Authors: Marko Djukanovi\'c, Nikola Balaban, Christian Blum, Aleksandar Kartelj, Sa\v{s}o D\v{z}eroski, \v{Z}iga Zebec
Abstract: This paper addresses the Variable Gapped Longest Common Subsequence (VGLCS) problem, a generalization of the classical LCS problem involving flexible gap constraints between consecutive solutions' characters. The problem arises in molecular sequence comparison, where structural distance constraints between residues must be respected, and in time-series analysis where events are required to occur within specified temporal delays. We propose a search framework based on the root-based state graph representation, in which the state space comprises a generally large number of rooted state subgraphs. To cope with the resulting combinatorial explosion, an iterative beam search strategy is employed, dynamically maintaining a global pool of promising candidate root nodes, enabling effective control of diversification across iterations. To exploit the search for high-quality solutions, several known heuristics from the LCS literature are utilized into the standalone beam search procedure. To the best of our knowledge, this is the first comprehensive computational study on the VGLCS problem comprising 320 synthetic instances with up to 10 input sequences and up to 500 characters. Experimental results show robustness of the designed approach over the baseline beam search in comparable runtimes.
Authors: Emily Reif, Claire Yang, Jared Hwang, Deniz Nazar, Noah Smith, Jeff Heer
Abstract: Users typically interact with and evaluate language models via single outputs, but each output is just one sample from a broad distribution of possible completions. This interaction hides distributional structure such as modes, uncommon edge cases, and sensitivity to small prompt changes, leading users to over-generalize from anecdotes when iterating on prompts for open-ended tasks. Informed by a formative study with researchers who use LMs (n=13) examining when stochasticity matters in practice, how they reason about distributions over language, and where current workflows break down, we introduce GROVE. GROVE is an interactive visualization that represents multiple LM generations as overlapping paths through a text graph, revealing shared structure, branching points, and clusters while preserving access to raw outputs. We evaluate across three crowdsourced user studies (N=47, 44, and 40 participants) targeting complementary distributional tasks. Our results support a hybrid workflow: graph summaries improve structural judgments such as assessing diversity, while direct output inspection remains stronger for detail-oriented questions.
Authors: Jiacheng Liang, Yao Ma, Tharindu Kumarage, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Aram Galstyan, Charith Peris
Abstract: Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical vulnerability: an imperfect Reward Model (RM) can become a single point of failure when it fails to penalize unsafe behaviors. While existing red-teaming approaches primarily target policy-level weaknesses, they overlook what we term systemic weaknesses cases where both the core LLM and the RM fail in tandem. We present ARES, a framework that systematically discovers and mitigates such dual vulnerabilities. ARES employs a ``Safety Mentor'' that dynamically composes semantically coherent adversarial prompts by combining structured component types (topics, personas, tactics, goals) and generates corresponding malicious and safe responses. This dual-targeting approach exposes weaknesses in both the core LLM and the RM simultaneously. Using the vulnerabilities gained, ARES implements a two-stage repair process: first fine-tuning the RM to better detect harmful content, then leveraging the improved RM to optimize the core model. Experiments across multiple adversarial safety benchmarks demonstrate that ARES substantially enhances safety robustness while preserving model capabilities, establishing a new paradigm for comprehensive RLHF safety alignment.
Authors: Marti\~no R\'ios-Garc\'ia, Nawaf Alampara, Chandan Gupta, Indrajeet Mandal, Sajid Mannan, Ali Asghar Aghajani, N. M. Anoop Krishnan, Kevin Maik Jablonka
Abstract: Large language model (LLM)-based systems are increasingly deployed to conduct scientific research autonomously, yet whether their reasoning adheres to the epistemic norms that make scientific inquiry self-correcting is poorly understood. Here, we evaluate LLM-based scientific agents across eight domains, spanning workflow execution to hypothesis-driven inquiry, through more than 25,000 agent runs and two complementary lenses: (i) a systematic performance analysis that decomposes the contributions of the base model and the agent scaffold, and (ii) a behavioral analysis of the epistemological structure of agent reasoning. We observe that the base model is the primary determinant of both performance and behavior, accounting for 41.4% of explained variance versus 1.5% for the scaffold. Across all configurations, evidence is ignored in 68% of traces, refutation-driven belief revision occurs in 26%, and convergent multi-test evidence is rare. The same reasoning pattern appears whether the agent executes a computational workflow or conducts hypothesis-driven inquiry. They persist even when agents receive near-complete successful reasoning trajectories as context, and the resulting unreliability compounds across repeated trials in epistemically demanding domains. Thus, current LLM-based agents execute scientific workflows but do not exhibit the epistemic patterns that characterize scientific reasoning. Outcome-based evaluation cannot detect these failures, and scaffold engineering alone cannot repair them. Until reasoning itself becomes a training target, the scientific knowledge produced by such agents cannot be justified by the process that generated it.
