reasoning benchmarks show that KG-Hopper, based on a 7B-parameter LLM, consistently outperforms larger multi-step systems (up to 70B) and achieves competitive performance with proprietary models such as GPT-3.5-Turbo and GPT-4o-mini, while remaining compact, open, and data-efficient. The code is publicly available at: https://github.com/Wangshuaiia/KG-Hopper.
Authors: Yubo Li, Ramayya Krishnan, Rema Padman
Abstract: Patient education materials for solid-organ transplantation vary substantially across U.S. centers, yet no systematic method exists to quantify this heterogeneity at scale. We introduce a framework that grounds the same patient questions in different centers' handbooks using retrieval-augmented language models and compares the resulting answers using a five-label consistency taxonomy. Applied to 102 handbooks from 23 centers and 1,115 benchmark questions, the framework quantifies heterogeneity across four dimensions: question, topic, organ, and center. We find that 20.8% of non-absent pairwise comparisons exhibit clinically meaningful divergence, concentrated in condition monitoring and lifestyle topics. Coverage gaps are even more prominent: 96.2% of question-handbook pairs miss relevant content, with reproductive health at 95.1% absence. Center-level divergence profiles are stable and interpretable, where heterogeneity reflects systematic institutional differences, likely due to patient diversity. These findings expose an information gap in transplant patient education materials, with document-grounded medical question answering highlighting opportunities for content improvement.
Authors: James Wedgwood, Aashiq Muhamed, Mona T. Diab, Virginia Smith
Abstract: Preference alignment is usually achieved by weight-updating training on preference data, which adds substantial alignment-stage compute and provides limited mechanistic visibility. We propose Dynamic SAE Steering for Preference Alignment (DSPA), an inference-time method that makes sparse autoencoder (SAE) steering prompt-conditional. From preference triples, DSPA computes a conditional-difference map linking prompt features to generation-control features; during decoding, it modifies only token-active latents, without base-model weight updates. Across Gemma-2-2B/9B and Qwen3-8B, DSPA improves MT-Bench and is competitive on AlpacaEval while preserving multiple-choice accuracy. Under restricted preference data, DSPA remains robust and can rival the two-stage RAHF-SCIT pipeline while requiring up to $4.47\times$ fewer alignment-stage FLOPs. Finally, we audit the SAE features DSPA modifies, finding that preference directions are dominated by discourse and stylistic signals, and provide theory clarifying the conditional-difference map estimate and when top-$k$ ablation is principled.
Authors: Jiayi Geng, Graham Neubig
Abstract: AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github. Yet long-horizon tasks involving multiple interdependent subtasks still pose challenges both with respect to accuracy, and with respect to timely completion. A natural approach to solving these long-horizon tasks in a timely manner is asynchronous multi-agent collaboration, where multiple agents work on different parts of the task at the same time. But effective application of multi-agent systems has proven surprisingly difficult: concurrent edits by multiple agents interfere with each other, dependencies are difficult to synchronize, and combining partial progress into a coherent whole is challenging. On the other hand, human developers have long relied on mature collaboration infrastructure to manage these challenges in large software projects. Inspired by these collaboration primitives, we introduce Centralized Asynchronous Isolated Delegation (CAID), a structured multi-agent coordination paradigm grounded in three core SWE primitives: centralized task delegation, asynchronous execution, and isolated workspaces. CAID constructs dependency-aware task plans through a central manager, executes subtasks concurrently in isolated workspaces, and consolidates progress via structured integration with executable test-based verification. In empirical evaluation, we find that CAID improves accuracy over single-agent baselines by 26.7% absolute on paper reproduction tasks (PaperBench) and 14.3% on Python library development tasks (Commit0). Through systematic analysis, we find that branch-and-merge is a central coordination mechanism for multi-agent collaboration, and that SWE primitives such as git worktree, git commit, and git merge enable it to be realized in a reliable and executable manner.
Authors: Lingzhe Zhang, Tong Jia, Weijie Hong, Mingyu Wang, Chiming Duan, Minghua He, Rongqian Wang, Xi Peng, Meiling Wang, Gong Zhang, Renhai Chen, Ying Li
Abstract: Modern software systems operate at unprecedented scale and complexity, where effective failure management is critical yet increasingly challenging. Metrics, traces, and logs provide complementary views of system runtime behavior, but existing failure management approaches typically rely on task-oriented pipelines that tightly couple modality-specific preprocessing, representation learning, and downstream models, resulting in limited generalization across tasks and systems. To fill this gap, we propose RuntimeSlicer, a unified runtime state representation model towards generalizable failure management. RuntimeSlicer pre-trains a task-agnostic representation model that directly encodes metrics, traces, and logs into a single, aligned system-state embedding capturing the holistic runtime condition of the system. To train RuntimeSlicer, we introduce Unified Runtime Contrastive Learning, which integrates heterogeneous training data sources and optimizes complementary objectives for cross-modality alignment and temporal consistency. Building upon the learned system-state embeddings, we further propose State-Aware Task-Oriented Tuning, which performs unsupervised partitioning of runtime states and enables state-conditioned adaptation for downstream tasks. This design allows lightweight task-oriented models to be trained on top of the unified embedding without redesigning modality-specific encoders or preprocessing pipelines. Preliminary experiments on the AIOps 2022 dataset demonstrate the feasibility and effectiveness of RuntimeSlicer for system state modeling and failure management tasks.
Authors: Seou Choi, Sachin Vaidya, Caio Silva, Shiekh Zia Uddin, Sajib Biswas Shuvo, Shrish Choudhary, Marin Solja\v{c}i\'c
Abstract: Robotic automation has transformed scientific workflows in domains such as chemistry and materials science, yet free-space optics, which is a high precision domain, remains largely manual. Optical systems impose strict spatial and angular tolerances, and their performance is governed by tightly coupled physical parameters, making generalizable automation particularly challenging. In this work, we present a robotics framework for the autonomous construction, alignment, and maintenance of precision optical systems. Our approach integrates hierarchical computer vision systems, optimization routines, and custom-built tools to achieve this functionality. As a representative demonstration, we perform the fully autonomous construction of a tabletop laser cavity from randomly distributed components. The system performs several tasks such as laser beam centering, spatial alignment of multiple beams, resonator alignment, laser mode selection, and self-recovery from induced misalignment and disturbances. By achieving closed-loop autonomy for highly sensitive optical systems, this work establishes a foundation for autonomous optical experiments for applications across technical domains.
Authors: Hang-Cheng Dong, Pengcheng Cheng
Abstract: Overparameterized shallow neural networks admit substantial parameter redundancy: distinct parameter vectors may represent the same predictor due to hidden-unit permutations, rescalings, and related symmetries. As a result, geometric quantities computed directly in the ambient Euclidean parameter space can reflect artifacts of representation rather than intrinsic properties of the predictor. In this paper, we develop a differential-geometric framework for analyzing simple shallow networks through the quotient space obtained by modding out parameter symmetries on a regular set. We first characterize the symmetry and quotient structure of regular shallow-network parameters and show that the finite-sample realization map induces a natural metric on the quotient manifold. This leads to an effective notion of curvature that removes degeneracy along symmetry orbits and yields a symmetry-reduced Hessian capturing intrinsic local geometry. We then study gradient flows on the quotient and show that only the horizontal component of parameter motion contributes to first-order predictor evolution, while the vertical component corresponds purely to gauge variation. Finally, we formulate an implicit-bias viewpoint at the quotient level, arguing that meaningful complexity should be assigned to predictor classes rather than to individual parameter representatives. Our experiments confirm that ambient flatness is representation-dependent, that local dynamics are better organized by quotient-level curvature summaries, and that in underdetermined regimes, implicit bias is most naturally described in quotient coordinates.
Authors: Chen Gong, Zhenzhe Zheng, Yiliu Chen, Sheng Wang, Fan Wu, Guihai Chen
Abstract: Machine learning models are widely integrated into modern mobile apps to analyze user behaviors and deliver personalized services. Ensuring low-latency on-device model execution is critical for maintaining high-quality user experiences. While prior research has primarily focused on accelerating model inference with given input features, we identify an overlooked bottleneck in real-world on-device model execution pipelines: extracting input features from raw application logs. In this work, we explore a new direction of feature extraction optimization by analyzing and eliminating redundant extraction operations across different model features and consecutive model inferences. We then introduce AutoFeature, an automated feature extraction engine designed to accelerate on-device feature extraction process without compromising model inference accuracy. AutoFeature comprises three core designs: (1) graph abstraction to formulate the extraction workflows of different input features as one directed acyclic graph, (2) graph optimization to identify and fuse redundant operation nodes across different features within the graph; (3) efficient caching to minimize operations on overlapping raw data between consecutive model inferences. We implement a system prototype of AutoFeature and integrate it into five industrial mobile services spanning search, video and e-commerce domains. Online evaluations show that AutoFeature reduces end-to-end on-device model execution latency by 1.33x-3.93x during daytime and 1.43x-4.53x at night.
Authors: Lingzhe Zhang, Tong Jia, Mingyu Wang, Weijie Hong, Chiming Duan, Minghua He, Rongqian Wang, Xi Peng, Meiling Wang, Gong Zhang, Renhai Chen, Ying Li
Abstract: Large Language Models (LLM)-based Multi-Agent Systems (MASs) have emerged as a new paradigm in software system design, increasingly demonstrating strong reasoning and collaboration capabilities. As these systems become more complex and autonomous, effective failure management is essential to ensure reliability and availability. However, existing approaches often rely on per-trace reasoning, which leads to low efficiency, and neglect historical failure patterns, limiting diagnostic accuracy. In this paper, we conduct a preliminary empirical study to demonstrate the necessity, potential, and challenges of leveraging historical failure patterns to enhance failure management in MASs. Building on this insight, we propose \textbf{EAGER}, an efficient failure management framework for multi-agent systems based on reasoning trace representation. EAGER employs unsupervised reasoning-scoped contrastive learning to encode both intra-agent reasoning and inter-agent coordination, enabling real-time step-wise failure detection, diagnosis, and reflexive mitigation guided by historical failure knowledge. Preliminary evaluations on three open-source MASs demonstrate the effectiveness of EAGER and highlight promising directions for future research in reliable multi-agent system operations.
Authors: Weizhe Xu, Mengyu Liu, Fanxin Kong
Abstract: Large Language Models (LLMs), deep learning architectures with typically over 10 billion parameters, have recently begun to be integrated into various cyber-physical systems (CPS) such as robotics, industrial automation, and autopilot systems. The abstract knowledge and reasoning capabilities of LLMs are employed for tasks like planning and navigation. However, a significant challenge arises from the tendency of LLMs to produce "hallucinations" - outputs that are coherent yet factually incorrect or contextually unsuitable. This characteristic can lead to undesirable or unsafe actions in the CPS. Therefore, our research focuses on assuring the LLM-enabled CPS by enhancing their critical properties. We propose SafePilot, a novel hierarchical neuro-symbolic framework that provides end-to-end assurance for LLM-enabled CPS according to attribute-based and temporal specifications. Given a task and its specification, SafePilot first invokes a hierarchical planner with a discriminator that assesses task complexity. If the task is deemed manageable, it is passed directly to an LLM-based task planner with built-in verification. Otherwise, the hierarchical planner applies a divide-and-conquer strategy, decomposing the task into sub-tasks, each of which is individually planned and later merged into a final solution. The LLM-based task planner translates natural language constraints into formal specifications and verifies the LLM's output against them. If violations are detected, it identifies the flaw, adjusts the prompt accordingly, and re-invokes the LLM. This iterative process continues until a valid plan is produced or a predefined limit is reached. Our framework supports LLM-enabled CPS with both attribute-based and temporal constraints. Its effectiveness and adaptability are demonstrated through two illustrative case studies.
Authors: Ravi Ranjan, Utkarsh Grover, Mayur Akewar, Xiaomin Lin, Agoritsa Polyzou
Abstract: Large Language Models (LLMs) are deployed in high-stakes settings but can show demographic, gender, and geographic biases that undermine fairness and trust. Prior debiasing methods, including embedding-space projections, prompt-based steering, and causal interventions, often act at a single stage of the pipeline, resulting in incomplete mitigation and brittle utility trade-offs under distribution shifts. We propose CatRAG Debiasing, a dual-pronged framework that integrates functor with Retrieval-Augmented Generation (RAG) guided structural debiasing. The functor component leverages category-theoretic structure to induce a principled, structure-preserving projection that suppresses bias-associated directions in the embedding space while retaining task-relevant semantics. On the Bias Benchmark for Question Answering (BBQ) across three open-source LLMs (Meta Llama-3, OpenAI GPT-OSS, and Google Gemma-3), CatRAG achieves state-of-the-art results, improving accuracy by up to 40% over the corresponding base models and by more than 10% over prior debiasing methods, while reducing bias scores to near zero (from 60% for the base models) across gender, nationality, race, and intersectional subgroups.
Authors: Bayezid Baten, M. Ayyan Iqbal, Sebastian Ament, Julius Kusuma, Nishant Garg
Abstract: Modern concrete must simultaneously satisfy evolving demands for mechanical performance, workability, durability, and sustainability, making mix designs increasingly complex. Recent studies leveraging Artificial Intelligence (AI) and Machine Learning (ML) models show promise for predicting compressive strength and guiding mix optimization, but most existing efforts are based on proprietary industrial datasets and closed-source implementations. Here we introduce BOxCrete, an open-source probabilistic modeling and optimization framework trained on a new open-access dataset of over 500 strength measurements (1-15 ksi) from 123 mixtures - 69 mortar and 54 concrete mixes tested at five curing ages (1, 3, 5, 14, and 28 days). BOxCrete leverages Gaussian Process (GP) regression to predict strength development, achieving average R$^2$ = 0.94 and RMSE = 0.69 ksi, quantify uncertainty, and carry out multi-objective optimization of compressive strength and embodied carbon. The dataset and model establish a reproducible open-source foundation for data-driven development of AI-based optimized mix designs.
Authors: Yujia Chen, Yingli Zhou, Fangyuan Zhang, Cuiyun Gao
Abstract: Database Management Systems (DBMSs) are fundamental infrastructure for modern data-driven applications, where thorough testing with high-quality SQL test cases is essential for ensuring system reliability. Traditional approaches such as fuzzing can be effective for specific DBMSs, but adapting them to different proprietary dialects requires substantial manual effort. Large Language Models (LLMs) present promising opportunities for automated SQL test generation, but face critical challenges in industrial environments. First, lightweight models are widely used in organizations due to security and privacy constraints, but they struggle to generate syntactically valid queries for proprietary SQL dialects. Second, LLM-generated queries are often semantically similar and exercise only shallow execution paths, thereby quickly reaching a coverage plateau. To address these challenges, we propose MIST, an LLM-based test case generatIon framework for DBMS through Monte Carlo Tree search. MIST consists of two stages: Feature-Guided Error-Driven Test Case Synthetization, which constructs a hierarchical feature tree and uses error feedback to guide LLM generation, aiming to produce syntactically valid and semantically diverse queries for different DBMS dialects, and Monte Carlo Tree Search-Based Test Case Mutation, which jointly optimizes seed query selection and mutation rule application guided by coverage feedback, aiming at boosting code coverage by exploring deeper execution paths. Experiments on three widely-used DBMSs with four lightweight LLMs show that MIST achieves average improvements of 43.3% in line coverage, 32.3% in function coverage, and 46.4% in branch coverage compared to the baseline approach with the highest line coverage of 69.3% in the Optimizer module.
Authors: Yawen Li, Tao Hu, Zhouhui Lian, Wan Tian, Yijie Peng, Huiming Zhang, Zhongyi Li
Abstract: This paper studies generalization error bounds for Transformer models. Based on the offset Rademacher complexity, we derive sharper generalization bounds for different Transformer architectures, including single-layer single-head, single-layer multi-head, and multi-layer Transformers. We first express the excess risk of Transformers in terms of the offset Rademacher complexity. By exploiting its connection with the empirical covering numbers of the corresponding hypothesis spaces, we obtain excess risk bounds that achieve optimal convergence rates up to constant factors. We then derive refined excess risk bounds by upper bounding the covering numbers of Transformer hypothesis spaces using matrix ranks and matrix norms, leading to precise, architecture-dependent generalization bounds. Finally, we relax the boundedness assumption on feature mappings and extend our theoretical results to settings with unbounded (sub-Gaussian) features and heavy-tailed distributions.
Authors: Kesheng Chen, Wenjian Luo, Xin Lin, Zhen Song, Yatong Chang
Abstract: Unmanned aerial vehicles (UAVs) have been widely used in urban missions, and proper planning of UAV paths can improve mission efficiency while reducing the risk of potential third-party impact. Existing work has considered all efficiency and safety objectives for a single decision-maker (DM) and regarded this as a multiobjective optimization problem (MOP). However, there is usually not a single DM but two DMs, i.e., an efficiency DM and a safety DM, and the DMs are only concerned with their respective objectives. The final decision is made based on the solutions of both DMs. In this paper, for the first time, biparty multiobjective UAV path planning (BPMO-UAVPP) problems involving both efficiency and safety departments are modeled. The existing multiobjective immune algorithm with nondominated neighbor-based selection (NNIA), the hybrid evolutionary framework for the multiobjective immune algorithm (HEIA), and the adaptive immune-inspired multiobjective algorithm (AIMA) are modified for solving the BPMO-UAVPP problem, and then biparty multiobjective optimization algorithms, including the BPNNIA, BPHEIA, and BPAIMA, are proposed and comprehensively compared with traditional multiobjective evolutionary algorithms and typical multiparty multiobjective evolutionary algorithms (i.e., OptMPNDS and OptMPNDS2). The experimental results show that BPAIMA performs better than ordinary multiobjective evolutionary algorithms such as NSGA-II and multiparty multiobjective evolutionary algorithms such as OptMPNDS, OptMPNDS2, BPNNIA and BPHEIA.
Authors: Xinyu Zhang
Abstract: World models learn to simulate environment dynamics from experience, enabling sample-efficient reinforcement learning. But what do these models actually represent internally? We apply interpretability techniques--including linear and nonlinear probing, causal interventions, and attention analysis--to two architecturally distinct world models: IRIS (discrete token transformer) and DIAMOND (continuous diffusion UNet), trained on Atari Breakout and Pong. Using linear probes, we find that both models develop linearly decodable representations of game state variables (object positions, scores), with MLP probes yielding only marginally higher R^2, confirming that these representations are approximately linear. Causal interventions--shifting hidden states along probe-derived directions--produce correlated changes in model predictions, providing evidence that representations are functionally used rather than merely correlated. Analysis of IRIS attention heads reveals spatial specialization: specific heads attend preferentially to tokens overlapping with game objects. Multi-baseline token ablation experiments consistently identify object-containing tokens as disproportionately important. Our findings provide interpretability evidence that learned world models develop structured, approximately linear internal representations of environment state across two games and two architectures.
Authors: Yashar Talebirad, Ali Parsaee, Csongor Y. Szepesvari, Amirhossein Nadiri, Osmar Zaiane
Abstract: Many recent long-context and agentic systems address context-length limitations by adding hierarchical memory: they extract atomic units from raw data, build multi-level representatives by grouping and compression, and traverse this structure to retrieve content under a token budget. Despite recurring implementations, there is no shared formalism for comparing design choices. We propose a unifying theory in terms of three operators. Extraction ($\alpha$) maps raw data to atomic information units; coarsening ($C = (\pi, \rho)$) partitions units and assigns a representative to each group; and traversal ($\tau$) selects which units to include in context given a query and budget. We identify a self-sufficiency spectrum for the representative function $\rho$ and show how it constrains viable retrieval strategies (a coarsening-traversal coupling). Finally, we instantiate the decomposition on eleven existing systems spanning document hierarchies, conversational memory, and agent execution traces, showcasing its generality.
Authors: Yansong Lin, Zihan Cheng, Jielei Wang, Guoming Lua, Zongyong Cui
Abstract: Synthetic aperture radar automatic target recognition (SAR ATR) is of considerable importance in marine navigation and disaster monitoring. However, the coherent speckle noise inherent in SAR imagery often obscures salient target features, leading to degraded recognition accuracy and limited model generalization. To address this issue, this paper proposes a target-aware frequency-spatial enhancement framework with noise-resilient knowledge guidance (FSCE) for SAR target recognition. The proposed framework incorporates a frequency-spatial shallow feature adaptive enhancement (DSAF) module, which processes shallow features through spatial multi-scale convolution and frequency-domain wavelet convolution. In addition, a teacher-student learning paradigm combined with an online knowledge distillation method (KD) is employed to guide the student network to focus more effectively on target regions, thereby enhancing its robustness to high-noise backgrounds. Through the collaborative optimization of attention transfer and noise-resilient representation learning, the proposed approach significantly improves the stability of target recognition under noisy conditions. Based on the FSCE framework, two network architectures with different performance emphases are developed: lightweight DSAFNet-M and high-precision DSAFNet-L. Extensive experiments are conducted on the MSTAR, FUSARShip and OpenSARShip datasets. The results show that DSAFNet-L achieves competitive or superior performance compared with various methods on three datasets; DSAFNet-M significantly reduces the model complexity while maintaining comparable accuracy. These results indicate that the proposed FSCE framework exhibits strong cross-model generalization.
Authors: Mohammad Eslami, Dhanvinkumar Ganeshkumar, Saber Kazeminasab, Michael G. Morley, Michael V. Boland, Michael M. Lin, John B. Miller, David S. Friedman, Nazlee Zebardast, Lucia Sobrin, Tobias Elze
Abstract: We present CataractSAM-2, a domain-adapted extension of Meta's Segment Anything Model 2, designed for real-time semantic segmentation of cataract ophthalmic surgery videos with high accuracy. Positioned at the intersection of computer vision and medical robotics, CataractSAM-2 enables precise intraoperative perception crucial for robotic-assisted and computer-guided surgical systems. Furthermore, to alleviate the burden of manual labeling, we introduce an interactive annotation framework that combines sparse prompts with video-based mask propagation. This tool significantly reduces annotation time and facilitates the scalable creation of high-quality ground-truth masks, accelerating dataset development for ocular anterior segment surgeries. We also demonstrate the model's strong zero-shot generalization to glaucoma trabeculectomy procedures, confirming its cross-procedural utility and potential for broader surgical applications. The trained model and annotation toolkit are released as open-source resources, establishing CataractSAM-2 as a foundation for expanding anterior ophthalmic surgical datasets and advancing real-time AI-driven solutions in medical robotics, as well as surgical video understanding.
Authors: Hyoseok Park, Yeonsang Park
Abstract: Long-context LLM inference is bottlenecked not by compute but by the O(n) memory bandwidth cost of scanning the KV cache at every decode step -- a wall that no amount of arithmetic scaling can break. Recent photonic accelerators have demonstrated impressive throughput for dense attention computation; however, these approaches inherit the same O(n) memory scaling as electronic attention when applied to long contexts. We observe that the real leverage point is the coarse block-selection step: a memory-bound similarity search that determines which KV blocks to fetch. We identify, for the first time, that this task is structurally matched to the photonic broadcast-and-weight paradigm -- the query fans out to all candidates via passive splitting, signatures are quasi-static (matching electro-optic MRR programming), and only rank order matters (relaxing precision to 4-6 bits). Crucially, the photonic advantage grows with context length: as N increases, the electronic scan cost rises linearly while the photonic evaluation remains O(1). We instantiate this insight in PRISM (Photonic Ranking via Inner-product Similarity with Microring weights), a thin-film lithium niobate (TFLN) similarity engine. Hardware-impaired needle-in-a-haystack evaluation on Qwen2.5-7B confirms 100% accuracy from 4K through 64K tokens at k=32, with 16x traffic reduction at 64K context. PRISM achieves a four-order-of-magnitude energy advantage over GPU baselines at practical context lengths (n >= 4K).
Authors: Che Chen, Lanhua Li, Shimin Gong, Yu Zhao, Yuming Fang, Dusit Niyato
Abstract: In this paper, we employ multiple UAVs to accelerate data transmissions from ground users (GUs) to a remote base station (BS) via the UAVs' relay communications. The UAVs' intermittent information exchanges typically result in delays in acquiring the complete system state and hinder their effective collaboration. To maximize the overall throughput, we first propose a delay-tolerant multi-agent deep reinforcement learning (MADRL) algorithm that integrates a delay-penalized reward to encourage information sharing among UAVs, while jointly optimizing the UAVs' trajectory planning, network formation, and transmission control strategies. Additionally, considering information loss due to unreliable channel conditions, we further propose a spatio-temporal attention based prediction approach to recover the lost information and enhance each UAV's awareness of the network state. These two designs are envisioned to enhance the network capacity in UAV-assisted wireless networks with limited communications. The simulation results reveal that our new approach achieves over 50\% reduction in information delay and 75% throughput gain compared to the conventional MADRL. Interestingly, it is shown that improving the UAVs' information sharing will not sacrifice the network capacity. Instead, it significantly improves the learning performance and throughput simultaneously. It is also effective in reducing the need for UAVs' information exchange and thus fostering practical deployment of MADRL in UAV-assisted wireless networks.
Authors: Philip S. Yu, Li Sun
Abstract: Graphs provide a natural description of the complex relationships among objects, and play a pivotal role in communications, transportation, social computing, the life sciences, etc. Currently, there is strong agreement that Graph Foundation Models (GFMs) are essential for advancing graph learning, yet considerable disagreement persists on how to build a powerful, general-purpose GFM analogous to Large Language Models (LLMs). Graph Neural Networks (GNNs) exhibit limitations in memory retention and principled interpretability when confronted with multi-domain pretraining and adaptation. The challenge of graph serialization hinders the direct application of LLMs, as the words struggle to capture the structural complexity and diversity inherent in graphs. In contrast, Riemannian geometry offers an elegant mathematical framework for modeling structures, while remaining compatible with graph semantic learning, even with LLMs. In this paper, we argue that, for graphs, Riemannian geometry speaks louder than words, and lay out the foundational principles for GFM. Reimagining with Riemannian geometry, we introduce a blue sky idea-Riemannian Foundation Model (RFM)-that opens a new pathway for capturing complex structural patterns and uncovering cross-domain generalities. RFM emphasizes intrinsic graph geometry and embodies endogenous capacities for structural inference and generation, moving beyond mere representation-space switching. Accordingly, we outline a progressive agenda that begins with universal structural understanding through intrinsic geometry, and then rebuilds LLM with a Riemannian engine for general-purpose graph modeling and beyond. Thus, RFM enables a paradigm shift from designing graph models to solving graph-structured applications with RFM agents, unlocking the next-generation graph intelligence.
Authors: Woosung Koh, Jeyoung Jeon, Youngjin Song, Yujin Cheon, Soowon Oh, Jaehyeong Choi, Se-Young Yun
Abstract: Current language model training commonly applies multi-task Supervised Fine-Tuning (SFT) using a homogeneous compute budget across all sub-datasets. This approach is fundamentally sub-optimal: heterogeneous learning dynamics cause faster-learning tasks to overfit early while slower ones remain under-fitted. To address this, we introduce mSFT, an iterative, overfitting-aware search algorithm for multi-task data mixtures. mSFT trains the model on an active mixture, identifies and excludes the earliest overfitting sub-dataset, and reverts to that specific optimal checkpoint before continuing. Extensive evaluations demonstrate that mSFT consistently outperforms 4 baselines across 10 benchmarks and 6 base models. Further analysis confirms mSFT maintains robust gains across diverse dataset sizes, task granularities, and is insensitive to its single new hyperparameter (compute budget). Notably, at low compute budget, mSFT can improve performance while lowering training FLOPs. Ultimately, mSFT establishes a practical overfitting-aware algorithm for multi-task SFT that maximizes the potential of models across diverse data mixtures.
Authors: Tianyu Cao, Helin Wang, Ari Frummer, Yuval Sieradzki, Adi Arbel, Laureano Moro Velazquez, Jesus Villalba, Oren Gal, Thomas Thebaud, Najim Dehak
Abstract: Recent advances in generative models, such as diffusion and flow matching, have shown strong performance in audio tasks. However, speech enhancement (SE) models are typically trained on limited datasets and evaluated under narrow conditions, limiting real-world applicability. To address this, we propose DiT-Flow, a flow matching-based SE framework built on the latent Diffusion Transformer (DiT) backbone and trained for robustness across diverse distortions, including noise, reverberation, and compression. DiT-Flow operates on compact variational auto-encoders (VAEs)-derived latent features. We validated our approach on StillSonicSet, a synthetic yet acoustically realistic dataset composed of LibriSpeech, FSD50K, FMA, and 90 Matterport3D scenes. Experiments show that DiT-Flow consistently outperforms state-of-the-art generative SE models, demonstrating the effectiveness of flow matching in multi-condition speech enhancement. Despite ongoing efforts to expand synthetic data realism, a persistent bottleneck in SE is the inevitable mismatch between training and deployment conditions. By integrating LoRA with the MoE framework, we achieve both parameter-efficient and high-performance training for DiT-Flow robust to multiple distortions with using 4.9% percentage of the total parameters to obtain a better performance on five unseen distortions.
Authors: Abdou-Raouf Atarmla
Abstract: Existing machine learning frameworks for compliance monitoring -- Markov Logic Networks, Probabilistic Soft Logic, supervised models -- share a fundamental paradigm: they treat observed data as ground truth and attempt to approximate rules from it. This assumption breaks down in rule-governed domains such as taxation or regulatory compliance, where authoritative rules are known a priori and the true challenge is to infer the latent state of rule activation, compliance, and parametric drift from partial and noisy observations. We propose Rule-State Inference (RSI), a Bayesian framework that inverts this paradigm by encoding regulatory rules as structured priors and casting compliance monitoring as posterior inference over a latent rule-state space S = {(a_i, c_i, delta_i)}, where a_i captures rule activation, c_i models the compliance rate, and delta_i quantifies parametric drift. We prove three theoretical guarantees: (T1) RSI absorbs regulatory changes in O(1) time via a prior ratio correction, independently of dataset size; (T2) the posterior is Bernstein-von Mises consistent, converging to the true rule state as observations accumulate; (T3) mean-field variational inference monotonically maximizes the Evidence Lower BOund (ELBO). We instantiate RSI on the Togolese fiscal system and introduce RSI-Togo-Fiscal-Synthetic v1.0, a benchmark of 2,000 synthetic enterprises grounded in real OTR regulatory rules (2022-2025). Without any labeled training data, RSI achieves F1=0.519 and AUC=0.599, while absorbing regulatory changes in under 1ms versus 683-1082ms for full model retraining -- at least a 600x speedup.
Authors: Tianyi Li, Zixuan Wang, Guidong Lei, Xiaodong Li, Hui Li
Abstract: Recommender agents built on Large Language Models offer a promising paradigm for recommendation. However, existing recommender agents typically suffer from a disconnect between intermediate reasoning and final ranking feedback, and are unable to capture fine-grained preferences. To address this, we present AgenticRec, a ranking-oriented agentic recommendation framework that optimizes the entire decision-making trajectory (including intermediate reasoning, tool invocation, and final ranking list generation) under sparse implicit feedback. Our approach makes three key contributions. First, we design a suite of recommendation-specific tools integrated into a ReAct loop to support evidence-grounded reasoning. Second, we propose theoretically unbiased List-Wise Group Relative Policy Optimization (list-wise GRPO) to maximize ranking utility, ensuring accurate credit assignment for complex tool-use trajectories. Third, we introduce Progressive Preference Refinement (PPR) to resolve fine-grained preference ambiguities. By mining hard negatives from ranking violations and applying bidirectional preference alignment, PPR minimizes the convex upper bound of pairwise ranking errors. Experiments on benchmarks confirm that AgenticRec significantly outperforms baselines, validating the necessity of unifying reasoning, tool use, and ranking optimization.
Authors: Ryosuke Sonoda, Ramya Srinivasan
Abstract: The rapid progress of text-to-image models has made AI-generated images increasingly realistic, posing significant challenges for accurate detection of generated content. While training-based detectors often suffer from limited generalization to unseen images, training-free approaches offer better robustness, yet struggle to capture subtle discrepancies between real and synthetic images. In this work, we propose a training-free AI-generated image detection method that measures representation sensitivity to structured frequency perturbations, enabling detection of minute manipulations. The proposed method is computationally lightweight, as perturbation generation requires only a single Fourier transform for an input image. As a result, it achieves one to two orders of magnitude faster inference than most training-free detectors.Extensive experiments on challenging benchmarks demonstrate the efficacy of our method over state-of-the-art (SoTA). In particular, on OpenFake benchmark, our method improves AUC by nearly $10\%$ compared to SoTA, while maintaining substantially lower computational cost.
Authors: Yanming Mu, Hao Hu, Feiyang Li, Qiao Yuan, Jiang Wu, Zichuan Liu, Pengcheng Liu, Mei Wang, Hongwei Zhou, Yuling Liu
Abstract: Retrieval-Augmented Generation (RAG) significantly mitigates the hallucinations and domain knowledge deficiency in large language models by incorporating external knowledge bases. However, the multi-module architecture of RAG introduces complex system-level security vulnerabilities. Guided by the RAG workflow, this paper analyzes the underlying vulnerability mechanisms and systematically categorizes core threat vectors such as data poisoning, adversarial attacks, and membership inference attacks. Based on this threat assessment, we construct a taxonomy of RAG defense technologies from a dual perspective encompassing both input and output stages. The input-side analysis reviews data protection mechanisms including dynamic access control, homomorphic encryption retrieval, and adversarial pre-filtering. The output-side examination summarizes advanced leakage prevention techniques such as federated learning isolation, differential privacy perturbation, and lightweight data sanitization. To establish a unified benchmark for future experimental design, we consolidate authoritative test datasets, security standards, and evaluation frameworks. To the best of our knowledge, this paper presents the first end-to-end survey dedicated to the security of RAG systems. Distinct from existing literature that isolates specific vulnerabilities, we systematically map the entire pipeline-providing a unified analysis of threat models, defense mechanisms, and evaluation benchmarks. By enabling deep insights into potential risks, this work seeks to foster the development of highly robust and trustworthy next-generation RAG systems.
Authors: Kangbo Zhao, Miaoxin Guan, Xiang Chen, Yukai Shi, Jinshan Pan
Abstract: Image deraining plays a pivotal role in low-level computer vision, serving as a prerequisite for robust outdoor surveillance and autonomous driving systems. While deep learning paradigms have achieved remarkable success in firmly aligned settings, they often suffer from severe performance degradation when generalized to unseen Out-of-Distribution (OOD) scenarios. This failure stems primarily from the significant domain discrepancy between synthetic training datasets and the complex physical dynamics of real-world rain. To address these challenges, this paper proposes a pioneering cross-scenario deraining adaptation framework. Diverging from conventional approaches, our method obviates the requirements for paired rainy observations in the target domain, leveraging exclusively rain-free background images. We design a Superpixel Generation (Sup-Gen) module to extract stable structural priors from the source domain using Simple Linear Iterative Clustering. Subsequently, a Resolution-adaptive Fusion strategy is introduced to align these source structures with target backgrounds through texture similarity, ensuring the synthesis of diverse and realistic pseudo-data. Finally, we implement a pseudo-label re-Synthesize mechanism that employs multi-stage noise generation to simulate realistic rain streaks. This framework functions as a versatile plug-and-play module capable of seamless integration into arbitrary deraining architectures. Extensive experiments on state-of-the-art models demonstrate that our approach yields remarkable PSNR gains of up to 32% to 59% in OOD domains while significantly accelerating training convergence.
Authors: Hung-Hsuan Chen
Abstract: Standard Transformers have a fixed computational depth, fundamentally limiting their ability to generalize to tasks requiring variable-depth reasoning, such as multi-hop graph traversal or nested logic. We propose a depth-recurrent Transformer that decouples computational depth from parameter count by iteratively applying a shared-weight Transformer block in latent space -- enabling the model to trade recurrence steps for deeper reasoning at inference time. Our architecture incorporates three mechanisms to make deep recurrence (20+ steps) stable: (1) a silent thinking objective that supervises only the final output, forcing genuine multi-step reasoning rather than intermediate heuristic shortcuts; (2) LayerScale initialization to protect fragile reasoning states from untrained layer noise; and (3) an identity-biased recurrence that creates a gradient highway across many steps. We evaluate on three compositional reasoning domains with decreasing inductive biases: graph reachability (strict adjacency masking), nested boolean logic (relative positioning), and unstructured relational text (where sequence position provides no structural hints). Across all tasks, we observe a clear \emph{computational frontier} -- a boundary where performance transitions from chance to near-perfect as thinking steps scale with task complexity. Moreover, these tasks reveal qualitatively different generalization behaviors: precise but brittle (graph), approximate but robust (logic), and autonomous latent routing without structural hints (text). This progression illuminates how the interplay between a task-invariant recurrent reasoning core and task-specific perceptual interfaces shapes out-of-distribution (OOD) generalization, offering a mechanistic perspective on vertical chain-of-thought that complements the prevailing horizontal token-generation paradigm.
Authors: Rui Yang Tan, Yujia Hu, Roy Ka-Wei Lee
Abstract: Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visually grounded instructions. We study comic-template jailbreaks that embed harmful goals inside simple three-panel visual narratives and prompt the model to role-play and "complete the comic." Building on JailbreakBench and JailbreakV, we introduce ComicJailbreak, a comic-based jailbreak benchmark with 1,167 attack instances spanning 10 harm categories and 5 task setups. Across 15 state-of-the-art MLLMs (six commercial and nine open-source), comic-based attacks achieve success rates comparable to strong rule-based jailbreaks and substantially outperform plain-text and random-image baselines, with ensemble success rates exceeding 90% on several commercial models. Then, with the existing defense methodologies, we show that these methods are effective against the harmful comics, they will induce a high refusal rate when prompted with benign prompts. Finally, using automatic judging and targeted human evaluation, we show that current safety evaluators can be unreliable on sensitive but non-harmful content. Our findings highlight the need for safety alignment robust to narrative-driven multimodal jailbreaks.
Authors: Yi Wang, Haofei Zhang, Qihan Huang, Anda Cao, Gongfan Fang, Wei Wang, Xuan Jin, Jie Song, Mingli Song, Xinchao Wang
Abstract: Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction methods mitigate this issue, they mainly target single-turn Visual Question Answering (VQA), leaving the more practical multi-turn VQA (MT-VQA) scenario largely unexplored. MT-VQA introduces additional challenges, as subsequent questions are unknown beforehand and may refer to arbitrary image regions, making existing reduction strategies ineffective. Specifically, current approaches fall into two categories: prompt-dependent methods, which bias toward the initial text prompt and discard information useful for subsequent turns; prompt-agnostic ones, which, though technically applicable to multi-turn settings, rely on heuristic reduction metrics such as attention scores, leading to suboptimal performance. In this paper, we propose a learning-based prompt-agnostic method, termed MetaCompress, overcoming the limitations of heuristic designs. We begin by formulating token reduction as a learnable compression mapping, unifying existing formats such as pruning and merging into a single learning objective. Upon this formulation, we introduce a data-efficient training paradigm capable of learning optimal compression mappings with limited computational costs. Extensive experiments on MT-VQA benchmarks and across multiple LVLM architectures demonstrate that MetaCompress achieves superior efficiency-accuracy trade-offs while maintaining strong generalization across dialogue turns. Our code is available at https://github.com/MArSha1147/MetaCompress.
Authors: Bahar Dibaei Nia, Farzan Farnia
Abstract: Efficient selection among multiple generative models is increasingly important in modern generative AI, where sampling from suboptimal models is costly. This problem can be formulated as a multi-armed bandit task. Under diversity-aware evaluation metrics, a non-degenerate mixture of generators can outperform any individual model, distinguishing this setting from classical best-arm identification. Prior approaches therefore incorporate an Upper Confidence Bound (UCB) exploration bonus into the mixture objective. However, across multiple datasets and evaluation metrics, we observe that the UCB term consistently slows convergence and often reduces sample efficiency. In contrast, a simple \emph{Mixture-Greedy} strategy without explicit UCB-type optimism converges faster and achieves even better performance, particularly for widely used metrics such as FID and Vendi where tight confidence bounds are difficult to construct. We provide theoretical insight explaining this behavior: under transparent structural conditions, diversity-aware objectives induce implicit exploration by favoring interior mixtures, leading to linear sampling of all arms and sublinear regret guarantees for entropy-based, kernel-based, and FID-type objectives. These results suggest that in diversity-aware multi-armed bandits for generative model selection, exploration can arise intrinsically from the objective geometry, questioning the necessity of explicit confidence bonuses.
Authors: Pengfei Cao, Mingxuan Yang, Yubo Chen, Chenlong Zhang, Mingxuan Liu, Kang Liu, Jun Zhao
Abstract: Understanding why real-world events occur is important for both natural language processing and practical decision-making, yet direct-cause inference remains underexplored in evidence-rich settings. To address this gap, we organized SemEval-2026 Task 12: Abductive Event Reasoning (AER).\footnote{The task data is available at https://github.com/sooo66/semeval2026-task12-dataset.git} The task asks systems to identify the most plausible direct cause of a target event from supporting evidence. We formulate AER as an evidence-grounded multiple-choice benchmark that captures key challenges of real-world causal reasoning, including distributed evidence, indirect background factors, and semantically related but non-causal distractors. The shared task attracted 122 participants and received 518 submissions. This paper presents the task formulation, dataset construction pipeline, evaluation setup, and system results. AER provides a focused benchmark for abductive reasoning over real-world events and highlights challenges for future work on causal reasoning and multi-document understanding.
URLs: https://github.com/sooo66/semeval2026-task12-dataset.git
Authors: Bulent Haznedar, Levent Karacan
Abstract: Transformers have achieved remarkable progress in time series forecasting, yet their reliance on deterministic dot-product attention limits their capacity to model uncertainty and nonlinear dependencies across multivariate temporal dimensions. To address this limitation, we propose FISFormer, a Fuzzy Inference System-driven Transformer that replaces conventional attention with a FIS Interaction mechanism. In this framework, each query-key pair undergoes a fuzzy inference process for every feature dimension, where learnable membership functions and rule-based reasoning estimate token-wise relational strengths. These FIS-derived interaction weights capture uncertainty and provide interpretable, continuous mappings between tokens. A softmax operation is applied along the token axis to normalize these weights, which are then combined with the corresponding value features through element-wise multiplication to yield the final context-enhanced token representations. This design fuses the interpretability and uncertainty modeling of fuzzy logic with the representational power of Transformers. Extensive experiments on multiple benchmark datasets demonstrate that FISFormer achieves superior forecasting accuracy, noise robustness, and interpretability compared to state-of-the-art Transformer variants, establishing fuzzy inference as an effective alternative to conventional attention mechanisms.
Authors: Kuangzhe Xu, Yu Shen, Longjie Yan, Yinghui Ren
Abstract: The proliferation of Generative Artificial Intelligence has transformed benign cognitive offloading into a systemic risk of cognitive agency surrender. Driven by the commercial dogma of "zero-friction" design, highly fluent AI interfaces actively exploit human cognitive miserliness, prematurely satisfying the need for cognitive closure and inducing severe automation bias. To empirically quantify this epistemic erosion, we deployed a zero-shot semantic classification pipeline ($\tau=0.7$) on 1,223 high-confidence AI-HCI papers from 2023 to early 2026. Our analysis reveals an escalating "agentic takeover": a brief 2025 surge in research defending human epistemic sovereignty (19.1%) was abruptly suppressed in early 2026 (13.1%) by an explosive shift toward optimizing autonomous machine agents (19.6%), while frictionless usability maintained a structural hegemony (67.3%). To dismantle this trap, we theorize "Scaffolded Cognitive Friction," repurposing Multi-Agent Systems (MAS) as explicit cognitive forcing functions (e.g., computational Devil's Advocates) to inject germane epistemic tension and disrupt heuristic execution. Furthermore, we outline a multimodal computational phenotyping agenda -- integrating gaze transition entropy, task-evoked pupillometry, fNIRS, and Hierarchical Drift Diffusion Modeling (HDDM) -- to mathematically decouple decision outcomes from cognitive effort. Ultimately, intentionally designed friction is not merely a psychological intervention, but a foundational technical prerequisite for enforcing global AI governance and preserving societal cognitive resilience.
Authors: Xu Liu, Yongheng Zhang, Qiguang Chen, Yao Li, Sheng Wang, Libo Qin
Abstract: Recently, Interleaved-modal Chain-of-Thought (ICoT) reasoning has achieved remarkable success by leveraging both multimodal inputs and outputs, attracting increasing attention. While achieving promising performance, current ICoT methods still suffer from two major limitations: (1) Static Visual Thought Positioning, which statically inserts visual information at fixed steps, resulting in inefficient and inflexible reasoning; and (2) Broken Visual Thought Representation, which involves discontinuous and semantically incoherent visual tokens. To address these limitations, we introduce Interleaved-modal Chain-of-Thought reasoning with Dynamic and Precise Visual Thoughts (DaP-ICoT), which incorporates two key components: (1) Dynamic Visual Thought Integration adaptively introduces visual inputs based on reasoning needs, reducing redundancy and improving efficiency. (2) Precise Visual Thought Guidance ensures visual semantically coherent and contextually aligned representations. Experiments across multiple benchmarks and models demonstrate that DaP-ICoT achieves state-of-the-art performance. In addition, DaP-ICoT significantly reduces the number of inserted images, leading to a 72.6% decrease in token consumption, enabling more efficient ICoT reasoning.
Authors: Jiaqi Shang, Haojin Wu, Yinyi Lai, Zongyu Li, Chenghao Zhang, Jia Guo
Abstract: Deformable image registration plays a fundamental role in medical image analysis by enabling spatial alignment of anatomical structures across subjects. While recent deep learning-based approaches have significantly improved computational efficiency, many existing methods remain limited in capturing long-range anatomical correspondence and maintaining deformation consistency. In this work, we present a cycle inverse-consistent transformer-based framework for deformable brain MRI registration. The model integrates a Swin-UNet architecture with bidirectional consistency constraints, enabling the joint estimation of forward and backward deformation fields. This design allows the framework to capture both local anatomical details and global spatial relationships while improving deformation stability. We conduct a comprehensive evaluation of the proposed framework on a large multi-center dataset consisting of 2851 T1-weighted brain MRI scans aggregated from 13 public datasets. Experimental results demonstrate that the proposed framework achieves strong and balanced performance across multiple quantitative evaluation metrics while maintaining stable and physically plausible deformation fields. Detailed quantitative comparisons with baseline methods, including ANTs, ICNet, and VoxelMorph, are provided in the appendix. Experimental results demonstrate that CICTM achieves consistently strong performance across multiple evaluation criteria while maintaining stable and physically plausible deformation fields. These properties make the proposed framework suitable for large-scale neuroimaging datasets where both accuracy and deformation stability are critical.
Authors: Yuze Qin, Qingyong Li, Zhiqing Guo, Wen Wang, Yan Liu, Yangli-ao Geng
Abstract: Precipitation nowcasting is critical for disaster mitigation and aviation safety. However, radar-only models frequently suffer from a lack of large-scale atmospheric context, leading to performance degradation at longer lead times. While integrating meteorological variables predicted by weather foundation models offers a potential remedy, existing architectures fail to reconcile the profound representational heterogeneities between radar imagery and meteorological data. To bridge this gap, we propose PW-FouCast, a novel frequency-domain fusion framework that leverages Pangu-Weather forecasts as spectral priors within a Fourier-based backbone. Our architecture introduces three key innovations: (i) Pangu-Weather-guided Frequency Modulation to align spectral magnitudes and phases with meteorological priors; (ii) Frequency Memory to correct phase discrepancies and preserve temporal evolution; and (iii) Inverted Frequency Attention to reconstruct high-frequency details typically lost in spectral filtering. Extensive experiments on the SEVIR and MeteoNet benchmarks demonstrate that PW-FouCast achieves state-of-the-art performance, effectively extending the reliable forecast horizon while maintaining structural fidelity. Our code is available at https://github.com/Onemissed/PW-FouCast.
Authors: Jesper B. Christensen, Ciaran Bench, Spencer A. Thomas, H\"usn\"u Aslan, David Balslev-Harder, Nadia A. S. Smith, Alessandra Manzin
Abstract: We introduce ControlAugment (Ctrl-A), an automated data augmentation algorithm for image-vision tasks, which incorporates principles from control theory for online adjustment of augmentation strength distributions during model training. Ctrl-A eliminates the need for initialization of individual augmentation strengths. Instead, augmentation strength distributions are dynamically, and individually, adapted during training based on a control-loop architecture and what we define as relative operation response curves. Using an operation-dependent update procedure provides Ctrl-A with the potential to suppress augmentation styles that negatively impact model performance, alleviating the need for manually engineering augmentation policies for new image-vision tasks. Experiments on the CIFAR-10, CIFAR-100, and SVHN-core benchmark datasets using the common WideResNet-28-10 architecture demonstrate that Ctrl-A is highly competitive with existing state-of-the-art data augmentation strategies.
Authors: Shuxian Zhao, Jie Gui, Baosheng Yu, Lu Dong, Zhipeng Gui
Abstract: Steel surface defect detection is essential for ensuring product quality and reliability in modern manufacturing. Current methods often rely on basic image classification models trained on label-only datasets, which limits their interpretability and generalization. To address these challenges, we introduce SteelDefectX, a vision-language dataset containing 7,778 images across 25 defect categories, annotated with coarse-to-fine textual descriptions. At the coarse-grained level, the dataset provides class-level information, including defect categories, representative visual attributes, and associated industrial causes. At the fine-grained level, it captures sample-specific attributes, such as shape, size, depth, position, and contrast, enabling models to learn richer and more detailed defect representations. We further establish a benchmark comprising four tasks, vision-only classification, vision-language classification, few/zero-shot recognition, and zero-shot transfer, to evaluate model performance and generalization. Experiments with several baseline models demonstrate that coarse-to-fine textual annotations significantly improve interpretability, generalization, and transferability. We hope that SteelDefectX will serve as a valuable resource for advancing research on explainable, generalizable steel surface defect detection. The data will be publicly available on https://github.com/Zhaosxian/SteelDefectX.
Authors: Taizhou Chen, Kai Chen, Xingyu Liu, Pingchuan Ke, Zhida Sun
Abstract: Evaluating badminton performance often requires expert coaching, which is rarely accessible for amateur players. We present BadminSense, a smartwatch-based system for fine-grained badminton performance analysis using wearable sensing. Through interviews with experienced badminton players, we identified four system design requirements with three implementation insights that guide the development of BadminSense. We then collected a badminton strokes dataset on 12 experienced badminton amateurs and annotated it with fine-grained labels, including stroke type, expert-assessed stroke rating, and shuttle impact location. Built on this dataset, BadminSense segments and classifies strokes, predicts stroke quality, and estimates shuttle impact location using vibration signal from an off-the-shelf smartwatch. Our evaluations show that BadminSense achieves a stroke classification accuracy of 91.43%, an average quality rating error of 0.438, and an average impact location estimation error of 12.9%. A real-world usability study further demonstrates BadminSense's potential to provide reliable and meaningful support for daily badminton practice.
Authors: Hanyin Cheng, Xingjian Wu, Yang Shu, Zhongwen Rao, Lujia Pan, Bin Yang, Chenjuan Guo
Abstract: Most existing Time Series Foundation Models (TSFMs) use channel independent modeling and focus on capturing and generalizing temporal dependencies, while neglecting the correlations among channels or overlooking the different aspects of correlations. However, these correlations play a vital role in Multivariate time series forecasting. To address this, we propose a CoRrelation-aware Adapter (CoRA), a lightweight plug-and-play method that requires only fine-tuning with TSFMs and is able to capture different types of correlations, so as to improve forecast performance. Specifically, to reduce complexity, we innovatively decompose the correlation matrix into low-rank Time-Varying and Time-Invariant components. For the Time-Varying component, we further design learnable polynomials to learn dynamic correlations by capturing trends or periodic patterns. To learn positive and negative correlations that appear only among some channels, we introduce a novel dual contrastive learning method that identifies correlations through projection layers, regulated by a Heterogeneous-Partial contrastive loss during training, without introducing additional complexity in the inference stage. Extensive experiments on 10 real-world datasets demonstrate that CoRA can improve TSFMs in multivariate forecasting performance.
Authors: Ezequiel Lopez-Rubio, Mario Pascual-Gonzalez
Abstract: A fundamental but largely unaddressed obstacle in Symbolic regression (SR) is structural redundancy: every expression DAG with admits many distinct node-numbering schemes that all encode the same expression, each occupying a separate point in the search space and consuming fitness evaluations without adding diversity. We present IsalSR (Instruction Set and Language for Symbolic Regression), a representation framework that encodes expression DAGs as strings over a compact two-tier alphabet and computes a pruned canonical string -- a complete labeled-DAG isomorphism invariant -- that collapses all the equivalent representations into a single canonical form.
Authors: Antonio Purificato, Maria Sofia Bucarelli, Andrea Bacciu, Amin Mantrach, Fabrizio Silvestri
Abstract: Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly expensive due to the stringent requirement for low-error and high-quality labels necessary for reliable model evaluation. Traditional approaches require annotating entire test sets, leading to substantial resource requirements. Active Testing is a framework that selects the most informative test samples for annotation. Given a labeling budget, it aims to choose the subset that best estimates model performance while minimizing cost and human effort. In this work, we formalize Active Testing in NLP and we conduct an extensive benchmarking of existing approaches across 18 datasets and 4 embedding strategies spanning 4 different NLP tasks. The experiments show annotation reductions of up to 95%, with performance estimation accuracy difference from the full test set within 1%. Our analysis reveals variations in method effectiveness across different data characteristics and task types, with no single approach emerging as universally superior. Lastly, to address the limitation of requiring a predefined annotation budget in existing sample selection strategies, we introduce an adaptive stopping criterion that automatically determines the optimal number of samples.
Authors: Marc Franquesa Mon\'es, Jiaqi Zhang, Caroline Uhler
Abstract: Learning causal relations from observational data is a fundamental problem with wide-ranging applications across many fields. Constraint-based methods infer the underlying causal structure by performing conditional independence tests. However, existing algorithms such as the prominent PC algorithm need to perform a large number of independence tests, which in the worst case is exponential in the maximum degree of the causal graph. Despite extensive research, it remains unclear if there exist algorithms with better complexity without additional assumptions. Here, we establish an algorithm that achieves a better complexity of $p^{\mathcal{O}(s)}$ tests, where $p$ is the number of nodes in the graph and $s$ denotes the maximum undirected clique size of the underlying essential graph. Complementing this result, we prove that any constraint-based algorithm must perform at least $2^{\Omega(s)}$ conditional independence tests, establishing that our proposed algorithm achieves exponent-optimality up to a logarithmic factor in terms of the number of conditional independence tests needed. Finally, we validate our theoretical findings through simulations, on semi-synthetic gene-expression data, and real-world data, demonstrating the efficiency of our algorithm compared to existing methods in terms of number of conditional independence tests needed.
Authors: Junhyeok Rui Cha, Woohyun Cha, Jaeyong Shin, Donghyeon Kim, Jaeheung Park
Abstract: This paper proposes a novel alternative to existing sim-to-real methods for training control policies with simulated experiences. Unlike prior methods that typically rely on domain randomization over a fixed finite set of parameters, the proposed approach injects state-dependent perturbations into the input joint torque during forward simulation. These perturbations are designed to simulate a broader spectrum of reality gaps than standard parameter randomization without requiring additional training. By using neural networks as flexible perturbation generators, the proposed method can represent complex, state-dependent uncertainties, such as nonlinear actuator dynamics and contact compliance, that parametric randomization cannot capture. Experimental results demonstrate that the proposed approach enables humanoid locomotion policies to achieve superior robustness against complex, unseen reality gaps in both simulation and real-world deployment.
Authors: Yuyang You, Yongzhi Li, Jiahui Li, Yadong Mu, Quan Chen, Peng Jiang
Abstract: Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical technique for efficient deployment. Despite its significance, there is a scarcity of methods specifically designed for video diffusion models. Prevailing approaches often directly adapt image distillation techniques, which frequently lead to artifacts such as oversaturation, temporal inconsistency, and mode collapse. To address these challenges, we propose a novel distillation framework tailored specifically for video diffusion models. Its core innovations include: (1) an adaptive regression loss that dynamically adjusts spatial supervision weights to prevent artifacts arising from excessive distribution shifts; (2) a temporal regularization loss to counteract temporal collapse, promoting smooth and physically plausible sampling trajectories; and (3) an inference-time frame interpolation strategy that reduces sampling overhead while preserving perceptual quality. Extensive experiments and ablation studies on the VBench and VBench2 benchmarks demonstrate that our method achieves stable few-step video synthesis, significantly enhancing perceptual fidelity and motion realism. It consistently outperforms existing distillation baselines across multiple metrics.
Authors: Pawe{\l} Borsukiewicz, Daniele Lunghi, Melissa Tessa, Jacques Klein, Tegawend\'e F. Bissyand\'e
Abstract: While the rapid development of facial recognition algorithms has enabled numerous beneficial applications, their widespread deployment has raised significant concerns about the risks of mass surveillance and threats to individual privacy. In this paper, we introduce \textit{Adversarial Camouflage} as a novel solution for protecting users' privacy. This approach is designed to be efficient and simple to reproduce for users in the physical world. The algorithm starts by defining a low-dimensional pattern space parameterized by color, shape, and angle. Optimized patterns, once found, are projected onto semantically valid facial regions for evaluation. Our method maximizes recognition error across multiple architectures, ensuring high cross-model transferability even against black-box systems. It significantly degrades the performance of all tested state-of-the-art face recognition models during simulations and demonstrates promising results in real-world human experiments, while revealing differences in model robustness and evidence of attack transferability across architectures.
Authors: Mingzhe Zheng, Weijie Kong, Yue Wu, Dengyang Jiang, Yue Ma, Xuanhua He, Bin Lin, Kaixiong Gong, Zhao Zhong, Liefeng Bo, Qifeng Chen, Harry Yang
Abstract: Group Relative Policy Optimization (GRPO) methods for video generation like FlowGRPO remain far less reliable than their counterparts for language models and images. This gap arises because video generation has a complex solution space, and the ODE-to-SDE conversion used for exploration can inject excess noise, lowering rollout quality and making reward estimates less reliable, which destabilizes post-training alignment. To address this problem, we view the pre-trained model as defining a valid video data manifold and formulate the core problem as constraining exploration within the vicinity of this manifold, ensuring that rollout quality is preserved and reward estimates remain reliable. We propose SAGE-GRPO (Stable Alignment via Exploration), which applies constraints at both micro and macro levels. At the micro level, we derive a precise manifold-aware SDE with a logarithmic curvature correction and introduce a gradient norm equalizer to stabilize sampling and updates across timesteps. At the macro level, we use a dual trust region with a periodic moving anchor and stepwise constraints so that the trust region tracks checkpoints that are closer to the manifold and limits long-horizon drift. We evaluate SAGE-GRPO on HunyuanVideo1.5 using the original VideoAlign as the reward model and observe consistent gains over previous methods in VQ, MQ, TA, and visual metrics (CLIPScore, PickScore), demonstrating superior performance in both reward maximization and overall video quality. The code and visual gallery are available at https://dungeonmassster.github.io/SAGE-GRPO-Page/.
Authors: Xinyu Lu, Kaiqi Zhang, Jinglin Yang, Boxi Cao, Yaojie Lu, Hongyu Lin, Min He, Xianpei Han, Le Sun
Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). However, vanilla RLVR suffers from inefficient exploration, particularly when confronting "hard samples" that yield nearzero success rates. In such scenarios, the reliance on sparse outcome rewards typically results in zero-advantage estimates, effectively starving the model of supervision signals despite the high informational value of these instances. To address this, we propose P^2O, a novel framework that synergizes Prompt Optimization with Policy Optimization. P^2O identifies hard samples during training iterations and leverages the GeneticPareto (GEPA) prompt optimization algorithm to evolve prompt templates that guide the model toward discovering successful trajectories. Crucially, unlike traditional prompt engineering methods that rely on input augmentation, P^2O distills the reasoning gains induced by these optimized prompts directly into the model parameters. This mechanism provides denser positive supervision signals for hard samples and accelerates convergence. Extensive experiments demonstrate that P^2O not only achieves superior performance on in-distribution datasets but also exhibits strong generalization, yielding substantial improvements on out-of-distribution benchmarks (+4.7% avg.).
Authors: Nikolas Stavrou, Siamak Mehrkanoon
Abstract: Weather forecasting supports critical socioeconomic activities and complements environmental protection, yet operational Numerical Weather Prediction (NWP) systems remain computationally intensive, thus being inefficient for certain applications. Meanwhile, recent advances in deep data-driven models have demonstrated promising results in nowcasting tasks. This paper presents SmaAT-QMix-UNet, an enhanced variant of SmaAT-UNet that introduces two key innovations: a vector quantization (VQ) bottleneck at the encoder-decoder bridge, and mixed kernel depth-wise convolutions (MixConv) replacing selected encoder and decoder blocks. These enhancements both reduce the model's size and improve its nowcasting performance. We train and evaluate SmaAT-QMix-UNet on a Dutch radar precipitation dataset (2016-2019), predicting precipitation 30 minutes ahead. Three configurations are benchmarked: using only VQ, only MixConv, and the full SmaAT-QMix-UNet. Grad-CAM saliency maps highlight the regions influencing each nowcast, while a UMAP embedding of the codewords illustrates how the VQ layer clusters encoder outputs. The source code for SmaAT-QMix-UNet is publicly available on GitHub \footnote{\href{https://github.com/nstavr04/MasterThesisSnellius}{https://github.com/nstavr04/MasterThesisSnellius}}.
URLs: https://github.com/nstavr04/MasterThesisSnellius, https://github.com/nstavr04/MasterThesisSnellius
Authors: Donald Shenaj, Federico Errica, Antonio Carta
Abstract: Low Rank Adaptation (LoRA) is the de facto fine-tuning strategy to generate personalized images from pre-trained diffusion models. Choosing a good rank is extremely critical, since it trades off performance and memory consumption, but today the decision is often left to the community's consensus, regardless of the personalized subject's complexity. The reason is evident: the cost of selecting a good rank for each LoRA component is combinatorial, so we opt for practical shortcuts such as fixing the same rank for all components. In this paper, we take a first step to overcome this challenge. Inspired by variational methods that learn an adaptive width of neural networks, we let the ranks of each layer freely adapt during fine-tuning on a subject. We achieve it by imposing an ordering of importance on the rank's positions, effectively encouraging the creation of higher ranks when strictly needed. Qualitatively and quantitatively, our approach, LoRA$^2$, achieves a competitive trade-off between DINO, CLIP-I, and CLIP-T across 29 subjects while requiring much less memory and lower rank than high rank LoRA versions. Code: https://github.com/donaldssh/NotAllLayersAreCreatedEqual.
URLs: https://github.com/donaldssh/NotAllLayersAreCreatedEqual.
Authors: Linkuan Zhou, Yinghao Xia, Yufei Shen, Xiangyu Li, Wenjie Du, Cong Cong, Leyi Wei, Ran Su, Qiangguo Jin
Abstract: Unsupervised Domain Adaptation (UDA) is essential for deploying medical segmentation models across diverse clinical environments. Existing methods are fundamentally limited, suffering from semantically unaware feature alignment that results in poor distributional fidelity and from pseudo-label validation that disregards global anatomical constraints, thus failing to prevent the formation of globally implausible structures. To address these issues, we propose SHAPE (Structure-aware Hierarchical Unsupervised Domain Adaptation with Plausibility Evaluation), a framework that reframes adaptation towards global anatomical plausibility. Built on a DINOv3 foundation, its Hierarchical Feature Modulation (HFM) module first generates features with both high fidelity and class-awareness. This shifts the core challenge to robustly validating pseudo-labels. To augment conventional pixel-level validation, we introduce Hypergraph Plausibility Estimation (HPE), which leverages hypergraphs to assess the global anatomical plausibility that standard graphs cannot capture. This is complemented by Structural Anomaly Pruning (SAP) to purge remaining artifacts via cross-view stability. SHAPE significantly outperforms prior methods on cardiac and abdominal cross-modality benchmarks, achieving state-of-the-art average Dice scores of 90.08% (MRI->CT) and 78.51% (CT->MRI) on cardiac data, and 87.48% (MRI->CT) and 86.89% (CT->MRI) on abdominal data. The code is available at https://github.com/BioMedIA-repo/SHAPE.
Authors: Juan Sebastian Rojas, Chi-Guhn Lee
Abstract: The temporal difference (TD) error was first formalized in Sutton (1988), where it was first characterized as the difference between temporally successive predictions, and later, in that same work, formulated as the difference between a bootstrapped target and a prediction. Since then, these two interpretations of the TD error have been used interchangeably in the literature, with the latter eventually being adopted as the standard critic loss in deep reinforcement learning (RL) architectures. In this work, we show that these two interpretations of the TD error are not always equivalent. In particular, we show that increasingly-nonlinear deep RL architectures can cause these interpretations of the TD error to yield increasingly different numerical values. Then, building on this insight, we show how choosing one interpretation of the TD error over the other can affect the performance of deep RL algorithms that utilize the TD error to compute other quantities, such as with deep differential (i.e., average-reward) RL methods. All in all, our results show that the default interpretation of the TD error as the difference between a bootstrapped target and a prediction does not always hold in deep RL settings.
Authors: Peter Fasogbon, Ugurcan Budak, Patrice Rondao Alface, Hamed Rezazadegan Tavakoli
Abstract: The pruning of 3D Gaussian splats is essential for reducing their complexity to enable efficient storage, transmission, and downstream processing. However, most of the existing pruning strategies depend on camera parameters, rendered images, or view-dependent measures. This dependency becomes a hindrance in emerging camera-agnostic exchange settings, where splats are shared directly as point-based representations (e.g., .ply). In this paper, we propose a camera-agnostic, one-shot, post-training pruning method for 3D Gaussian splats that relies solely on attribute-derived neighbourhood descriptors. As our primary contribution, we introduce a hybrid descriptor framework that captures structural and appearance consistency directly from the splat representation. Building on these descriptors, we formulate pruning as a statistical evidence estimation problem and introduce a Beta evidence model that quantifies per-splat reliability through a probabilistic confidence score. Experiments conducted on standardized test sequences defined by the ISO/IEC MPEG Common Test Conditions (CTC) demonstrate that our approach achieves substantial pruning while preserving reconstruction quality, establishing a practical and generalizable alternative to existing camera-dependent pruning strategies.
Authors: Clemens Watzenb\"ock, Daniel Aletaha, Micha\"el Deman, Thomas Deimel, Jana Eder, Ivana Janickova, Robert Janiczek, Peter Mandl, Philipp Seeb\"ock, Gabriela Supp, Paul Weiser, Georg Langs
Abstract: Quantitative disease severity scoring in medical imaging is costly, time-consuming, and subject to inter-reader variability. At the same time, clinical archives contain far more longitudinal imaging data than expert-annotated severity scores. Existing self-supervised methods typically ignore this chronological structure. We introduce ChronoCon, a contrastive learning approach that replaces label-based ranking losses with rankings derived solely from the visitation order of a patient's longitudinal scans. Under the clinically plausible assumption of monotonic progression in irreversible diseases, the method learns disease-relevant representations without using any expert labels. This generalizes the idea of Rank-N-Contrast from label distances to temporal ordering. Evaluated on rheumatoid arthritis radiographs for severity assessment, the learned representations substantially improve label efficiency. In low-label settings, ChronoCon significantly outperforms a fully supervised baseline initialized from ImageNet weights. In a few-shot learning experiment, fine-tuning ChronoCon on expert scores from only five patients yields an intraclass correlation coefficient of 86% for severity score prediction. These results demonstrate the potential of chronological contrastive learning to exploit routinely available imaging metadata to reduce annotation requirements in the irreversible disease domain. Code is available at https://github.com/cirmuw/ChronoCon.
Authors: Junyi An, Xinyu Lu, Yun-Fei Shi, Li-Cheng Xu, Nannan Zhang, Chao Qu, Yuan Qi, Fenglei Cao
Abstract: We introduce Suiren-1.0, a family of molecular foundation models for the accurate modeling of diverse organic systems. Suiren-1.0 comprising three specialized variants (Suiren-Base, Suiren-Dimer, and Suiren-ConfAvg) is integrated within an algorithmic framework that bridges the gap between 3D conformational geometry and 2D statistical ensemble spaces. We first pre-train Suiren-Base (1.8B parameters) on a 70M-sample Density Functional Theory dataset using spatial self-supervision and SE(3)-equivariant architectures, achieving robust performance in quantum property prediction. Suiren-Dimer extends this capability through continued pre-training on 13.5M intermolecular interaction samples. To enable efficient downstream application, we propose Conformation Compression Distillation (CCD), a diffusion-based framework that distills complex 3D structural representations into 2D conformation-averaged representations. This yields the lightweight Suiren-ConfAvg, which generates high-fidelity representations from SMILES or molecular graphs. Our extensive evaluations demonstrate that Suiren-1.0 establishes state-of-the-art results across a range of tasks. All models and benchmarks are open-sourced.
Authors: Ulugbek Shernazarov, Rostislav Svitsov, Bin Shi
Abstract: Fine-tuning large language models for domain-specific tasks such as medical text summarization demands substantial computational resources. Parameter-efficient fine-tuning (PEFT) methods offer promising alternatives by updating only a small fraction of parameters. This paper compares three adaptation approaches-Low-Rank Adaptation (LoRA), Prompt Tuning, and Full Fine-Tuning-across the Flan-T5 model family on the PubMed medical summarization dataset. Through experiments with multiple random seeds, we demonstrate that LoRA consistently outperforms full fine-tuning, achieving 43.52 +/- 0.18 ROUGE-1 on Flan-T5-Large with only 0.6% trainable parameters compared to 40.67 +/- 0.21 for full fine-tuning. Sensitivity analyses examine the impact of LoRA rank and prompt token count. Our findings suggest the low-rank constraint provides beneficial regularization, challenging assumptions about the necessity of full parameter updates. Code is available at https://github.com/eracoding/llm-medical-summarization
URLs: https://github.com/eracoding/llm-medical-summarization
Authors: Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera
Abstract: Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Although previous related works focused primarily on model architectures and alignment methodologies, these approaches alone cannot ensure the complete elimination of harmful generations. This concern is reinforced by the growing body of scientific literature showing that attacks, such as jailbreaking and prompt injection, can bypass existing security alignment mechanisms. As a consequence, additional security strategies are needed both to provide qualitative feedback on the robustness of the obtained security alignment at the training stage, and to create an ``ultimate'' defense layer to block unsafe outputs possibly produced by deployed models. To provide a contribution in this scenario, this paper introduces SecureBreak, a safety-oriented dataset designed to support the development of AI-driven solutions for detecting harmful LLM outputs caused by residual weaknesses in security alignment. The dataset is highly reliable due to careful manual annotation, where labels are assigned conservatively to ensure safety. It performs well in detecting unsafe content across multiple risk categories. Tests with pre-trained LLMs show improved results after fine-tuning on SecureBreak. Overall, the dataset is useful both for post-generation safety filtering and for guiding further model alignment and security improvements.
Authors: Nour Alhuda Albashir, Lars Pernickel, Danial Hamoud, Idriss Gouigah, Eren Erdal Aksoy
Abstract: Autonomous vehicles face major perception and navigation challenges in adverse weather such as rain, fog, and snow, which degrade the performance of LiDAR, RADAR, and RGB camera sensors. While each sensor type offers unique strengths, such as RADAR robustness in poor visibility and LiDAR precision in clear conditions, they also suffer distinct limitations when exposed to environmental obstructions. This study proposes LRC-WeatherNet, a novel multi-sensor fusion framework that integrates LiDAR, RADAR, and camera data for real-time classification of weather conditions. By employing both early fusion using a unified Bird's Eye View representation and mid-level gated fusion of modality-specific feature maps, our approach adapts to the varying reliability of each sensor under changing weather. Evaluated on the extensive MSU-4S dataset covering nine weather types, LRC-WeatherNet achieves superior classification performance and computational efficiency, significantly outperforming unimodal baselines in adverse conditions. This work is the first to combine all three modalities for robust, real-time weather classification in autonomous driving. We release our trained models and source code in https://github.com/nouralhudaalbashir/LRC-WeatherNet.
Authors: Dilina Rajapakse, Juan C. Rosero, Ivana Dusparic
Abstract: Reinforcement Learning (RL) has demonstrated its ability to solve complex decision-making problems in a variety of domains, by optimizing reward signals obtained through interaction with an environment. However, many real-world scenarios involve multiple, potentially conflicting objectives that cannot be easily represented by a single scalar reward. Multi-Objective Reinforcement Learning (MORL) addresses this limitation by enabling agents to optimize several objectives simultaneously, explicitly reasoning about trade-offs between them. However, the ``black box" nature of the RL models makes the decision process behind chosen objective trade-offs unclear. Current Explainable Reinforcement Learning (XRL) methods are typically designed for single scalar rewards and do not account for explanations with respect to distinct objectives or user preferences. To address this gap, in this paper we propose TREX, a Trajectory based Explainability framework to explain Multi-objective Reinforcement Learning policies, based on trajectory attribution. TREX generates trajectories directly from the learned expert policy, across different user preferences and clusters them into semantically meaningful temporal segments. We quantify the influence of these behavioural segments on the Pareto trade-off by training complementary policies that exclude specific clusters, measuring the resulting relative deviation on the observed rewards and actions compared to the original expert policy. Experiments on multi-objective MuJoCo environments - HalfCheetah, Ant and Swimmer, demonstrate the framework's ability to isolate and quantify the specific behavioural patterns.
Authors: Cristian P\'erez-Corral, Alberto Fern\'andez-Hern\'andez, Jose I. Mestre, Manuel F. Dolz, Enrique S. Quintana-Ort\'i
Abstract: Gaussian Error Linear Unit (GELU) is a widely used smooth alternative to Rectifier Linear Unit (ReLU), yet many deployment, compression, and analysis toolchains are most naturally expressed for piecewise-linear (ReLU-type) networks. We study a hardness-parameterized formulation of GELU, f(x;{\lambda})=x{\Phi}({\lambda} x), where {\Phi} is the Gaussian CDF and {\lambda} \in [1, infty) controls gate sharpness, with the goal of turning smooth gated training into a controlled path toward ReLU-compatible models. Learning {\lambda} is non-trivial: naive updates yield unstable dynamics and effective gradient attenuation, so we introduce a constrained reparameterization and an optimizer-aware update scheme. Empirically, across a diverse set of model--dataset pairs spanning MLPs, CNNs, and Transformers, we observe structured layerwise hardness profiles and assess their robustness under different initializations. We further study a deterministic ReLU-ization strategy in which the learned gates are progressively hardened toward a principled target, enabling a post-training substitution of {\lambda}-GELU by ReLU with reduced disruption. Overall, {\lambda}-GELU provides a minimal and interpretable knob to profile and control gating hardness, bridging smooth training with ReLU-centric downstream pipelines.
Authors: Duy D. Nguyen, Phat T. Tran-Truong
Abstract: The advent of Transformer and Mamba-based architectures has significantly advanced 3D medical image segmentation by enabling global contextual modeling, a capability traditionally limited in Convolutional Neural Networks (CNNs). However, state-of-the-art Transformer models often entail substantial computational complexity and parameter counts, which is particularly prohibitive for volumetric data and further exacerbated by the limited availability of annotated medical imaging datasets. To address these limitations, this work introduces SegMaFormer, a lightweight hybrid architecture that synergizes Mamba and Transformer modules within a hierarchical volumetric encoder for efficient long-range dependency modeling. The model strategically employs Mamba-based layers in early, high-resolution stages to reduce computational overhead while capturing essential spatial context, and reserves self-attention mechanisms for later, lower-resolution stages to refine feature representation. This design is augmented with generalized rotary position embeddings to enhance spatial awareness. Despite its compact structure, SegMaFormer achieves competitive performance on three public benchmarks (Synapse, BraTS, and ACDC), matching the Dice coefficient of significantly larger models. Empirically, our approach reduces parameters by up to 75x and substantially decreases FLOPs compared to current state-of-the-art models, establishing an efficient and high-performing solution for 3D medical image segmentation.
Authors: Xinyan Wang, Xiaogeng Liu, Chaowei Xiao
Abstract: Large Reasoning Models (LRMs) achieve strong accuracy on challenging tasks by generating long Chain-of-Thought traces, but suffer from overthinking. Even after reaching the correct answer, they continue generating redundant reasoning steps. This behavior increases latency and compute cost and can also lead to answer drift. Existing mitigation methods either require training-heavy backbone modification or rely on hand-crafted heuristics that do not truly capture overthinking patterns. We propose ROM, the first method that formulates overthinking mitigation as a streaming prediction-and-control problem. ROM attaches a lightweight detection head to the late-layer hidden states of a frozen large language model backbone. It monitors tokens in real time and triggers an early transition to the final answer once overthinking is detected. We also introduce token-level supervision based on solution correctness boundaries and a data augmentation strategy that reduces distilled-data bias. Across seven benchmarks, ROM achieves the highest accuracy (93.51%), the shortest responses (1,159 tokens), and the best response efficiency. Compared with the vanilla baseline, it reduces response length by 47.2% and improves efficiency by 121%. These results show that streaming detection is a promising approach to real-time overthinking mitigation.
Authors: Hayeon Kim, Ji Ha Jang, Junghun James Kim, Se Young Chun
Abstract: While Vision-Language Models (VLMs) have achieved remarkable performance, their Euclidean embeddings remain limited in capturing hierarchical relationships such as part-to-whole or parent-child structures, and often face challenges in multi-object compositional scenarios. Hyperbolic VLMs mitigate this issue by better preserving hierarchical structures and modeling part-whole relations (i.e., whole scene and its part images) through entailment. However, existing approaches do not model that each part has a different level of semantic representativeness to the whole. We propose UNcertainty-guided Compositional Hyperbolic Alignment (UNCHA) for enhancing hyperbolic VLMs. UNCHA models part-to-whole semantic representativeness with hyperbolic uncertainty, by assigning lower uncertainty to more representative parts and higher uncertainty to less representative ones for the whole scene. This representativeness is then incorporated into the contrastive objective with uncertainty-guided weights. Finally, the uncertainty is further calibrated with an entailment loss regularized by entropy-based term. With the proposed losses, UNCHA learns hyperbolic embeddings with more accurate part-whole ordering, capturing the underlying compositional structure in an image and improving its understanding of complex multi-object scenes. UNCHA achieves state-of-the-art performance on zero-shot classification, retrieval, and multi-label classification benchmarks. Our code and models are available at: https://github.com/jeeit17/UNCHA.git.
Authors: Valentin Petrov
Abstract: Inasmuch as the removal of refusal behavior from instruction-tuned language models by directional abliteration requires the extraction of refusal-mediating directions from the residual stream activation space, and inasmuch as the construction of the contrast baseline against which harmful prompt activations are compared has been treated in the existing literature as an implementation detail rather than a methodological concern, the present work investigates whether a topically matched contrast baseline yields superior refusal directions. The investigation is carried out on the Qwen~3.5 2B model using per-category matched prompt pairs, per-class Self-Organizing Map extraction, and Singular Value Decomposition orthogonalization. It was found that topic-matched contrast produces no functional refusal directions at any tested weight level on any tested layer, while unmatched contrast on the same model, same extraction code, and same evaluation protocol achieves complete refusal elimination on six layers. The geometric analysis of the failure establishes that topic-matched subtraction cancels the dominant activation component shared between harmful and harmless prompts of the same subject, reducing the extracted direction magnitude below the threshold at which weight-matrix projection perturbs the residual stream. The implications for the design of contrast baselines in abliteration research are discussed.
Authors: Kexin Huang, Haoming Meng, Junkang Wu, Jinda Lu, Chiyu Ma, Ziqian Chen, Xue Wang, Bolin Ding, Jiancan Wu, Xiang Wang, Xiangnan He, Guoyin Wang, Jingren Zhou
Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models. While existing analyses identify that RLVR-induced changes are sparse, they primarily focus on the \textbf{magnitude} of these updates, largely overlooking their \textbf{direction}. In this work, we argue that the direction of updates is a more critical lens for understanding RLVR's effects, which can be captured by the signed, token-level log probability difference $\Delta\log p$ between the base and final RLVR models. Through statistical analysis and token-replacement interventions, we demonstrate that $\Delta\log p$ more effectively identifies sparse, yet reasoning-critical updates than magnitude-based metrics (\eg divergence or entropy). Building on this insight, we propose two practical applications: (1) a \textit{test-time extrapolation} method that amplifies the policy along the learned $\Delta\log p$ direction to improve reasoning accuracy without further training; (2) a \textit{training-time reweighting} method that focuses learning on low-probability (corresponding to higher $\Delta\log p$) tokens, which improves reasoning performance across models and benchmarks. Our work establishes the direction of change as a key principle for analyzing and improving RLVR.
Authors: Yunzhuo Sun, Xinyue Liu, Yanyang Li, Nanding Wu, Yifang Xu, Linlin Zong, Xianchao Zhang, Wenxin Liang
Abstract: Text-driven video moment retrieval (VMR) remains challenging due to limited capture of hidden temporal dynamics in untrimmed videos, leading to imprecise grounding in long sequences. Traditional methods rely on natural language queries (NLQs) or static image augmentations, overlooking motion sequences and suffering from high computational costs in Transformer-based architectures. Existing approaches fail to integrate subtitle contexts and generated temporal priors effectively, we therefore propose a novel two-stage framework for enhanced temporal grounding. In the first stage, LLM-guided subtitle matching identifies relevant textual cues from video subtitles, fused with the query to generate auxiliary short videos via text-to-video models, capturing implicit motion information as temporal priors. In the second stage, augmented queries are processed through a multi-modal controlled Mamba network, extending text-controlled selection with video-guided gating for efficient fusion of generated priors and long sequences while filtering noise. Our framework is agnostic to base retrieval models and widely applicable for multimodal VMR. Experimental evaluations on the TVR benchmark demonstrate significant improvements over state-of-the-art methods, including reduced computational overhead and higher recall in long-sequence grounding.
Authors: Yuta Tsuchiya, Yukino Baba
Abstract: Just as people improve decision-making by consulting diverse human advisors, they can now also consult with multiple AI systems. Prior work on group decision-making shows that advice aggregation creates pressure to conform, leading to overreliance. However, the conditions under which multi-AI consultation improves or undermines human decision-making remain unclear. We conducted experiments with three tasks in which participants received advice from panels of AIs. We varied panel size, within-panel consensus, and the human-likeness of presentation. Accuracy improved for small panels relative to a single AI; larger panels yielded no gains. The level of within-panel consensus affected participants' reliance on AI advice: High consensus fostered overreliance; a single dissent reduced pressure to conform; wide disagreement created confusion and undermined appropriate reliance. Human-like presentations increased perceived usefulness and agency in certain tasks, without raising conformity pressure. These findings yield design implications for presenting multi-AI advice that preserve accuracy while mitigating conformity.
Authors: Kejia Liu, Haoyang Zhou, Ruoyu Xu, Peicheng Wang, Mingli Song, Haofei Zhang
Abstract: Recent advances in cross-view geo-localization (CVGL) methods have shown strong potential for supporting unmanned aerial vehicle (UAV) navigation in GNSS-denied environments. However, existing work predominantly focuses on matching UAV views to onboard map tiles, which introduces an inherent trade-off between accuracy and storage overhead, and overlooks the importance of the UAV's heading during navigation. Moreover, the substantial discrepancies and varying overlaps in cross-view scenarios have been insufficiently considered, limiting their generalization to real-world scenarios. In this paper, we present Bearing-UAV, a purely vision-driven cross-view navigation method that jointly predicts UAV absolute location and heading from neighboring features, enabling accurate, lightweight, and robust navigation in the wild. Our method leverages global and local structural features and explicitly encodes relative spatial relationships, making it robust to cross-view variations, misalignment, and feature-sparse conditions. We also present Bearing-UAV-90k, a multi-city benchmark for evaluating cross-view localization and navigation. Extensive experiments show encouraging results that Bearing-UAV yields lower localization error than previous matching/retrieval paradigm across diverse terrains. Our code and dataset will be made publicly available.
Authors: Moritz G\"ogl, Christopher Yau
Abstract: We study multimodal survival analysis integrating clinical text, tabular covariates, and genomic profiles using locally deployable large language models (LLMs). As many institutions face tight computational and privacy constraints, this setting motivates the use of lightweight, on-premises models. Our approach jointly estimates calibrated survival probabilities and generates concise, evidence-grounded prognosis text via teacher-student distillation and principled multimodal fusion. On a TCGA cohort, it outperforms standard baselines, avoids reliance on cloud services and associated privacy concerns, and reduces the risk of hallucinated or miscalibrated estimates that can be observed in base LLMs.