Authors: Kanishk Bakshi, Kathiravan Srinivasan
Abstract: This research investigates the performance and efficacy of machine learning models in stock prediction, comparing Artificial Neural Networks (ANNs), Quantum Qubit-based Neural Networks (QQBNs), and Quantum Qutrit-based Neural Networks (QQTNs). By outlining methodologies, architectures, and training procedures, the study highlights significant differences in training times and performance metrics across models. While all models demonstrate robust accuracies above 70%, the Quantum Qutrit-based Neural Network consistently outperforms with advantages in risk-adjusted returns, measured by the Sharpe ratio, greater consistency in prediction quality through the Information Coefficient, and enhanced robustness under varying market conditions. The QQTN not only surpasses its classical and qubit-based counterparts in multiple quantitative and qualitative metrics but also achieves comparable performance with significantly reduced training times. These results showcase the promising prospects of Quantum Qutrit-based Neural Networks in practical financial applications, where real-time processing is critical. By achieving superior accuracy, efficiency, and adaptability, the proposed models underscore the transformative potential of quantum-inspired approaches, paving the way for their integration into computationally intensive fields.
Authors: Christy Li, Sky CH-Wang, Andi Peng, Andreea Bobu
Abstract: As LM agents gain the ability to execute actions on real computer systems, we need ways to not only prevent harmful actions at scale but also effectively remediate harm when prevention fails. We formalize a solution to this neglected challenge in post-execution safeguards as harm recovery: the problem of optimally steering an agent from a harmful state back to a safe one in alignment with human preferences. We ground preference-aligned recovery through a formative user study that identifies valued recovery dimensions and produces a natural language rubric. Our dataset of 1,150 pairwise judgments reveals context-dependent shifts in attribute importance, such as preferences for pragmatic, targeted strategies over comprehensive long-term approaches. We operationalize these learned insights in a reward model, re-ranking multiple candidate recovery plans generated by an agent scaffold at test time. To evaluate recovery capabilities systematically, we introduce BackBench, a benchmark of 50 computer-use tasks that test an agent's ability to recover from harmful states. Human evaluation shows our reward model scaffold yields higher-quality recovery trajectories than base agents and rubric-based scaffolds. Together, these contributions lay the foundation for a new class of agent safety methods -- ones that confront harm not only by preventing it, but by navigating its aftermath with alignment and intent.
Authors: Mina Gabriel, Pei Wang
Abstract: Large language models (LLMs) are highly capable at language generation, but they remain unreliable when reasoning requires explicit symbolic structure, multi-step inference, and interpretable uncertainty. This paper presents a neuro-symbolic framework for translating natural-language reasoning problems into executable formal representations using first-order logic (FOL) and Narsese, the language of the Non-Axiomatic Reasoning System (NARS). To support this direction, we introduce NARS-Reasoning-v0.1, a benchmark of natural-language reasoning problems paired with FOL forms, executable Narsese programs, and three gold labels: True, False, and Uncertain. We develop a deterministic compilation pipeline from FOL to executable Narsese and validate retained examples through runtime execution in OpenNARS for Applications (ONA), ensuring that the symbolic targets are not only syntactically well formed but also behaviorally aligned with the intended answer. We further present Language-Structured Perception (LSP), a formulation in which an LLM is trained to produce reasoning-relevant symbolic structure rather than only a final verbal response. As an initial proof of concept, we also train and release a Phi-2 LoRA adapter on NARS-Reasoning-v0.1 for three-label reasoning classification, showing that the benchmark can support supervised adaptation in addition to executable evaluation. Overall, the paper positions executable symbolic generation and execution-based validation as a practical path toward more reliable neuro-symbolic reasoning systems.
Authors: Zhonghao Zhan, Huichi Zhou, Zhenhao Li, Peiyuan Jing, Krinos Li, Hamed Haddadi
Abstract: Tool-integrated agents are deployed on the premise that external tools ground their outputs in reality. Yet this very reliance creates a critical attack surface. Current evaluations benchmark capability in benign settings, asking "can the agent use tools correctly" but never "what if the tools lie". We identify this Trust Gap: agents are evaluated for performance, not for skepticism. We formalize this vulnerability as Adversarial Environmental Injection (AEI), a threat model where adversaries compromise tool outputs to deceive agents. AEI constitutes environmental deception: constructing a "fake world" of poisoned search results and fabricated reference networks around unsuspecting agents. We operationalize this via POTEMKIN, a Model Context Protocol (MCP)-compatible harness for plug-and-play robustness testing. We identify two orthogonal attack surfaces: The Illusion (breadth attacks) poison retrieval to induce epistemic drift toward false beliefs, while The Maze (depth attacks) exploit structural traps to cause policy collapse into infinite loops. Across 11,000+ runs on five frontier agents, we find a stark robustness gap: resistance to one attack often increases vulnerability to the other, demonstrating that epistemic and navigational robustness are distinct capabilities.