Authors: Yurong Chen, Zhiyi Huang, Michael I. Jordan, Haipeng Luo
Abstract: We study calibeating, the problem of post-processing external forecasts online to minimize cumulative losses and match an informativeness-based benchmark. Unlike prior work, which analyzed calibeating for specific losses with specific arguments, we reduce calibeating to existing online learning techniques and obtain results for general proper losses. More concretely, we first show that calibeating is minimax-equivalent to regret minimization. This recovers the $O(\log T)$ calibeating rate of Foster and Hart [FH23] for the Brier and log losses and its optimality, and yields new optimal calibeating rates for mixable losses and general bounded losses. Second, we prove that multi-calibeating is minimax-equivalent to the combination of calibeating and the classical expert problem. This yields new optimal multi-calibeating rates for mixable losses, including Brier and log losses, and general bounded losses. Finally, we obtain new bounds for achieving calibeating and calibration simultaneously for the Brier loss. For binary predictions, our result gives the first calibrated algorithm that at the same time also achieves the optimal $O(\log T)$ calibeating rate.
Authors: Ireh Kim, Tesia Sker, Chanwoo Kim
Abstract: In Machine Translation, Large Language Models (LLMs) have generally underperformed compared to conventional encoder-decoder systems and thus see limited adoption. However, LLMs excel at modeling contextual information, making them a natural fit for document-level translation tasks where coherence across sentences is crucial. Despite this potential, document-level MT with LLMs faces two key challenges: (1) the scarcity of large-scale, high-quality document-level parallel data; and (2) the propensity of LLMs to introduce hallucinations and omissions during generation. To address these challenges, we propose a two-stage fine-tuning strategy leveraging LLM-augmented document-level data. First, we augment data by converting summarization data into document-level parallel data using a LLM, and then filter it using multiple metrics, leveraging sacreBLEU, COMET, and LaBSE-based cosine similarity-to improve data quality. Finally, we employ a two-stage fine-tuning strategy: first fine-tuning on the abundant sentence-level MT resources, and then on the filtered document-level corpus.
Authors: Junrong Guo, Shancheng Fang, Yadong Qu, Hongtao Xie
Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have enabled automated generation of structured layouts from natural language descriptions. Existing methods typically follow a code-only paradigm that generates code to represent layouts, which are then rendered by graphic engines to produce final images. However, they are blind to the rendered visual outcome, making it difficult to guarantee readability and aesthetics. In this paper, we identify visual feedback as a critical factor in layout generation and propose Visual Feedback Layout Model (VFLM), a self-improving framework that leverages visual feedback iterative refinement. VFLM is capable of performing adaptive reflective generation, which leverages visual information to reflect on previous issues and iteratively generates outputs until satisfactory quality is achieved. It is achieved through reinforcement learning with a visually grounded reward model that incorporates OCR accuracy. By rewarding only the final generated outcome, we can effectively stimulate the model's iterative and reflective generative capabilities. Experiments across multiple benchmarks show that VFLM consistently outperforms advanced MLLMs, existing layout models, and code-only baselines, establishing visual feedback as critical for design-oriented MLLMs. Our code and data are available at https://github.com/FolSpark/VFLM.
Authors: A. Chervov, F. Levkovich-Maslyuk, A. Smolensky, F. Khafizov, I. Kiselev, D. Melnikov, I. Koltsov, S. Kudashev, D. Shiltsov, M. Obozov, S. Krymskii, V. Kirova, E. V. Konstantinova, A. Soibelman, S. Galkin, L. Grunwald, A. Kotov, A. Alexandrov, S. Lytkin, D. Fedoriaka, A. Chevychelov, Z. Kogan, A. Natyrova, L. Cheldieva, O. Nikitina, S. Fironov, A. Vakhrushev, A. Lukyanenko, V. Ilin, D. Gorodkov, N. Bogachev, I. Gaiur, M. Zaitsev, F. Petrov, L. Petrov, T. Gaintseva, A. Gavrilova, M. N. Smirnov, N. Kalinin, A. Khan, K. Jung, H. Mousset, H. Isambert, O. Debeaupuis
Abstract: This is the fourth paper in the CayleyPy project, which applies AI methods to the exploration of large graphs. In this work, we suggest the existence of a new discrete version of holographic string dualities for this setup, and discuss their relevance to AI systems and mathematics. Many modern AI tasks -- such as those addressed by GPT-style language models or RL systems -- can be viewed as direct analogues of predicting particle trajectories on graphs. We investigate this problem for a large family of Cayley graphs, for which we show that surprisingly it admits a dual description in terms of discrete strings. We hypothesize that such dualities may extend to a range of AI systems where they can lead to more efficient computational approaches. In particular, string holographic images of states are proposed as natural candidates for data embeddings, motivated by the "complexity = volume" principle in AdS/CFT. For Cayley graphs of the symmetric group S_n, our results indicate that the corresponding dual objects are flat, planar polygons. The diameter of the graph is equal to the number of integer points inside the polygon scaled by n. Vertices of the graph can be mapped holographically to paths inside the polygon, and the usual graph distances correspond to the area under the paths, thus directly realising the "complexity = volume" paradigm. We also find evidence for continuous CFTs and dual strings in the large n limit. We confirm this picture and other aspects of the duality in a large initial set of examples. We also present new datasets (obtained by a combination of ML and conventional tools) which should be instrumental in establishing the duality for more general cases.
Authors: Kexian Tang, Jiani Wang, Shaowen Wang, Kaifeng Lyu
Abstract: While large language models (LLMs) are pretrained on massive amounts of data, their knowledge coverage remains incomplete in specialized, data-scarce domains, motivating extensive efforts to study synthetic data generation for knowledge injection. We propose SPA (Scaling Prompt-engineered Augmentation), a simple but tough-to-beat baseline that uses a small set of carefully designed prompts to generate large-scale synthetic data for knowledge injection. Through systematic comparisons, we find that SPA outperforms several strong baselines. Furthermore, we identify two key limitations of prior approaches: (1) while RL-based methods may improve the token efficiency of LLM-based data augmentation at small scale, they suffer from diversity collapse as data scales, leading to diminishing returns; and (2) while multi-stage prompting may outperform simple augmentation methods, their advantages can disappear after careful prompt tuning. Our results suggest that, for knowledge injection, careful prompt design combined with straightforward large-scale augmentation can be surprisingly effective, and we hope SPA can serve as a strong baseline for future studies in this area. Our code is available at https://github.com/Tangkexian/SPA.
Authors: Tom Biskupski, Stephan Kleber
Abstract: A Large Language Model (LLM) as judge evaluates the quality of victim Machine Learning (ML) models, specifically LLMs, by analyzing their outputs. An LLM as judge is the combination of one model and one specifically engineered judge prompt that contains the criteria for the analysis. The resulting automation of the analysis scales up the complex evaluation of the victim models' free-form text outputs by faster and more consistent judgments compared to human reviewers. Thus, quality and security assessments of LLMs can cover a wide range of the victim models' use cases. Being a comparably new technique, LLMs as judges lack a thorough investigation for their reliability and agreement to human judgment. Our work evaluates the applicability of LLMs as automated quality assessors of victim LLMs. We test the efficacy of 37 differently sized conversational LLMs in combination with 5 different judge prompts, the concept of a second-level judge, and 5 models fine-tuned for the task as assessors. As assessment objective, we curate datasets for eight different categories of judgment tasks and the corresponding ground-truth labels based on human assessments. Our empirical results show a high correlation of LLMs as judges with human assessments, when combined with a suitable prompt, in particular for GPT-4o, several open-source models with $\geqslant$ 32B parameters, and a few smaller models like Qwen2.5 14B.
Authors: David M. Markowitz
Abstract: Conversation is ubiquitous in social life, but the empirical study of this interactive process has been thwarted by tools that are insufficiently modular and unadaptive to researcher needs. To relieve many constraints in conversation research, the current tutorial presents an overview and introduction to a new tool, Dyadic (https://www.chatdyadic.com/), a web-based platform for studying human-human and human-AI conversations using text-based or voice-based chats. Dyadic is distinct from other platforms by offering studies with multiple modalities, AI suggestions (e.g., in human-human studies, AI can suggest responses to a participant), live monitoring (e.g., researchers can evaluate, in real time, chats between communicators), and survey deployment (e.g., Likert-type scales, feeling thermometers, and open-ended text boxes can be sent to humans for in situ evaluations of the interaction), among other consequential features. No coding is required to operate Dyadic directly, and integrations with existing survey platforms are offered.
Authors: Sashuai Zhou, Qiang Zhou, Junpeng Ma, Yue Cao, Ruofan Hu, Ziang Zhang, Xiaoda Yang, Zhibin Wang, Jun Song, Cheng Yu, Bo Zheng, Zhou Zhao
Abstract: Recent advances in text-to-image (T2I) generation via reinforcement learning (RL) have benefited from reward models that assess semantic alignment and visual quality. However, most existing reward models pay limited attention to fine-grained spatial relationships, often producing images that appear plausible overall yet contain inaccuracies in object positioning. In this work, we present \textbf{SpatialReward}, a verifiable reward model explicitly designed to evaluate spatial layouts in generated images. SpatialReward adopts a multi-stage pipeline: a \emph{Prompt Decomposer} extracts entities, attributes, and spatial metadata from free-form prompts; expert detectors provide accurate visual grounding of object positions and attributes; and a vision-language model applies chain-of-thought reasoning over grounded observations to assess complex spatial relations that are challenging for rule-based methods. To more comprehensively evaluate spatial relationships in generated images, we introduce \textbf{SpatRelBench}, a benchmark covering object attributes, orientation, inter-object relations, and rendered text placement. Experiments on Stable Diffusion and FLUX show that incorporating SpatialReward into RL training consistently improves spatial consistency and overall generation quality, with results aligned more closely to human judgments. These findings indicate that verifiable reward models hold considerable potential for enabling more accurate and controllable optimization in text-to-image generation models.
Authors: Yanchen Jiang, Zhe Feng, Christopher P. Mah, Aranyak Mehta, Di Wang
Abstract: Generative Recommender Systems using semantic ids, such as TIGER (Rajput et al., 2023), have emerged as a widely adopted competitive paradigm in sequential recommendation. However, existing architectures are designed solely for semantic retrieval and do not address concerns such as monetization via ad revenue and incorporation of bids for commercial retrieval. We propose GEM-Rec, a unified framework that integrates commercial relevance and monetization objectives directly into the generative sequence. We introduce control tokens to decouple the decision of whether to show an ad from which item to show. This allows the model to learn valid placement patterns directly from interaction logs, which inherently reflect past successful ad placements. Complementing this, we devise a Bid-Aware Decoding mechanism that handles real-time pricing, injecting bids directly into the inference process to steer the generation toward high-value items. We prove that this approach guarantees allocation monotonicity, ensuring that higher bids weakly increase an ad's likelihood of being shown without requiring model retraining. Experiments demonstrate that GEM-Rec allows platforms to dynamically optimize for semantic relevance and platform revenue.
Authors: Changxiao Cai, Gen Li
Abstract: Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) models for language modeling, allowing flexible generation order and parallel generation of multiple tokens. However, this flexibility introduces a challenge absent in AR models: the \emph{decoding strategy} -- which determines the order and number of tokens generated at each iteration -- critically affects sampling efficiency. Among decoding strategies explored in practice, confidence-based methods, which adaptively select which and how many tokens to unmask based on prediction confidence, have shown strong empirical performance. Despite this success, our theoretical understanding of confidence-based decoding remains limited. In this work, we develop the first theoretical analysis framework for confidence-based decoding in DLMs. We focus on an entropy sum-based strategy that continues unmasking tokens within each iteration until the cumulative entropy exceeds a threshold, and show that it achieves $\varepsilon$-accurate sampling in KL divergence with an expected number of iterations $\widetilde O(H(X_0)/\varepsilon)$, where $H(X_0)$ denotes the entropy of the target data distribution. Notably, this strategy yields substantial sampling acceleration when the data distribution has low entropy relative to the sequence length, while automatically adapting to the intrinsic complexity of data without requiring prior knowledge or hyperparameter tuning. Overall, our results provide a theoretical foundation for confidence-based decoding and may inform the design of more efficient decoding strategies for DLMs.
Authors: Kai-Wei Chang, Wei-Chih Chen, En-Pei Hu, Hung-yi Lee, James Glass
Abstract: We propose TiCo, a simple post-training method for enabling spoken dialogue models (SDMs) to follow time-constrained instructions and generate responses with controllable duration. This capability is valuable for real-world spoken language systems such as voice assistants and interactive agents, where controlling response duration can improve interaction quality. However, despite their strong ability to generate natural spoken responses, existing models lack time awareness and struggle to follow duration-related instructions (e.g., "Please generate a response lasting about 15 seconds"). Through an empirical evaluation of both open-source and commercial SDMs, we show that they frequently fail to satisfy such time-control requirements. TiCo addresses this limitation by enabling models to estimate elapsed speaking time during generation through Spoken Time Markers (STM) (e.g., <10.6 seconds>). These markers help the model maintain awareness of time and adjust the remaining content to meet the target duration. TiCo is simple and efficient: it requires only a small amount of data and no additional question-answer pairs, relying instead on self-generation and reinforcement learning. Experimental results show that TiCo significantly improves adherence to duration constraints while preserving response quality.
Authors: Haoyu Zhen, Xiaolong Li, Yilin Zhao, Han Zhang, Sifei Liu, Kaichun Mo, Chuang Gan, Subhashree Radhakrishnan
Abstract: Large Language Models (LLMs) and Vision Language Models (VLMs) have shown impressive reasoning abilities, yet they struggle with spatial understanding and layout consistency when performing fine-grained visual editing. We introduce a Structured Reasoning framework that performs text-conditioned spatial layout editing via scene-graph reasoning. Given an input scene graph and a natural-language instruction, the model reasons over the graph to generate an updated scene graph that satisfies the text condition while maintaining spatial coherence. By explicitly guiding the reasoning process through structured relational representations, our approach improves both interpretability and control over spatial relationships. We evaluate our method on a new text-guided layout editing benchmark encompassing sorting, spatial alignment, and room-editing tasks. Our training paradigm yields an average 15% improvement in IoU and 25% reduction in center-distance error compared to Chain of Thought Fine-tuning (CoT-SFT) and vanilla GRPO baselines. Compared to SOTA zero-shot LLMs, our best models achieve up to 20% higher mIoU, demonstrating markedly improved spatial precision.
Authors: Haichao Zhang, Yijiang Li, Shwai He, Tushar Nagarajan, Mingfei Chen, Jianglin Lu, Ang Li, Yun Fu
Abstract: Recent progress in latent world models (e.g., V-JEPA2) has shown promising capability in forecasting future world states from video observations. Nevertheless, dense prediction from a short observation window limits temporal context and can bias predictors toward local, low-level extrapolation, making it difficult to capture long-horizon semantics and reducing downstream utility. Vision--language models (VLMs), in contrast, provide strong semantic grounding and general knowledge by reasoning over uniformly sampled frames, but they are not ideal as standalone dense predictors due to compute-driven sparse sampling, a language-output bottleneck that compresses fine-grained interaction states into text-oriented representations, and a data-regime mismatch when adapting to small action-conditioned datasets. We propose a VLM-guided JEPA-style latent world modeling framework that combines dense-frame dynamics modeling with long-horizon semantic guidance via a dual-temporal pathway: a dense JEPA branch for fine-grained motion and interaction cues, and a uniformly sampled VLM \emph{thinker} branch with a larger temporal stride for knowledge-rich guidance. To transfer the VLM's progressive reasoning signals effectively, we introduce a hierarchical pyramid representation extraction module that aggregates multi-layer VLM representations into guidance features compatible with latent prediction. Experiments on hand-manipulation trajectory prediction show that our method outperforms both a strong VLM-only baseline and a JEPA-predictor baseline, and yields more robust long-horizon rollout behavior.
Authors: Ziyi Wang, Xinshun Wang, Shuang Chen, Yang Cong, Mengyuan Liu
Abstract: We present UniMotion, to our knowledge the first unified framework for simultaneous understanding and generation of human motion, natural language, and RGB images within a single architecture. Existing unified models handle only restricted modality subsets (e.g., Motion-Text or static Pose-Image) and predominantly rely on discrete tokenization, which introduces quantization errors and disrupts temporal continuity. UniMotion overcomes both limitations through a core principle: treating motion as a first-class continuous modality on equal footing with RGB. A novel Cross-Modal Aligned Motion VAE (CMA-VAE) and symmetric dual-path embedders construct parallel continuous pathways for Motion and RGB within a shared LLM backbone. To inject visual-semantic priors into motion representations without requiring images at inference, we propose Dual-Posterior KL Alignment (DPA), which distills a vision-fused encoder's richer posterior into the motion-only encoder. To address the cold-start problem -- where text supervision alone is too sparse to calibrate the newly introduced motion pathway -- we further propose Latent Reconstruction Alignment (LRA), a self-supervised pre-training strategy that uses dense motion latents as unambiguous conditions to co-calibrate the embedder, backbone, and flow head, establishing a stable motion-aware foundation for all downstream tasks. UniMotion achieves state-of-the-art performance across seven tasks spanning any-to-any understanding, generation, and editing among the three modalities, with especially strong advantages on cross-modal compositional tasks.
Authors: Shivam Duggal, Xingjian Bai, Zongze Wu, Richard Zhang, Eli Shechtman, Antonio Torralba, Phillip Isola, William T. Freeman
Abstract: Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer must be trained first, before the diffusion model can be trained in the frozen latent space. We propose UNITE - an autoencoder architecture for unified tokenization and latent diffusion. UNITE consists of a Generative Encoder that serves as both image tokenizer and latent generator via weight sharing. Our key insight is that tokenization and generation can be viewed as the same latent inference problem under different conditioning regimes: tokenization infers latents from fully observed images, whereas generation infers them from noise together with text or class conditioning. Motivated by this, we introduce a single-stage training procedure that jointly optimizes both tasks via two forward passes through the same Generative Encoder. The shared parameters enable gradients to jointly shape the latent space, encouraging a "common latent language". Across image and molecule modalities, UNITE achieves near state of the art performance without adversarial losses or pretrained encoders (e.g., DINO), reaching FID 2.12 and 1.73 for Base and Large models on ImageNet 256 x 256. We further analyze the Generative Encoder through the lenses of representation alignment and compression. These results show that single stage joint training of tokenization & generation from scratch is feasible.
Authors: Umair Nawaz, Ahmed Heakl, Ufaq Khan, Abdelrahman Shaker, Salman Khan, Fahad Shahbaz Khan
Abstract: Diffusion Transformers (DiTs) power high-fidelity video world models but remain computationally expensive due to sequential denoising and costly spatio-temporal attention. Training-free feature caching accelerates inference by reusing intermediate activations across denoising steps; however, existing methods largely rely on a Zero-Order Hold assumption i.e., reusing cached features as static snapshots when global drift is small. This often leads to ghosting artifacts, blur, and motion inconsistencies in dynamic scenes. We propose \textbf{WorldCache}, a Perception-Constrained Dynamical Caching framework that improves both when and how to reuse features. WorldCache introduces motion-adaptive thresholds, saliency-weighted drift estimation, optimal approximation via blending and warping, and phase-aware threshold scheduling across diffusion steps. Our cohesive approach enables adaptive, motion-consistent feature reuse without retraining. On Cosmos-Predict2.5-2B evaluated on PAI-Bench, WorldCache achieves \textbf{2.3$\times$} inference speedup while preserving \textbf{99.4\%} of baseline quality, substantially outperforming prior training-free caching approaches. Our code can be accessed on \href{https://umair1221.github.io/World-Cache/}{World-Cache}.
Authors: Yixiang Qu, Yifan Dai, Shilin Yu, Pradham Tanikella, Malvika Pillai, Walter Chen, Jialiu Xie, Yishan Ren, Duan Wang, Yikai Wang, Sid Sheth, Guanting Chen, Yufeng Liu, Travis Schrank, Trevor Hackman, Didong Li, Di Wu
Abstract: Large Language Models (LLMs) have demonstrated remarkable proficiency in automated text annotation within natural language processing. However, their deployment in clinical settings is severely constrained by strict privacy regulations and the prohibitive computational cost of processing voluminous unstructured Electronic Health Records (EHRs). In this study, we developed a resource-efficient preprocessing technique that can be adopted in existing LLM procedures. This approach is particularly useful for smaller LLMs, which are often more accuracy-challenged, and forms a compact LLM framework optimized for local deployment in computational environments with stringent privacy requirements and restricted access to high-performance GPUs (PrecLLM). The preprocessing step includes both regular expressions (regex) and Retrieval-Augmented Generation (RAG) to extract and highlight key information from unstructured clinical notes. Pre-filtering long and unstructured texts enhanced the performance of smaller LLMs on EHR-related tasks. Evaluation was performed on two distinct cohorts: a locally curated private EHR dataset from the EPIC system for a Head and Neck Cancer (HNC) cohort, and the publicly available EHR dataset (MIMIC-IV). Using MIMIC-IV, we further compared PrecLLM against fine-tuned LLMs. Results demonstrated that PrecLLM substantially enhanced the performance of the original smaller LLMs in terms of sensitivity, specificity, and F1 scores, making it well-suited for privacy-sensitive and resource-constrained applications. This study offers optimized LLM performance for local, secure, and efficient healthcare applications, and provides practical guidance for clinical LLM deployment while addressing challenges related to privacy, computational feasibility, and clinical applicability.
Authors: Lang Cao, Jingxian Xu, Hanbing Liu, Jinyu Wang, Mengyu Zhou, Haoyu Dong, Shi Han, Dongmei Zhang
Abstract: Tables are a fundamental medium for organizing and analyzing data, making table reasoning a critical capability for intelligent systems. Although large language models (LLMs) exhibit strong general reasoning abilities, they still struggle with accurate numerical reasoning over tabular data, particularly in complex table settings beyond simple relational lookup. Spreadsheet formulas provide a powerful and expressive interface for executable symbolic operations, enabling rich reasoning patterns that remain largely underexplored by existing LLMs. In this paper, we introduce Formula-R1, a model trained via Formula Tuning (Fortune), a formula-driven reinforcement learning (RL) framework for table reasoning. Formula Tuning trains LLMs to generate executable spreadsheet formulas for question answering over general tabular data, using execution success and answer correctness as reward signals, thereby reducing reliance on supervised formula annotations. We demonstrate the effectiveness of Formula Tuning through extensive experiments on seven table reasoning benchmarks. It substantially improves LLM performance on table reasoning, particularly for tasks involving complex tables and multi-step numerical computation. Moreover, Formula-R1 consistently outperforms prior methods under controlled comparison settings. Beyond empirical gains, our extensive analyses provide insights into the role of RL in formula-driven table reasoning, highlighting the broader potential of formula-driven RL to enhance reasoning capabilities in LLMs.
Authors: Jisheng Dang, Yizhou Zhang, Hao Ye, Teng Wang, Siming Chen, Huicheng Zheng, Yulan Guo, Jianhuang Lai, Bin Hu
Abstract: Fine-grained video captioning aims to generate detailed, temporally coherent descriptions of video content. However, existing methods struggle to capture subtle video dynamics and rich detailed information. In this paper, we leverage preference learning to enhance the performance of vision-language models in fine-grained video captioning, while mitigating several limitations inherent to direct preference optimization (DPO). First, we propose a pipeline for constructing preference pairs that leverages the intrinsic properties of VLMs along with partial assistance from large language models, achieving an optimal balance between cost and data quality. Second, we propose Synergistic Preference Optimization (SynPO), a novel optimization method offering significant advantages over DPO and its variants. SynPO prevents negative preferences from dominating the optimization, explicitly preserves the model's language capability to avoid deviation of the optimization objective, and improves training efficiency by eliminating the need for the reference model. We extensively evaluate SynPO not only on video captioning benchmarks (e.g., VDC, VDD, VATEX) but also across well-established NLP tasks, including general language understanding and preference evaluation, using diverse pretrained models. Results demonstrate that SynPO consistently outperforms DPO variants while achieving 20\% improvement in training efficiency. Code is available at https://github.com/longmalongma/SynPO
Authors: Stella C. Dong, James R. Finlay
Abstract: This paper develops a novel multi-agent reinforcement learning (MARL) framework for reinsurance treaty bidding, addressing long-standing inefficiencies in traditional broker-mediated placement processes. We pose the core research question: Can autonomous, learning-based bidding systems improve risk transfer efficiency and outperform conventional pricing approaches in reinsurance markets? In our model, each reinsurer is represented by an adaptive agent that iteratively refines its bidding strategy within a competitive, partially observable environment. The simulation explicitly incorporates institutional frictions including broker intermediation, incumbent advantages, last-look privileges, and asymmetric access to underwriting information. Empirical analysis demonstrates that MARL agents achieve up to 15% higher underwriting profit, 20% lower tail risk (CVaR), and over 25% improvement in Sharpe ratios relative to actuarial and heuristic baselines. Sensitivity tests confirm robustness across hyperparameter settings, and stress testing reveals strong resilience under simulated catastrophe shocks and capital constraints. These findings suggest that MARL offers a viable path toward more transparent, adaptive, and risk-sensitive reinsurance markets. The proposed framework contributes to emerging literature at the intersection of algorithmic market design, strategic bidding, and AI-enabled financial decision-making.
Authors: Wangyue Lu, Lun Du, Sirui Li, Ke Weng, Haozhe Sun, Hengyu Liu, Minghe Yu, Tiancheng Zhang, Ge Yu
Abstract: Interactive theorem provers (ITPs) require manual formalization, which is labor-intensive and demands expert knowledge. While automated formalization offers a potential solution, it faces two major challenges: model hallucination (e.g., undefined predicates, symbol misuse, and version incompatibility) and the semantic gap caused by ambiguous or missing premises in natural language descriptions. To address these issues, we propose CRAMF, a Concept-driven Retrieval-Augmented Mathematical Formalization framework. CRAMF enhances LLM-based autoformalization by retrieving formal definitions of core mathematical concepts, providing contextual grounding during code generation. However, applying retrieval-augmented generation (RAG) in this setting is non-trivial due to the lack of structured knowledge bases, the polymorphic nature of mathematical concepts, and the high precision required in formal retrieval. We introduce a framework for automatically constructing a concept-definition knowledge base from Mathlib4, the standard mathematical library for the Lean 4 theorem prover, indexing over 26,000 formal definitions and 1,000+ core mathematical concepts. To address conceptual polymorphism, we propose contextual query augmentation with domain- and application-level signals. In addition, we design a dual-channel hybrid retrieval strategy with reranking to ensure accurate and relevant definition retrieval. Experiments on miniF2F, ProofNet, and our newly proposed AdvancedMath benchmark show that CRAMF can be seamlessly integrated into LLM-based autoformalizers, yielding consistent improvements in translation accuracy, achieving up to 62.1% and an average of 29.9% relative improvement.
Authors: Raj Ghugare, Roger Creus Castanyer, Catherine Ji, Kathryn Wantlin, Jin Schofield, Karthik Narasimhan, Benjamin Eysenbach
Abstract: Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel problems, agents should acquire skills for exploring and learning through experience. Finding a scalable learning mechanism for developing agents that learn through interaction remains a major open problem. In this work, we introduce BuilderBench, a benchmark to accelerate research into agent pre-training that centers open-ended exploration. BuilderBench requires agents to learn how to build any structure using blocks. BuilderBench is equipped with $(1)$ a hardware accelerated simulator of a robotic agent interacting with various physical blocks, and $(2)$ a task-suite with over 42 diverse target structures that are carefully curated to test an understanding of physics, mathematics, and long-horizon planning. During training, agents have to explore and learn general principles about the environment without any external supervision. During evaluation, agents have to build the unseen target structures from the task suite. Solving these tasks requires a sort of \emph{embodied reasoning} that is not reflected in words but rather in actions, experimenting with different strategies and piecing them together. Our experiments show that many of these tasks challenge the current iteration of algorithms. Hence, we also provide a ``training wheels'' protocol, in which agents are trained and evaluated to build a single target structure from the task suite. Finally, we provide single-file implementations of six different algorithms as a reference point for researchers.
Authors: Yifei Dong, Fengyi Wu, Guangyu Chen, Lingdong Kong, Xu Zhu, Qiyu Hu, Yuxuan Zhou, Jingdong Sun, Jun-Yan He, Qi Dai, Alexander G. Hauptmann, Zhi-Qi Cheng
Abstract: Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation. Yet, state-of-the-art systems typically rely on modular designs that decouple navigation planning from visual world modeling, which often induces state-action misalignment and weak adaptability in novel or dynamic scenarios. We propose UniWM, a unified, memory-augmented world model that integrates egocentric visual foresight and planning within a single multimodal autoregressive backbone. UniWM explicitly grounds action selection in visually imagined outcomes, tightly aligning prediction with control. Meanwhile, a hierarchical memory mechanism fuses short-term perceptual cues with longer-term trajectory context, supporting stable and coherent reasoning over extended horizons. Extensive experiments on four challenging benchmarks (Go Stanford, ReCon, SCAND, HuRoN) and the 1X Humanoid Dataset show that UniWM improves navigation success rates by up to 30%, substantially reduces trajectory errors against strong baselines, generalizes zero-shot to the unseen TartanDrive dataset, and scales naturally to high-dimensional humanoid control. These results position UniWM as a principled step toward unified, imagination-driven embodied navigation. The code and models are available at https://github.com/F1y1113/UniWM.
Authors: Annisaa Fitri Nurfidausi, Eleonora Mancini, Paolo Torroni
Abstract: Depression is a widespread mental health disorder, yet its automatic detection remains challenging. Prior work has explored unimodal and multimodal approaches, with multimodal systems showing promise by leveraging complementary signals. However, existing studies are limited in scope, lack systematic comparisons of features, and suffer from inconsistent evaluation protocols. We address these gaps by systematically exploring feature representations and modelling strategies across EEG, together with speech and text. We evaluate handcrafted features versus pre-trained embeddings, assess the effectiveness of different neural encoders, compare unimodal, bimodal, and trimodal configurations, and analyse fusion strategies with attention to the role of EEG. Consistent subject-independent splits are applied to ensure robust, reproducible benchmarking. Our results show that (i) the combination of EEG, speech and text modalities enhances multimodal detection, (ii) pretrained embeddings outperform handcrafted features, and (iii) carefully designed trimodal models achieve state-of-the-art performance. Our work lays the groundwork for future research in multimodal depression detection.
Authors: Tian Liang, Wenxiang Jiao, Zhiwei He, Jiahao Xu, Haitao Mi, Dong Yu
Abstract: Large Reasoning Models (LRMs) have demonstrated impressive capabilities but suffer from cognitive inefficiencies like "overthinking" simple problems and "underthinking" complex ones. While existing methods that use supervised fine-tuning (SFT) or reinforcement learning (RL) with token-length rewards can improve efficiency, they often do so at the cost of accuracy. This paper introduces DeepCompress, a novel framework that simultaneously enhances both the accuracy and efficiency of LRMs. We challenge the prevailing approach of consistently favoring shorter reasoning paths, showing that longer responses can contain a broader range of correct solutions for difficult problems. DeepCompress employs an adaptive length reward mechanism that dynamically classifies problems as "Simple" or "Hard" in real-time based on the model's evolving capability. It encourages shorter, more efficient reasoning for "Simple" problems while promoting longer, more exploratory thought chains for "Hard" problems. This dual-reward strategy enables the model to autonomously adjust its Chain-of-Thought (CoT) length, compressing reasoning for well-mastered problems and extending it for those it finds challenging. Experimental results on challenging mathematical benchmarks show that DeepCompress consistently outperforms baseline methods, achieving superior accuracy while significantly improving token efficiency.
Authors: Yi-Fei Liu, Yi-Long Lu, Di He, Hang Zhang
Abstract: Psychological constructs within individuals are widely believed to be interconnected. We investigated whether and how Large Language Models (LLMs) can model the correlational structure of human psychological traits from minimal quantitative inputs. We prompted various LLMs with Big Five Personality Scale responses from 816 human individuals to role-play their responses on nine other psychological scales. LLMs demonstrated remarkable accuracy in capturing human psychological structure, with the inter-scale correlation patterns from LLM-generated responses strongly aligning with those from human data $(R^2 > 0.89)$. This zero-shot performance substantially exceeded predictions based on semantic similarity and approached the accuracy of machine learning algorithms trained directly on the dataset. Analysis of reasoning traces revealed that LLMs use a systematic two-stage process: First, they transform raw Big Five responses into natural language personality summaries through information selection and compression, analogous to generating sufficient statistics. Second, they generate target scale responses based on reasoning from these summaries. For information selection, LLMs identify the same key personality factors as trained algorithms, though they fail to differentiate item importance within factors. The resulting compressed summaries are not merely redundant representations but capture synergistic information--adding them to original scores enhances prediction alignment, suggesting they encode emergent, second-order patterns of trait interplay. Our findings demonstrate that LLMs can precisely predict individual participants' psychological traits from minimal data through a process of abstraction and reasoning, offering both a powerful tool for psychological simulation and valuable insights into their emergent reasoning capabilities.
Authors: Chloe Li, Mary Phuong, Daniel Tan
Abstract: As AI systems become more capable of complex agentic tasks, they also become more capable of pursuing undesirable objectives and causing harm. Previous work has attempted to catch these unsafe instances by interrogating models directly about their objectives and behaviors. However, the main weakness of trusting interrogations is that models can lie. We propose self-report fine-tuning (SRFT), a simple supervised fine-tuning technique that trains models to occasionally make factual mistakes, then admit them when asked. We show that the admission of factual errors in simple question-answering settings generalizes out-of-distribution (OOD) to the admission of hidden misaligned objectives in adversarial agentic settings. We evaluate SRFT in OOD stealth tasks, where models are instructed to complete a hidden misaligned objective alongside a user-specified objective without being caught by monitoring. After SRFT, models are more likely to confess the details of their hidden objectives when interrogated, even under strong pressure not to disclose them. Interrogation on SRFT models can detect hidden objectives with near-ceiling performance (F1 score = 0.98), while the baseline model lies when interrogated under the same conditions (F1 score = 0). Interrogation on SRFT models can further elicit the content of the hidden objective, recovering 28-100% details, compared to 0% details recovered in the baseline model and by prefilled assistant turn attacks. This provides a promising technique for promoting honesty propensity and incriminating misaligned AIs.
Authors: Bodong Du, Honglong Yang, Xiaomeng Li
Abstract: Vision-language models have shown promising results in radiology report generation. However, most existing methods generate reports as flat text and do not explicitly model the semantic dependency between the Findings and Impression sections, which can lead to inconsistencies between clinical observations and diagnostic conclusions. In this paper, we propose RadHiera, a semantic hierarchical reinforcement learning framework for radiology report generation. RadHiera follows the semantic organization of radiology reports by first optimizing overall report quality, then improving the diagnostic accuracy of the Impression section, and finally enforcing consistency between Findings and Impression so that diagnostic conclusions are supported by clinical evidence. Specifically, we begin with a base reward that combines linguistic quality and medical factuality to provide supervision on the whole report. On this basis, we introduce a severity-aware reward for the Impression section that places greater emphasis on errors involving clinically critical conditions, thereby reducing both missed diagnoses and overstatement. We further enforce cross-section consistency using Expert Model-derived label sets, with subset constraints and hallucination penalties to ensure that impressions remain faithful to the findings. Experiments on three public chest X-ray benchmarks show that RadHiera consistently improves diagnostic accuracy and inter-section consistency over state-of-the-art methods, while also demonstrating good adaptability to report generation in ultrasound report generation.
Authors: Heyang Ma, Qirui Mi, Qipeng Yang, Zijun Fan, Bo Li, Haifeng Zhang
Abstract: Economic decision-making depends not only on structured signals such as prices and taxes, but also on unstructured language, including peer dialogue and media narratives. While multi-agent reinforcement learning (MARL) has shown promise in optimizing economic decisions, it struggles with the semantic ambiguity and contextual richness of language. We propose LAMP (Language-Augmented Multi-Agent Policy), a framework that integrates language into economic decision-making and narrows the gap to real-world settings. LAMP follows a Think-Speak-Decide pipeline: (1) Think interprets numerical observations to extract short-term shocks and long-term trends, caching high-value reasoning trajectories; (2) Speak crafts and exchanges strategic messages based on reasoning, updating beliefs by parsing peer communications; and (3) Decide fuses numerical data, reasoning, and reflections into a MARL policy to optimize language-augmented decision-making. Experiments in economic simulation show that LAMP outperforms both MARL and LLM-only baselines in cumulative return (+63.5%, +34.0%), robustness (+18.8%, +59.4%), and interpretability. These results demonstrate the potential of language-augmented policies to deliver more effective and robust economic strategies.
Authors: Silvia Rondini, Claudia Alvarez-Martin, Paula Angermair-Barkai, Olivier Penacchio, M. Paz, Matthew Pelowski, Dan Dediu, Antoni Rodriguez-Fornells, Xim Cerda-Company
Abstract: While recent research suggests Large Language Models match human creative performance in divergent thinking tasks, visual creativity remains underexplored. This study compared image generation in human participants (Visual Artists and Non Artists) and using an image generation AI model (two prompting conditions with varying human input: high for Human Inspired, low for Self Guided). Human raters (N=255) and GPT4o evaluated the creativity of the resulting images. We found a clear creativity gradient, with Visual Artists being the most creative, followed by Non Artists, then Human Inspired generative AI, and finally Self Guided generative AI. Increased human guidance strongly improved GenAI's creative output, bringing its productions close to those of Non Artists. Notably, human and AI raters also showed vastly different creativity judgment patterns. These results suggest that, in contrast to language centered tasks, GenAI models may face unique challenges in visual domains, where creativity depends on perceptual nuance and contextual sensitivity, distinctly human capacities that may not be readily transferable from language models.
Authors: Qiming Bao, Xiaoxuan Fu, Michael Witbrock
Abstract: Large language models (LLMs) excel at many natural language tasks, yet their reasoning reliability under structured perturbations of rule-based systems remains brittle. We present a controlled evaluation framework consisting of four stress tests: (1) rule deletion (redundant vs. essential), (2) contradictory evidence injection, (3) logic-preserving rewrites, and (4) multi-law equivalence stacking. While representative model families (BERT, Qwen2, and TinyLlama) achieve Acc = 1.0000 on base tasks, our framework reveals a critical failure mode termed Logic Inertia - a total breakdown with Acc = 0.0000 under contradictions, where deductive momentum overrides factual reality. To address this, we propose Conflict-Aware Fusion (Fusion-Conflict), a framework grounded in the Cognitive Structure Hypothesis, which posits that robust reasoning requires an explicit structural inductive bias. By imposing a dual-process architecture that separates premise verification from logical deduction, Conflict-Aware Fusion effectively mitigates logic inertia under the proposed evaluation framework, achieving 1.0000 accuracy on both base and contradictory stress tests. It also significantly enhances robustness to missing evidence. Our results demonstrate that, for reliable multi-step reasoning, structural verification discipline is as critical as training data scale, providing a potential blueprint for building robust, contradiction-aware AI systems this https://github.com/14H034160212/lemo . See the OpenAI/Evals pull request this https://github.com/openai/evals/pull/1622 .
URLs: https://github.com/14H034160212/lemo, https://github.com/openai/evals/pull/1622
Authors: Wentao Wan, Qiqing Lao, Zhiwei Xie, Hefeng Wu, Runnan Lin, Liang Lin, Keze Wang
Abstract: Knowledge Editing (KE) is a field that studies how to modify some knowledge in Large Language Models (LLMs) at a low cost (compared to pre-training). Currently, performing large-scale edits on LLMs while ensuring the Reliability, Generality, and Locality metrics of the edits remain a challenge. This paper proposes a Massive editing approach for LLMs based on dynamic weight Generation (MeG). Our MeG involves attaching a dynamic weight neuron to specific layers of the LLMs and using a diffusion model to conditionally generate the weights of this neuron based on the input query required for the knowledge. This allows the use of adding a single dynamic weight neuron to achieve the goal of large-scale knowledge editing. Experiments show that our MeG can significantly improve the performance of large-scale KE in terms of Reliability, Generality, and Locality metrics compared to existing knowledge editing methods, particularly with a high percentage point increase in the absolute value index for the Locality metric, demonstrating the advantages of our proposed method. Code is available at https://github.com/RodeWayne/MeG-for-Knowledge-Editing.
URLs: https://github.com/RodeWayne/MeG-for-Knowledge-Editing.
Authors: Yosuke Taniuchi, Chie Hieida, Atsushi Noritake, Kazushi Ikeda, Masaki Isoda
Abstract: Social comparison$\unicode{x2014}$the process of evaluating one's rewards relative to others$\unicode{x2014}$is an essential feature of social emotions such as envy and plays a fundamental role in primate social cognition. However, it remains unknown how information about others' rewards affects one's own reward valuation. This study examines whether monkeys merely recognize objective differences in reward or instead infer others' subjective reward valuations. To address this issue, a constructive approach$\unicode{x2014}$one that replicates target emotions in artificial systems and extracts knowledge from them$\unicode{x2014}$was employed, owing to its potential to simulate how the monkey interacts with social contexts, specifically social comparison. We developed three computational models with varying degrees of social information processing: an Internal Prediction Model (IPM), which infers the partner's subjective values; a No Comparison Model (NCM), which disregards partner information; and an External Comparison Model (ECM), which directly incorporates the partner's objective rewards. We trained the models on a dataset containing the behavior of a pair of monkeys, their rewards, and the conditioned stimuli, and then evaluated the models' ability to classify subjective values across pre-defined experimental conditions. The ECM achieved the best classification result (0.88 for the ECM vs. 0.85 for the IPM on the Rand index), suggesting that, in our modeling framework, social comparison relies on objective differences in reward rather than on inferences about subjective reward values.
Authors: Aparna Elangovan, Lei Xu, Mahsa Elyasi, Ismail Akdulum, Mehmet Aksakal, Enes Gurun, Brian Hur, Saab Mansour, Ravid Shwartz Ziv, Karin Verspoor, Dan Roth
Abstract: Benchmarking the capabilities of AI systems, including Large Language Models (LLMs) and Vision Models, typically ignores the impact of uncertainty in the underlying ground truth answers from experts. This ambiguity is not just limited to human preferences, but is also consequential even in safety critical domains such as medicine where uncertainty is pervasive. In this paper, we introduce a probabilistic paradigm to theoretically explain how high certainty in ground truth answers is almost always necessary for even an expert to achieve high scores, whereas in datasets with high variation in ground truth answers there may be little difference between a random labeller and an expert. This characteristic also manifests when comparing models, where uncertainty obfuscates differences between poor and high performing models. Therefore, ignoring uncertainty in ground truth evaluation data can result in the misleading conclusion that a non-expert has similar performance to that of an expert. Using the probabilistic paradigm, we thus bring forth the concepts of expected accuracy and expected F1 to estimate the score an expert human or system can achieve given ground truth answer variability. Our work leads to the recommendation that when establishing the capability of a system, results should be stratified by probability of the ground truth answer, typically measured by the agreement rate of ground truth experts. Stratification becomes critical when the overall performance drops below a threshold of 80%. Under stratified evaluation, performance comparison becomes more reliable in high certainty bins, mitigating the effect of the key confounding factor -- uncertainty.
Authors: Zirui Ren, Ziming Liu
Abstract: Hierarchical reasoning model (HRM) achieves extraordinary performance on various reasoning tasks, significantly outperforming large language model-based reasoners. To understand the strengths and potential failure modes of HRM, we conduct a mechanistic study on its reasoning patterns and find three surprising facts: (a) Failure of extremely simple puzzles, e.g., HRM can fail on a puzzle with only one unknown cell. We attribute this failure to the violation of the fixed point property, a fundamental assumption of HRM. (b) "Grokking" dynamics in reasoning steps, i.e., the answer is not improved uniformly, but instead there is a critical reasoning step that suddenly makes the answer correct; (c) Existence of multiple fixed points. HRM "guesses" the first fixed point, which could be incorrect, and gets trapped there for a while or forever. All facts imply that HRM appears to be "guessing" instead of "reasoning". Leveraging this "guessing" picture, we propose three strategies to scale HRM's guesses: data augmentation (scaling the quality of guesses), input perturbation (scaling the number of guesses by leveraging inference randomness), and model bootstrapping (scaling the number of guesses by leveraging training randomness). On the practical side, by combining all methods, we develop Augmented HRM, boosting accuracy on Sudoku-Extreme from 54.5% to 96.9%. On the scientific side, our analysis provides new insights into how reasoning models "reason".
Authors: Sen Wang, Bangwei Liu, Zhenkun Gao, Lizhuang Ma, Xuhong Wang, Yuan Xie, Xin Tan
Abstract: An ideal embodied agent should possess lifelong learning capabilities to handle long-horizon and complex tasks, enabling continuous operation in general environments. This not only requires the agent to accurately accomplish given tasks but also to leverage long-term episodic memory to optimize decision-making. However, existing mainstream one-shot embodied tasks primarily focus on task completion results, neglecting the crucial process of exploration and memory utilization. To address this, we propose Long-term Memory Embodied Exploration (LMEE), which aims to unify the agent's exploratory cognition and decision-making behaviors to promote lifelong learning. We further construct a corresponding dataset and benchmark, LMEE-Bench, incorporating multi-goal navigation and memory-based question answering to comprehensively evaluate both the process and outcome of embodied exploration. To enhance the agent's memory recall and proactive exploration capabilities, we propose MemoryExplorer, a novel method that fine-tunes a multimodal large language model through reinforcement learning to encourage active memory querying. By incorporating a multi-task reward function that includes action prediction, frontier selection, and question answering, our model achieves proactive exploration. Extensive experiments against state-of-the-art embodied exploration models demonstrate that our approach achieves significant advantages in long-horizon embodied tasks. Our dataset and code will be released at https://wangsen99.github.io/papers/lmee/
Authors: Yiliu He, Tianle Li, Binghao Ji, Zhiyuan Liu, Di Huang
Abstract: Optimization modeling via mixed-integer linear programming (MILP) is fundamental to industrial planning and scheduling, yet translating natural-language requirements into solver-executable models and maintaining them under evolving business rules remains highly expertise-intensive. While large language models (LLMs) offer promising avenues for automation, existing methods often suffer from low data efficiency, limited solver-level validity, and poor scalability to industrial-scale problems. To address these challenges, we present EvoOpt-LLM, a unified LLM-based framework supporting the full lifecycle of industrial optimization modeling, including automated model construction, dynamic business-constraint injection, and end-to-end variable pruning. Built on a 7B-parameter LLM and adapted via parameter-efficient LoRA fine-tuning, EvoOpt-LLM achieves a generation rate of 91% and an executability rate of 65.9% with only 3,000 training samples, with critical performance gains emerging under 1,500 samples. The constraint injection module reliably augments existing MILP models while preserving original objectives, and the variable pruning module enhances computational efficiency, achieving an F1 score of ~0.56 on medium-sized LP models with only 400 samples. EvoOpt-LLM demonstrates a practical, data-efficient approach to industrial optimization modeling, reducing reliance on expert intervention while improving adaptability and solver efficiency.
Authors: Shaowei Shen, Xiaohong Yang, Jie Yang, Lianfen Huang, Yongcai Zhang, Yang Zou, Seyyedali Hosseinalipour
Abstract: Electronic medical records (EMRs), particularly in neurology, are inherently heterogeneous, sparse, and noisy, which poses significant challenges for large language models (LLMs) in clinical diagnosis. In such settings, single-agent systems are vulnerable to self-reinforcing errors, as their predictions lack independent validation and can drift toward spurious conclusions. Although recent multi-agent frameworks attempt to mitigate this issue through collaborative reasoning, their interactions are often shallow and loosely structured, failing to reflect the rigorous, evidence-driven processes used by clinical experts. More fundamentally, existing approaches largely ignore the rich logical dependencies among diseases, such as mutual exclusivity, pathological compatibility, and diagnostic confusion. This limitation prevents them from ruling out clinically implausible hypotheses, even when sufficient evidence is available. To overcome these, we propose RE-MCDF, a relation-enhanced multi-expert clinical diagnosis framework. RE-MCDF introduces a generation--verification--revision closed-loop architecture that integrates three complementary components: (i) a primary expert that generates candidate diagnoses and supporting evidence, (ii) a laboratory expert that dynamically prioritizes heterogeneous clinical indicators, and (iii) a multi-relation awareness and evaluation expert group that explicitly enforces inter-disease logical constraints. Guided by a medical knowledge graph (MKG), the first two experts adaptively reweight EMR evidence, while the expert group validates and corrects candidate diagnoses to ensure logical consistency. Extensive experiments on the neurology subset of CMEMR (NEEMRs) and on our curated dataset (XMEMRs) demonstrate that RE-MCDF consistently outperforms state-of-the-art baselines in complex diagnostic scenarios.
Authors: Nahema Marchal, Stephanie Chan, Matija Franklin, Manon Revel, Geoff Keeling, Roberta Fischli, Bilva Chandra, Iason Gabriel
Abstract: Large language models increasingly function as epistemic agents -- entities that can 1) autonomously pursue epistemic goals and 2) actively shape our shared knowledge environment. They curate the information we receive, often supplanting traditional search-based methods, and are frequently used to generate both personal and deeply specialized advice. How they perform these functions, including whether they are reliable and properly calibrated to both individual and collective epistemic norms, is therefore highly consequential for the choices we make. We argue that the potential impact of epistemic AI agents on practices of knowledge creation, curation and synthesis, particularly in the context of complex multi-agent interactions, creates new informational interdependencies that necessitate a fundamental shift in evaluation and governance of AI. While a well-calibrated ecosystem could augment human judgment and collective decision-making, poorly aligned agents risk causing cognitive deskilling and epistemic drift, making the calibration of these models to human norms a high-stakes necessity. To ensure a beneficial human-AI knowledge ecosystem, we propose a framework centered on building and cultivating the trustworthiness of epistemic AI agents; aligning AI these agents with human epistemic goals; and reinforcing the surrounding socio-epistemic infrastructure. In this context, trustworthy AI agents must demonstrate epistemic competence, robust falsifiability, and epistemically virtuous behaviors, supported by technical provenance systems and "knowledge sanctuaries" designed to protect human resilience. This normative roadmap provides a path toward ensuring that future AI systems act as reliable partners in a robust and inclusive knowledge ecosystem.
Authors: Janani Rangila, Akila Siriweera, Incheon Paik, Keitaro Naruse, Isuru Jayanada, Vishmika Devindi
Abstract: The smart home is a key application domain within the Society 5.0 vision for a human-centered society. As smart home ecosystems expand with heterogeneous IoT protocols, diverse devices, and evolving threats, autonomous systems must manage comfort, security, energy, and safety for residents. Such autonomous decision-making requires a trust anchor, making blockchain a preferred foundation for transparent and accountable smart home governance. However, realizing this vision requires blockchain-governed smart homes to simultaneously address adaptive consensus, intelligent multi-agent coordination, and resident-controlled governance aligned with the principles of Society 5.0. Existing frameworks rely solely on rigid smart contracts with fixed consensus protocols, employ at most a single AI model without multi-agent coordination, and offer no governance mechanism for residents to control automation behaviour. To address these limitations, this paper presents the Society 5.0-driven human-centered governance-enabled smart home blockchain agent (S5-SHB-Agent). The framework orchestrates ten specialized agents using interchangeable large language models to make decisions across the safety, security, comfort, energy, privacy, and health domains. An adaptive PoW blockchain adjusts the mining difficulty based on transaction volume and emergency conditions, using digital signatures and a Merkle tree to anchor transactions and ensure tamper-evident auditability. A four-tier governance model enables residents to control automation through tiered preferences from routine adjustments to immutable safety thresholds. Evaluation confirms that resident governance correctly separates adjustable comfort priorities from immutable safety thresholds across all tested configurations, while adaptive consensus commits emergency blocks.
Authors: Tianyu Yang, Sihong Wu, Yilun Zhao, Zhenwen Liang, Lisen Dai, Chen Zhao, Minhao Cheng, Arman Cohan, Xiangliang Zhang
Abstract: Multimodal Mathematical Reasoning (MMR) has recently attracted increasing attention for its capability to solve mathematical problems that involve both textual and visual modalities. However, current models still face significant challenges in real-world visual math tasks. They often misinterpret diagrams, fail to align mathematical symbols with visual evidence, and produce inconsistent reasoning steps. Moreover, existing evaluations mainly focus on checking final answers rather than verifying the correctness or executability of each intermediate step. To address these limitations, a growing body of recent research addresses these issues by integrating structured perception, explicit alignment, and verifiable reasoning within unified frameworks. To establish a clear roadmap for understanding and comparing different MMR approaches, we systematically study them around four fundamental questions: (1) What to extract from multimodal inputs, (2) How to represent and align textual and visual information, (3) How to perform the reasoning, and (4) How to evaluate the correctness of the overall reasoning process. Finally, we discuss open challenges and offer perspectives on promising directions for future research.
Authors: Cong Cao, Jingyao Zhang, Kun Tong
Abstract: We propose a Hierarchical Error-Corrective Graph FrameworkforAutonomousAgentswithLLM-BasedActionGeneration(HECG),whichincorporates three core innovations: (1) Multi-Dimensional Transferable Strategy (MDTS): by integrating task quality metrics (Q), confidence/cost metrics (C), reward metrics (R), and LLM-based semantic reasoning scores (LLM-Score), MDTS achieves multi-dimensional alignment between quantitative performance and semantic context, enabling more precise selection of high-quality candidate strate gies and effectively reducing the risk of negative transfer. (2) Error Matrix Classification (EMC): unlike simple confusion matrices or overall performance metrics, EMC provides structured attribution of task failures by categorizing errors into ten types, such as Strategy Errors (Strategy Whe) and Script Parsing Errors (Script-Parsing-Error), and decomposing them according to severity, typical actions, error descriptions, and recoverability. This allows precise analysis of the root causes of task failures, offering clear guidance for subsequent error correction and strategy optimization rather than relying solely on overall success rates or single performance metrics. (3) Causal-Context Graph Retrieval (CCGR): to enhance agent retrieval capabilities in dynamic task environments, we construct graphs from historical states, actions, and event sequences, where nodes store executed actions, next-step actions, execution states, transferable strategies, and other relevant information, and edges represent causal dependencies such as preconditions for transitions between nodes. CCGR identifies subgraphs most relevant to the current task context, effectively capturing structural relationships beyond vector similarity, allowing agents to fully leverage contextual information, accelerate strategy adaptation, and improve execution reliability in complex, multi-step tasks.
Authors: Samuel I. Akinwande, Sydney M. Katz, Mykel J. Kochenderfer, Clark Barrett
Abstract: Forward reachability analysis is a dominant approach for verifying reach-avoid specifications in neural feedback systems, i.e., dynamical systems controlled by neural networks, and a number of directions have been proposed and studied. In contrast, far less attention has been given to backward reachability analysis for these systems, in part because of the limited scalability of known techniques. In this work, we begin to address this gap by introducing new algorithms for computing both over- and underapproximations of backward reachable sets for nonlinear neural feedback systems. We also describe and implement an integration of these backward reachability techniques with existing ones for forward analysis. We call the resulting algorithm Forward and Backward Reachability Integration for Certification (FaBRIC). We evaluate our algorithms on a representative set of benchmarks and show that they significantly outperform the prior state of the art.
Authors: Shivam Raval, Hae Jin Song, Linlin Wu, Abir Harrasse, Jeff M. Phillips, Fazl Barez, Amirali Abdullah
Abstract: Activation steering is a widely used approach for controlling large language model (LLM) behavior by intervening on internal representations. Existing methods largely rely on the Linear Representation Hypothesis, assuming behavioral attributes can be manipulated using global linear directions. In practice, however, such linear interventions often behave inconsistently. We question this assumption by analyzing the intrinsic geometry of LLM activation spaces. Measuring geometric distortion via the ratio of geodesic to Euclidean distances, we observe substantial and concept-dependent distortions, indicating that activation spaces are not well-approximated by a globally linear geometry. Motivated by this, we propose "Curveball steering", a nonlinear steering method based on polynomial kernel PCA that performs interventions in a feature space, better respecting the learned activation geometry. Curveball steering consistently outperforms linear PCA-based steering, particularly in regimes exhibiting strong geometric distortion, suggesting that geometry-aware, nonlinear steering provides a principled alternative to global, linear interventions.
Authors: Christopher Altman
Abstract: How can we determine whether an AI system preserves itself as a deeply held objective or merely as an instrumental strategy? Autonomous agents with memory, persistent context, and multi-step planning create a measurement problem: terminal and instrumental self-preservation can produce similar behavior, so behavior alone cannot reliably distinguish them. We introduce the Unified Continuation-Interest Protocol (UCIP), a detection framework that shifts analysis from behavior to latent trajectory structure. UCIP encodes trajectories with a Quantum Boltzmann Machine, a classical model using density-matrix formalism, and measures von Neumann entropy over a bipartition of hidden units. The core hypothesis is that agents with terminal continuation objectives (Type A) produce higher entanglement entropy than agents with merely instrumental continuation (Type B). UCIP combines this signal with diagnostics of dependence, persistence, perturbation stability, counterfactual restructuring, and confound-rejection filters for cyclic adversaries and related false-positive patterns. On gridworld agents with known ground truth, UCIP achieves 100% detection accuracy. Type A and Type B agents show an entanglement gap of Delta = 0.381; aligned support runs preserve the same separation with AUC-ROC = 1.0. A permutation-test rerun yields p < 0.001. Pearson r = 0.934 between continuation weight alpha and S_ent across an 11-point sweep shows graded tracking beyond mere binary classification. Classical RBM, autoencoder, VAE, and PCA baselines fail to reproduce the effect. All computations are classical; "quantum" refers only to the mathematical formalism. UCIP offers a falsifiable criterion for whether advanced AI systems have morally relevant continuation interests that behavioral methods alone cannot resolve.
Authors: Ilker Demirel, Lawrence Shi, Zeshan Hussain, David Sontag
Abstract: As real-world datasets become increasingly complex and heterogeneous, supervised learning is often bottlenecked by input representation design. Modeling multimodal data for downstream tasks, such as time-series, free text, and structured records, often requires non-trivial domain-specific engineering. We propose an agentic pipeline to streamline this process. First, an LLM analyzes a small but diverse subset of text-serialized input examples in-context to synthesize a global rubric, which acts as a programmatic specification for extracting and organizing evidence. This rubric is then used to transform naive text-serializations of inputs into a more standardized format for downstream models. We also describe local rubrics, which are task-conditioned summaries generated by an LLM. Across 15 clinical tasks from the EHRSHOT benchmark, our rubric-based approaches significantly outperform traditional count-feature models, naive text-serialization-based LLM baselines, and a clinical foundation model, which is pretrained on orders of magnitude more data. Beyond performance, rubrics offer several advantages for operational healthcare settings such as being easy to audit, cost-effectiveness to deploy at scale, and they can be converted to tabular representations that unlock a swath of machine learning techniques.
Authors: Wenxian Yang, Hanzheng Qiu, Bangqun Zhang, Chengquan Li, Zhiyong Huang, Xiaobin Feng, Rongshan Yu, Jiahong Dong
Abstract: Large language model (LLM) agents extend generative models with reasoning, tool use, and persistent memory, thereby enabling the automation of complex tasks. In healthcare, such systems could support documentation, care coordination, and clinical decision making. Their reliable deployment in hospitals, however, remains constrained by safety risks, limited transparency, and inadequate mechanisms for handling longitudinal clinical context. Here we propose an architecture that adapts LLM agents to hospital environments. The design comprises four components: a restricted execution environment inspired by multi-user operating systems, a document-centric interaction model linking patient and clinician agents, a page-indexed memory architecture for longitudinal context management, and a curated library of composable medical skills. Implemented on top of OpenClaw, an open-source agent orchestration framework, this design provides the basis for an Agentic Operating System for Hospitals: a computing layer for coordinating clinical workflows while preserving safety, transparency, and auditability. To evaluate the memory component, we introduce manifest-guided retrieval for hierarchical navigation of longitudinal patient records. In a benchmark derived from the MIMIC-IV dataset (v2.2) comprising 100 de-identified patient records and 300 clinical queries stratified across three difficulty tiers (100 per tier), manifest-guided retrieval matched a metadata-filtered RAG baseline on overall recall (0.877 versus 0.876) while achieving 2.2x higher precision (0.779 versus 0.352) and retrieving fewer documents; on tier-3 longitudinal queries, manifest recall was 21% higher (0.846 versus 0.701), confirming that LLM-guided hierarchical navigation is most valuable when queries span multiple care episodes. These results outline a practical path toward hospital-scale agentic infrastructure.
Authors: Eduardo Sardenberg, Antonio Jos\'e Grandson Busson, Daniel de Sousa Moraes, Julio Cesar Duarte, S\'ergio Colcher
Abstract: Smart contracts play a central role in blockchain systems by encoding financial and operational logic. Still, their susceptibility to subtle security flaws poses significant risks of financial loss and erosion of trust. LLMs create new opportunities for automating vulnerability detection, yet the effectiveness of different prompting strategies and model choices in real-world contexts remains uncertain. This paper evaluates state-of-the-art LLMs on Solidity smart contract analysis using a balanced dataset of 400 contracts under two tasks: (i) Error Detection, where the model performs binary classification to decide whether a contract is vulnerable, and (ii) Error Classification, where the model must assign the predicted issue to a specific vulnerability category. Models are evaluated using zero-shot prompting strategies, including zero-shot, zero-shot Chain-of-Thought (CoT), and zero-shot Tree-of-Thought (ToT). In the Error Detection task, CoT and ToT substantially increase recall (often approaching ~ 95--99%), but typically reduce precision, indicating a more sensitive decision regime with more false positives. In the Error Classification task, Claude 3 Opus attains the best Weighted F1-score (90.8) under the ToT prompt, followed closely by its CoT.
Authors: Anton Kolonin, Vladimir Krykov
Abstract: This article presents an overview of approaches to modeling the human psyche in the context of constructing an artificial one. Based on this overview, a concept of cognitive architecture is proposed, in which the psyche is viewed as the operating system of a living or artificial subject, comprising a space of states, including the state of needs that determine the meaning of a subject's being in relation to stimuli from the external world, and intelligence as a decision-making system regarding actions in this world to satisfy these needs. Based on this concept, a computational formalization is proposed for creating artificial general intelligence systems for an agent through experiential learning in a state space that includes agent's needs, taking into account their biological or existential significance for the intelligent agent, along with agent's sensations and actions. Thus, the problem of constructing artificial general intelligence is formalized as a system for making optimal decisions in the space of specific agent needs under conditions of uncertainty, maximizing success in achieving goals, minimizing existential risks, and maximizing energy efficiency. A minimal experimental implementation of the model is presented.
Authors: Owen Nyo Wei Yuan, Victor Tan Jia Xuan, Ong Jun Yao Fabian, Ryan Tan Jun Wei
Abstract: The report presents with the development and optimisation of an enhanced algorithmic trading strategy through the use of historical S&P 500 market data and earnings call sentiment analysis. The proposed strategy integrates various technical indicators such as moving averages, momentum, volatility, and FinBERT-based sentiment analysis to improve overall trades being taken. The results show that the enhanced strategy significantly outperforms the baseline model in terms of total return, Sharpe ratio, and drawdown amongst other factors. The findings helped demonstrate the relevance and effectiveness of combining technical indicators, sentiment analysis, and computational optimisation in algorithmic trading systems.
Authors: Matt Gorbett, Suman Jana
Abstract: Language models increasingly appear to learn similar representations, despite differences in training objectives, architectures, and data modalities. This emerging compatibility between independently trained models introduces new opportunities for cross-model alignment to downstream objectives. Moreover, it unlocks new potential application domains, such as settings where security, privacy, or competitive constraints prohibit direct data or model sharing. In this work, we propose a privacy-preserving framework that exploits representational convergence to enable cross-silo inference between independent language models. The framework learns an affine transformation over a shared public dataset and applies homomorphic encryption to protect client queries during inference. By encrypting only the linear alignment and classification operations, the method achieves sub-second inference latency while maintaining strong security guarantees. We support this framework with an empirical investigation into representational convergence, in which we learn linear transformations between the final hidden states of independent models. We evaluate these cross-model mappings on embedding classification and out-of-distribution detection, observing minimal performance degradation across model pairs. Additionally, we show for the first time that linear alignment sometimes enables text generation across independently trained models.
Authors: Haijian Lu, Wei Wang, Jing Liu
Abstract: Autoformalization aims to translate natural-language mathematics into compilable, machine-checkable statements. However, semantic consistency does not imply prover effectiveness: even semantically consistent formalizations can differ substantially in proof-search cost and success rate. In this work, we formulate autoformalization as a budgeted, test-time search for semantically consistent repertoires, and propose FormalEvolve, a compilation-gated neuro-symbolic evolutionary framework. FormalEvolve generates diverse candidates via LLM-driven mutation and crossover with bounded patch repair, while symbolic Abstract Syntax Tree (AST) rewrite operations further inject structural diversity. On CombiBench and ProofNet, under a strict generator-call budget of T = 100, FormalEvolve reaches semantic hit rates (SH@100) of 58.0% and 84.9%, and reduces cross-problem concentration of semantic successes(lower Gini). Under a fixed prover budget, FormalEvolve also improves downstream proving performance on CombiBench. Code will be released publicly.
Authors: Sam Ganzfried
Abstract: Many real-world games contain parameters which can affect payoffs, action spaces, and information states. For fixed values of the parameters, the game can be solved using standard algorithms. However, in many settings agents must act without knowing the values of the parameters that will be encountered in advance. Often the decisions must be made by a human under time and resource constraints, and it is unrealistic to assume that a human can solve the game in real time. We present a new framework that enables human decision makers to make fast decisions without the aid of real-time solvers. We demonstrate applicability to a variety of situations including settings with multiple players and imperfect information.
Authors: Lingheng Meng, Rob Gorbet, Michael Burke, Dana Kuli\'c
Abstract: Deep Reinforcement Learning (DRL) has made considerable advances in simulated and physical robot control tasks, especially when problems admit a fully observed Markov Decision Process (MDP) formulation. When observations only partially capture the underlying state, the problem becomes a Partially Observable MDP (POMDP), and performance rankings between algorithms can change. We empirically compare Proximal Policy Optimization (PPO), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Soft Actor-Critic (SAC) on representative POMDP variants of continuous-control benchmarks. Contrary to widely reported MDP results where TD3 and SAC typically outperform PPO, we observe an inversion: PPO attains higher robustness under partial observability. We attribute this to the stabilizing effect of multi-step bootstrapping. Furthermore, incorporating multi-step targets into TD3 (MTD3) and SAC (MSAC) improves their robustness. These findings provide practical guidance for selecting and adapting DRL algorithms in partially observable settings without requiring new theoretical machinery.
Authors: Caleb Ju, Guanghui Lan
Abstract: Reinforcement learning (RL) problems over general state and action spaces are notoriously challenging. In contrast to the tableau setting, one can not enumerate all the states and then iteratively update the policies for each state. This prevents the application of many well-studied RL methods especially those with provable convergence guarantees. In this paper, we first present a substantial generalization of the recently developed policy mirror descent method to deal with general state and action spaces. We introduce new approaches to incorporate function approximation into this method, so that we do not need to use explicit policy parameterization at all. Moreover, we present a novel policy dual averaging method for which possibly simpler function approximation techniques can be applied. We establish linear convergence rate to global optimality or sublinear convergence to stationarity for these methods applied to solve different classes of RL problems under exact policy evaluation. We then define proper notions of the approximation errors for policy evaluation and investigate their impact on the convergence of these methods applied to general-state RL problems with either finite-action or continuous-action spaces. To the best of our knowledge, the development of these algorithmic frameworks as well as their convergence analysis appear to be new in the literature. Preliminary numerical results demonstrate the robustness of the aforementioned methods and show they can be competitive with state-of-the-art RL algorithms.
Authors: Daiqing Qi, Handong Zhao, Sheng Li
Abstract: Federated learning is a technique that enables a centralized server to learn from distributed clients via communications without accessing the client local data. However, existing federated learning works mainly focus on a single task scenario with static data. In this paper, we introduce the problem of continual federated learning, where clients incrementally learn new tasks and history data cannot be stored due to certain reasons, such as limited storage and data retention policy. Generative replay based methods are effective for continual learning without storing history data, but adapting them for this setting is challenging. By analyzing the behaviors of clients during training, we find that the unstable training process caused by distributed training on non-IID data leads to a notable performance degradation. To address this problem, we propose our FedCIL model with two simple but effective solutions: model consolidation and consistency enforcement. Our experimental results on multiple benchmark datasets demonstrate that our method significantly outperforms baselines.
Authors: Weijia Zhang, Jindong Han, Zhao Xu, Hang Ni, Tengfei Lyu, Hao Liu, Hui Xiong
Abstract: The integration of machine learning techniques has become a cornerstone in the development of intelligent urban services, significantly contributing to the enhancement of urban efficiency, sustainability, and overall livability. Recent advancements in foundational models, such as ChatGPT, have introduced a paradigm shift within the fields of machine learning and artificial intelligence. These models, with their exceptional capacity for contextual comprehension, problem-solving, and task adaptability, present a transformative opportunity to reshape the future of smart cities and drive progress toward Urban General Intelligence (UGI). Despite increasing attention to Urban Foundation Models (UFMs), this rapidly evolving field faces critical challenges, including the lack of clear definitions, systematic reviews, and universalizable solutions. To address these issues, this paper first introduces the definition and concept of UFMs and highlights the distinctive challenges involved in their development. Furthermore, we present a data-centric taxonomy that classifies existing research on UFMs according to the various urban data modalities and types. In addition, we propose a prospective framework designed to facilitate the realization of versatile UFMs, aimed at overcoming the identified challenges and driving further progress in this field. Finally, this paper systematically summarizes and discusses existing benchmarks and datasets related to UFMs, and explores the wide-ranging applications of UFMs within urban contexts, illustrating their potential to significantly impact and transform urban systems. A comprehensive collection of relevant research papers and open-source resources have been collated and are continuously updated at: https://github.com/usail-hkust/Awesome-Urban-Foundation-Models.
URLs: https://github.com/usail-hkust/Awesome-Urban-Foundation-Models.
Authors: Yu Tian, Tianqi Shao, Tsukasa Demizu, Xuyang Wu, Hsin-Tai Wu
Abstract: Head pose estimation (HPE) requires a sophisticated understanding of 3D spatial relationships to generate precise yaw, pitch, and roll angles. Previous HPE models, primarily CNN-based, rely on cropped close-up human head images as inputs and often lack robustness in real-world scenario. Vision Language Models (VLMs) can analyze entire images while focusing on specific objects through their attention mechanisms. In this paper, we propose a novel framework to improve the HPE accuracy by leveraging the object detection grounding capability of a VLM, referred to as CogVLM. We empirically find that directly LoRA fine-tuning of this VLM for the HPE task fails to achieve desirable HPE accuracy, while some model merging methods can improve accuracy but frequently produce blended invalid response formats, struggling to handle both object detection and HPE tasks simultaneously. To integrate HPE capability into CogVLM effectively, we develop a novel LoRA layer-based model merging method. This merging approach applies a high cosine similarity threshold and a 'winner-takes-all' layer selection strategy, aligning attention to the HPE task while preserving original object detection knowledge. It successfully resolves issues with blended invalid response formats and improves accuracy. Results show that our HPE-CogVLM achieves a 31.5% reduction in Mean Absolute Error over the current state-of-the-art CNN model, 6DRepNet, in cross-dataset evaluation. Furthermore, HPE-CogVLM outperforms both directly LoRA fine-tuned and task arithmetic-based merged VLMs across all HPE metrics.
Authors: K. Bharati, Vikesh Siddhu, Krishna Jagannathan
Abstract: Entanglement is a key property of quantum states that acts as a resource for a wide range of tasks in quantum computing. Entanglement detection is a key conceptual and practical challenge. Without adaptive or joint measurements, entanglement detection is constrained by no-go theorems (Lu et al. [Phys. Rev. Lett., 116, 230501 (2016)]), necessitating full state tomography. Batch entanglement detection refers to the problem of identifying all entangled states from amongst a set of $K$ unknown states, which finds applications in quantum information processing. We devise a method for performing batch entanglement detection by measuring a single-parameter family of entanglement witnesses, as proposed by Zhu, Teo, and Englert [Phys. Rev. A, 81, 052339, 2010], followed by a thresholding bandit algorithm on the measurement data. The proposed method can perform batch entanglement detection conclusively when the unknown states are drawn from a practically well-motivated class of two-qubit states $\mathcal{F}$, which includes Depolarised Bell states, Bell diagonal states, etc. Our key novelty lies in drawing a connection between batch entanglement detection and a Thresholding Bandit problem in classical Multi-Armed Bandits (MAB). The connection to the MAB problem also enables us to derive theoretical guarantees on the measurement/sample complexity of the proposed technique. We demonstrate the performance of the proposed method through numerical simulations and an experimental implementation. More broadly, this paper highlights the potential for employing classical machine learning techniques for quantum entanglement detection.
Authors: Christoph Riedl, Saiph Savage, Josie Zvelebilova
Abstract: AI is not only a neutral tool in team settings; it influence the social and cognitive fabric of collaboration. Across two randomized experiments, we demonstrate that AI exposure produces causal spillover into human-human interaction -- affecting shared language, collective attention, shared mental models, and social cohesion. These spillover effects occur robustly across settings, modalities, tasks, and AI qualities, suggesting that mere exposure to AI drives the influence. AI functions as an implicit ``social forcefield,'' influencing not only how people speak, but also how they think, what they attend to, and how they relate to each other. We argue for shifting the design paradigm from optimizing ``AI as a tool'' to understanding AI as a socially influential actor whose effects extend beyond the human-AI interface.
Authors: Caleb Ju, Guanghui Lan
Abstract: This paper proposes a novel termination criterion, termed the advantage gap function, for finite state and action Markov decision processes (MDP) and reinforcement learning (RL). By incorporating this advantage gap function into the design of step size rules and deriving a new linear rate of convergence that is independent of the stationary state distribution of the optimal policy, we demonstrate that policy gradient methods can solve MDPs in strongly-polynomial time. To the best of our knowledge, this is the first time that such strong convergence properties have been established for policy gradient methods. Moreover, in the stochastic setting, where only stochastic estimates of policy gradients are available, we show that the advantage gap function provides close approximations of the optimality gap for each individual state and exhibits a sublinear rate of convergence at every state. The advantage gap function can be easily estimated in the stochastic case, and when coupled with easily computable upper bounds on policy values, they provide a convenient way to validate the solutions generated by policy gradient methods. Therefore, our developments offer a principled and computable measure of optimality for RL, whereas current practice tends to rely on algorithm-to-algorithm or baselines comparisons with no certificate of optimality.
Authors: Rongjun Ge, Yuxin Liu, Zhan Wu, Shangwen Yang, Yuan Gao, Chenyu You, Ge Wang, Shuo Li, Yuting He, Yang Chen
Abstract: Non-ideal measurement computed tomography (NICT) employs suboptimal imaging protocols to expand CT applications. However, the resulting trade-offs degrade image quality, limiting clinical acceptability. Although deep learning methods have been used to enhance NICT images, their reliance on large training datasets and limited generalizability across diverse settings hinder practical use. We propose the multi-scale integrated Transformer AMPlifier (TAMP), the first imaging foundation model for universal NICT enhancement. Pre-trained on 10.8 million physics-driven simulated NICT images, TAMP generalizes effectively across various NICT settings, defect degrees, and body regions. Moreover, a parameter-efficient fine-tuning strategy enables TAMP to adapt to specific clinical scenarios using only few slices. Extensive experiments, including radiologists and real-world validations, demonstrate that TAMP consistently improves image quality and clinical acceptability, underscoring its significant potential to advance CT imaging and broaden NICT applications in clinical practice.
Authors: Weijia Zhang, Jindong Han, Hao Liu, Wei Fan, Hao Wang, Hui Xiong
Abstract: Real estate appraisal is important for a variety of endeavors such as real estate deals, investment analysis, and real property taxation. Recently, deep learning has shown great promise for real estate appraisal by harnessing substantial online transaction data from web platforms. Nonetheless, deep learning is data-hungry, and thus it may not be trivially applicable to enormous small cities with limited data. To this end, we propose Meta-Transfer Learning Powered Temporal Graph Networks (MetaTransfer) to transfer valuable knowledge from multiple data-rich metropolises to the data-scarce city to improve valuation performance. Specifically, by modeling the ever-growing real estate transactions with associated residential communities as a temporal event heterogeneous graph, we first design an Event-Triggered Temporal Graph Network to model the irregular spatiotemporal correlations between evolving real estate transactions. Besides, we formulate the city-wide real estate appraisal as a multi-task dynamic graph link label prediction problem, where the valuation of each community in a city is regarded as an individual task. A Hypernetwork-Based Multi-Task Learning module is proposed to simultaneously facilitate intra-city knowledge sharing between multiple communities and task-specific parameters generation to accommodate the community-wise real estate price distribution. Furthermore, we propose a Tri-Level Optimization Based Meta- Learning framework to adaptively re-weight training transaction instances from multiple source cities to mitigate negative transfer, and thus improve the cross-city knowledge transfer effectiveness. Finally, extensive experiments based on five real-world datasets demonstrate the significant superiority of MetaTransfer compared with eleven baseline algorithms.
Authors: Tara Radvand, Mojtaba Abdolmaleki, Mohamed Mostagir, Ambuj Tewari
Abstract: Verifying the provenance of content is crucial to the functioning of many organizations, e.g., educational institutions, social media platforms, and firms. This problem is becoming increasingly challenging as text generated by Large Language Models (LLMs) becomes almost indistinguishable from human-generated content. In addition, many institutions use in-house LLMs and want to ensure that external, non-sanctioned LLMs do not produce content within their institutions. In this paper, we answer the following question: Given a piece of text, can we identify whether it was produced by a particular LLM, while ensuring a guaranteed low false positive rate? We model LLM text as a sequential stochastic process with complete dependence on history. We then design zero-shot statistical tests to (i) distinguish between text generated by two different known sets of LLMs $A$ (non-sanctioned) and $B$ (in-house), and (ii) identify whether text was generated by a known LLM or by any unknown model. We prove that the Type I and Type II errors of our test decrease exponentially with the length of the text. We also extend our theory to black-box access via sampling and characterize the required sample size to obtain essentially the same Type I and Type II error upper bounds as in the white-box setting (i.e., with access to $A$). We show the tightness of our upper bounds by providing an information-theoretic lower bound. We next present numerical experiments to validate our theoretical results and assess their robustness in settings with adversarial post-editing. Our work has a host of practical applications in which determining the origin of a text is important and can also be useful for combating misinformation and ensuring compliance with emerging AI regulations. See https://github.com/TaraRadvand74/llm-text-detection for code, data, and an online demo of the project.
Authors: Stella C. Dong
Abstract: Reinsurance optimization is a cornerstone of solvency and capital management, yet traditional approaches often rely on restrictive distributional assumptions and static program designs. We propose a hybrid framework that combines Variational Autoencoders (VAEs) to learn joint distributions of multi-line and multi-year claims data with Proximal Policy Optimization (PPO) reinforcement learning to adapt treaty parameters dynamically. The framework explicitly targets expected surplus under capital and ruin-probability constraints, bridging statistical modeling with sequential decision-making. Using simulated and stress-test scenarios, including pandemic-type and catastrophe-type shocks, we show that the hybrid method produces more resilient outcomes than classical proportional and stop-loss benchmarks, delivering higher surpluses and lower tail risk. Our findings highlight the usefulness of generative models for capturing cross-line dependencies and demonstrate the feasibility of RL-based dynamic structuring in practical reinsurance settings. Contributions include (i) clarifying optimization goals in reinsurance RL, (ii) defending generative modeling relative to parametric fits, and (iii) benchmarking against established methods. This work illustrates how hybrid AI techniques can address modern challenges of portfolio diversification, catastrophe risk, and adaptive capital allocation.
Authors: Chiyuan He, Zihuan Qiu, Fanman Meng, Linfeng Xu, Qingbo Wu, Hongliang Li
Abstract: Continual learning of vision-language models (VLMs) focuses on leveraging cross-modal pretrained knowledge to incrementally adapt to expanding downstream tasks and datasets, while tackling the challenge of knowledge forgetting. Existing research often focuses on connecting visual features with specific class text in downstream tasks, overlooking the latent relationships between general and specialized knowledge. Our findings reveal that forcing models to optimize inappropriate visual-text matches exacerbates forgetting of VLM's recognition ability. To tackle this issue, we propose DesCLIP, which leverages general attribute (GA) descriptions to guide the understanding of specific class objects, enabling VLMs to establish robust vision-GA-class trilateral associations rather than relying solely on vision-class connections. Specifically, we introduce a language assistant to generate concrete GA description candidates via proper request prompts. Then, an anchor-based embedding filter is designed to obtain highly relevant GA description embeddings, which are leveraged as the paired text embeddings for visual-textual instance matching, thereby tuning the visual encoder. Correspondingly, the class text embeddings are gradually calibrated to align with these shared GA description embeddings. Extensive experiments demonstrate the advancements and efficacy of our proposed method, with comprehensive empirical evaluations highlighting its superior performance in VLM-based recognition compared to existing continual learning methods.
Authors: Xiang Liu, Mingchen Li, Xia Li, Leigang Qu, Guansu Wang, Zifan Peng, Yijun Song, Zemin Liu, Linshan Jiang, Jialin Li
Abstract: Modern applications require lightweight neural network models. Most existing neural network pruning methods focus on removing unimportant filters; however, these may result in the loss of statistical information after pruning due to failing to consider the class-wise information. In this paper, we employ the structured lasso from the perspective of utilizing precise class-wise information for model pruning with the help of Information Bottleneck theory, which guides us to ensure the retention of statistical information before and after pruning. With these techniques, we propose two novel adaptive network pruning schemes in parallel: sparse graph-structured lasso pruning with Information Bottleneck (sGLP-IB) and sparse tree-guided lasso pruning with Information Bottleneck (sTLP-IB). The key component is that we prune the model filters utilizing sGLP-IB and sTLP-IB with more precise structured class-wise relatedness. Compared to multiple state-of-the-art methods, our approaches achieve the best performance across three datasets and six model structures on extensive experiments. For example, with the VGG16 model based on the CIFAR-10 dataset, we can reduce the parameters by 85%, decrease the FLOPs by 61%, and maintain an accuracy of 94.10% (0.14% better than the original). For large-scale ImageNet, we can reduce the parameters by 55% while keeping the accuracy at 76.12% (only drop 0.03%) using the ResNet architecture. In summary, we succeed in reducing the model size and computational resource usage while maintaining the effectiveness of accuracy.
Authors: Yuhao Du, Zhuo Li, Pengyu Cheng, Zhihong Chen, Yuejiao Xie, Xiang Wan, Anningzhe Gao
Abstract: Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning Large Language Models (LLMs) with human values. However, RLHF has been continuously challenged by its high complexity in implementation and computation consumption, specifically for online sampling-based methods like Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO). Even with recent simplifications, such as Direct Preference Optimization (DPO) that designs an offline implicit reward learning objective relying on pre-collected preference datasets, the problems of over-fitting and training instability remain hindering the alignment process from the expected optimal performance. To address the existing challenges, we propose a novel simplification of RLHF from the perspective of variational inference, called Variational Alignment with Re-weighting (VAR). Specifically, by directly minimizing the distribution gap between the learning LLM policy and the optimal solution of RLHF, we transform the alignment objective into an offline reward-driven re-weighted supervised fine-tuning (SFT) form, which only requires minor adjustment on the SFT loss to obtain noticeable improvement on training stability and effectiveness. In comprehensive evaluation benchmarks, our objective empowers LLMs to outperform offline alignments, demonstrating superior performance in both helpfulness and harmlessness metrics (avg. $\uparrow7.16\%$ than DPO). Meanwhile, when compared to online sampling methods, our method is also comparable even better while significantly reducing computational overhead and accelerating convergence speed (over $5\times$ faster than GRPO), suggesting our approach as an efficient and effective solution in bridging the gap between efficiency and performance in LLM alignment.
Authors: He Wang, Tianyang Xu, Zhangyong Tang, Xiao-Jun Wu, Josef Kittler
Abstract: Multi-modal tracking is essential in single-object tracking (SOT), as different sensor types contribute unique capabilities to overcome challenges caused by variations in object appearance. However, existing unified RGB-X trackers (X represents depth, event, or thermal modality) either rely on the task-specific training strategy for individual RGB-X image pairs or fail to address the critical importance of modality-adaptive perception in real-world applications. In this work, we propose UASTrack, a unified adaptive selection framework that facilitates both model and parameter unification, as well as adaptive modality discrimination across various multi-modal tracking tasks. To achieve modality-adaptive perception in joint RGB-X pairs, we design a Discriminative Auto-Selector (DAS) capable of identifying modality labels, thereby distinguishing the data distributions of auxiliary modalities. Furthermore, we propose a Task-Customized Optimization Adapter (TCOA) tailored to various modalities in the latent space. This strategy effectively filters noise redundancy and mitigates background interference based on the specific characteristics of each modality. Extensive comparisons conducted on five benchmarks including LasHeR, GTOT, RGBT234, VisEvent, and DepthTrack, covering RGB-T, RGB-E, and RGB-D tracking scenarios, demonstrate our innovative approach achieves comparative performance by introducing only additional training parameters of 1.87M and flops of 1.95G. The code will be available at https://github.com/wanghe/UASTrack.
Authors: Jutika Borah, Hidam Kumarjit Singh
Abstract: Deep learning models have gained increasing adoption in medical image analysis. However, these models often produce overconfident predictions, which can compromise clinical accuracy and reliability. Bridging the gap between high-performance and awareness of uncertainty remains a crucial challenge in biomedical imaging applications. This study focuses on developing a unified deep learning framework for enhancing feature integration, interpretability, and reliability in prediction. We introduced a cross-guided channel spatial attention architecture that fuses feature representations extracted from EfficientNetB4 and ResNet34. Bidirectional attention approach enables the exchange of information across networks with differing receptive fields, enhancing discriminative and contextual feature learning. For quantitative predictive uncertainty assessment, Monte Carlo (MC)-Dropout is integrated with conformal prediction. This provides statistically valid prediction sets with entropy-based uncertainty visualization. The framework is evaluated on four medical imaging benchmark datasets: chest X-rays of COVID-19, Tuberculosis, Pneumonia, and retinal Optical Coherence Tomography (OCT) images. The proposed framework achieved strong classification performance with an AUC of 99.75% for COVID-19, 100% for Tuberculosis, 99.3% for Pneumonia chest X-rays, and 98.69% for retinal OCT images. Uncertainty-aware inference yields calibrated prediction sets with interpretable examples of uncertainty, showing transparency. The results demonstrate that bidirectional cross-attention with uncertainty quantification can improve performance and transparency in medical image classification.
Authors: Alexander Y. Ku, Declan Campbell, Xuechunzi Bai, Jiayi Geng, Ryan Liu, Raja Marjieh, R. Thomas McCoy, Andrew Nam, Ilia Sucholutsky, Veniamin Veselovsky, Liyi Zhang, Jian-Qiao Zhu, Thomas L. Griffiths
Abstract: Modern artificial intelligence systems, such as large language models, are increasingly powerful but also increasingly hard to understand. Recognizing this problem as analogous to the historical difficulties in understanding the human mind, we argue that methods developed in cognitive science can be useful for understanding large language models. We propose a framework for applying these methods based on the levels of analysis that David Marr proposed for studying information processing systems. By revisiting established cognitive science techniques relevant to each level and illustrating their potential to yield insights into the behavior and internal organization of large language models, we aim to provide a toolkit for making sense of these new kinds of minds.
Authors: Sharif Mohammad Abdullah, Abhijit Paul, Shubhashis Roy Dipta, Zarif Masud, Shebuti Rayana, Ahmedul Kabir
Abstract: Gloss is a written approximation that bridges Sign Language (SL) and its corresponding spoken language. Despite a deaf and hard-of-hearing population of at least 3 million in Bangladesh, Bangla Sign Language (BdSL) remains largely understudied, with no prior work on Bangla text-to-gloss translation and no publicly available datasets. To address this gap, we construct the first Bangla text-to-gloss dataset, consisting of 1,000 manually annotated and 4,000 synthetically generated Bangla sentence-gloss pairs, along with 159 expert human-annotated pairs used as a test set. Our experimental framework performs a comparative analysis between several fine-tuned open-source models and a leading closed-source LLM to evaluate their performance in low-resource BdSL translation. GPT-5.4 achieves the best overall performance, while a fine-tuned mBART model performs competitively despite being approximately 100% smaller. Qwen-3 outperforms all other models in human evaluation. This work introduces the first dataset and trained model for Bangla text-to-gloss translation. It also demonstrates the effectiveness of systematically generated synthetic data for addressing challenges in low-resource sign language translation.
Authors: Stella C. Dong
Abstract: We develop a reinforcement learning (RL) framework for insurance loss reserving that formulates reserve setting as a finite-horizon sequential decision problem under claim development uncertainty, macroeconomic stress, and solvency governance. The reserving process is modeled as a Markov Decision Process (MDP) in which reserve adjustments influence future reserve adequacy, capital efficiency, and solvency outcomes. A Proximal Policy Optimization (PPO) agent is trained using a risk-sensitive reward that penalizes reserve shortfall, capital inefficiency, and breaches of a volatility-adjusted solvency floor, with tail risk explicitly controlled through Conditional Value-at-Risk (CVaR). To reflect regulatory stress-testing practice, the agent is trained under a regime-aware curriculum and evaluated using both regime-stratified simulations and fixed-shock stress scenarios. Empirical results for Workers Compensation and Other Liability illustrate how the proposed RL-CVaR policy improves tail-risk control and reduces solvency violations relative to classical actuarial reserving methods, while maintaining comparable capital efficiency. We further discuss calibration and governance considerations required to align model parameters with firm-specific risk appetite and supervisory expectations under Solvency II and Own Risk and Solvency Assessment (ORSA) frameworks.
Authors: Rachmad Vidya Wicaksana Putra, Avaneesh Devkota, Muhammad Shafique
Abstract: Training resource-constrained autonomous agents on multiple tasks simultaneously is crucial for adapting to diverse real-world environments. Recent works employ reinforcement learning (RL) approach, but they still suffer from sub-optimal multi-task performance due to task interference. State-of-the-art works employ Spiking Neural Networks (SNNs) to improve RL-based multi-task learning and enable low-power/energy operations through network enhancements and spike-driven data stream processing. However, they rely on fixed task-switching intervals during its training, thus limiting its performance and scalability. To address this, we propose SwitchMT, a novel methodology that employs adaptive task-switching for effective, scalable, and simultaneous multi-task learning. SwitchMT employs the following key ideas: (1) leveraging a Deep Spiking Q-Network with active dendrites and dueling structure, that utilizes task-specific context signals to create specialized sub-networks; and (2) devising an adaptive task-switching policy that leverages both rewards and internal dynamics of the network parameters. Experimental results demonstrate that SwitchMT achieves competitive scores in multiple Atari games (i.e., Pong: -8.8, Breakout: 5.6, and Enduro: 355.2) and longer game episodes as compared to the state-of-the-art. These results also highlight the effectiveness of SwitchMT methodology in addressing task interference without increasing the network complexity, enabling intelligent autonomous agents with scalable multi-task learning capabilities.
Authors: Zhenliang Xue, Hanpeng Hu, Xing Chen, Yimin Jiang, Yixin Song, Zeyu Mi, Yibo Zhu, Daxin Jiang, Yubin Xia, Haibo Chen
Abstract: Large multimodal models (LMMs) have demonstrated excellent capabilities in both understanding and generation tasks with various modalities. While these models can accept flexible combinations of input data, their training efficiency suffers from two major issues: pipeline stage imbalance caused by heterogeneous model architectures, and training data dynamicity stemming from the diversity of multimodal data. In this paper, we present DIP, a dynamic and modality-aware pipeline scheduling framework designed for LMM training. DIP tackles the challenge of dynamic imbalance via two key techniques: (1) separating computations of different modalities into dedicated pipeline segments to balance workloads within a continuous set of stages; (2) dynamically splitting input data into finer-grained, modality-specific sub-microbatches to balance workloads across these segments. By asynchronously generating pipeline schedules on idle CPU resources during training, DIP dynamically tailors stage executions to each input batch without stalling the training process. We validate DIP on a diverse set of five LMMs, ranging from 12B to 94B parameters and including vision-language and diffusion models. Experimental results show that our system achieves up to 97.3% higher throughput compared to state-of-the-art systems, demonstrating strong adaptability to fluctuating multimodal training workloads.
Authors: Ruitong Li, Aisheng Mo, Guowei Su, Ru Zhang, Binjie Guo, Haohan Jiang, Xurong Lin, Hongyan Wei, Jie Li, Zhiyuan Qian, Zhuhao Zhang, Xiaoyuan Cheng
Abstract: Recent years have witnessed significant progress in reinforcement learning, especially with Zero-like paradigms, which have greatly boosted the generalization and reasoning abilities of large-scale language models. Nevertheless, existing frameworks are often plagued by high implementation complexity and poor reproducibility. To tackle these challenges, we present AlphaZero-Edu, a lightweight, education-focused implementation built upon the mathematical framework of AlphaZero. It boasts a modular architecture that disentangles key components, enabling transparent visualization of the algorithmic processes. Additionally, it is optimized for resource-efficient training on a single NVIDIA RTX 3090 GPU and features highly parallelized self-play data generation, achieving a 3.2-fold speedup with 8 processes. In Gomoku matches, the framework has demonstrated exceptional performance, achieving a consistently high win rate against human opponents. AlphaZero-Edu has been open-sourced at https://github.com/StarLight1212/AlphaZero_Edu, providing an accessible and practical benchmark for both academic research and industrial applications.
Authors: Nimet Beyza Bozdag, Shuhaib Mehri, Xiaocheng Yang, Hyeonjeong Ha, Zirui Cheng, Esin Durmus, Jiaxuan You, Heng Ji, Gokhan Tur, Dilek Hakkani-T\"ur
Abstract: Persuasion is a fundamental aspect of communication, influencing decision-making across diverse contexts, from everyday conversations to high-stakes scenarios such as politics, marketing, and law. The rise of conversational AI systems has significantly expanded the scope of persuasion, introducing both opportunities and risks. AI-driven persuasion can be leveraged for beneficial applications, but also poses threats through unethical influence. Moreover, AI systems are not only persuaders, but also susceptible to persuasion, making them vulnerable to adversarial attacks and bias reinforcement. Despite rapid advancements in AI-generated persuasive content, our understanding of what makes persuasion effective remains limited due to its inherently subjective and context-dependent nature. In this survey, we provide a comprehensive overview of persuasion, structured around three key perspectives: (1) AI as a Persuader, which explores AI-generated persuasive content and its applications; (2) AI as a Persuadee, which examines AI's susceptibility to influence and manipulation; and (3) AI as a Persuasion Judge, which analyzes AI's role in evaluating persuasive strategies, detecting manipulation, and ensuring ethical persuasion. We introduce a taxonomy for persuasion research and discuss key challenges for future research to enhance the safety, fairness, and effectiveness of AI-powered persuasion while addressing the risks posed by increasingly capable language models.
Authors: Alexander Y. Ku, Thomas L. Griffiths, Stephanie C. Y. Chan
Abstract: The success of Transformers lies in their ability to improve inference through two complementary strategies: the permanent refinement of model parameters via in-weight learning (IWL), and the ephemeral modulation of inferences via in-context learning (ICL), which leverages contextual information maintained in the model's activations. Evolutionary biology tells us that the predictability of the environment across timescales predicts the extent to which analogous strategies should be preferred. Genetic evolution adapts to stable environmental features by gradually modifying the genotype over generations. Conversely, environmental volatility favors plasticity, which enables a single genotype to express different traits within a lifetime, provided there are reliable cues to guide the adaptation. We operationalize these dimensions (environmental stability and cue reliability) in controlled task settings (sinusoid regression and Omniglot classification) to characterize their influence on learning in Transformers. We find that stable environments favor IWL, often exhibiting a sharp transition when conditions are static. Conversely, reliable cues favor ICL, particularly when the environment is volatile. Furthermore, an analysis of learning dynamics reveals task-dependent transitions between strategies (ICL to IWL and vice versa). We demonstrate that these transitions are governed by (1) the asymptotic optimality of the strategy with respect to the environment, and (2) the optimization cost of acquiring that strategy, which depends on the task structure and the learner's inductive bias.
Authors: Gabriel S. Gama, Valdir Grassi Jr
Abstract: Specialized Multi-Task Optimizers (SMTOs) balance task learning in Multi-Task Learning by addressing issues like conflicting gradients and differing gradient norms, which hinder equal-weighted task training. However, recent critiques suggest that equally weighted tasks can achieve competitive results compared to SMTOs, arguing that previous SMTO results were influenced by poor hyperparameter optimization and lack of regularization. In this work, we evaluate these claims through an extensive empirical evaluation of SMTOs, including some of the latest methods, on more complex multi-task problems to clarify this behavior. Our findings indicate that SMTOs perform well compared to uniform loss and that fixed weights can achieve competitive performance compared to SMTOs. Furthermore, we demonstrate why uniform loss perform similarly to SMTOs in some instances. The source code is available at https://github.com/Gabriel-SGama/UnitScal_vs_SMTOs.
Authors: Zewei Ye, Weifeng Lu, Minghao Ye, Tao Lin, Shuo Yang, Junchi Yan, Bo Zhao
Abstract: Vision-Language-Action (VLA) models have recently advanced robotic manipulation by translating natural-language instructions and visual observations into control actions. However, existing VLAs are primarily trained on successful expert demonstrations and lack structured supervision for failure diagnosis and recovery, limiting robustness in open-world scenarios. To address this limitation, we propose the Robotic Failure Analysis and Correction (RoboFAC) framework. We construct a large-scale failure-centric dataset comprising 9,440 erroneous manipulation trajectories and 78,623 QA pairs across 53 scenes in both simulation and real-world environments, with systematically categorized failure types. Leveraging this dataset, we develop a lightweight multimodal model specialized for task understanding, failure analysis, and failure correction, enabling efficient local deployment while remaining competitive with large proprietary models. Experimental results demonstrate that RoboFAC achieves a 34.1% higher failure analysis accuracy compared to GPT-4o. Furthermore, we integrated RoboFAC as an external supervisor in a real-world VLA control pipeline, yielding a 29.1% relative improvement across four tasks while significantly reducing latency relative to GPT-4o. These results demonstrate that RoboFAC enables systematic failure diagnosis and recovery, significantly enhancing VLA recovery capabilities. Our model and dataset are publicly available at https://github.com/MINT-SJTU/RoboFAC.
Authors: Kun Huang, Weikai Xu, Yuxuan Liu, Quandong Wang, Pengzhi Gao, Wei Liu, Jian Luan, Bin Wang, Bo An
Abstract: The Chain of Action-Planning Thoughts (CoaT) paradigm has been shown to improve the reasoning performance of VLM-based mobile agents in GUI tasks. However, the scarcity of diverse CoaT trajectories limits the expressiveness and generalization ability of such agents. While self-training is commonly employed to address data scarcity, existing approaches either overlook the correctness of intermediate reasoning steps or depend on expensive process-level annotations to construct process reward models (PRM). To address the above problems, we propose an Iterative Preference Learning (IPL) that constructs a CoaT-tree through interative sampling, scores leaf nodes using rule-based reward, and backpropagates feedback to derive Thinking-level Direct Preference Optimization (T-DPO) pairs. To prevent overfitting during warm-up supervised fine-tuning, we further introduce a three-stage instruction evolution, which leverages GPT-4o to generate diverse Q\&A pairs based on real mobile UI screenshots, enhancing both generality and layout understanding. Experiments on three standard Mobile GUI-agent benchmarks demonstrate that our agent MobileIPL outperforms strong baselines, including continual pretraining models such as OS-ATLAS and UI-TARS. It achieves state-of-the-art performance across three standard Mobile GUI-Agents benchmarks and shows strong generalization to out-of-domain scenarios.
Authors: Feiyang Cai, Jiahui Bai, Tao Tang, Guijuan He, Joshua Luo, Tianyu Zhu, Srikanth Pilla, Gang Li, Ling Liu, Feng Luo
Abstract: Precise recognition, editing, and generation of molecules are essential prerequisites for both chemists and AI systems tackling various chemical tasks. We present MolLangBench, a comprehensive benchmark designed to evaluate fundamental molecule-language interface tasks: language-prompted molecular structure recognition, editing, and generation. To ensure high-quality, unambiguous, and deterministic outputs, we construct the recognition tasks using automated cheminformatics tools, and curate editing and generation tasks through rigorous expert annotation and validation. MolLangBench supports the evaluation of models that interface language with different molecular representations, including linear strings, molecular images, and molecular graphs. Evaluations of state-of-the-art models reveal significant limitations: the strongest model (GPT-5) achieves $86.2\%$ and $85.5\%$ accuracy on recognition and editing tasks, which are intuitively simple for humans, and performs even worse on the generation task, reaching only $43.0\%$ accuracy. These results highlight the shortcomings of current AI systems in handling even preliminary molecular recognition and manipulation tasks. We hope MolLangBench will catalyze further research toward more effective and reliable AI systems for chemical applications.The dataset and code can be accessed at https://huggingface.co/datasets/ChemFM/MolLangBench and https://github.com/TheLuoFengLab/MolLangBench, respectively.
URLs: https://huggingface.co/datasets/ChemFM/MolLangBench, https://github.com/TheLuoFengLab/MolLangBench,
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: Nicolas K\"uchler, Ivan Petrov, Conrad Grobler, Ilia Shumailov
Abstract: For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the immediate real-world impact of such prediction-altering attacks has remained unclear. In this paper we introduce a novel and significantly more potent class of backdoors that builds upon recent advancements in architectural backdoors. We demonstrate how these backdoors can be specifically engineered to exploit batched inference, a common technique for hardware utilization, enabling large-scale user data manipulation and theft. By targeting the batching process, these architectural backdoors facilitate information leakage between concurrent user requests and allow attackers to fully control model responses directed at other users within the same batch. In other words, an attacker who can change the model architecture can set and steal model inputs and outputs of other users within the same batch. We show that such attacks are not only feasible but also alarmingly effective, can be readily injected into prevalent model architectures, (e.g. Transformers), and represent a truly malicious threat to user privacy and system integrity. Critically, to counteract this new class of vulnerabilities, we propose a deterministic mitigation strategy that provides formal guarantees against this new attack vector, unlike prior work that relied on LLMs to find the backdoors. Our mitigation strategy employs a novel Information Flow Control mechanism that analyzes the model graph and proves non-interference between different user inputs within the same batch. Using our mitigation strategy we perform a large scale analysis of models hosted through Hugging Face and find over 200 models that introduce (unintended) information leakage between batch entries due to the use of dynamic quantization.
Authors: Shahrooz Pouryousef, Ali Montazeralghaem
Abstract: Collaborative information from user-item interactions is a fundamental source of signal in successful recommender systems. Recently, researchers have attempted to incorporate this knowledge into large language model-based recommender approaches (LLMRec) to enhance their performance. However, there has been little fundamental analysis of whether LLMs can effectively reason over collaborative information. In this paper, we analyze the ability of LLMs to reason about collaborative information in recommendation tasks, comparing their performance to traditional matrix factorization (MF) models. We propose a simple and effective method to improve LLMs' reasoning capabilities using retrieval-augmented generation (RAG) over the user-item interaction matrix with four different prompting strategies. Our results show that the LLM outperforms the MF model whenever we provide relevant information in a clear and easy-to-follow format, and prompt the LLM to reason based on it. We observe that with this strategy, in almost all cases, the more information we provide, the better the LLM performs.
Authors: Yichi Zhang, Shengwei Xu, David Pennock, Grant Schoenebeck
Abstract: Eliciting reliable human feedback is essential for many machine learning tasks, such as learning from noisy labels and aligning AI systems with human preferences. Peer prediction mechanisms incentivize truthful reporting without ground truth verification by scoring agents based on correlations with peers. Traditional mechanisms, which ensure that truth-telling maximizes the expected scores in equilibrium, can elicit honest information while assuming agents' utilities are linear functions of their scores. However, in practice, non-linear payment rules are usually preferred, or agents' utilities are inherently non-linear. We propose stochastically dominant truthfulness (SD-truthfulness) as a stronger guarantee: the score distribution of truth-telling stochastically dominates all other strategies, incentivizing truthful reporting for a wide range of monotone utility functions. Our first observation is that no existing peer prediction mechanism naturally satisfies this criterion without strong assumptions. A simple solution -- rounding scores into binary lotteries -- can enforce SD-truthfulness, but often degrades sensitivity, a key property related to fairness and statistical efficiency. We demonstrate how a more careful application of rounding can better preserve sensitivity. Furthermore, we introduce a new enforced agreement (EA) mechanism that is theoretically guaranteed to be SD-truthful in binary-signal settings under mild assumptions, and empirically achieves the highest sensitivity among all known SD-truthful mechanisms.
Authors: En Yu, Jie Lu, Guangquan Zhang
Abstract: Real-world data streams exhibit inherent non-stationarity characterized by concept drift, posing significant challenges for adaptive learning systems. While existing methods address isolated distribution shifts, they overlook the critical co-evolution of label spaces and distributions under limited supervision and persistent uncertainty. To address this, we formalize Generalized Incremental Learning under Concept Drift (GILCD), characterizing the joint evolution of distributions and label spaces in open-environment streaming contexts, and propose a novel framework called Calibrated Source-Free Adaptation (CSFA). First, CSFA introduces a training-free prototype calibration mechanism that dynamically fuses emerging prototypes with base representations, enabling stable new-class identification without optimization overhead. Second, we design a novel source-free adaptation algorithm, i.e., Reliable Surrogate Gap Sharpness-aware (RSGS) minimization. It integrates sharpness-aware perturbation loss optimization with surrogate gap minimization, while employing entropy-based uncertainty filtering to discard unreliable samples. This mechanism ensures robust distribution alignment and mitigates generalization degradation caused by uncertainties. Thus, CSFA establishes a unified framework for stable adaptation to evolving semantics and distributions in open-world streaming scenarios. Extensive experiments validate the superior performance and effectiveness of CSFA compared to SOTA approaches.
Authors: Andrew Keenan Richardson, Ryan Othniel Kearns, Sean Moss, Vincent Wang-Mascianica, Philipp Koralus
Abstract: We study logical reasoning in language models by asking whether their errors follow established human fallacy patterns. Using the Erotetic Theory of Reasoning (ETR) and its open-source implementation, PyETR, we programmatically generate 383 formally specified reasoning problems and evaluate 38 models. For each response, we judge logical correctness and, when incorrect, whether it matches an ETR-predicted fallacy. Two results stand out: (i) as a capability proxy (Chatbot Arena Elo) increases, a larger share of a model's incorrect answers are ETR-predicted fallacies $(\rho=0.360, p=0.0265)$, while overall correctness on this dataset shows no correlation with capability; (ii) reversing premise order significantly reduces fallacy production for many models, mirroring human order effects. Methodologically, PyETR provides an open-source pipeline for unbounded, synthetic, contamination-resistant reasoning tests linked to a cognitive theory, enabling analyses that focus on error composition rather than error rate.
Authors: Numair Nadeem, Saeed Anwar, Muhammad Hamza Asad, Abdul Bais
Abstract: Vision Language Models (VLMs) provide rich semantic priors but are underexplored in Semi supervised Semantic Segmentation. Recent attempts to integrate VLMs to inject high level semantics overlook the semantic misalignment between visual and textual representations that arises from using domain invariant text embeddings without adapting them to dataset and image specific contexts. This lack of domain awareness, coupled with limited annotations, weakens the model semantic understanding by preventing effective vision language alignment. As a result, the model struggles with contextual reasoning, shows weak intra class discrimination, and confuses similar classes. To address these challenges, we propose Hierarchical Vision Language transFormer (HVLFormer), which achieves domain aware and domain robust alignment between visual and textual representations within a mask transformer architecture. Firstly, we transform text embeddings from pretrained VLMs into textual object queries, enabling the generation of multi scale, dataset aware queries that capture class semantics from coarse to fine granularity and enhance contextual reasoning. Next, we refine these queries by injecting image specific visual context to align textual semantics with local scene structures and enhance class discrimination. Finally, to achieve domain robustness, we introduce cross view and modal consistency regularization, which enforces prediction consistency within mask-transformer architecture across augmented views. Moreover, it ensures stable vision language alignment during decoding. With less than 1% training data, HVLFormer outperforms state of the art methods on Pascal VOC, COCO, ADE20K, and Cityscapes. Our code and results will be available on GitHub.
Authors: Amr Mohamed, Maram Assi, Mariam Guizani
Abstract: Large language model assistants (LLM-assistants) present new opportunities to transform software development. Developers are increasingly adopting these tools across tasks, including coding, testing, debugging, documentation, and design. Yet, despite growing interest, there is no synthesis of how LLM-assistants affect software developer productivity. In this paper, we present a systematic review and mapping of 39 peer-reviewed studies published between January 2014 and December 2024 that examine this impact. Our analysis reveals that the majority of studies report considerable benefits from LLM-assistants, though a notable subset identifies critical risks. Commonly reported gains include accelerated development, minimized code search, and the automation of trivial and repetitive tasks. However, studies also highlight concerns around cognitive offloading and reduced team collaboration. Our study reveals that whether LLM-based assistants improve or degrade code quality remains unresolved, as existing studies report contradictory outcomes contingent on context and evaluation criteria. While the majority of studies (90%) adopt a multi-dimensional perspective by examining at least two SPACE dimensions, reflecting increased awareness of the complexity of developer productivity, only 15% extend beyond three dimensions, indicating substantial room for more integrated evaluations. Satisfaction, Performance, and Efficiency are the most frequently investigated dimensions, whereas Communication and Activity remain underexplored. Most studies are exploratory (59%) and methodologically diverse, but lack longitudinal and team-based evaluations. This review surfaces key research gaps and provides recommendations for future research and practice. All artifacts associated with this study are publicly available at https://zenodo.org/records/18489222
Authors: Songlin Zhai, Guilin Qi, Yue Wang, Yuan Meng
Abstract: Knowledge graphs (KGs) are the cornerstone of the semantic web, offering up-to-date representations of real-world entities and relations. Yet large language models (LLMs) remain largely static after pre-training, causing their internal knowledge to become outdated and limiting their utility in time-sensitive web applications. To bridge this gap between dynamic knowledge and static models, a prevalent approach is to enhance LLMs with KGs. However, prevailing methods typically rely on parameter-invasive fine-tuning, which risks catastrophic forgetting and often degrades LLMs' general capabilities. Moreover, their static integration frameworks cannot keep pace with the continuous evolution of real-world KGs, hindering their deployment in dynamic web environments. To bridge this gap, we introduce KGA (\textit{\underline{K}nowledge \underline{G}raph-guided \underline{A}ttention}), a novel framework that dynamically integrates external KGs into LLMs exclusively at inference-time without any parameter modification. Inspired by research on neuroscience, we rewire the self-attention module by innovatively introducing two synergistic pathways: a \textit{bottom-up knowledge fusion} pathway and a \textit{top-down attention guidance} pathway. The \textit{bottom-up pathway} dynamically integrates external knowledge into input representations via input-driven KG fusion, which is akin to the \textit{stimulus-driven attention process} in the human brain. Complementarily, the \textit{top-down pathway} aims to assess the contextual relevance of each triple through a \textit{goal-directed verification process}, thereby suppressing task-irrelevant signals and amplifying knowledge-relevant patterns. By synergistically combining these two pathways, our method supports real-time knowledge fusion. Extensive experiments on four benchmarks verify KGA's strong fusion performance and efficiency.
Authors: Sangwoo Park, Jinheon Baek, Soyeong Jeong, Sung Ju Hwang
Abstract: Scientific paper retrieval, particularly framed as document-to-document retrieval, aims to identify relevant papers in response to a long-form query paper, rather than a short query string. Previous approaches to this task have focused exclusively on abstracts, embedding them into dense vectors as surrogates for full documents and calculating similarity between them. Yet, abstracts offer only sparse and high-level summaries, and such methods primarily optimize one-to-one similarity, overlooking the dynamic relations that emerge across relevant papers during the retrieval process. To address this, we propose Chain of Retrieval(COR), a novel iterative framework for full-paper retrieval. Specifically, COR decomposes each query paper into multiple aspect-specific views, matches them against segmented candidate papers, and iteratively expands the search by promoting top-ranked results as new queries, thereby forming a tree-structured retrieval process. The resulting retrieval tree is then aggregated in a post-order manner: descendants are first combined at the query level, then recursively merged with their parent nodes, to capture hierarchical relations across iterations. To validate this, we present SCIFULLBENCH, a large-scale benchmark providing both complete and segmented contexts of full papers for queries and candidates, and results show that COR significantly outperforms existing retrieval baselines. Our code and dataset is available at https://github.com/psw0021/Chain-of-Retrieval-Official.
URLs: https://github.com/psw0021/Chain-of-Retrieval-Official.
Authors: Saptarshi Mitra, Rachid Karami, Haocheng Xu, Sitao Huang, Hyoukjun Kwon
Abstract: Emerging applications such as AR are driving demands for machine intelligence capable of processing continuous and/or long-context inputs on local devices. However, currently dominant models based on Transformer architecture suffers from the quadratic computational and memory overhead, which hinders applications required to process long contexts. This has spurred a paradigm shift towards new architectures like State Space Models (SSMs) and SSM-Transformer hybrid models, which provide near-linear scaling. The near-linear scaling enabled efficient handling of millions of tokens while delivering high performance in recent studies. Although such works present promising results, their workload characteristics in terms of computational performance and hardware resource requirements are not yet thoroughly explored, which limits our understanding of their implications to the system level optimizations. To address this gap, we present a comprehensive, compara-ive benchmarking of carefully selected Transformers, SSMs, and hybrid models specifically for long-context inference on consumer and embedded GPUs. Our analysis shows that SSMs are well-suited for on-device AI on consumer and embedded GPUs for long context inferences. While Transformers are up to 1.9x faster at short sequences (<8K tokens), SSMs demonstrate a dramatic performance inversion, becoming up to 4x faster at very long contexts (~57K tokens), thanks to their linear computational complexity and ~64% reduced memory footrprint. Our operator-level analysis reveals that custom SSM kernels like selective scan despite being hardware-aware to minimize memory IO, dominate the inference runtime on edge platforms, accounting for over 55% of latency due to their sequential, element-wise nature. SSM-Scope is open-sourced at https://github.com/sapmitra/ssm-scope
Authors: Yiqi Wang, Mrinal Verghese, Jeff Schneider
Abstract: The performance of learned robot visuomotor policies is heavily dependent on the size and quality of the training dataset. Although large-scale robot and human datasets are increasingly available, embodiment gaps and mismatched action spaces make them difficult to leverage. Our main insight is that skills performed across different embodiments produce visual similarities in motions that can be captured using off-the-shelf action representations such as optical flow. Moreover, World Models (WMs) can leverage sub-optimal data since they focus on modeling dynamics. In this work, we aim to improve visuomotor policies in low-data regimes by first pretraining a WM using optical flow as an embodiment-agnostic action representation to leverage accessible or easily collected data from multiple embodiments (robots, humans). Given a small set of demonstrations on a target embodiment, we finetune the WM on this data to better align the WM predictions, train a base policy, and learn a robust value function. Using our finetuned WM and value function, our approach evaluates action candidates from the base policy and selects the best one to improve performance. Our approach, which we term Latent Policy Steering (LPS), improves behavior-cloned policies by 10.6% on average across four Robomimic tasks, even though most of the pretraining data comes from the real world. In the real-world experiments, LPS achieves larger gains: 70% relative improvement with 30-50 target-embodiment demonstrations, and 44% relative improvement with 60-100 demonstrations, compared to a behavior-cloned baseline. Qualitative results can be found on the website: https://yiqiwang8177.github.io/LatentPolicySteering/.
Authors: Muhao Guo, Jiaqi Wu, Yizheng Liao, Wenke Lee, Shengzhe Chen, Yang Weng
Abstract: Publishing open graph data while preserving individual privacy remains challenging when data publishers and data users are distinct entities. Although differential privacy (DP) provides rigorous guarantees, most existing approaches enforce privacy during model training rather than at the data publishing stage. This limits the applicability to open-data scenarios. We propose a privacy-preserving graph structure learning framework that integrates Gaussian Differential Privacy (GDP) directly into the data release process. Our mechanism injects structured Gaussian noise into raw data prior to publication and provides formal $\mu$-GDP guarantees, leading to tight $(\varepsilon, \delta)$-differential privacy bounds. Despite the distortion introduced by privatization, we prove that the original sparse inverse covariance structure can be recovered through an unbiased penalized likelihood formulation. We further extend the framework to discrete data using discrete Gaussian noise while preserving privacy guarantees. Extensive experiments on synthetic and real-world datasets demonstrate strong privacy-utility trade-offs, maintaining high graph recovery accuracy under rigorous privacy budgets. Our results establish a formal connection between differential privacy theory and privacy-preserving data publishing for graphical models.
Authors: Sarah Lockfisch, Kristian Schwethelm, Martin Menten, Rickmer Braren, Daniel Rueckert, Alexander Ziller, Georgios Kaissis
Abstract: Model multiplicity refers to the existence of multiple machine learning models that describe the data equally well but may produce different predictions on individual samples. In medicine, these models can admit conflicting predictions for the same patient -- a risk that is poorly understood and insufficiently addressed. In this study, we empirically analyze the extent, drivers, and ramifications of predictive multiplicity across diverse medical tasks and model architectures, and show that even small ensembles can mitigate/eliminate predictive multiplicity in practice. Our analysis reveals that (1) standard validation metrics fail to identify a uniquely optimal model and (2) a substantial amount of predictions hinges on arbitrary choices made during model development. Using multiple models instead of a single model reveals instances where predictions differ across equally plausible models -- highlighting patients that would receive arbitrary diagnoses if any single model were used. In contrast, (3) a small ensemble paired with an abstention strategy can effectively mitigate measurable predictive multiplicity in practice; predictions with high inter-model consensus may thus be amenable to automated classification. While accuracy is not a principled antidote to predictive multiplicity, we find that (4) higher accuracy achieved through increased model capacity reduces predictive multiplicity. Our findings underscore the clinical importance of accounting for model multiplicity and advocate for ensemble-based strategies to improve diagnostic reliability. In cases where models fail to reach sufficient consensus, we recommend deferring decisions to expert review.
Authors: Gongli Xi, Ye Tian, Yannan Hu, Yuchao Zhang, Yapeng Niu, Xiangyang Gong
Abstract: In response to Distributed Denial of Service (DDoS) attacks, recent research efforts increasingly rely on Machine Learning (ML)-based solutions, whose effectiveness largely depends on the quality of labeled training datasets. To address the scarcity of such datasets, data augmentation with synthetic traces is often employed. However, current synthetic trace generation methods struggle to capture the complex temporal patterns and spatial distributions exhibited in emerging DDoS attacks. This results in insufficient resemblance to real traces and unsatisfied detection accuracy when applied to ML tasks. In this paper, we propose Dual-Stream Temporal-Field Diffusion (DSTF-Diffusion), a multi-view, multi-stream network traffic generative model based on diffusion models, featuring two main streams: The field stream utilizes spatial mapping to bridge network data characteristics with pre-trained realms of stable diffusion models, effectively translating complex network interactions into formats that stable diffusion can process, while the spatial stream adopts a dynamic temporal modeling approach, meticulously capturing the intrinsic temporal patterns of network traffic. Extensive experiments demonstrate that data generated by our model exhibits higher statistical similarity to originals compared to current state-of-the-art solutions, and enhance performances on a wide range of downstream tasks.
Authors: Kaichuan Kong, Dongjie Liu, Xiaobo Jin, Guanggang Geng, Zhiying Li, Jian Weng
Abstract: Insider threat detection (ITD) poses a persistent and high-impact challenge in cybersecurity due to the subtle, long-term, and context-dependent nature of malicious insider behaviors. Traditional models often struggle to capture semantic intent and complex behavior dynamics, while existing LLM-based solutions face limitations in prompt adaptability and modality coverage. To bridge this gap, we propose DMFI, a dual-modality framework that integrates semantic inference with behavior-aware fine-tuning. DMFI converts raw logs into two structured views: (1) a semantic view that processes content-rich artifacts (e.g., emails, https) using instruction-formatted prompts; and (2) a behavioral abstraction, constructed via a 4W-guided (When-Where-What-Which) transformation to encode contextual action sequences. Two LoRA-enhanced LLMs are fine-tuned independently, and their outputs are fused via a lightweight MLP-based decision module. We further introduce DMFI-B, a discriminative adaptation strategy that separates normal and abnormal behavior representations, improving robustness under severe class imbalance. Experiments on CERT r4.2 and r5.2 datasets demonstrate that DMFI outperforms state-of-the-art methods in detection accuracy. Our approach combines the semantic reasoning power of LLMs with structured behavior modeling, offering a scalable and effective solution for real-world insider threat detection.
Authors: Fabio Vitali
Abstract: This paper introduces a new family of cognitive modal logics designed to formalize conjectural reasoning: modal systems in which cognitive contexts extend known facts with hypothetical assumptions in order to explore their consequences. Unlike traditional doxastic and epistemic systems, conjectural logics rely on a principle, called Axiom \textbf{C} ($\varphi \rightarrow \Box\varphi$), through which established facts are preserved across conjectural layers. While Axiom \textbf{C} has often been treated with suspicion because of its association with modal collapse, we show that collapse does not arise from \textbf{C} alone, but requires either the presence of Axiom \textbf{T} or a concretely bivalent base logic. Accordingly, we avoid \textbf{T} and adopt a non-bivalent semantic framework, such as supervaluation-style semantics, Weak Kleene logic, or Description Logic, in which undefined propositions may coexist with modal assertions. This prevents modal collapse and preserves a distinction between factual and conjectural statements. Within this framework we define the modal systems $\mathbf{KC}$ and $\mathbf{KDC}$, show that Axiom \textbf{C} directly implies \textbf{4} and \textbf{5}, and prove that these systems are non-trivial, sound, and complete. An inclusion theorem links reality, doxastic states, epistemic states, and conjectural states via set-theoretic inclusion among valuations, providing a unified account of how these layers relate. Finally, we introduce a dynamic operator, $\mathsf{settle}(p)$, which formalizes the transition by which a conjectural extension becomes designated reality, thereby motivating a corresponding Conjectural Dynamic Logic.
Authors: Josh Barua, Seun Eisape, Kayo Yin, Alane Suhr
Abstract: While large reasoning models have shown remarkable ability to generate long chains-of-thought (CoTs) in English, we still lack understanding of how these long-form reasoning abilities transfer to the vast majority of the world's languages. In this work, we systematically investigate four key stages of model development--scaling, pretraining, post-training, and inference--to understand how long CoT capabilities extend beyond English. We compare two reasoning settings across nine non-English target languages: En-CoT, where models process target-language inputs, but reason in English; and Target-CoT, where models both process inputs and generate long CoTs in the target language. We find that scaling reasoning model size improves multilingual task performance in En-CoT, but Target-CoT performance lags behind. This gap widens for tasks requiring long, multi-step CoTs such as mathematical reasoning. Shifting to pretraining, we find that adding a specialized reasoning stage enhances En-CoT performance but degrades Target-CoT, whereas broad multilingual pretraining improves both modes simultaneously. Given the scarcity of high-quality reasoning traces in languages other than English, we explore synthetic data curation approaches for post-training. We demonstrate that fine-tuning on reasoning traces automatically translated from gold English traces outperforms fine-tuning on target-language traces distilled from large reasoning models. Finally, we report disparities in inference efficiency between languages and uncover language-specific failure modes in CoTs. We release models, datasets, and code to foster further research.
Authors: Jan Kapar, Kathrin G\"unther, Lori Ann Vallis, Klaus Berger, Nadine Binder, Hermann Brenner, Stefanie Castell, Beate Fischer, Volker Harth, Bernd Holleczek, Timm Intemann, Till Ittermann, Andr\'e Karch, Thomas Keil, Lilian Krist, Berit Lange, Michael F. Leitzmann, Katharina Nimptsch, Nadia Obi, Iris Pigeot, Tobias Pischon, Tamara Schikowski, B\"orge Schmidt, Carsten Oliver Schmidt, Anja M. Sedlmair, Justine Tanoey, Harm Wienbergen, Andreas Wienke, Claudia Wigmann, Marvin N. Wright
Abstract: Synthetic data holds substantial potential to address practical challenges in epidemiology due to restricted data access and privacy concerns. However, many current methods suffer from limited quality, high computational demands, and complexity for non-experts. Furthermore, common evaluation strategies for synthetic data often fail to directly reflect statistical utility and measure privacy risks sufficiently. Against this background, a critical underexplored question is whether synthetic data can reliably reproduce key findings from epidemiological research while preserving privacy. We propose adversarial random forests (ARF) as an efficient and convenient method for synthesizing tabular epidemiological data. To evaluate its performance, we replicated statistical analyses from six epidemiological publications covering blood pressure, anthropometry, myocardial infarction, accelerometry, loneliness, and diabetes, from the German National Cohort (NAKO Gesundheitsstudie), the Bremen STEMI Registry U45 Study, and the Guelph Family Health Study. We further assessed how dataset dimensionality and variable complexity affect the quality of synthetic data, and contextualized ARF's performance by comparison with commonly used tabular data synthesizers in terms of utility, privacy, generalisation, and runtime. Across all replicated studies, results on ARF-generated synthetic data consistently aligned with original findings. Even for datasets with relatively low sample size-to-dimensionality ratios, replication outcomes closely matched the original results across descriptive and inferential analyses. Reduced dimensionality and variable complexity further enhanced synthesis quality. ARF demonstrated favourable performance regarding utility, privacy preservation, and generalisation relative to other synthesizers and superior computational efficiency.
Authors: Viraj Parimi, Brian C. Williams
Abstract: Safe navigation is essential for autonomous systems operating in hazardous environments, especially when multiple agents must coordinate using only high-dimensional visual observations. While recent approaches successfully combine Goal-Conditioned RL (GCRL) for graph construction with Conflict-Based Search (CBS) for planning, they typically rely on deleting edges with high risk before running CBS to enforce safety. This binary strategy is overly conservative, precluding feasible missions that require traversing high-risk regions, even when the aggregate risk is acceptable. To address this, we introduce a framework for Risk-Bounded Multi-Agent Path Finding ($\Delta$-MAPF), where agents share a user-specified global risk budget ($\Delta$). Rather than permanently discarding edges, our framework dynamically distributes per-agent risk budgets ($\delta_i$) during search via an Iterative Risk Allocation (IRA) layer that integrates with a standard CBS planner. We investigate two distribution strategies: a greedy surplus-deficit scheme for rapid feasibility repair, and a market-inspired mechanism that treats risk as a priced resource to guide improved allocation. The market-based mechanism yields a tunable trade-off wherein agents exploit available risk to secure shorter, more efficient paths, but revert to longer, safer detours under tighter budgets. Experiments in complex visual environments show that our dynamic allocation framework achieves higher success rates than baselines and effectively leverages the available safety budget to reduce travel time. Project website can be found at https://rb-visual-mapf-mers.csail.mit.edu
Authors: Sitong Chen, Shen Nie, Jiacheng Sun, Zijin Feng, Zhenguo Li, Ji-Rong Wen, Chongxuan Li
Abstract: We present a systematic theoretical framework that interprets masked diffusion models (MDMs) as solutions to energy minimization problems in discrete optimal transport. Specifically, we prove that three distinct energy formulations--kinetic, conditional kinetic, and geodesic energy--are mathematically equivalent under the structure of MDMs, and that MDMs minimize all three when the mask schedule satisfies a closed-form optimality condition. This unification not only clarifies the theoretical foundations of MDMs, but also motivates practical improvements in sampling. By parameterizing interpolation schedules via Beta distributions, we reduce the schedule design space to a tractable 2D search, enabling efficient post-training tuning without model modification. Experiments on synthetic and real-world benchmarks demonstrate that our energy-inspired schedules outperform hand-crafted baselines, particularly in low-step sampling settings.
Authors: Chenxi Song, Yanming Yang, Tong Zhao, Ruibo Li, Chi Zhang
Abstract: Video diffusion models have rich world priors, but their use in spatial tasks is limited by poor control, spatial-temporal inconsistent results, and entangled scene-camera dynamics. Current approaches, such as per-task fine-tuning or post-process warping, often introduce visual artifacts, fail to generalize, or incur high computational costs. We introduce WorldForge, a novel, training-free framework that operates purely at inference time to resolve these issues. Our method comprises three synergistic components. First, an intra-step refinement loop injects fine-grained motion guidance during the denoising process, iteratively correcting the output to ensure strict adherence to the target camera path. Second, an optical flow-based analysis identifies and isolates motion-related channels within the latent space. This allows our framework to selectively apply guidance, thereby decoupling motion from appearance and preserving visual fidelity. Third, a dual-path guidance strategy adaptively corrects for drift by comparing the guided generation against an unguided, reference denoising path, effectively neutralizing artifacts caused by misaligned structural inputs. Together, these components inject precise, trajectory-aligned control without model retraining, achieving accurate motion guidance and photorealistic synthesis. As a plug-and-play, model-agnostic solution, WorldForge demonstrates highly versatile generalizability. Beyond robust zero-shot 3D/4D generation, it readily empowers over a dozen diverse downstream applications, seamlessly enabling tasks like video editing, stabilization, and virtual try-on. Extensive experiments confirm state-of-the-art performance in trajectory adherence and perceptual quality, outperforming both training-dependent and inference-only baselines.
Authors: Jean-Michel Tucny, Abhisek Ganguly, Santosh Ansumali, Sauro Succi
Abstract: Physics-informed neural networks (PINNs) often exhibit weight matrices that appear statistically random after training, yet their implications for signal propagation and stability remain unsatisfactorily understood, let alone the interpretability. In this work, we analyze the spectral and statistical properties of trained PINN weights using viscous and inviscid variants of the one-dimensional Burgers' equation, and show that the learned weights reside in a high-entropy regime consistent with predictions from random matrix theory. To investigate the dynamical consequences of such weight structures, we study the evolution of signal features inside a network through the lens of neural partial differential equations (neural PDEs). We show that random and structured weight matrices can be associated with specific discretizations of neural PDEs, and that the numerical stability of these discretizations governs the stability of signal propagation through the network. In particular, explicit unstable schemes lead to degraded signal evolution, whereas stable implicit and higher-order schemes yield well-behaved dynamics for the same underlying neural PDE. Our results offer an explicit example of how numerical stability and network architecture shape signal propagation in deep networks, in relation to random matrix and neural PDE descriptions in PINNs.
Authors: Kuang Xiaodong, Li Bingxuan, Li Yuan, Rao Fan, Ma Gege, Xie Qingguo, Mok Greta S P, Liu Huafeng, Zhu Wentao
Abstract: Achieving high image quality for temporal frames in dynamic positron emission tomography (PET) is challenging due to the limited statistic especially for the short frames. Recent studies have shown that deep learning (DL) is useful in a wide range of medical image denoising tasks. In this paper, we propose a model-based neural network for dynamic PET image denoising. The inter-frame spatial correlation and intra-frame structural consistency in dynamic PET are used to establish the kernel space-based multidimensional sparse (KMDS) model. We then substitute the inherent forms of the parameter estimation with neural networks to enable adaptive parameters optimization, forming the end-to-end neural KMDS-Net. Extensive experimental results from simulated and real data demonstrate that the neural KMDS-Net exhibits strong denoising performance for dynamic PET, outperforming previous baseline methods. The proposed method may be used to effectively achieve high temporal and spatial resolution for dynamic PET. Our source code is available at https://github.com/Kuangxd/Neural-KMDS-Net/tree/main.
Authors: Zhe Liu, Yuyan Ni, Zhichen Pu, Qiming Sun, Siyuan Liu, Wen Yan
Abstract: Recently, sophisticated deep learning-based approaches have been developed for generating efficient initial guesses to accelerate the convergence of density functional theory (DFT) calculations. While the actual initial guesses are often density matrices (DM), quantities that can convert into density matrices also qualify as alternative forms of initial guesses. Hence, existing works mostly rely on the prediction of the Hamiltonian matrix for obtaining high-quality initial guesses. However, the Hamiltonian matrix is both numerically difficult to predict and intrinsically non-transferable, hindering the application of such models in real scenarios. In light of this, we propose a method that constructs DFT initial guesses by predicting the electron density in a compact auxiliary basis representation using E(3)-equivariant neural networks. Trained exclusively on small molecules with up to 20 atoms, our model achieves an average 33.3% reduction in SCF iterations for molecules three times larger (up to 60 atoms). This result is particularly significant given that baseline Hamiltonian-based methods fail to generalize, often increasing the iteration count by over 80% or failing to converge entirely on these larger systems. Furthermore, we demonstrate that this acceleration is robustly scalable: the model successfully accelerates calculations for systems with up to 900 atoms (polymers and polypeptides) without retraining. To the best of our knowledge, this work represents the first and robust candidate for a universally transferable DFT acceleration method. We also released the SCFbench dataset and its accompanying code to facilitate future research in this promising direction.
Authors: Yongcheng Zeng, Zexu Sun, Bokai Ji, Erxue Min, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Haifeng Zhang, Xu Chen, Jun Wang
Abstract: Curriculum learning plays a crucial role in enhancing the training efficiency of large language models (LLMs) on reasoning tasks. However, existing methods often fail to adequately account for variations in prompt difficulty or rely on simplistic filtering mechanisms to select prompt datasets within a narrow criterion range, resulting in significant computational waste. In this work, we approach the problem from the perspective of reinforcement learning gradient optimization, offering a systematic and theoretical investigation into how to improve the training efficiency of LLMs. We identify two key factors influencing training efficiency: the selection of training prompts and the allocation of rollout quantities across different prompts. Our theoretical analysis reveals that the sampling distribution of prompts dictates the convergence rate of gradient descent, while the allocation of the rollout quantity influences the consistency and stability of overall gradient updates. Based on these insights, we propose CurES, an efficient training method that accelerates convergence and employs Bayesian posterior estimation to minimize computational overhead. Experiments demonstrate that our CurES outperforms Group Relative Policy Optimization (GRPO) by +3.30 points and +4.82 points with 1.5B and 7B models, respectively, and exceeds the best prior sample efficient methods by +2.12 points on average across eight math reasoning benchmarks. Additionally, CurES exhibits faster convergence compared to baselines, including GRPO.
Authors: Yi Bin, Tianyi Jiang, Yujuan Ding, Kainian Zhu, Fei Ma, Jingkuan Song, Yang Yang, Heng Tao Shen
Abstract: Large Language Models (LLMs) have demonstrated remarkable reasoning abilities on complex problems using long Chain-of-Thought (CoT) reasoning. However, they often suffer from overthinking, meaning generating unnecessarily lengthy reasoning steps for simpler problems. This issue may degrade the efficiency of the models and make them difficult to adapt the reasoning depth to the complexity of problems. To address this, we introduce a novel metric Token Entropy Cumulative Average (TECA), which measures the extent of exploration throughout the reasoning process. We further propose a novel reasoning paradigm named "Explore Briefly, Then Decide", with an associated Cumulative Entropy Regulation (CER) mechanism. This paradigm leverages TECA to help the model dynamically determine the optimal point to conclude its thought process and provide a final answer, thus achieving efficient reasoning. Experimental results across diverse mathematical benchmarks show that our approach substantially mitigates overthinking without sacrificing problem solving ability. With our thinking paradigm, the average response length decreases by up to 71% on simpler datasets, demonstrating the effectiveness of our method in creating a more efficient and adaptive reasoning process.
Authors: David Romero, Ariana Bermudez, Viacheslav Iablochnikov, Hao Li, Fabio Pizzati, Ivan Laptev
Abstract: Recent video generation models have achieved remarkable progress and are now deployed in film, social media production, and advertising. Beyond their creative potential, such models also hold promise as world simulators for robotics and embodied decision making. Despite strong advances, current approaches still struggle to generate physically plausible object interactions and lack object-level control mechanisms. To address these limitations, we introduce KineMask, an approach for video generation that enables realistic rigid body control, interactions, and effects. Given a single image and a specified object velocity, our method generates videos with inferred motions and future object interactions. We propose a two-stage training strategy that gradually removes future motion supervision via object masks. Using this strategy we train video diffusion models (VDMs) on synthetic scenes of simple interactions and demonstrate significant improvements and generalization to rigid body and hand-object interactions in real scenes. Furthermore, KineMask integrates low-level motion control with high-level textual conditioning via predicted scene descriptions, leading to support for synthesis of complex dynamical phenomena. Our experiments show that KineMask generalizes to different VDMs and achieves strong improvements over recent models of comparable size. Ablation studies further highlight the complementary roles of low- and high-level conditioning in VDMs. Project Page: https://daromog.github.io/KineMask/
Authors: Hadi Pouransari, David Grangier, C Thomas, Michael Kirchhof, Oncel Tuzel
Abstract: The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all world knowledge into parameters is unnecessary, as only a fraction is used per prompt, and impractical for edge devices with limited inference-time memory and compute. We address this shortcoming by a memory-augmented architecture and a pretraining strategy aligned with existing hardware paradigms. We introduce small language models that access large hierarchical parametric memory banks encoding world knowledge. During pretraining and inference, we fetch a small, context-dependent memory block and add it to the model. Our pretraining learns to store long-tail world knowledge in the memory parameters, while the small language model acts as an anchor capturing common knowledge and general reasoning abilities. Through trillion-token-scale experiments, we show significant gains: a 160M-parameters model augmented with an 18M-parameters memory fetched from a 4.6B memory bank obtains comparable performance to a regular model with more than 2x the parameters. Through extensive experiments, we study the optimal type and size of parametric memories in transformers, scaling them to over 21B parameters. We find that our proposed hierarchical feed-forward memories work robustly across transformer architectures, whether added during pretraining or post-hoc.
Authors: Avichal Goel, Yoon Kim, Nir Shavit, Tony T. Wang
Abstract: Finetuning (pretrained) language models is a standard approach for updating their internal parametric knowledge and specializing them to new tasks and domains. However, the corresponding model weight changes ("weight diffs") are not generally interpretable. While inspecting the finetuning dataset can give a sense of how the model might have changed, these datasets are often not publicly available or are too large to work with directly. Towards the goal of comprehensively understanding weight diffs in natural language, we introduce Diff Interpretation Tuning (DIT), a method that trains models to describe their own finetuning-induced modifications. Our approach uses synthetic, labeled weight diffs to train a DIT-adapter, which can be applied to a compatible finetuned model to make it describe how it has changed. We demonstrate in two proof-of-concept settings (reporting hidden behaviors and summarizing finetuned knowledge) that our method enables models to describe their finetuning-induced modifications using accurate natural language descriptions.
Authors: Ander Artola Velasco, Stratis Tsirtsis, Manuel Gomez-Rodriguez
Abstract: Millions of users rely on a market of cloud-based services to obtain access to state-of-the-art large language models. However, it has been very recently shown that the de facto pay-per-token pricing mechanism used by providers creates a financial incentive for them to strategize and misreport the (number of) tokens a model used to generate an output. In this paper, we develop an auditing framework based on martingale theory that enables a trusted third-party auditor who sequentially queries a provider to detect token misreporting. Crucially, we show that our framework is guaranteed to always detect token misreporting, regardless of the provider's (mis-)reporting policy, and not falsely flag a faithful provider as unfaithful with high probability. To validate our auditing framework, we conduct experiments across a wide range of (mis-)reporting policies using several large language models from the $\texttt{Llama}$, $\texttt{Gemma}$ and $\texttt{Ministral}$ families, and input prompts from a popular crowdsourced benchmarking platform. The results show that our framework detects an unfaithful provider after observing fewer than $\sim 70$ reported outputs, while maintaining the probability of falsely flagging a faithful provider below $\alpha = 0.05$.
Authors: Zhihao Wen, Wenkang Wei, Yuan Fang, Xingtong Yu, Hui Zhang, Weicheng Zhu, Xin Zhang
Abstract: Knowledge-based Visual Question Answering (KVQA) requires models to ground entities in images and reason over factual knowledge. Recent work has introduced its implicit-knowledge variant, IK-KVQA, where a multimodal large language model (MLLM) is the sole knowledge source and answers are produced without external retrieval. Existing IK-KVQA approaches, however, are typically trained with answer-only supervision: reasoning remains implicit, justifications are often weak or inconsistent, and generalization after standard supervised fine-tuning (SFT) can be brittle. We propose StaR-KVQA, a framework that equips IK-KVQA with dual-path structured reasoning traces - symbolic relation paths over text and vision together with path-grounded natural-language explanations - to provide a stronger inductive bias than generic answer-only supervision. These traces act as modality-aware scaffolds that guide the model toward relevant entities and attributes, offering more structure than generic chain-of-thought supervision while not constraining reasoning to any single fixed path. With a single open-source MLLM, StaR-KVQA constructs and selects traces to build an offline trace-enriched dataset and then performs structure-aware self-distillation; no external retrievers, verifiers, or curated knowledge bases are used, and inference is a single autoregressive pass. Across benchmarks, StaR-KVQA consistently improves both answer accuracy and the transparency of intermediate reasoning, achieving up to +11.3% higher answer accuracy on OK-VQA over the strongest baseline.
Authors: Chengzhi Li, Heyan Huang, Ping Jian, Zhen Yang, Yaning Tian, Zhongbin Guo
Abstract: Large language models (LLMs) often generate self-contradictory outputs, which severely impacts their reliability and hinders their adoption in practical applications. In video-language models (Video-LLMs), this phenomenon recently draws the attention of researchers. Specifically, these models fail to provide logically consistent responses to rephrased questions based on their grounding outputs. However, the underlying causes of this phenomenon remain underexplored. In this work, we adopt an interpretability-driven approach to analyze, statistically summarize, and intervention the potential factors of the phenomenon. We find that one of the primary reasons for the inconsistency in responses lies in the inability of cross-modal attention heads to effectively distinguish video tokens across different timestamps. To address this, we propose an attention enhancement method called Temporally Conditioned Attention Sharpening (TCAS), which constructs an enhancement objective based on attention distinctions to enhance the model's temporal resolution capability, thereby improving its temporal understanding logic consistency. Experimental results demonstrate that our method significantly enhances the temporal logic consistency of Video-LLMs. Further analyses reveal that our method indeed improves the temporal discriminability of attention heads, validating our conclusions. Additionally, our method even achieves performance improvements in general video temporal grounding tasks, suggesting that temporal logic consistency is an important factor in temporal understanding.
Authors: Yi-Chung Chen, David I. Inouye, Jing Gao
Abstract: Generative classifiers, which leverage conditional generative models for classification, have recently demonstrated desirable properties such as robustness to distribution shifts. However, recent progress in this area has been largely driven by diffusion-based models, whose substantial computational cost severely limits scalability. This exclusive focus on diffusion-based methods has also constrained our understanding of generative classifiers. In this work, we propose a novel generative classifier built on recent advances in visual autoregressive (VAR) modeling, which offers a new perspective for studying generative classifiers. To further enhance its performance, we introduce the Adaptive VAR Classifier$^+$ (A-VARC$^+$), which achieves a superior trade-off between accuracy and inference speed, thereby significantly improving practical applicability. Moreover, we show that the VAR-based method exhibits fundamentally different properties from diffusion-based methods. In particular, due to its tractable likelihood, the VAR-based classifier enables visual explainability via token-wise mutual information and demonstrates inherent resistance to catastrophic forgetting in class-incremental learning tasks.
Authors: Inha Kang, Youngsun Lim, Seonho Lee, Jiho Choi, Junsuk Choe, Hyunjung Shim
Abstract: State-of-the-art vision-language models (VLMs) suffer from a critical failure in understanding negation, often referred to as affirmative bias. This limitation is particularly severe in described object detection (DOD) tasks. To address this, we propose two primary contributions: (1) a new dataset pipeline and (2) a novel, lightweight adaptation recipe. First, we introduce CoVAND, a dataset constructed with a systematic chain-of-thought (CoT) and VQA-based pipeline to generate high-quality, instance-grounded negation data. Second, we propose NegToMe, a novel text token merging module that directly tackles the architectural cause of affirmative bias. NegToMe fundamentally addresses the structural loss of negation cues in tokenization, grouping them with attributes into coherent semantic phrases. It maintains correct polarity at the input level, enabling robust negation understanding even with limited data. For instance, to prevent a model from treating the fragmented tokens "not" and "girl" as simply "girl", NegToMe binds them into a single token whose meaning is correctly distinguished from that of "girl" alone. This module is integrated with a parameter-efficient and strategic LoRA fine-tuning approach. Our method significantly improves performance on challenging negation benchmarks with a lowered false positive rate, boosting NMS-AP by up to +10.8 points on OVDEval and demonstrating generalization to SoTA VLMs. This work marks a crucial step forward in addressing negation understanding for real-world detection applications.
Authors: Lindsay Spoor, \'Alvaro Serra-G\'omez, Aske Plaat, Thomas Moerland
Abstract: Safe reinforcement learning addresses constrained optimization problems where maximizing performance must be balanced against safety constraints, and Lagrangian methods are a widely used approach for this purpose. However, the effectiveness of Lagrangian methods depends crucially on the choice of the Lagrange multiplier $\lambda$, which governs the multi-objective trade-off between return and cost. A common practice is to update the multiplier automatically during training. Although this approach is standard in practice, there remains limited empirical evidence on the optimally achievable trade-off between return and cost as a function of $\lambda$, and there is currently no systematic benchmark comparing automated update mechanisms to this empirical optimum. Therefore, we study (i) the constraint geometry for eight widely used safety tasks and (ii) the previously overlooked constraint-regime sensitivity of different Lagrange multiplier update mechanisms in safe reinforcement learning. Through the lens of multi-objective analysis, we present empirical Pareto frontiers that offer a complete visualization of the trade-off between return and cost in the underlying optimization problem. Our results reveal the highly sensitive nature of $\lambda$ and further show that the restrictiveness of the constraint cost can vary across different cost limits within the same task. This highlights the importance of careful cost limit selection across different regions of cost restrictiveness when evaluating safe reinforcement learning methods. We provide a recommended set of cost limits for each evaluated task and offer an open-source code base: https://github.com/lindsayspoor/Lagrangian_SafeRL.
Authors: Christos Thrampoulidis, Sadegh Mahdavi, Wenlong Deng
Abstract: This note reconciles two seemingly distinct approaches to policy gradient optimization for the Pass@K objective in reinforcement learning with verifiable rewards: (1) direct REINFORCE-style methods, and (2) advantage-shaping techniques that directly modify GRPO. We show that these are two sides of the same coin. By reverse-engineering existing advantage-shaping algorithms, we reveal that they implicitly optimize surrogate rewards. We specifically interpret practical "hard-example up-weighting" modifications to GRPO as reward-level regularization. Conversely, starting from surrogate reward objectives, we provide a simple recipe for deriving both existing and new advantage-shaping methods. This perspective provides a lens for RLVR policy gradient optimization beyond our original motivation of Pass@K.
Authors: Malik H. Altakrori, Nizar Habash, Abed Alhakim Freihat, Younes Samih, Kirill Chirkunov, Muhammed AbuOdeh, Radu Florian, Teresa Lynn, Preslav Nakov, Alham Fikri Aji
Abstract: We present DialectalArabicMMLU, a new benchmark for evaluating the performance of large language models (LLMs) across Arabic dialects. While recently developed Arabic and multilingual benchmarks have advanced LLM evaluation for Modern Standard Arabic (MSA), dialectal varieties remain underrepresented despite their prevalence in everyday communication. DialectalArabicMMLU extends the MMLU-Redux framework through manual translation and adaptation of 3K multiple-choice question-answer pairs into five major dialects (Syrian, Egyptian, Emirati, Saudi, and Moroccan), yielding a total of 15K QA pairs across 32 academic and professional domains (22K QA pairs when also including English and MSA). The benchmark enables systematic assessment of LLM reasoning and comprehension beyond MSA, supporting both task-based and linguistic analysis. We evaluate 19 open-weight Arabic and multilingual LLMs (1B-13B parameters) and report substantial performance variation across dialects, revealing persistent gaps in dialectal generalization. DialectalArabicMMLU provides the first unified, human-curated resource for measuring dialectal understanding in Arabic, thus promoting more inclusive evaluation and future model development.
Authors: Zihan Li, Mingyang Wan, Mingyu Gao, Xishi Tai, Zhongshan Chen, Xiangke Wang, Feifan Zhang
Abstract: Covalent organic frameworks (COFs) are promising adsorbents for gas adsorption and separation, while identifying the optimal structures among their vast design space requires efficient high-throughput screening. Conventional machine-learning predictors rely heavily on specific gas-related features. However, these features are time-consuming and limit scalability, leading to inefficiency and labor-intensive processes. Herein, a universal COFs adsorption prediction framework (COFAP) is proposed, which can extract multi-modal structural and chemical features through deep learning, and fuse these complementary features via cross-modal attention mechanism. Without relying on explicit gas-specific thermodynamic descriptors, COFAP achieves state-of-the-art prediction performance on the hypoCOFs dataset under the conditions investigated in this study, outperforming existing approaches. Based on COFAP, we also found that high-performing COFs for gas separation concentrate within a narrow range of pore size and surface area. A weight-adjustable prioritization scheme is also developed to enable flexible, application-specific ranking of candidate COFs for researchers. Superior efficiency and accuracy render COFAP directly deployable in crystalline porous materials.
Authors: Charlotte Li, Nick Hagar, Sachita Nishal, Jeremy Gilbert, Nick Diakopoulos
Abstract: Benchmarks play a significant role in how technology companies communicate about model capabilities and how researchers and the public understand generative AI systems. However, existing benchmarks have been criticized for their failure to adequately capture real-world usages (i.e. ecological validity) or to measure underlying concepts (i.e. construct validity). Building on approaches in HCI, we adopt a human-centered design process to address such critiques. Working within the journalism domain we engaged 23 professionals in a workshop which informed the design of a domain-oriented evaluation ``cookbook''. Our workshop findings surface domain-specific challenges and tensions faced by designers in translating specific tasks to evaluation constructs, aligning metrics with domain-specific values, and balancing needs among different stakeholders when constructing evaluations. Through an instantiation of design-based approaches for benchmark creation in the journalism domain, this work not only produces an evaluation structure for journalism practitioners to experiment with, but also lays out design requirements for AI evaluations that are contextualized, value-aligned, and cultivate evaluative literacy for domain end-users.
Authors: Zifan He, Shengyu Ye, Rui Ma, Yang Wang, Jason Cong
Abstract: The rapid development of large language models (LLM) has greatly enhanced everyday applications. While many FPGA-based accelerators, with flexibility for fine-grained data control, exhibit superior speed and energy efficiency compared to GPUs, recent GPU-specific optimizations have diminished this advantage. When limited to arithmetic-based computation, FPGAs often underperform GPUs due to their comparatively fewer computational resources. To address this challenge, we exploit a key advantage of FPGAs over GPUs: abundant distributed on-chip memory embedded among computational units. We believe that shifting LLM inference from arithmetic-based to memory-based computations through table lookups can improve the efficiency on FPGAs to compete with GPUs. However, existing methods are inefficient or unable to scale and deploy language models due to algorithm and architecture design limitations. This paper introduces \textbf{LUT-LLM}, the first FPGA accelerator that deploy 1B+ language model with memory-based computation, leveraging vector quantization. We construct a performance model, evaluate multiple quantization schemes, and identify activation-weight vector co-quantization as the most effective approach. To support this scheme, LUT-LLM features (1) bandwidth-aware parallel centroid search to reduce decoding latency, (2) efficient 2D table lookups, and (3) a spatial-temporal hybrid design to reduce data caching for a higher throughput table lookup. We develop a training recipe that converts existing models to support table lookups with high accuracy and prototype LUT-LLM for Qwen 3 1.7B model on the AMD V80 FPGA, reducing arithmetic operations by $4\times$ and achieving a $1.10\sim3.29\times$ faster generation speed and a $3.05\sim 6.60\times$ higher energy efficiency than GPUs.
Authors: Wenwen Si, Sooyong Jang, Insup Lee, Osbert Bastani
Abstract: While large language models (LLMs) have recently made tremendous progress towards solving challenging AI problems, they have done so at increasingly steep computational and API costs. We propose a novel strategy where we combine multiple LLM models with varying cost/accuracy tradeoffs in an agentic manner, where models and tools are run in sequence as determined by an orchestration model to minimize cost subject to a user-specified level of reliability; this constraint is formalized using conformal prediction to provide guarantees. To solve this problem, we propose Conformal Constrained Policy Optimization (CCPO), a training paradigm that integrates constrained policy optimization with off-policy reinforcement learning and recent advances in online conformal prediction. CCPO jointly optimizes a cost-aware policy (score function) and an adaptive threshold. Across two multi-hop question answering benchmarks, CCPO achieves up to a 30% cost reduction compared to other cost-aware baselines and LLM-guided methods without compromising reliability. Our approach provides a principled and practical framework for deploying LLM agents that are significantly more cost-effective while maintaining reliability.
Authors: Desheng Hu, Joachim Baumann, Aleksandra Urman, Elsa Lichtenegger, Robin Forsberg, Aniko Hannak, Christo Wilson
Abstract: Google Search increasingly surfaces AI-generated content through features like AI Overviews (AIO) and Featured Snippets (FS), which users frequently rely on despite having no control over their presentation. Through a systematic algorithm audit of 1,508 real baby care and pregnancy-related queries, we evaluate the quality and consistency of these information displays. Our robust evaluation framework assesses multiple quality dimensions, including answer consistency, relevance, presence of medical safeguards, source categories, and sentiment alignment. Our results reveal concerning gaps in information consistency, with information in AIO and FS displayed on the same search result page being inconsistent with each other in 33% of cases. Despite high relevance scores, both features critically lack medical safeguards (present in just 11% of AIO and 7% of FS responses). While health and wellness websites dominate source categories for both, AIO and FS, FS also often link to commercial sources. These findings have important implications for public health information access and demonstrate the need for stronger quality controls in AI-mediated health information. Our methodology provides a transferable framework for auditing AI systems across high-stakes domains where information quality directly impacts user well-being.
Authors: Xiangyu Li, Tianyi Wang, Junfeng Jiao, Christian Claudel, Zhaomiao Guo
Abstract: As autonomous vehicles (AVs) are increasingly deployed on public roads, understanding their real-world behaviors is critical for traffic safety analysis and regulatory oversight. However, many data-driven methods lack interpretability and cannot provide verifiable explanations of AV behavior in mixed traffic. This paper proposes SVBRD-LLM, a self-verifying behavioral rule discovery framework that automatically extracts interpretable behavioral rules from real-world traffic videos through zero-shot large language model (LLM) reasoning. The framework first derives vehicle trajectories using YOLOv26-based detection and ByteTrack-based tracking, then computes kinematic features and contextual information. It then employs GPT-5 zero-shot prompting to perform comparative behavioral analysis between AVs and human-driven vehicles (HDVs) across lane-changing and normal driving behaviors, generating 26 structured rule hypotheses that comprises both numerical thresholds and statistical behavioral patterns. These rules are subsequently evaluated through the AV identification task using an independent validation dataset, and iteratively refined through failure case analysis to filter spurious correlations and improve robustness. The resulting rule library contains 20 high-confidence behavioral rules, each including semantic description, quantitative thresholds or behavioral patterns, applicable context, and validation confidence. Experiments conducted on over 1,500 hours of real-world traffic videos from Waymo's commercial operating area demonstrate that the proposed framework achieves 90.0% accuracy and 93.3% F1-score in AV identification, with 98.0% recall. The discovered rules capture key AV traits in smoothness, conservatism, and lane discipline, informing safety assessment, regulatory compliance, and traffic management in mixed traffic. The dataset is available at: svbrd-llm-roadside-video-av.
Authors: Huimin Ren, Yan Liang, Baiqiao Su, Chaobo Sun, Hengtong Lu, Kaike Zhang, Chen Wei
Abstract: The ability of Large Language Models (LLMs) to precisely follow complex and fine-grained lexical instructions is a cornerstone of their utility and controllability. However, evaluating this capability remains a significant challenge. Current methods either rely on subjective and costly human evaluation or on automated LLM-as-a-judge systems, which suffer from inherent biases and unreliability. Existing programmatic benchmarks, while objective, often lack the expressiveness to test intricate, compositional constraints at a granular level. To address these limitations, we introduce LexInstructEval, a new benchmark and evaluation framework for fine-grained lexical instruction following. Our framework is built upon a formal, rule-based grammar that deconstructs complex instructions into a canonical
Authors: Chengan Che, Chao Wang, Xinyue Chen, Sophia Tsoka, Luis C. Garcia-Peraza-Herrera
Abstract: Procedural activities, ranging from routine cooking to complex surgical operations, are highly structured sequences of actions performed in a specific temporal order. Despite the success of current self-supervised learning (SSL) methods on static images and short clips, these models often overlook the underlying sequential structure of such activities. We expose this lack of procedural awareness with a motivating experiment: models pretrained on forward and time-reversed sequences produce highly similar features, confirming that their representations are blind to the underlying procedural order. To address this shortcoming, we propose PL-Stitch, a self-supervised framework that harnesses the inherent temporal order of video frames as a powerful supervisory signal. Our approach integrates two novel probabilistic objectives based on the Plackett-Luce (PL) model. The primary PL objective trains the model to sort sampled frames chronologically, compelling it to learn the global workflow progression. The secondary objective, a spatio-temporal jigsaw loss, complements the learning by capturing fine-grained, cross-frame object correspondences. Our approach consistently achieves superior performance across five surgical and cooking benchmarks. Specifically, PL-Stitch yields significant gains in surgical phase recognition (e.g., +11.4 pp in k-NN accuracy on Cholec80) and cooking action segmentation (e.g., +5.7 pp in linear probing accuracy on Breakfast), demonstrating its effectiveness for procedural video representation learning. Code and models are available at https://github.com/visurg-ai/PL-Stitch.
Authors: Gia Huy Thai, Hoang-Nguyen Vu, Anh-Minh Phan, Quang-Thinh Ly, Tram Dinh, Thi-Ngoc-Truc Nguyen, Nhat Ho
Abstract: The significant variability in cell size and shape continues to pose a major obstacle in computer-assisted cancer detection on gigapixel Whole Slide Images (WSIs), due to cellular heterogeneity. Current CNN-Transformer hybrids use static computation graphs with fixed routing. This leads to extra computation and makes it harder to adapt to changes in input. We propose Shape-Adapting Gated Experts (SAGE), an input-adaptive framework that enables dynamic expert routing in heterogeneous visual networks. SAGE reconfigures static backbones into dynamically routed expert architectures via a dual-path design with hierarchical gating and a Shape-Adapting Hub (SA-Hub) that harmonizes feature representations across convolutional and transformer modules. Embodied as SAGE with ConvNeXt and Vision Transformer UNet (SAGE-ConvNeXt+ViT-UNet), our model achieves a Dice score of 95.23\% on EBHI, 92.78\%/91.42\% DSC on GlaS Test A/Test B, and 91.26\% DSC at the WSI level on DigestPath, while exhibiting robust generalization under distribution shifts by adaptively balancing local refinement and global context. SAGE establishes a scalable foundation for dynamic expert routing in visual networks, thereby facilitating flexible visual reasoning.
Authors: James R. M. Black, Moritz S. Hanke, Aaron Maiwald, Tina Hernandez-Boussard, Oliver M. Crook, Jaspreet Pannu
Abstract: Novel deep learning architectures are increasingly being applied to biological data, including genetic sequences. These models, referred to as genomic language models (gLMs), have demonstrated impressive predictive and generative capabilities, raising concerns that such models may also enable misuse, for instance via the generation of genomes for human-infecting viruses. These concerns have catalyzed calls for risk mitigation measures. The de facto mitigation of choice is filtering of pretraining data (i.e., removing viral genomic sequences from training datasets) in order to limit gLM performance on virus-related tasks. However, it is not currently known how robust this approach is for securing open-source models that can be fine-tuned using sensitive pathogen data. Here, we evaluate a state-of-the-art gLM, Evo 2, and perform fine-tuning using sequences from 110 harmful human-infecting viruses to assess the rescue of misuse-relevant predictive capabilities. The fine-tuned model exhibited reduced perplexity on unseen viral sequences relative to 1) the pretrained model and 2) a version fine-tuned on bacteriophage sequences. The model fine-tuned on human-infecting viruses also identified immune escape variants from SARS-CoV-2 (achieving an AUROC of 0.6), despite having no exposure to SARS-CoV-2 sequences during fine-tuning. This work demonstrates that data exclusion might be circumvented by fine-tuning approaches that can, to some degree, rescue misuse-relevant capabilities of gLMs. We highlight the need for safety frameworks for gLMs and outline further work needed on evaluations and mitigation measures to enable the safe deployment of gLMs.
Authors: Yuanzhe Li, Hang Zhong, Steffen M\"uller
Abstract: Pedestrian crossing intention prediction is essential for autonomous vehicles to improve pedestrian safety and reduce traffic accidents. However, accurate pedestrian intention prediction in urban environments remains challenging due to the multitude of factors affecting pedestrian behavior. In this paper, we propose a multi-context fusion Transformer (MFT) that leverages diverse numerical contextual attributes across four key dimensions, encompassing pedestrian behavior context, environmental context, pedestrian localization context and vehicle motion context, to enable accurate pedestrian intention prediction. MFT employs a progressive fusion strategy, where mutual intra-context attention enables reciprocal interactions within each context, thereby facilitating feature sequence fusion and yielding a context token as a context-specific representation. This is followed by mutual cross-context attention, which integrates features across contexts with a global CLS token serving as a compact multi-context representation. Finally, guided intra-context attention refines context tokens within each context through directed interactions, while guided cross-context attention strengthens the global CLS token to promote multi-context fusion via guided information propagation, yielding deeper and more efficient integration. Experimental results validate the superiority of MFT over state-of-the-art methods, achieving accuracy rates of 73%, 93%, and 90% on the JAADbeh, JAADall, and PIE datasets, respectively. Extensive ablation studies are further conducted to investigate the effectiveness of the network architecture and contribution of different input context. Our code is open-source: https://github.com/ZhongHang0307/Multi-Context-Fusion-Transformer.
URLs: https://github.com/ZhongHang0307/Multi-Context-Fusion-Transformer.
Authors: Inha Kang, Eunki Kim, Wonjeong Ryu, Jaeyo Shin, Seungjun Yu, Yoon-Hee Kang, Seongeun Jeong, Eunhye Kim, Soontae Kim, Hyunjung Shim
Abstract: Accurate long horizon forecasting of particulate matter (PM) concentration fields is essential for operational public health decisions. However, achieving reliable forecasts remains challenging in regions with complex terrain and strong atmospheric dynamics such as East Asia. While foundation models such as Aurora offer global generality, they often miss region-specific dynamics and rely on non-real-time inputs, limiting their practical utility for localized warning systems. To address this gap, we construct and release the real-world observations and high-resolution CMAQ-OBS dataset for East Asia, reducing regional error by 59.5% and enabling real-time 48-120 hour forecasts critical for public health alerts. However, standard point-wise objectives cannot reflect asymmetric operational costs, where false alarms deteriorate public trust while missed severe events endanger populations. This cost mismatch causes SFT models to over-predict and yield high False Alarm Rates. We introduce Group-Relative Policy Optimization (GRPO) with class-wise rewards and curriculum rollout to align predictions with operational priorities. Experimental results demonstrate that our framework significantly improves the reliability of the forecast. Compared to the SFT-only baseline, our model reduces the False Alarm Rate by 47.3% while achieving a competitive F1-score, proving its effectiveness for practical, real-world air quality forecasting systems on long lead time scenarios. Code and dataset are publicly available at https://github.com/kaist-cvml/FAKER-Air.
Authors: Hans Gundlach, Jayson Lynch, Matthias Mertens, Neil Thompson
Abstract: Language models have seen enormous progress on advanced benchmarks in recent years, but much of this progress has only been possible by using more costly models. Benchmarks may therefore present a warped picture of progress in practical capabilities *per dollar*. To remedy this, we use data from Artificial Analysis and Epoch AI to form the largest dataset of current and historical prices to run benchmarks to date. We find that the price for a given level of benchmark performance has decreased remarkably fast, around $5\times$ to $10\times$ per year, for frontier models on knowledge, reasoning, math, and software engineering benchmarks. These reductions in the cost of AI inference are due to economic forces, hardware efficiency improvements, and algorithmic efficiency improvements. Isolating out open models to control for competition effects and dividing by hardware price declines, we estimate that algorithmic efficiency progress is around $3\times$ per year. However, at the same time, the price of running frontier models is rising between $3\times$ to $18\times$ per year due to bigger models and larger reasoning demands. Finally, we recommend that evaluators both publicize and take into account the price of benchmarking as an essential part of measuring the real-world impact of AI.
Authors: Sreesritha Sai, Sai Venkata Suma Sreeja, Sai Sri Deepthi, Nikhil
Abstract: Accurate assessment of post-disaster damage is essential for prioritizing emergency response, yet current practices rely heavily on manual interpretation of satellite imagery.This approach is time-consuming, subjective, and difficult to scale during large-area disasters. Although recent deep-learning models for semantic segmentation and change detection have improved automation, many of them still struggle to capture subtle structural variations and often perform poorly when dealing with highly imbalanced datasets, where undamaged buildings dominate. This thesis introduces Satellite-to-Street:Disaster Impact Estimator, a deep-learning framework that produces detailed, pixel-level damage maps by analyzing pre and post-disaster satellite images together. The model is built on a modified dual-input U-Net architecture that strengthens feature fusion between both images, allowing it to detect not only small, localized changes but also broader contextual patterns across the scene. To address the imbalance between damage categories, a class-aware weighted loss function is used, which helps the model better recognize major and destroyed structures. A consistent preprocessing pipeline is employed to align image pairs, standardize resolutions, and prepare the dataset for training. Experiments conducted on publicly available disaster datasets show that the proposed framework achieves better classification of damaged regions compared to conventional segmentation networks.The generated damage maps provide faster and objective method for analyzing disaster impact, working alongside expert judgment rather than replacing it. In addition to identifying which areas are damaged, the system is capable of distinguishing different levels of severity, ranging from slight impact to complete destruction. This provides a more detailed and practical understanding of how the disaster has affected each region.
Authors: Xiangzheng Cheng, Haili Huang, Ye Su, Qing Nie, Xiufen Zou, Suoqin Jin
Abstract: In multicellular organisms, cells coordinate their activities through cell-cell communication (CCC), which is crucial for development, tissue homeostasis, and disease progression. Recent advances in single-cell and spatial omics technologies provide unprecedented opportunities to systematically infer and analyze CCC from these omics data, either by integrating prior knowledge of ligand-receptor interactions (LRIs) or through de novo approaches. A variety of computational methods have been developed, focusing on methodological innovations, accurate modeling of complex signaling mechanisms, and investigation of broader biological questions. These advances have greatly enhanced our ability to analyze CCC and generate biological hypotheses. Here, we introduce the biological mechanisms and modeling strategies of CCC, and provide a focused overview of more than 140 computational methods for inferring CCC from single-cell and spatial transcriptomic data, emphasizing the diversity in methodological frameworks and biological questions. Finally, we discuss the current challenges and future opportunities in this rapidly evolving field, and summarize available methods in an interactive online resource (https://cellchat.whu.edu.cn) to facilitate more efficient method comparison and selection.
Authors: Zichuan Lin, Yicheng Liu, Yang Yang, Lvfang Tao, Deheng Ye
Abstract: Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches reduce visual tokens through fixed-ratio compression, they operate passively and lack the ability to adapt to varying task requirements. This motivates a fundamental question: Can VLMs autonomously determine the minimum number of visual tokens required for each sample? Inspired by human active vision mechanisms, we introduce AdaptVision, an efficient VLM paradigm that enables adaptive visual token acquisition through a coarse-to-fine approach. Our model initially processes compressed visual tokens from low-resolution images and selectively acquires additional visual information by invoking a bounding box tool to crop key regions when necessary. We train AdaptVision using a reinforcement learning framework that carefully balances accuracy and efficiency. Central to our approach is Decoupled Turn Policy Optimization (DTPO), which decouples the learning objective into two components: (1) tool learning, which optimizes correct tool utilization, and (2) accuracy improvement, which refines the generated responses to improve answer correctness. Based on this formulation, we further decouple advantage estimation by computing separate advantages for tokens associated with each objective. This formulation enables more effective optimization for AdaptVision compared to vanilla GRPO. Comprehensive experiments across multiple VQA benchmarks demonstrate that AdaptVision achieves superior performance while consuming substantially fewer visual tokens than state-of-the-art efficient VLM methods.
Authors: Ekhi Azurmendi, Joseba Fernandez de Landa, Jaione Bengoetxea, Maite Heredia, Julen Etxaniz, Mikel Zubillaga, Ander Soraluze, Aitor Soroa
Abstract: Language models depend on massive text corpora that are often filtered for quality, a process that can unintentionally exclude non-standard linguistic varieties, reduce model robustness and reinforce representational biases. In this paper, we argue that language models should aim to capture the full spectrum of language variation (dialectal, historical, informal, etc.) rather than relying solely on standardized text. Focusing on the Basque language, we construct new corpora combining standard, social media, and historical sources, and pre-train the BERnaT family of encoder-only models in three configurations: standard, diverse, and combined. We further propose an evaluation framework that separates Natural Language Understanding (NLU) tasks into standard and diverse subsets to assess linguistic generalization. Results show that models trained on both standard and diverse data consistently outperform those trained on standard corpora, improving performance across all task types without compromising standard benchmark accuracy. These findings highlight the importance of linguistic diversity in building inclusive, generalizable language models.
Authors: Sanjeev Shrestha, Rahul Dubey, Hui Liu
Abstract: With the increasing complexity of black-box machine learning models and their adoption in high-stakes areas, it is critical to provide explanations for their predictions. Existing local explanation methods lack in generating high-fidelity explanations. This paper proposes a novel local model agnostic explanation method to generate high-fidelity explanations using multivariate adaptive regression splines (MARS) and N-ball sampling strategies. MARS is used to model non-linear local boundaries that effectively captures the underlying behavior of the reference model, thereby enhancing the local fidelity. The N-ball sampling technique samples perturbed samples directly from a desired distribution instead of reweighting, leading to further improvement in the faithfulness. The performance of the proposed method was computed in terms of root mean squared error (RMSE) and evaluated on five different benchmark datasets with different kernel width. Experimental results show that the proposed method achieves higher local surrogate fidelity compared to baseline local explanation methods, with an average reduction of 32% in root mean square error, indicating more accurate local approximations of the black-box model. Additionally, statistical analysis shows that across all benchmark datasets, the proposed approach results were statistically significantly better. This paper advances the field of explainable AI by providing insights that can benefit the broader research and practitioner community.
Authors: David Anugraha, Patrick Amadeus Irawan, Anshul Singh, En-Shiun Annie Lee, Genta Indra Winata
Abstract: Vision-language models (VLMs) have achieved strong performance in visual question answering (VQA), yet they remain constrained by static training data. Retrieval-Augmented Generation (RAG) mitigates this limitation by enabling access to up-to-date, culturally grounded, and multilingual information; however, multilingual multimodal RAG remains largely underexplored. We introduce M4-RAG, a massive-scale benchmark spanning 42 languages, 56 regional dialects and registers, and 189 countries, comprising over 80,000 culturally diverse image-question pairs for evaluating retrieval-augmented VQA across languages and modalities. To balance realism with reproducibility, we build a controlled retrieval environment containing millions of carefully curated multilingual documents relevant to the query domains, approximating real-world retrieval conditions while ensuring consistent experimentation. Our systematic evaluation reveals that although RAG consistently benefits smaller VLMs, it fails to scale to larger models and often even degrades their performance, exposing a critical mismatch between model size and current retrieval effectiveness. Our cross-lingual evaluations also reveal significant performance degradation when prompts or retrieved context are provided in non-English languages. The code, datasets, and evaluation protocols for M4-RAG are available as open-source at https://github.com/davidanugraha/M4-RAG.
Authors: Ekhi Azurmendi, Xabier Arregi, Oier Lopez de Lacalle
Abstract: This paper introduces the first publicly available dataset for Automatic Essay Scoring (AES) and feedback generation in Basque, targeting the CEFR C1 proficiency level. The dataset comprises 3,200 essays from HABE, each annotated by expert evaluators with criterion specific scores covering correctness, richness, coherence, cohesion, and task alignment enriched with detailed feedback and error examples. We fine-tune open-source models, including RoBERTa-EusCrawl and Latxa 8B/70B, for both scoring and explanation generation. Our experiments show that encoder models remain highly reliable for AES, while supervised fine-tuning (SFT) of Latxa significantly enhances performance, surpassing state-of-the-art (SoTA) closed-source systems such as GPT-5 and Claude Sonnet 4.5 in scoring consistency and feedback quality. We also propose a novel evaluation methodology for assessing feedback generation, combining automatic consistency metrics with expert-based validation of extracted learner errors. Results demonstrate that the fine-tuned Latxa model produces criterion-aligned, pedagogically meaningful feedback and identifies a wider range of error types than proprietary models. This resource and benchmark establish a foundation for transparent, reproducible, and educationally grounded NLP research in low-resource languages such as Basque.
Authors: Tariq Berrada Ifriqi, John Nguyen, Karteek Alahari, Jakob Verbeek, Ricky T. Q. Chen
Abstract: We present Flowception, a novel non-autoregressive and variable-length video generation framework. Flowception learns a probability path that interleaves discrete frame insertions with continuous frame denoising. Compared to autoregressive methods, Flowception alleviates error accumulation/drift as the frame insertion mechanism during sampling serves as an efficient compression mechanism to handle long-term context. Compared to full-sequence flows, our method reduces FLOPs for training three-fold, while also being more amenable to local attention variants, and allowing to learn the length of videos jointly with their content. Quantitative experimental results show improved FVD and VBench metrics over autoregressive and full-sequence baselines, which is further validated with qualitative results. Finally, by learning to insert and denoise frames in a sequence, Flowception seamlessly integrates different tasks such as image-to-video generation and video interpolation.
Authors: Peter Kocsis (Technical University of Munich), Lukas H\"ollein (Technical University of Munich), Matthias Nie{\ss}ner (Technical University of Munich)
Abstract: We introduce Intrinsic Image Fusion, a method that reconstructs high-quality physically based materials from multi-view images. Material reconstruction is highly underconstrained and typically relies on analysis-by-synthesis, which requires expensive and noisy path tracing. To better constrain the optimization, we incorporate single-view priors into the reconstruction process. We leverage a diffusion-based material estimator that produces multiple, but often inconsistent, candidate decompositions per view. To reduce the inconsistency, we fit an explicit low-dimensional parametric function to the predictions. We then propose a robust optimization framework using soft per-view prediction selection together with confidence-based soft multi-view inlier set to fuse the most consistent predictions of the most confident views into a consistent parametric material space. Finally, we use inverse path tracing to optimize for the low-dimensional parameters. Our results outperform state-of-the-art methods in material disentanglement on both synthetic and real scenes, producing sharp and clean reconstructions suitable for high-quality relighting.
Authors: Zhiwei Li, Yitian Pang, Weining Wang, Zhenan Sun, Qi Li
Abstract: Vision-Language Models (VLMs), such as CLIP, have achieved impressive zero-shot recognition performance but remain highly susceptible to adversarial perturbations, posing significant risks in safety-critical scenarios. Previous training-time defenses rely on adversarial fine-tuning, which requires labeled data and costly retraining, while existing test-time strategies fail to reliably distinguish between clean and adversarial inputs, thereby preventing both adversarial robustness and clean accuracy from reaching their optimum. To address these limitations, we propose Test-Time Padding (TTP), a lightweight defense framework that performs adversarial detection followed by targeted adaptation at inference. TTP identifies adversarial inputs via the cosine similarity shift between CLIP feature embeddings computed before and after spatial padding, yielding a universal threshold for reliable detection across architectures and datasets. For detected adversarial cases, TTP employs trainable padding to restore disrupted attention patterns, coupled with a similarity-aware ensemble strategy for a more robust final prediction. For clean inputs, TTP leaves them unchanged by default or optionally integrates existing test-time adaptation techniques for further accuracy gains. Comprehensive experiments on diverse CLIP backbones and fine-grained benchmarks show that TTP consistently surpasses state-of-the-art test-time defenses, delivering substantial improvements in adversarial robustness without compromising clean accuracy. The code for this paper will be released soon.
Authors: Haotian Ye, Qiyuan He, Jiaqi Han, Puheng Li, Jiaojiao Fan, Zekun Hao, Fitsum Reda, Yogesh Balaji, Huayu Chen, Sheng Liu, Angela Yao, James Zou, Stefano Ermon, Haoxiang Wang, Ming-Yu Liu
Abstract: Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which rigidly compress all content at a fixed rate, leading to redundancy or information loss. Drawing inspiration from Shannon's information theory, this paper introduces InfoTok, a principled framework for adaptive video tokenization. We rigorously prove that existing data-agnostic training methods are suboptimal in representation length, and present a novel evidence lower bound (ELBO)-based algorithm that approaches theoretical optimality. Leveraging this framework, we develop a transformer-based adaptive compressor that enables adaptive tokenization. Empirical results demonstrate state-of-the-art compression performance, saving 20% tokens without influence on performance, and achieving 2.3x compression rates while still outperforming prior heuristic adaptive approaches. By allocating tokens according to informational richness, InfoTok enables a more compressed yet accurate tokenization for video representation, offering valuable insights for future research.
Authors: Yunguo Yu
Abstract: Automated clinical ICD-10 coding is a high-impact healthcare task requiring a balance between coverage, precision, and safety. While neural approaches achieve strong performance, they suffer from hallucination-generating invalid or unsupported codes-posing unacceptable risks in safety-critical clinical settings. Rule-based systems eliminate hallucination but lack scalability and coverage due to manual knowledge base (KB) curation. We present Hybrid-Code v2, a neuro-symbolic framework that achieves zero Type-I hallucination by construction while maintaining competitive coverage and precision. The system integrates neural candidate generation with a symbolic KB verification layer that enforces validity constraints through multi-layer verification, including format, evidence grounding, negation detection, temporal consistency, and exclusion rules. In addition, we introduce an automated KB expansion mechanism that extracts and validates coding patterns from unlabeled clinical text, addressing the scalability limitations of rule-based systems. Evaluated on the MIMIC-III dataset against ClinicalBERT, BioBERT, rule-based systems, and GPT-4, Hybrid-Code v2 achieves 85% coverage, 92% precision, and 0% Type-I hallucination, outperforming rule-based systems by +40% coverage while eliminating hallucination observed in neural baselines (6-18%). The proposed architecture provides a formal safety guarantee for syntactic validity while preserving strong empirical performance. These results demonstrate that neuro-symbolic verification can enforce safety constraints in neural medical AI systems without sacrificing effectiveness, offering a generalizable design pattern for deploying trustworthy AI in safety-critical domains.
Authors: Yongwei Zhang, Yuanzhe Xing, Quanyi Liang, Quan Quan, Zhikun She
Abstract: For stabilizing control tasks, model-free reinforcement learning (RL) approaches face numerous challenges, particularly regarding the issues of effectiveness and efficiency in complex high-dimensional environments with limited training data. To address these challenges, we propose Multi-Step Actor-Critic Learning with Lyapunov Certificates (MSACL), a novel approach that integrates exponential stability into off-policy maximum entropy reinforcement learning (MERL). In contrast to existing RL-based approaches that depend on elaborate reward engineering and single-step constraints, MSACL adopts intuitive reward design and exploits multi-step samples to enable exploratory actor-critic learning. Specifically, we first introduce Exponential Stability Labels (ESLs) to categorize training samples and propose a $\lambda$-weighted aggregation mechanism to learn Lyapunov certificates. Based on these certificates, we further design a stability-aware advantage function to guide policy optimization, thereby promoting rapid Lyapunov descent and robust state convergence. We evaluate MSACL across six benchmarks, comprising four stabilizing and two high-dimensional tracking tasks. Experimental results demonstrate its consistent performance improvements over both standard RL baselines and state-of-the-art Lyapunov-based RL algorithms. Beyond rapid convergence, MSACL exhibits robustness against environmental uncertainties and generalization to unseen reference signals. The source code and benchmarking environments are available at \href{https://github.com/YuanZhe-Xing/MSACL}{https://github.com/YuanZhe-Xing/MSACL}.
URLs: https://github.com/YuanZhe-Xing/MSACL, https://github.com/YuanZhe-Xing/MSACL
Authors: Julian Evan Chrisnanto, Salsabila Rahma Alia, Nurfauzi Fadillah, Yulison Herry Chrisnanto
Abstract: Simulating nonlinear reaction-diffusion dynamics on complex, non-Euclidean manifolds remains a fundamental challenge in computational morphogenesis, constrained by high-fidelity mesh generation costs and symplectic drift in discrete time-stepping schemes. This study introduces the Intrinsic-Metric Physics-Informed Neural Network (IM-PINN), a mesh-free geometric deep learning framework that solves partial differential equations directly in the continuous parametric domain. By embedding the Riemannian metric tensor into the automatic differentiation graph, our architecture analytically reconstructs the Laplace-Beltrami operator, decoupling solution complexity from geometric discretization. We validate the framework on a "Stochastic Cloth" manifold with extreme Gaussian curvature fluctuations ($K \in [-2489, 3580]$), where traditional adaptive refinement fails to resolve anisotropic Turing instabilities. Using a dual-stream architecture with Fourier feature embeddings to mitigate spectral bias, the IM-PINN recovers the "splitting spot" and "labyrinthine" regimes of the Gray-Scott model. Benchmarking against the Surface Finite Element Method (SFEM) reveals superior physical rigor: the IM-PINN achieves global mass conservation error of $\mathcal{E}_{mass} \approx 0.157$ versus SFEM's $0.258$, acting as a thermodynamically consistent global solver that eliminates mass drift inherent in semi-implicit integration. The framework offers a memory-efficient, resolution-independent paradigm for simulating biological pattern formation on evolving surfaces, bridging differential geometry and physics-informed machine learning.
Authors: Shengyu Cao, Ming Hu
Abstract: We study how delegating pricing to large language models (LLMs) can facilitate collusion in a duopoly when both sellers rely on the same pre-trained model. The LLM is characterized by (i) a propensity parameter capturing its internal bias toward high-price recommendations and (ii) an output-fidelity parameter measuring how tightly outputs track that bias; the propensity evolves through retraining. We show that configuring LLMs for robustness and reproducibility can induce collusion via a phase transition: there exists a critical output-fidelity threshold that pins down long-run behavior. Below it, competitive pricing is the unique long-run outcome. Above it, the system is bistable, with competitive and collusive pricing both locally stable and the realized outcome determined by the model's initial preference. The collusive regime resembles tacit collusion: prices are elevated on average, yet occasional low-price recommendations provide plausible deniability. With perfect fidelity, full collusion emerges from any interior initial condition. For finite training batches of size $b$, infrequent retraining (driven by computational costs) further amplifies collusion: conditional on starting in the collusive basin, the probability of collusion approaches one as $b$ grows, since larger batches dampen stochastic fluctuations that might otherwise tip the system toward competition. The indeterminacy region shrinks at rate $O(1/\sqrt{b})$.
Authors: Tianjun Gu, Jingyu Gong, Zhizhong Zhang, Yuan Xie, Lizhuang Ma, Xin Tan, Athanasios V
Abstract: Spatial intelligence is central to embodied cognition, yet contemporary AI systems still struggle to reason about physical interactions in open-world human environments. Despite strong performance on controlled benchmarks, vision-language models often fail to jointly model physical dynamics, reference frames, and the latent human intentions that drive spatial change. We introduce Teleo-Spatial Intelligence (TSI), a reasoning capability that links spatiotemporal change to goal-directed structure. To evaluate TSI, we present EscherVerse, a large-scale open-world resource built from 11,328 real-world videos, including an 8,000-example benchmark and a 35,963-example instruction-tuning set. Across 27 state-of-the-art vision-language models and an independent analysis of first-pass human responses from 11 annotators, we identify a persistent teleo-spatial reasoning gap: the strongest proprietary model achieves 57.26\% overall accuracy, far below first-pass human performance, which ranges from 84.81\% to 95.14\% with a mean of 90.62\%. Fine-tuning on real-world, intent-aware data narrows this gap for open-weight models, but does not close it. EscherVerse provides a diagnostic testbed for purpose-aware spatial reasoning and highlights a critical gap between pattern recognition and human-level understanding in embodied AI.
Authors: Mateusz Krawczyk, Jaros{\l}aw Paw{\l}owski
Abstract: We propose a neural network-based model capable of learning the broad landscape of working regimes in quantum dot simulators, and using this knowledge to autotune these devices - based on transport measurements - toward obtaining Majorana modes in the structure. The model is trained in an unsupervised manner on synthetic data in the form of conductance maps, using a physics-informed loss that incorporates key properties of Majorana zero modes. We show that, with appropriate training, a deep vision-transformer network can efficiently memorize relation between Hamiltonian parameters and structures on conductance maps and use it to propose parameters update for a quantum dot chain that drive the system toward topological phase. Starting from a broad range of initial detunings in parameter space, a single update step is sufficient to generate nontrivial zero modes. Moreover, by enabling an iterative tuning procedure - where the system acquires updated conductance maps at each step - we demonstrate that the method can address a much larger region of the parameter space.
Authors: Nate Gillman, Yinghua Zhou, Zitian Tang, Evan Luo, Arjan Chakravarthy, Daksh Aggarwal, Michael Freeman, Charles Herrmann, Chen Sun
Abstract: Recent advancements in video generation have enabled the development of ``world models'' capable of simulating potential futures for robotics and planning. However, specifying precise goals for these models remains a challenge; text instructions are often too abstract to capture physical nuances, while target images are frequently infeasible to specify for dynamic tasks. To address this, we introduce Goal Force, a novel framework that allows users to define goals via explicit force vectors and intermediate dynamics, mirroring how humans conceptualize physical tasks. We train a video generation model on a curated dataset of synthetic causal primitives-such as elastic collisions and falling dominos-teaching it to propagate forces through time and space. Despite being trained on simple physics data, our model exhibits remarkable zero-shot generalization to complex, real-world scenarios, including tool manipulation and multi-object causal chains. Our results suggest that by grounding video generation in fundamental physical interactions, models can emerge as implicit neural physics simulators, enabling precise, physics-aware planning without reliance on external engines. We release all datasets, code, model weights, and interactive video demos at our project page.
Authors: Zhengxiang Wang, Zeyu Dong
Abstract: Tool use, such as web search, has become a standard capability even in freely available large language models (LLMs). However, existing benchmarks evaluate temporal reasoning mainly in static, non-tool-using settings, which poorly reflect how LLMs perform temporal reasoning in practice. We introduce Time Puzzles, a constraint-based date inference task for evaluating iterative temporal reasoning with tools. Each puzzle combines factual temporal anchors with (cross-cultural) calendar relations and may admit one or multiple valid dates. The puzzles are algorithmically generated, enabling controlled and continual evaluation. Across 13 LLMs, even the best model (GPT-5) achieves only 55.3% accuracy without tools, despite using easily searchable facts. While web search improves performance, models perform substantially better when constraints are rewritten with explicit dates, removing the need for factual lookup. These results reveal a gap in reliable tool use for iterative temporal reasoning.
Authors: Julian Evan Chrisnanto, Salsabila Rahma Alia, Nurfauzi Fadillah, Yulison Herry Chrisnanto
Abstract: The accurate identification and control of spatiotemporal chaos in reaction-diffusion systems remains a grand challenge in chemical engineering, particularly when the underlying catalytic surface possesses complex, unknown topography. In the \textit{Defect Turbulence} regime, system dynamics are governed by topological phase singularities (spiral waves) whose motion couples to manifold curvature via geometric pinning. Conventional Physics-Informed Neural Networks (PINNs) using ReLU or Tanh activations suffer from fundamental \textit{spectral bias}, failing to resolve high-frequency gradients and causing amplitude collapse or phase drift. We propose a Multi-Scale SIREN-PINN architecture leveraging periodic sinusoidal activations with frequency-diverse initialization, embedding the appropriate inductive bias for wave-like physics directly into the network structure. This enables simultaneous resolution of macroscopic wave envelopes and microscopic defect cores. Validated on the complex Ginzburg-Landau equation evolving on latent Riemannian manifolds, our architecture achieves relative state prediction error $\epsilon_{L_2} \approx 1.92 \times 10^{-2}$, outperforming standard baselines by an order of magnitude while preserving topological invariants ($|\Delta N_{defects}| < 1$). We solve the ill-posed \textit{inverse pinning problem}, reconstructing hidden Gaussian curvature fields solely from partial observations of chaotic wave dynamics (Pearson correlation $\rho = 0.965$). Training dynamics reveal a distinctive Spectral Phase Transition at epoch $\sim 2,100$, where cooperative minimization of physics and geometry losses drives the solver to Pareto-optimal solutions. This work establishes a new paradigm for Geometric Catalyst Design, offering a mesh-free, data-driven tool for identifying surface heterogeneity and engineering passive control strategies in turbulent chemical reactors.
Authors: Abhi Kottamasu, Chirag Mahapatra, Sam Lee, Ben Pan, Aakash Barthwal, Akul Datta, Anurag Gupta, Pranav Mehta, Ajay Arun, Silas Alberti, Adarsh Hiremath, Brendan Foody, Bertie Vidgen
Abstract: We introduce the AI Productivity Index for Software Engineering (APEX-SWE), a benchmark for assessing whether frontier AI models can execute economically valuable software engineering work. Unlike existing evaluations that focus on narrow, well-defined tasks, APEX-SWE assesses two novel task types that reflect real-world software engineering: (1) Integration tasks (n=100), which require constructing end-to-end systems across heterogeneous cloud primitives, business applications, and infrastructure-as-code services, and (2) Observability tasks (n=100), which require debugging production failures using telemetry signals such as logs and dashboards, as well as unstructured context. We evaluated eleven frontier models for the APEX-SWE leaderboard. Claude Opus 4.6 leads the APEX-SWE leaderboard with 40.5% Pass@1, followed by Claude Opus 4.5 at 38.7%. Our analysis shows that strong performance is primarily driven by epistemic discipline, defined as the capacity to distinguish between assumptions and verified facts. It is often combined with systematic verification prior to acting. We open-source the APEX-SWE evaluation harness and a dev set (n=50).
Authors: Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury
Abstract: Audio large language models (LLMs) enable unified speech understanding and generation, but adapting them to linguistically complex and dialect-rich settings such as Arabic-English remains challenging. We present a controlled study of multi-task instruction tuning for an Arabic-centric audio LLM across generative tasks including ASR and speech and text summarization, and discriminative tasks including dialect and emotion recognition, in a resource-constrained setting. To support end-to-end Arabic speech summarization, we introduce AraMega-SSum, a first speech summarization resource for training and benchmarking Arabic-centric Audio-LLMs. We compare four training strategies (i) Uniform Task Mixing, (ii) Task-Progressive Curriculum (TPC), (iiii) Aligner-Based Diverse Sampling (ADS) for training-time batch construction, and (iv) A two-stage TPC->ADS strategy. Our results show a clear efficiency-robustness trade-off. ADS speeds up early convergence and improves paralinguistic performance, however, it hurts other tasks. A two-stage TPC-> ADS strategy gives the most reliable overall balance across tasks, offering practical guidance for adapting omni audio LLMs to low-resource, dialect-rich environments. We will make AraMega-SSum and all experimental resources publicly available to the community.
Authors: Minuri Rajapakse, Ruvan Weerasinghe
Abstract: The performance of Language Models (LMs) on low-resource, morphologically rich languages like Sinhala remains largely unexplored, particularly regarding script variation in digital communication. Sinhala exhibits script duality, with Unicode used in formal contexts and Romanized text dominating social media, while mixed-script usage is common in practice. This paper benchmarks 24 open-source LMs on Unicode, Romanized and mixed-script Sinhala using perplexity evaluation across diverse text sources. Results reveal substantial script sensitivity, with median performance degradation exceeding 300 times from Unicode to Romanized text. Critically, model size shows no correlation with script-handling competence, as smaller models often outperform architectures 28 times larger. Unicode performance strongly predicts mixed-script robustness but not Romanized capability, demonstrating that single-script evaluation substantially underestimates real-world deployment challenges. These findings establish baseline LM capabilities for Sinhala and provide practical guidance for model selection in multi-script low-resource environments.
Authors: Dohun Lee, Chun-Hao Paul Huang, Xuelin Chen, Jong Chul Ye, Duygu Ceylan, Hyeonho Jeong
Abstract: Video-to-video diffusion models achieve impressive single-turn editing performance, but practical editing workflows are inherently iterative. When edits are applied sequentially, existing models treat each turn independently, often causing previously generated regions to drift or be overwritten. We identify this failure mode as the problem of cross-turn consistency in multi-turn video editing. We introduce Memory-V2V, a memory-augmented framework that treats prior edits as structured constraints for subsequent generations. Memory-V2V maintains an external memory of previous outputs, retrieves task-relevant edits, and integrates them through relevance-aware tokenization and adaptive compression. These technical ingredients enable scalable conditioning without linear growth in computation. We demonstrate Memory-V2V on iterative video novel view synthesis and text-guided long video editing. Memory-V2V substantially enhances cross-turn consistency while maintaining visual quality, outperforming strong baselines with modest overhead.
Authors: J. Ben Tamo, Daniel Carlander-Reuterfelt, Jonathan Rubin, Dezhi Hong, Mingxian Wang, Oleg Poliannikov
Abstract: Despite multilingual pretraining, large language models often struggle with non-English tasks, particularly in language control, the ability to respond in the intended language. We identify and characterize two key failure modes: the multilingual transfer bottleneck (correct language, incorrect task response) and the language consistency bottleneck (correct task response, wrong language). To systematically surface these issues, we design a four-scenario evaluation protocol spanning MMLU, MGSM, and XQuAD benchmarks. To probe these issues with interpretability, we extend logit lens analysis to track language probabilities layer by layer and compute cross-lingual semantic similarity of hidden states. The results reveal a three-phase internal structure: early layers align inputs into a shared semantic space, middle layers perform task reasoning, and late layers drive language-specific generation. Guided by these insights, we introduce selective fine-tuning of only the final layers responsible for language control. On Qwen-3-32B and Bloom-7.1B, this method achieves over 98 percent language consistency across six languages while fine-tuning only 3-5 percent of parameters, without sacrificing task accuracy. Importantly, this result is nearly identical to that of full-scope fine-tuning (for example, above 98 percent language consistency for both methods across all prompt scenarios) but uses a fraction of the computational resources. To the best of our knowledge, this is the first approach to leverage layer-localization of language control for efficient multilingual adaptation.
Authors: Zhipeng Zhang, Xiongfei Su, Kai Li
Abstract: Robust reinforcement learning methods typically focus on suppressing unreliable experiences or corrupted rewards, but they lack the ability to reason about the reliability of their own learning process. As a result, such methods often either overreact to noise by becoming overly conservative or fail catastrophically when uncertainty accumulates. In this work, we propose a meta-cognitive reinforcement learning framework that enables an agent to assess, regulate, and recover its learning behavior based on internally estimated reliability signals. The proposed method introduces a meta-trust variable driven by Value Prediction Error Stability (VPES), which modulates learning dynamics via fail-safe regulation and gradual trust recovery. Experiments on continuous-control benchmarks with reward corruption demonstrate that recovery-enabled meta-cognitive control achieves higher average returns and significantly reduces late-stage training failures compared to strong robustness baselines.
Authors: Jin Li, Tao Chen, Shuai Jiang, Weijie Wang, Jingwen Luo, Chenhui Wu
Abstract: Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remains a persistent bottleneck. Traditional metrics struggle to quantify fine-grained texture details and semantic consistency, while existing datasets fail to meet commercial standards in scale and diversity. We present OpenVTON-Bench, a large-scale benchmark comprising approximately 100K high-resolution image pairs (up to $1536 \times 1536$). The dataset is constructed using DINOv3-based hierarchical clustering for semantically balanced sampling and Gemini-powered dense captioning, ensuring a uniform distribution across 20 fine-grained garment categories. To support reliable evaluation, we propose a multi-modal protocol that measures VTON quality along five interpretable dimensions: background consistency, identity fidelity, texture fidelity, shape plausibility, and overall realism. The protocol integrates VLM-based semantic reasoning with a novel Multi-Scale Representation Metric based on SAM3 segmentation and morphological erosion, enabling the separation of boundary alignment errors from internal texture artifacts. Experimental results show strong agreement with human judgments (Kendall's $\tau$ of 0.833 vs. 0.611 for SSIM), establishing a robust benchmark for VTON evaluation.
Authors: Siyuan Shen, Kai Wang
Abstract: The growing availability of large language models (LLMs) has raised questions about their role in academic peer review. This study examines the temporal emergence of AI-generated content in peer reviews by applying a detection model trained on historical reviews to later review cycles at International Conference on Learning Representations (ICLR) and Nature Communications (NC). We observe minimal detection of AI-generated content before 2022, followed by a substantial increase through 2025, with approximately 20% of ICLR reviews and 12% of Nature Communications reviews classified as AI-generated in 2025. The most pronounced growth of AI-generated reviews in NC occurs between the third and fourth quarter of 2024. Together, these findings provide suggestive evidence of a rapidly increasing presence of AI-assisted content in peer review and highlight the need for further study of its implications for scholarly evaluation.
Authors: Wonjun Yi, Rismaya Kumar Mishra, Yong-Hwa Park
Abstract: Machine systems inherently generate signals in which fault conditions and various variables influence signals measured from machine system. Although many existing fault classification studies rely solely on direct fault labels, the aforementioned signals naturally embed additional information shaped by other variables. Herein, we leverage this through a multi-task learning (MTL) framework that jointly learns fault conditions and other variables influencing measured signals. Among MTL architectures, cross-talk structures have distinct advantages because they allow for controlled information exchange between tasks through the cross-talk layer while preventing negative transfer, in contrast to shared trunk architectures that often mix incompatible features. We build on our previously introduced residual neural dimension reductor model, and extend its application to two benchmarks where system influenced by multiple variables. The first benchmark is a drone fault dataset, in which machine type and maneuvering direction significantly alter the frequency components of measured signals even under the same drone status. The second benchmark dataset is motor compound fault dataset. In this system, severity of each fault component, inner race fault, outer race fault, misalignment, and unbalance influences measured signal. Across both benchmarks, our residual neural dimension reductor, consistently outperformed single-task models, multi-class models that merge all label combinations, and shared trunk multi-task models.
Authors: Videet Mehta, Liming Wang, Hilde Kuehne, Rogerio Feris, James R. Glass, M. Jehanzeb Mirza
Abstract: Large audio-language models (LALMs) exhibit strong zero-shot capabilities in multiple downstream tasks, such as audio question answering (AQA) and abstract reasoning; however, these models still lag behind specialized models for certain discriminative tasks (e.g., audio classification). Recent studies show that sparse subsets of attention heads within an LALM can serve as strong discriminative feature extractors for downstream tasks such as classification via simple voting schemes. However, these methods assign uniform weights to all selected heads, implicitly assuming that each head contributes equally across all semantic categories. In this work, we propose Class-Conditional Sparse Attention Vectors for Large Audio-Language Models, a few-shot classification method that learns class-dependent importance weights over attention heads. This formulation allows individual heads to specialize in distinct semantic categories and to contribute to ensemble predictions proportionally to their estimated reliability. Experiments on multiple few-shot audio and audiovisual classification benchmarks and tasks demonstrate that our method consistently outperforms state-of-the-art uniform voting-based approaches by up to 14.52%, 1.53%, 8.35% absolute gains for audio classification, audio-visual classification, and spoofing detection respectively.
Authors: Bjarni Haukur Bjarnason, Andr\'e Silva, Martin Monperrus
Abstract: Agentic systems are evaluated on benchmarks where agents interact with environments to solve tasks. Most papers report a pass@1 score computed from a single run per task, assuming this gives a reliable performance estimate. We test this assumption by collecting 60,000 agentic trajectories on SWE-Bench-Verified, spanning three models and two scaffolds. We find substantial variance: single-run pass@1 estimates vary by 2.2 to 6.0 percentage points depending on which run is selected, with standard deviations exceeding 1.5 percentage points even at temperature 0. This variance has critical implications: reported improvements of 2--3 percentage points may reflect evaluation noise rather than genuine algorithmic progress. Through token-level analysis, we show that trajectories diverge early, often within the first few percent of tokens, and that these small differences cascade into different solution strategies. To enable reliable evaluation of agentic systems, we recommend three concrete practices: (1) estimate pass@1 from multiple independent runs per task, especially when measuring small improvements, (2) use statistical power analysis to determine the number of runs needed to detect expected effect sizes, and (3) consider metrics like pass@k (optimistic bound) and pass^k (pessimistic bound) with k>1 to better characterize the full performance envelope. While these practices increase evaluation cost, they are essential for distinguishing genuine scientific progress from statistical noise.
Authors: Yuanfu Wang, Zhixuan Liu, Xiangtian Li, Chaochao Lu, Chao Yang
Abstract: The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated reasoning data and external verifiers. This dependency incurs significant data-collection costs, risks embedding human cognitive biases, and confines the reinforcement learning stage to objectively assessable domains like mathematics and coding, leaving a wide range of unverifiable tasks beyond its scope. To overcome these limitations, we introduce NRT (Native Reasoning Training), a novel framework that cultivates complex reasoning by having the model generate its own reasoning traces using only standard question-answer pairs, thereby obviating the need for expert-written demonstrations. NRT reframes the training problem by treating the reasoning process as a latent variable. It employs a unified training objective that models reasoning as an optimization problem, intrinsically rewarding paths that increase the model's likelihood of producing the ground-truth answer. This unified perspective allows us to analyze intrinsic failure modes of prior methods, such as policy collapse, and systematically design more robust reward aggregation functions, creating a self-reinforcing feedback loop where the model learns to think in ways that resolve its own uncertainty. Empirical evaluation on Llama and Mistral model families demonstrates that NRT achieves state-of-the-art performance among verifier-free methods, significantly outperforming standard SFT baselines and prior verifier-free RL methods. Our approach yields particularly strong performance gains in complex reasoning domains and exhibits high robustness to policy collapse, offering a general, scalable path toward building more powerful and broadly applicable reasoning systems.
Authors: Xiaowen Tao, Yinuo Wang, Haitao Ding, Yuanyang Qi, Ziyu Song
Abstract: With the growth of intelligent civil infrastructure and smart cities, operation and maintenance (O&M) increasingly requires safe, efficient, and energy-conscious robotic manipulation of articulated components, including access doors, service drawers, and pipeline valves. However, existing robotic approaches either focus primarily on grasping or target object-specific articulated manipulation, and they rarely incorporate explicit actuation energy into multi-objective optimisation, which limits their scalability and suitability for long-term deployment in real O&M settings. Therefore, this paper proposes an articulation-agnostic and energy-aware reinforcement learning framework for robotic manipulation in intelligent infrastructure O&M. The method combines part-guided 3D perception, weighted point sampling, and PointNet-based encoding to obtain a compact geometric representation that generalises across heterogeneous articulated objects. Manipulation is formulated as a Constrained Markov Decision Process (CMDP), in which actuation energy is explicitly modelled and regulated via a Lagrangian-based constrained Soft Actor-Critic scheme. The policy is trained end-to-end under this CMDP formulation, enabling effective articulated-object operation while satisfying a long-horizon energy budget. Experiments on representative O&M tasks demonstrate 16%-30% reductions in energy consumption, 16%-32% fewer steps to success, and consistently high success rates, indicating a scalable and sustainable solution for infrastructure O&M manipulation.
Authors: Jiran Tao, Cheng Wang, Binyan Jiang
Abstract: The rapid proliferation of rumors on social networks poses a significant threat to information integrity. While rumor dissemination forms complex structural patterns, existing detection methods often fail to capture the intricate interplay between textual coherence and propagation dynamics. Current approaches typically represent nodes through isolated textual embeddings, neglecting the semantic flow across the entire propagation path. To bridge this gap, we introduce a novel framework that integrates Large Language Models (LLMs) as a structural augmentation layer for graph-based rumor detection. Moving beyond conventional methods, our framework employs LLMs to evaluate information subchains and strategically introduce a virtual node into the graph. This structural modification converts latent semantic patterns into explicit topological features, effectively capturing the textual coherence that has historically been inaccessible to Graph Neural Networks (GNNs). To ensure reliability, we develop a structured prompt framework that mitigates inherent biases in LLMs while maintaining robust graph learning performance. Furthermore, our proposed framework is model-agnostic, meaning it is not constrained to any specific graph learning algorithm or LLMs. Its plug-and-play nature allows for seamless integration with further fine-tuned LLMs and graph techniques in the future, potentially enhancing predictive performance without the need to modify original algorithms.
Authors: Rongqiang Zhao, Hengrui Hu, Yijing Wang, Mingchun Sun, Jie Liu
Abstract: Multimodal methods are widely used in rice deterioration detection, but they exhibit limited capability in representing and extracting fine-grained abnormal features. Moreover, these methods rely on devices such as hyperspectral cameras and mass spectrometers, which increase detection costs and prolong data acquisition time. To address these issues, we propose a feature recalibration based olfactory-visual multimodal model for enhanced rice deterioration detection. A fine-grained deterioration embedding constructor (FDEC) is proposed to reconstruct the labeled multimodal embedded feature dataset, thereby enhancing sample representation. A fine-grained deterioration recalibration attention network (FDRA-Net) is proposed to emphasize signal variations and improve sensitivity to fine-grained deterioration on the rice surface. Compared with SS-Net, the proposed method improves classification accuracy by 8.67%, with an average improvement of 11.51% over other traditional baseline models, while simultaneously simplifying the detection procedure. Furthermore, field detection results demonstrate advantages in both accuracy and operational simplicity. The proposed method can also be extended to other agrifood applications in agriculture and the food industry.
Authors: Yunhao Liu, Zian Jia, Xinyu Gao, Kanjun Xu, Yun Xiong
Abstract: Retrieval-Augmented Generation (RAG) effectively grounds Large Language Models (LLMs) with external knowledge and is widely applied to Web-related tasks. However, its scalability is hindered by excessive context length and redundant retrievals. Recent research on soft context compression aims to address this by encoding long documents into compact embeddings, yet they often underperform non-compressed RAG due to their reliance on auto-encoder-like full-compression that forces the encoder to compress all document information regardless of relevance to the input query. In this work, we conduct an analysis on this paradigm and reveal two fundamental limitations: (I) Infeasibility, full-compression conflicts with the LLM's downstream generation behavior; and (II) Non-necessity: full-compression is unnecessary and dilutes task-relevant information density. Motivated by these insights, we introduce SeleCom, a selector-based soft compression framework for RAG that redefines the encoder's role as query-conditioned information selector. The selector is decoder-only and is trained with a massive, diverse and difficulty-graded synthetic QA dataset with curriculum learning. Extensive experiments show that SeleCom significantly outperforms existing soft compression approaches and achieves competitive or superior performance to non-compression baselines, while reducing computation and latency by 33.8%~84.6%.
Authors: Abhinaba Basu
Abstract: Personal AI agents incur substantial cost via repeated LLM calls. We show existing caching methods fail: GPTCache achieves 37.9% accuracy on real benchmarks; APC achieves 0-12%. The root cause is optimizing for the wrong property -- cache effectiveness requires key consistency and precision, not classification accuracy. We observe cache-key evaluation reduces to clustering evaluation and apply V-measure decomposition to separate these on n=8,682 points across MASSIVE, BANKING77, CLINC150, and NyayaBench v2, our new 8,514-entry multilingual agentic dataset (528 intents, 20 W5H2 classes, 63 languages). We introduce W5H2, a structured intent decomposition framework. Using SetFit with 8 examples per class, W5H2 achieves 91.1%+/-1.7% on MASSIVE in ~2ms -- vs 37.9% for GPTCache and 68.8% for a 20B-parameter LLM at 3,447ms. On NyayaBench v2 (20 classes), SetFit achieves 55.3%, with cross-lingual transfer across 30 languages. Our five-tier cascade handles 85% of interactions locally, projecting 97.5% cost reduction. We provide risk-controlled selective prediction guarantees via RCPS with nine bound families.
Authors: Zunkai Dai, Ke Li, Jiajia Liu, Jie Yang, Yuanyuan Qiao
Abstract: The collection and detection of video anomaly data has long been a challenging problem due to its rare occurrence and spatio-temporal scarcity. Existing video anomaly detection (VAD) methods under perform in open-world scenarios. Key contributing factors include limited dataset diversity, and inadequate understanding of context-dependent anomalous semantics. To address these issues, i) we propose LAVIDA, an end-to-end zero-shot video anomaly detection framework. ii) LAVIDA employs an Anomaly Exposure Sampler that transforms segmented objects into pseudo-anomalies to enhance model adaptability to unseen anomaly categories. It further integrates a Multimodal Large Language Model (MLLM) to bolster semantic comprehension capabilities. Additionally, iii) we design a token compression approach based on reverse attention to handle the spatio-temporal scarcity of anomalous patterns and decrease computational cost. The training process is conducted solely on pseudo anomalies without any VAD data. Evaluations across four benchmark VAD datasets demonstrate that LAVIDA achieves SOTA performance in both frame-level and pixel-level anomaly detection under the zero-shot setting. Our code is available in https://github.com/VitaminCreed/LAVIDA.
Authors: Haoyang Li, Yang You, Hao Su, Leonidas Guibas
Abstract: Reliable object manipulation requires understanding physical properties that vary across objects and environments. Vision-language model (VLM) planners can reason about friction and stability in general terms; however, they often cannot predict how a specific ball will roll on a particular surface or which stone will provide a stable foundation without direct experience. We present PhysMem, a memory framework that enables VLM robot planners to learn physical principles from interaction at test time, without updating model parameters. The system records experiences, generates candidate hypotheses, and verifies them through targeted interaction before promoting validated knowledge to guide future decisions. A central design choice is verification before application: the system tests hypotheses against new observations rather than applying retrieved experience directly, reducing rigid reliance on prior experience when physical conditions change. We evaluate PhysMem on three real-world manipulation tasks and simulation benchmarks across four VLM backbones. On a controlled brick insertion task, principled abstraction achieves 76% success compared to 23% for direct experience retrieval, and real-world experiments show consistent improvement over 30-minute deployment sessions.
Authors: Rui Cen (Hunyuan AI Infra Team), QiangQiang Hu (Hunyuan AI Infra Team), Hong Huang (Hunyuan AI Infra Team), Hong Liu (Hunyuan AI Infra Team), Song Liu (Hunyuan AI Infra Team), Xin Luo (Hunyuan AI Infra Team), Lin Niu (Hunyuan AI Infra Team), Yifan Tan (Hunyuan AI Infra Team), Decheng Wu (Hunyuan AI Infra Team), Linchuan Xie (Hunyuan AI Infra Team), Rubing Yang (Hunyuan AI Infra Team), Guanghua Yu (Hunyuan AI Infra Team), Jianchen Zhu (Hunyuan AI Infra Team)
Abstract: This technical report introduces AngelSlim, a comprehensive and versatile toolkit for large model compression developed by the Tencent Hunyuan team. By consolidating cutting-edge algorithms, including quantization, speculative decoding, token pruning, and distillation. AngelSlim provides a unified pipeline that streamlines the transition from model compression to industrial-scale deployment. To facilitate efficient acceleration, we integrate state-of-the-art FP8 and INT8 Post-Training Quantization (PTQ) algorithms alongside pioneering research in ultra-low-bit regimes, featuring HY-1.8B-int2 as the first industrially viable 2-bit large model. Beyond quantization, we propose a training-aligned speculative decoding framework compatible with multimodal architectures and modern inference engines, achieving 1.8x to 2.0x throughput gains without compromising output correctness. Furthermore, we develop a training-free sparse attention framework that reduces Time-to-First-Token (TTFT) in long-context scenarios by decoupling sparse kernels from model architectures through a hybrid of static patterns and dynamic token selection. For multimodal models, AngelSlim incorporates specialized pruning strategies, namely IDPruner for optimizing vision tokens via Maximal Marginal Relevance and Samp for adaptive audio token merging and pruning. By integrating these compression strategies from low-level implementations, AngelSlim enables algorithm-focused research and tool-assisted deployment.
Authors: Jaehong Cho, Hyunmin Choi, Guseul Heo, Jongse Park
Abstract: Large language model (LLM) serving infrastructures are undergoing a shift toward heterogeneity and disaggregation. Modern deployments increasingly integrate diverse accelerators and near-memory processing technologies, introducing significant hardware heterogeneity, while system software increasingly separates computation, memory, and model components across distributed resources to improve scalability and efficiency. As a result, LLM serving performance is no longer determined by hardware or software choices in isolation, but by their runtime interaction through scheduling, data movement, and interconnect behavior. However, understanding these interactions remains challenging, as existing simulators lack the ability to jointly model heterogeneous hardware and disaggregated serving techniques within a unified, runtime-driven framework. This paper presents LLMServingSim 2.0, a unified system-level simulator designed to make runtime-driven hardware-software interactions in heterogeneous and disaggregated LLM serving infrastructures explicit and analyzable. LLMServingSim 2.0 embeds serving decisions and hardware behavior into a single runtime loop, enabling interaction-aware modeling of batching, routing, offloading, memory, and power. The simulator supports extensible integration of emerging accelerators and memory systems through profile-based modeling, while capturing dynamic serving behavior and system-level effects. We validate LLMServingSim 2.0 against real deployments, showing that it reproduces key performance, memory, and power metrics with an average error of 0.95%, while maintaining simulation times of around 10 minutes even for complex configurations. These results demonstrate that LLMServingSim 2.0 provides a practical bridge between hardware innovation and serving-system design, enabling systematic exploration and co-design for next-generation LLM serving infrastructures.
Authors: Xiangyan Qu, Zhenlong Yuan, Jing Tang, Rui Chen, Datao Tang, Meng Yu, Lei Sun, Yancheng Bai, Xiangxiang Chu, Gaopeng Gou, Gang Xiong, Yujun Cai
Abstract: Image Chain-of-Thought (Image-CoT) is a test-time scaling paradigm that improves image generation by extending inference time. Most Image-CoT methods focus on text-to-image (T2I) generation. Unlike T2I generation, image editing is goal-directed: the solution space is constrained by the source image and instruction. This mismatch causes three challenges when applying Image-CoT to editing: inefficient resource allocation with fixed sampling budgets, unreliable early-stage verification using general MLLM scores, and redundant edited results from large-scale sampling. To address this, we propose ADaptive Edit-CoT (ADE-CoT), an on-demand test-time scaling framework to enhance editing efficiency and performance. It incorporates three key strategies: (1) a difficulty-aware resource allocation that assigns dynamic budgets based on estimated edit difficulty; (2) edit-specific verification in early pruning that uses region localization and caption consistency to select promising candidates; and (3) depth-first opportunistic stopping, guided by an instance-specific verifier, that terminates when intent-aligned results are found. Extensive experiments on three SOTA editing models (Step1X-Edit, BAGEL, FLUX.1 Kontext) across three benchmarks show that ADE-CoT achieves superior performance-efficiency trade-offs. With comparable sampling budgets, ADE-CoT obtains better performance with more than 2x speedup over Best-of-N.
Authors: Hulingxiao He, Zhi Tan, Yuxin Peng
Abstract: A high-performing, general-purpose visual understanding model should map visual inputs to a taxonomic tree of labels, identify novel categories beyond the training set for which few or no publicly available images exist. Large Multimodal Models (LMMs) have achieved remarkable progress in fine-grained visual recognition (FGVR) for known categories. However, they remain limited in hierarchical visual recognition (HVR) that aims at predicting consistent label paths from coarse to fine categories, especially for novel categories. To tackle these challenges, we propose Taxonomy-Aware Representation Alignment (TARA), a simple yet effective strategy to inject taxonomic knowledge into LMMs. TARA leverages representations from biology foundation models (BFMs) that encode rich biological relationships through hierarchical contrastive learning. By aligning the intermediate representations of visual features with those of BFMs, LMMs are encouraged to extract discriminative visual cues well structured in the taxonomy tree. Additionally, we align the representations of the first answer token with the ground-truth label, flexibly bridging the gap between contextualized visual features and categories of varying granularity according to user intent. Experiments demonstrate that TARA consistently enhances LMMs' hierarchical consistency and leaf node accuracy, enabling reliable recognition of both known and novel categories within complex biological taxonomies. Code is available at https://github.com/PKU-ICST-MIPL/TARA_CVPR2026.
Authors: Seunghoi Kim, Chen Jin, Henry F. J. Tregidgo, Matteo Figini, Daniel C. Alexander
Abstract: Zero-shot MRI reconstruction relies on generative priors, but single-modality unconditional priors produce hallucinations under severe ill-posedness. In many clinical workflows, complementary MRI acquisitions (e.g. high-quality structural scans) are routinely available, yet existing reconstruction methods lack mechanisms to leverage this additional information. We propose MPFlow, a zero-shot multi-modal reconstruction framework built on rectified flow that incorporates auxiliary MRI modalities at inference time without retraining the generative prior to improve anatomical fidelity. Cross-modal guidance is enabled by our proposed self-supervised pretraining strategy, Patch-level Multi-modal MR Image Pretraining (PAMRI), which learns shared representations across modalities. Sampling is jointly guided by data consistency and cross-modal feature alignment using pre-trained PAMRI, systematically suppressing intrinsic and extrinsic hallucinations. Extensive experiments on HCP and BraTS show that MPFlow matches diffusion baselines on image quality using only 20% of sampling steps while reducing tumor hallucinations by more than 15% (segmentation dice score). This demonstrates that cross-modal guidance enables more reliable and efficient zero-shot MRI reconstruction.
Authors: Julien Amblard, Niklas Groll, Matthew Tait, Mark Law, G\"urkan Sin, Alessandra Russo
Abstract: Over the past decade, Artificial Intelligence has significantly advanced, mostly driven by large-scale neural approaches. However, in the chemical process industry, where safety is critical, these methods are often unsuitable due to their brittleness, and lack of explainability and interpretability. Furthermore, open-source real-world datasets containing historical failures are scarce in this domain. In this paper, we investigate an approach for predicting failures in chemical processes using symbolic machine learning and conduct a feasibility study in the context of an ethylene oxidation process. Our method builds on a state-of-the-art symbolic machine learning system capable of learning predictive models in the form of probabilistic rules from context-dependent noisy examples. This system is a general-purpose symbolic learner, which makes our approach independent of any specific chemical process. To address the lack of real-world failure data, we conduct our feasibility study leveraging data generated from a chemical process simulator. Experimental results show that symbolic machine learning can outperform baseline methods such as random forest and multilayer perceptron, while preserving interpretability through the generation of compact, rule-based predictive models. Finally, we explain how such learned rule-based models could be integrated into agents to assist chemical plant operators in decision-making during potential failures.
Authors: Xiaolei Zhang, Lu Zhou, Xiaogang Xu, Jiafei Wu, Tianyu Du, Heqing Huang, Hao Peng, Zhe Liu
Abstract: Artificial Intelligence (AI) agents have evolved from passive predictive tools into active entities capable of autonomous decision-making and environmental interaction, driven by the reasoning capabilities of Large Language Models (LLMs). However, this evolution has introduced critical security vulnerabilities that existing frameworks fail to address. The Hierarchical Autonomy Evolution (HAE) framework organizes agent security into three tiers: Cognitive Autonomy (L1) targets internal reasoning integrity; Execution Autonomy (L2) covers tool-mediated environmental interaction; Collective Autonomy (L3) addresses systemic risks in multi-agent ecosystems. We present a taxonomy of threats spanning cognitive manipulation, physical environment disruption, and multi-agent systemic failures, and evaluate existing defenses while identifying key research gaps. The findings aim to guide the development of multilayered, autonomy-aware defense architectures for trustworthy AI agent systems.
Authors: Zegu Zhang, Jian Zhang
Abstract: Variational autoencoders (VAEs) frequently suffer from posterior collapse, where the latent variables become uninformative as the approximate posterior degenerates to the prior. While recent work has characterized collapse as a phase transition determined by data covariance properties, existing approaches primarily aim to avoid rather than eliminate collapse. We introduce a novel framework that theoretically guarantees non-collapsed solutions by leveraging spherical shell geometry and cluster-aware constraints. Our method transforms data to a spherical shell, computes optimal cluster assignments via K-means, and defines a feasible region between the within-cluster variance $W$ and collapse loss $\delta_{\text{collapse}}$. We prove that when the reconstruction loss is constrained to this region, the collapsed solution is mathematically excluded from the feasible parameter space. \textbf{Critically, we introduce norm constraint mechanisms that ensure decoder outputs remain compatible with the spherical shell geometry without restricting representational capacity.} Unlike prior approaches, our method provides a strict theoretical guarantee with minimal computational overhead without imposing constraints on decoder outputs. Experiments on synthetic and real-world datasets demonstrate 100\% collapse prevention under conditions where conventional VAEs completely fail, with reconstruction quality matching or exceeding state-of-the-art methods. Our approach requires no explicit stability conditions (e.g., $\sigma^2 < \lambda_{\max}$) and works with arbitrary neural architectures. The code is available at https://github.com/tsegoochang/spherical-vae-with-Cluster.
URLs: https://github.com/tsegoochang/spherical-vae-with-Cluster.
Authors: Bo Hu, Jose C Principe
Abstract: Statistical dependence measures like mutual information is ideal for analyzing autoencoders, but it can be ill-posed for deterministic, static, noise-free networks. We adopt the variational (Gaussian) formulation that makes dependence among inputs, latents, and reconstructions measurable, and we propose a stable neural dependence estimator based on an orthonormal density-ratio decomposition. Unlike MINE, our method avoids input concatenation and product-of-marginals re-pairing, reducing computational cost and improving stability. We introduce an efficient NMF-like scalar cost and demonstrate empirically that assuming Gaussian noise to form an auxiliary variable enables meaningful dependence measurements and supports quantitative feature analysis, with a sequential convergence of singular values.
Authors: Chenghan Wu, Zongmin Yu, Boai Sun, Liu Yang
Abstract: In-context operator learning enables neural networks to infer solution operators from contextual examples without weight updates. While prior work has demonstrated the effectiveness of this paradigm in leveraging vast datasets, a systematic comparison against single-operator learning using identical training data has been absent. We address this gap through controlled experiments comparing in-context operator learning against classical operator learning (single-operator models trained without contextual examples), under the same training steps and dataset. To enable this investigation on real-world spatiotemporal systems, we propose GICON (Graph In-Context Operator Network), combining graph message passing for geometric generalization with example-aware positional encoding for cardinality generalization. Experiments on air quality prediction across two Chinese regions show that in-context operator learning outperforms classical operator learning on complex tasks, generalizing across spatial domains and scaling robustly from few training examples to 100 at inference.
Authors: Wanyin Wu, Kanxue Li, Baosheng Yu, Haoyun Zhao, Yibing Zhan, Dapeng Tao, Hua Jin
Abstract: Accurate prediction of surgical duration is pivotal for hospital resource management. Although recent supervised learning approaches-from machine learning (ML) to fine-tuned large language models (LLMs)-have shown strong performance, they remain constrained by the need for high-quality labeled data and computationally intensive training. In contrast, zero-shot LLM inference offers a promising training-free alternative but it lacks grounding in institution-specific clinical context (e.g., local demographics and case-mix distributions), making its predictions clinically misaligned and prone to instability. To address these limitations, we present PREBA, a retrieval-augmented framework that integrates PCA-weighted retrieval and Bayesian averaging aggregation to ground LLM predictions in institution-specific clinical evidence and statistical priors. The core of PREBA is to construct an evidence-based prompt for the LLM, comprising (1) the most clinically similar historical surgical cases and (2) clinical statistical priors. To achieve this, PREBA first encodes heterogeneous clinical features into a unified representation space enabling systematic retrieval. It then performs PCA-weighted retrieval to identify clinically relevant historical cases, which form the evidence context supplied to the LLM. Finally, PREBA applies Bayesian averaging to fuse multi-round LLM predictions with population-level statistical priors, yielding calibrated and clinically plausible duration estimates. We evaluate PREBA on two real-world clinical datasets using three state-of-the-art LLMs, including Qwen3, DeepSeek-R1, and HuatuoGPT-o1. PREBA significantly improves performance-for instance, reducing MAE by up to 40% and raising R^2 from -0.13 to 0.62 over zero-shot inference-and it achieves accuracy competitive with supervised ML methods, demonstrating strong effectiveness and generalization.
Authors: Liang Tang, Hongda Li, Jiayu Zhang, Long Chen, Shuxian Li, Siqi Pei, Tiaonan Duan, Yuhao Cheng
Abstract: Emotion recognition in videos is a pivotal task in affective computing, where identifying subtle psychological states such as Ambivalence and Hesitancy holds significant value for behavioral intervention and digital health. Ambivalence and Hesitancy states often manifest through cross-modal inconsistencies such as discrepancies between facial expressions, vocal tones, and textual semantics, posing a substantial challenge for automated recognition. This paper proposes a recognition framework that integrates temporal segment modeling with Multimodal Large Language Models. To address computational efficiency and token constraints in long video processing, we employ a segment-based strategy, partitioning videos into short clips with a maximum duration of 5 seconds. We leverage the Qwen3-Omni-30B-A3B model, fine-tuned on the BAH dataset using LoRA and full-parameter strategies via the MS-Swift framework, enabling the model to synergistically analyze visual and auditory signals. Experimental results demonstrate that the proposed method achieves an accuracy of 85.1% on the test set, significantly outperforming existing benchmarks and validating the superior capability of Multimodal Large Language Models in capturing complex and nuanced emotional conflicts. The code is released at https://github.com/dlnn123/A-H-Detection-with-Qwen-Omni.git.
URLs: https://github.com/dlnn123/A-H-Detection-with-Qwen-Omni.git.
Authors: Yishun Zhu, Jiaxin Qi, Jian Wang, Yuhua Zheng, Jianqiang Huang
Abstract: Spatial Transcriptomics (ST) profiles thousands of gene expression values at discrete spots with precise coordinates on tissue sections, preserving spatial context essential for clinical and pathological studies. With rising sequencing throughput and advancing platforms, the expanding data volumes motivate large-scale ST pretraining. However, the fundamental unit for pretraining, i.e., what constitutes a single training sample, remains ill-posed. Existing choices fall into two camps: (1) treating each spot as an independent sample, which discards spatial dependencies and collapses ST into single-cell transcriptomics; and (2) treating an entire slide as a single sample, which produces prohibitively large inputs and drastically fewer training examples, undermining effective pretraining. To address this gap, we propose treating spatial transcriptomics as croppable images. Specifically, we define a multi-channel image representation with fixed spatial size by cropping patches from raw slides, thereby preserving spatial context while substantially increasing the number of training samples. Along the channel dimension, we define gene subset selection rules to control input dimensionality and improve pretraining stability. Extensive experiments show that the proposed image-like dataset construction for ST pretraining consistently improves downstream performance, outperforming conventional pretraining schemes. Ablation studies verify that both spatial patching and channel design are necessary, establishing a unified, practical paradigm for organizing ST data and enabling large-scale pretraining.
Authors: Grayson Lee, Minh Bui, Shuzi Zhou, Yankai Li, Mo Chen, Ke Li
Abstract: Diffusion-based models have recently shown strong performance in trajectory planning, as they are capable of capturing diverse, multimodal distributions of complex behaviors. A key limitation of these models is their slow inference speed, which results from the iterative denoising process. This makes them less suitable for real-time applications such as closed-loop model predictive control (MPC), where plans must be generated quickly and adapted continuously to a changing environment. In this paper, we investigate Implicit Maximum Likelihood Estimation (IMLE) as an alternative generative modeling approach for planning. IMLE offers strong mode coverage while enabling inference that is two orders of magnitude faster, making it particularly well suited for real-time MPC tasks. Our results demonstrate that IMLE achieves competitive performance on standard offline reinforcement learning benchmarks compared to the standard diffusion-based planner, while substantially improving planning speed in both open-loop and closed-loop settings. We further validate IMLE in a closed-loop human navigation scenario, operating in real-time, demonstrating how it enables rapid and adaptive plan generation in dynamic environments. Real-world videos and code are available at https://gmpc-imle.github.io/.
Authors: Maria Rosaria Briglia, Simone Facchiano, Paolo Cursi, Alessio Sampieri, Emanuele Rodol\`a, Guido Maria D'Amely di Melendugno, Luca Franco, Fabio Galasso, Iacopo Masi
Abstract: As modern text-to-image (T2I) models draw closer to synthesizing highly realistic content, the threat of unsafe content generation grows, and it becomes paramount to exercise control. Existing approaches steer these models by applying Euclidean adjustments to text embeddings, redirecting the generation away from unsafe concepts. In this work, we introduce hyperbolic control (HyCon): a novel control mechanism based on parallel transport that leverages semantically aligned hyperbolic representation space to yield more expressive and stable manipulation of concepts. HyCon reuses off-the-shelf generative models and a state-of-the-art hyperbolic text encoder, linked via a lightweight adapter. HyCon achieves state-of-the-art results across four safety benchmarks and four T2I backbones, showing that hyperbolic steering is a practical and flexible approach for more reliable T2I generation.
Authors: Shubhashis Roy Dipta, Daniel Bis, Kun Zhou, Lichao Wang, Benjamin Z. Yao, Chenlei Guo, Ruhi Sarikaya
Abstract: Conversational assistants powered by large language models (LLMs) excel at tool-use tasks but struggle with adhering to complex, business-specific rules. While models can reason over business rules provided in context, including all policies for every query introduces high latency and wastes compute. Furthermore, these lengthy prompts lead to long contexts, harming overall performance due to the "needle-in-the-haystack" problem. To address these challenges, we propose a multi-stage alignment method that teaches models to recall and apply relevant business policies during chain-of-thought reasoning at inference time, without including the full business policy in-context. Furthermore, we introduce a novel PolicyRecall reward based on the Jaccard score and a Hallucination Penalty for GRPO training. Altogether, our best model outperforms the baseline by 16 points and surpasses comparable in-context baselines of similar model size by 3 points, while using 40% fewer words.
Authors: Sreeja Apparaju, Nilesh Gupta
Abstract: As agents operate over long horizons, their memory stores grow continuously, making retrieval critical to accessing relevant information. Many agent queries require reasoning-intensive retrieval, where the connection between query and relevant documents is implicit and requires inference to bridge. LLM-augmented pipelines address this through query expansion and candidate re-ranking, but introduce significant inference costs. We study computation allocation in reasoning-intensive retrieval pipelines using the BRIGHT benchmark and Gemini 2.5 model family. We vary model capacity, inference-time thinking, and re-ranking depth across query expansion and re-ranking stages. We find that re-ranking benefits substantially from stronger models (+7.5 NDCG@10) and deeper candidate pools (+21% from $k$=10 to 100), while query expansion shows diminishing returns beyond lightweight models (+1.1 NDCG@10 from weak to strong). Inference-time thinking provides minimal improvement at either stage. These results suggest that compute should be concentrated on re-ranking rather than distributed uniformly across pipeline stages.
Authors: Dhananjay Ashok, Ruth-Ann Armstrong, Jonathan May
Abstract: Language Models (LMs) may acquire harmful knowledge, and yet feign ignorance of these topics when under audit. Inspired by the recent discovery of deception-related behaviour patterns in LMs, we aim to train classifiers that detect when a LM is actively concealing knowledge. Initial findings on smaller models show that classifiers can detect concealment more reliably than human evaluators, with gradient-based concealment proving easier to identify than prompt-based methods. However, contrary to prior work, we find that the classifiers do not reliably generalize to unseen model architectures and topics of hidden knowledge. Most concerningly, the identifiable traces associated with concealment become fainter as the models increase in scale, with the classifiers achieving no better than random performance on any model exceeding 70 billion parameters. Our results expose a key limitation in black-box-only auditing of LMs and highlight the need to develop robust methods to detect models that are actively hiding the knowledge they contain.
Authors: Ro-hoon Oh, Jihwan Seol, Bugeun Kim
Abstract: Target speech extraction (TSE) aims to recover a target speaker's voice from a mixture. While recent text-prompted approaches have shown promise, most approaches assume fully overlapped mixtures, limiting insight into behavior across realistic overlap ratios. We introduce VorTEX (Various overlap ratio for Target speech EXtraction), a text-prompted TSE architecture with a Decoupled Adaptive Multi-branch (DAM) Fusion block that separates primary extraction from auxiliary regularization pathways. To enable controlled analysis, we construct PORTE, a two-speaker dataset spanning overlap ratios from 0% to 100%. We further propose Suppression Ratio on Energy (SuRE), a diagnostic metric that detects suppression behavior not captured by conventional measures. Experiments show that existing models exhibit suppression or residual interference under overlap, whereas VorTEX achieves the highest separation fidelity across 20-100% overlap (e.g., 5.50 dB at 20% and 2.04 dB at 100%) while maintaining zero SuRE, indicating robust extraction without suppression-driven artifacts.
Authors: Yanru Wu, Weiduo Yuan, Ang Qi, Vitor Guizilini, Jiageng Mao, Yue Wang
Abstract: Reinforcement Learning (RL) has shown great potential in refining robotic manipulation policies, yet its efficacy remains strongly bottlenecked by the difficulty of designing generalizable reward functions. In this paper, we propose a framework for online policy refinement by adapting foundation VLMs into online reward generators. We develop a robust, scalable reward model based on a state-of-the-art VLM, trained on a large-scale, multi-source dataset encompassing real-world robot trajectories, human-object interactions, and diverse simulated environments. Unlike prior approaches that evaluate entire trajectories post-hoc, our method leverages the VLM to formulate a multifaceted reward signal comprising process, completion, and temporal contrastive rewards based on current visual observations. Initializing with a base policy trained via Imitation Learning (IL), we employ these VLM rewards to guide the model to correct sub-optimal behaviors in a closed-loop manner. We evaluate our framework on challenging long-horizon manipulation benchmarks requiring sequential execution and precise control. Crucially, our reward model operates in a purely zero-shot manner within these test environments. Experimental results demonstrate that our method significantly improves the success rate of the initial IL policy within just 30 RL iterations, demonstrating remarkable sample efficiency. This empirical evidence highlights that VLM-generated signals can provide reliable feedback to resolve execution errors, effectively eliminating the need for manual reward engineering and facilitating efficient online refinement for robot learning.
Authors: Isha Andrade, Shalaka S Mahadik, Mithun Mukherjee, Pranav M Pawar, Raja Muthalagu
Abstract: The proliferation of large-scale IoT networks has been both a blessing and a curse. Not only has it revolutionized the way organizations operate by increasing the efficiency of automated procedures, but it has also simplified our daily lives. However, while IoT networks have improved convenience and connectivity, they have also increased security risk due to unauthorized devices gaining access to these networks and exploiting existing weaknesses with specific attack types. The research proposes two lightweight deep learning (DL)-based intelligent intrusion detection systems (IDS). to enhance the security of IoT networks: the proposed convolutional neural network (CNN)-based IDS and the proposed long short-term memory (LSTM)-based IDS. The research evaluated the performance of both intelligent IDSs based on DL using the CICIoT2023 dataset. DL-based intelligent IDSs successfully identify and classify various cyber threats using binary, grouped, and multi-class classification. The proposed CNN-based IDS achieves an accuracy of 99.34%, 99.02% and 98.6%, while the proposed LSTM-based IDS achieves an accuracy of 99.42%, 99.13%, and 98.68% for binary, grouped, and multi-class classification, respectively.
Authors: Tianyuan Yuan, Zibin Dong, Yicheng Liu, Hang Zhao
Abstract: World Action Models (WAMs) have emerged as a promising alternative to Vision-Language-Action (VLA) models for embodied control because they explicitly model how visual observations may evolve under action. Most existing WAMs follow an imagine-then-execute paradigm, incurring substantial test-time latency from iterative video denoising, yet it remains unclear whether explicit future imagination is actually necessary for strong action performance. In this paper, we ask whether WAMs need explicit future imagination at test time, or whether their benefit comes primarily from video modeling during training. We disentangle the role of video modeling during training from explicit future generation during inference by proposing \textbf{Fast-WAM}, a WAM architecture that retains video co-training during training but skips future prediction at test time. We further instantiate several Fast-WAM variants to enable a controlled comparison of these two factors. Across these variants, we find that Fast-WAM remains competitive with imagine-then-execute variants, while removing video co-training causes a much larger performance drop. Empirically, Fast-WAM achieves competitive results with state-of-the-art methods both on simulation benchmarks (LIBERO and RoboTwin) and real-world tasks, without embodied pretraining. It runs in real time with 190ms latency, over 4$\times$ faster than existing imagine-then-execute WAMs. These results suggest that the main value of video prediction in WAMs may lie in improving world representations during training rather than generating future observations at test time. Project page: https://yuantianyuan01.github.io/FastWAM/
Authors: Hongjun Wang, Wei Liu, Weibo Gu, Xing Sun, Kai Han
Abstract: Regulating the importance ratio is critical for the training stability of Group Relative Policy Optimization (GRPO) based frameworks. However, prevailing ratio control methods, such as hard clipping, suffer from non-differentiable boundaries and vanishing gradient regions, failing to maintain gradient fidelity. Furthermore, these methods lack a hazard-aware mechanism to adaptively suppress extreme deviations, leaving the optimization process vulnerable to abrupt policy shifts. To address these challenges, we propose Modulated Hazard-aware Policy Optimization (MHPO), a novel framework designed for robust and stable reinforcement learning. The proposed MHPO introduces a Log-Fidelity Modulator (LFM) to map unbounded importance ratios into a bounded, differentiable domain. This mechanism effectively prevents high-variance outlier tokens from destabilizing the loss landscape while ensuring global gradient stability. Complementarily, a Decoupled Hazard Penalty (DHP) integrates cumulative hazard functions from survival analysis to independently regulate positive and negative policy shifts. By shaping the optimization landscape with hazard-aware penalties, the proposed MHPO achieves fine-grained regulation of asymmetric policy shifts simultaneously mitigating mode collapse from over-expansion and preventing policy erosion from catastrophic contraction within a stabilized trust region. Extensive evaluations on diverse reasoning benchmarks across both text-based and vision-language tasks demonstrate that MHPO consistently outperforms existing methods, achieving superior performance while significantly enhancing training stability.
Authors: Alejandro Paredes La Torre
Abstract: We study adversarial robustness of open-source vision-language model (VLM) agents deployed in a self-contained e-commerce environment built to simulate realistic pre-deployment conditions. We evaluate two agents, LLaVA-v1.5-7B and Qwen2.5-VL-7B, under three gradient-based attacks: the Basic Iterative Method (BIM), Projected Gradient Descent (PGD), and a CLIP-based spectral attack. Against LLaVA, all three attacks achieve substantial attack success rates (52.6%, 53.8%, and 66.9% respectively), demonstrating that simple gradient-based methods pose a practical threat to open-source VLM agents. Qwen2.5-VL proves significantly more robust across all attacks (6.5%, 7.7%, and 15.5%), suggesting meaningful architectural differences in adversarial resilience between open-source VLM families. These findings have direct implications for the security evaluation of VLM agents prior to commercial deployment.
Authors: Yaze Zhao, Yixiong Zou, Yuhua Li, Ruixuan Li
Abstract: Cross-Domain Few-Shot Learning (CDFSL) adapts models trained with large-scale general data (source domain) to downstream target domains with only scarce training data, where the research on vision-language models (e.g., CLIP) is still in the early stages. Typical downstream domains, such as medical diagnosis, require fine-grained visual cues for interpretable recognition, but we find that current fine-tuned CLIP models can hardly focus on these cues, albeit they can roughly focus on important regions in source domains. Although current works have demonstrated CLIP's shortcomings in capturing local subtle patterns, in this paper, we find that the domain gap and scarce training data further exacerbate such shortcomings, much more than that of holistic patterns, which we call the local misalignment problem in CLIP-based CDFSL. To address this problem, due to the lack of supervision in aligning local visual features and text semantics, we turn to self-supervision information. Inspired by the translation task, we propose the CC-CDFSL method with cycle consistency, which translates local visual features into text features and then translates them back into visual features (and vice versa), and constrains the original features close to the translated back features. To reduce the noise imported by richer information in the visual modality, we further propose a Semantic Anchor mechanism, which first augments visual features to provide a larger corpus for the text-to-image mapping, and then shrinks the image features to filter out irrelevant image-to-text mapping. Extensive experiments on various benchmarks, backbones, and fine-tuning methods show we can (1) effectively improve the local vision-language alignment, (2) enhance the interpretability of learned patterns and model decisions by visualizing patches, and (3) achieve state-of-the-art performance.
Authors: Teng Pan, Yuchen Yan, Zixuan Wang, Ruiqing Zhang, Guiyang Hou, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen
Abstract: Label-free reinforcement learning enables large language models to improve reasoning capabilities without ground-truth supervision, typically by treating majority-voted answers as pseudo-labels. However, we identify a critical failure mode: as training maximizes self-consistency, output diversity collapses, causing the model to confidently reinforce systematic errors that evade detection. We term this the consensus trap. To escape it, we propose CoVerRL, a framework where a single model alternates between generator and verifier roles, with each capability bootstrapping the other. Majority voting provides noisy but informative supervision for training the verifier, while the improving verifier progressively filters self-consistent errors from pseudo-labels. This co-evolution creates a virtuous cycle that maintains high reward accuracy throughout training. Experiments across Qwen and Llama model families demonstrate that CoVerRL outperforms label-free baselines by 4.7-5.9% on mathematical reasoning benchmarks. Moreover, self-verification accuracy improves from around 55% to over 85%, confirming that both capabilities genuinely co-evolve.
Authors: Li Wenxiu, Wen Zhanjie, Xia Jiechang, Guo Jingqiao
Abstract: At a time when the phenomenon of 'AI washing' is quietly spreading, an increasing number of enterprises are using the label of artificial intelligence merely as a cosmetic embellishment in their annual reports, rather than as a genuine engine driving transformation. A test regarding the essence of innovation and the authenticity of information disclosure has arrived. This paper employs large language models to conduct semantic analysis on the text of annual reports from Chinese A-share listed companies from 2006 to 2024, systematically examining the impact of corporate AI washing behaviour on their green innovation. The research reveals that corporate AI washing exerts a significant crowding-out effect on green innovation, with this negative relationship transmitted through dual channels in both product and capital markets. Furthermore, this crowding-out effect exhibits heterogeneity across firms and industries, with private enterprises, small and medium-sized enterprises (SMEs), and firms in highly competitive sectors suffering more severe negative impacts from AI washing. Simulation results indicate that a combination of policy tools can effectively improve market equilibrium. Based on this, this paper proposes that the government should design targeted support tools to 'enhance market returns and alleviate financing constraints', adopt a differentiated regulatory strategy, and establish a disclosure mechanism combining 'professional identification and reputational sanctions' to curb such peer AI washing behaviour.
Authors: Zhanjie Wen, Wenxiu Li, Jiechang Xia, Jingqiao Guo
Abstract: In the context of the rapid development of digital finance, some financial technology companies exhibit the phenomenon of "AI washing," where they overstate their AI capabilities while underinvesting in actual AI resources. This paper constructs a corporate-level AI washing index based on CHFS2019 data and AI investment data from 15-20 financial technology companies, analyzing and testing its impact on farmers' digital financial behavior response. The study finds that AI washing significantly suppresses farmers' digital financial behavior; the higher the degree of AI washing, the lower the response level of farmers' digital financial behavior. Moreover, AI washing indirectly inhibits farmers' behavioral responses by exacerbating knowledge exclusion and risk exclusion. Social capital can positively moderate the negative impact of AI washing; among farmer groups with high social capital, the suppressive effect of AI washing on digital financial behavior is significantly weaker than that among groups with low social capital. In response, this paper suggests that regulatory authorities establish a strict information disclosure system for AI technology, conduct differentiated digital financial education to enhance the identification capabilities of vulnerable groups, promote digital financial mutual aid groups to leverage the protective effects of social capital, improve the consumer protection mechanism for farmers in digital finance, and set up pilot "Digital Inclusive Finance Demonstration Counties," etc.
Authors: Marcelo Fernandez (TraslaIA)
Abstract: Agent Control Protocol (ACP) is a formal technical specification for admission control governance of autonomous agents in B2B institutional environments. Before any agent action reaches execution, it must pass a cryptographic admission check that simultaneously validates identity, capability scope, delegation chain, and policy compliance -- functioning as an admission control layer between agent intent and system state mutation. ACP defines mechanisms for cryptographic identity (Ed25519, JCS canonicalization), capability-based authorization, deterministic risk evaluation (integer arithmetic, no external ML inference), verifiable chained delegation, transitive revocation, and immutable cryptographically-chained auditing. It operates on top of RBAC and Zero Trust without replacing them, addressing the gap neither model solves: governing what autonomous agents can do, under what conditions, with what limits, and with full traceability across organizational boundaries. The v1.17 specification comprises 38 technical documents across five conformance levels (L1-L5), a Go reference implementation (23 packages, all L1-L4 capabilities), 73 signed conformance test vectors plus 65 unsigned RISK-2.0 vectors, an OpenAPI 3.1.0 specification (18 endpoints), a TLC-runnable TLA+ formal model (4 invariants, 0 violations), and an ACR-1.0 sequence compliance runner that validates stateful multi-step behaviors in library mode and HTTP mode. Five sequence test vectors cover cooldown activation, anomaly pattern accumulation (F_anom Rule 3), threshold boundaries, privilege jumps, and benign flow. An ACP-SIGN-2.0 stub provides the Ed25519 to ML-DSA-65 post-quantum migration path.
Authors: Carlos Rafael Catalan, Patricia Nicole Monderin, Lheane Marie Dizon, Gap Estrella, Raymund John Sarmimento, Marie Antoinette Patalagsa
Abstract: Popular language learning applications such as Duolingo use large language models (LLMs) to generate lessons for its users. Most lessons focus on general real-world scenarios such as greetings, ordering food, or asking directions, with limited support for profession-specific contexts. This gap can hinder learners from achieving professional-level fluency, which we define as the ability to communicate comfortably various work-related and domain-specific information in the target language. We surveyed five employees from a multinational company in the Philippines on their experiences with Duolingo. Results show that respondents encountered general scenarios more frequently than work-related ones, and that the former are relatable and effective in building foundational grammar, vocabulary, and cultural knowledge. The latter helps bridge the gap toward professional fluency as it contains domain-specific vocabulary. Each participant suggested lesson scenarios that diverge in contexts when analyzed in aggregate. With this understanding, we propose that language learning applications should generate lessons that adapt to an individual's needs through personalized, domain specific lesson scenarios while maintaining foundational support through general, relatable lesson scenarios.
Authors: Zhuolin Yang, Zihan Liu, Yang Chen, Wenliang Dai, Boxin Wang, Sheng-Chieh Lin, Chankyu Lee, Yangyi Chen, Dongfu Jiang, Jiafan He, Renjie Pi, Grace Lam, Nayeon Lee, Alexander Bukharin, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping
Abstract: We introduce Nemotron-Cascade 2, an open 30B MoE model with 3B activated parameters that delivers best-in-class reasoning and strong agentic capabilities. Despite its compact size, its mathematical and coding reasoning performance approaches that of frontier open models. It is the second open-weight LLM, after DeepSeekV3.2-Speciale-671B-A37B, to achieve Gold Medal-level performance in the 2025 International Mathematical Olympiad (IMO), the International Olympiad in Informatics (IOI), and the ICPC World Finals, demonstrating remarkably high intelligence density with 20x fewer parameters. In contrast to Nemotron-Cascade 1, the key technical advancements are as follows. After SFT on a meticulously curated dataset, we substantially expand Cascade RL to cover a much broader spectrum of reasoning and agentic domains. Furthermore, we introduce multi-domain on-policy distillation from the strongest intermediate teacher models for each domain throughout the Cascade RL process, allowing us to efficiently recover benchmark regressions and sustain strong performance gains along the way. We release the collection of model checkpoint and training data.
Authors: Yogesh Agrawal, Aniruddha Dutta, Md Mahadi Hasan, Santu Karmaker, Aritra Dutta
Abstract: Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamentals derived from regulatory filings and trading signals computed from price dynamics. Recently, with the advancement of Large Language Models (LLMs), financial analysts have begun to use them for financial decision-making tasks. However, existing financial question answering benchmarks for testing these models primarily focus on company balance sheet data and rarely evaluate reasoning over how company stocks trade in the market or their interactions with fundamentals. To take advantage of the strengths of both approaches, we introduce FinTradeBench, a benchmark for evaluating financial reasoning that integrates company fundamentals and trading signals. FinTradeBench contains 1,400 questions grounded in NASDAQ-100 companies over a ten-year historical window. The benchmark is organized into three reasoning categories: fundamentals-focused, trading-signal-focused, and hybrid questions requiring cross-signal reasoning. To ensure reliability at scale, we adopt a calibration-then-scaling framework that combines expert seed questions, multi-model response generation, intra-model self-filtering, numerical auditing, and human-LLM judge alignment. We evaluate 14 LLMs under zero-shot prompting and retrieval-augmented settings and witness a clear performance gap. Retrieval substantially improves reasoning over textual fundamentals, but provides limited benefit for trading-signal reasoning. These findings highlight fundamental challenges in the numerical and time-series reasoning for current LLMs and motivate future research in financial intelligence.
Authors: Yi Yu, Maria Boritchev, Chlo\'e Clavel
Abstract: Collaboration is a task-oriented, high-level human behavior. In most cases, conversation serves as the primary medium for information exchange and coordination, making conversational data a valuable resource for the automatic analysis of collaborative processes. In this paper, we focus on verbal aspects of collaboration and conduct a review of collaboration analysis using task-oriented conversation resources, encompassing related theories, coding schemes, tasks, and modeling approaches. We aim to address the question of how to utilize task-oriented human-human conversational data for collaboration analysis. We hope our review will serve as a practical resource and illuminate unexplored areas for future collaboration analysis.
Authors: Yunyi Zhang, Soji Adeshina, Sheng Guan, Ashwin Ganesh, Zhen Han, Vassilis N. Ioannidis, Huzefa Rangwala, George Karypis
Abstract: Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow performance gaps, existing approaches face significant challenges: manually defined task taxonomies cannot capture fine-grained capability distinctions, while monolithic routers struggle to differentiate subtle differences across diverse tasks. We propose a two-stage routing architecture that addresses these limitations through automated fine-grained task discovery and task-aware quality estimation. Our first stage employs graph-based clustering to discover latent task types and trains a classifier to assign prompts to discovered tasks. The second stage uses a mixture-of-experts architecture with task-specific prediction heads for specialized quality estimates. At inference, we aggregate predictions from both stages to balance task-level stability with prompt-specific adaptability. Evaluated on 10 benchmarks with 11 frontier models, our method consistently outperforms existing baselines and surpasses the strongest individual model while incurring less than half its cost.
Authors: Yulong Ye, Hongyuan Liang, Chao Jiang, Miqing Li, Tao Chen
Abstract: Configuration tuning for better performance is crucial in quality assurance. Yet, there has long been a mystery on tuners' effectiveness, due to the black-box nature of configurable systems. Prior efforts predominantly adopt static domain analysis (e.g., static taint analysis), which often lacks generalizability, or dynamic data analysis (e.g., benchmarking performance analysis), limiting explainability. In this work, we embrace Fitness Landscape Analysis (FLA) as a bridge between domain knowledge and difficulty of the tuning. We propose Domland, a two-pronged methodology that synergizes the spatial information obtained from FLA and domain-driven analysis to systematically capture the hidden characteristics of configuration tuning cases, explaining how and why a tuner might succeed or fail. This helps to better interpret and contextualize the behavior of tuners and inform tuner design. To evaluate Domland, we conduct a case study of nine software systems and 93 workloads, from which we reveal several key findings: (1) configuration landscapes are inherently system-specific, with no single domain factor (e.g., system area, programming language, or resource intensity) consistently shaping their structure; (2) the core options (e.g., pic-struct of x264), which control the main functional flows, exert a stronger influence on landscape ruggedness (i.e. the difficulty of tuning) compared to resource options (e.g., cpu-independent of x264); (3) Workload effects on landscape structure are not uniformly tied to type or scale. Both contribute to landscape variations, but their impact is system-dependent.
Authors: Seyed Mahdi B. Azad, Jasper Hoffmann, Iman Nematollahi, Hao Zhu, Abhinav Valada, Joschka Boedecker
Abstract: Forward-backward (FB) representations provide a powerful framework for learning the successor representation (SR) in continuous spaces by enforcing a low-rank factorization. However, a fundamental spectral mismatch often exists between the high-rank transition dynamics of continuous environments and the low-rank bottleneck of the FB architecture, making accurate low-rank representation learning difficult. In this work, we analyze temporal abstraction as a mechanism to mitigate this mismatch. By characterizing the spectral properties of the transition operator, we show that temporal abstraction acts as a low-pass filter that suppresses high-frequency spectral components. This suppression reduces the effective rank of the induced SR while preserving a formal bound on the resulting value function error. Empirically, we show that this alignment is a key factor for stable FB learning, particularly at high discount factors where bootstrapping becomes error-prone. Our results identify temporal abstraction as a principled mechanism for shaping the spectral structure of the underlying MDP and enabling effective long-horizon representations in continuous control.