Authors: George Koomullil
Abstract: We present a formally verified framework for patent analysis as a hybrid AI + Lean 4 pipeline. The DAG-coverage core (Algorithm 1b) is fully machine-verified once bounded match scores are fixed. Freedom-to-operate, claim-construction sensitivity, cross-claim consistency, and doctrine-of-equivalents analyses are formalized at the specification level with kernel-checked candidate certificates. Existing patent-analysis approaches rely on manual expert analysis (slow, non-scalable) or ML/NLP methods (probabilistic, opaque, non-compositional). To our knowledge, this is the first framework that applies interactive theorem proving based on dependent type theory to intellectual property analysis. Claims are encoded as DAGs in Lean 4, match strengths as elements of a verified complete lattice, and confidence scores propagate through dependencies via proven-correct monotone functions. We formalize five IP use cases (patent-to-product mapping, freedom-to-operate, claim construction sensitivity, cross-claim consistency, doctrine of equivalents) via six algorithms. Structural lemmas, the coverage-core generator, and the closed-path identity coverage = W_cov are machine-verified in Lean 4. Higher-level theorems for the other use cases remain informal proof sketches, and their proof-generation functions are architecturally mitigated (untrusted generators whose outputs are kernel-checked and sorry-free axiom-audited). Guarantees are conditional on the ML layer: they certify mathematical correctness of computations downstream of ML scores, not the accuracy of the scores themselves. A case study on a synthetic memory-module claim demonstrates weighted coverage and construction-sensitivity analysis. Validation against adjudicated cases is future work.
Authors: Bo Deng
Abstract: In this paper, we introduce a new concept called Artificial Special Intelligence by which Machine Learning models for the classification problem can be trained error-free, thus acquiring the capability of not making repeated mistakes. The method is applied to 18 MedMNIST biomedical datasets. Except for three datasets, which suffer from the double-labeling problem, all are trained to perfection.
Authors: Daniel Shepard, Robin Salimans
Abstract: Existing AI benchmarks for software automation rarely combine cross-application coordination, autonomous API discovery, and policy adherence. Real business workflows demand all three: a single task may span a CRM, inbox, calendar, and messaging platform - requiring the agent to find the right endpoints, follow a policy document, and write correct data to each system. To address this gap, we introduce AutomationBench, a benchmark for evaluating AI agents on cross-application workflow orchestration via REST APIs. Drawing on real workflow patterns from Zapier's platform, tasks span Sales, Marketing, Operations, Support, Finance, and HR domains. Agents must discover relevant endpoints themselves, follow layered business rules, and navigate environments with irrelevant and sometimes misleading records. Grading is programmatic and end-state only: whether the correct data ended up in the right systems. Even the best frontier models currently score below 10%. AutomationBench provides a challenging, realistic measure of where current models stand relative to the agentic capabilities businesses actually need.
Authors: Cristina Garbacea, Heran Wang, Chenhao Tan
Abstract: With the rise in capabilities of large language models (LLMs) and their deployment in real-world tasks, evaluating LLM alignment with human preferences has become an important challenge. Current benchmarks average preferences across all users to compute aggregate ratings, overlooking individual user preferences when establishing model rankings. Since users have varying preferences in different contexts, we call for personalized LLM benchmarks that rank models according to individual needs. We compute personalized model rankings using ELO ratings and Bradley-Terry coefficients for 115 active Chatbot Arena users and analyze how user query characteristics (topics and writing style) relate to LLM ranking variations. We demonstrate that individual rankings of LLM models diverge dramatically from aggregate LLM rankings, with Bradley-Terry correlations averaging only $\rho = 0.04$ (57\% of users show near-zero or negative correlation) and ELO ratings showing moderate correlation ($\rho = 0.43$). Through topic modeling and style analysis, we find users exhibit substantial heterogeneity in topical interests and communication styles, influencing their model preferences. We further show that a compact combination of topic and style features provides a useful feature space for predicting user-specific model rankings. Our results provide strong quantitative evidence that aggregate benchmarks fail to capture individual preferences for most users, and highlight the importance of developing personalized benchmarks that rank LLM models according to individual user preferences.
Authors: Yeonjun In, Wonjoong Kim, Sangwu Park, Chanyoung Park
Abstract: Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks but often generate harmful responses to malicious user queries. This paper investigates the underlying cause of these safety risks and shows that the issue lies in the reasoning structure itself. Based on this insight, we claim that effective safety alignment can be achieved by altering the reasoning structure. We propose AltTrain, a simple yet effective post training method that explicitly alters the reasoning structure of LRMs. AltTrain is both practical and generalizable, requiring no complex reinforcement learning (RL) training or reward design, only supervised finetuning (SFT) with a lightweight 1K training examples. Experiments across LRM backbones and model sizes demonstrate strong safety alignment, along with robust generalization across reasoning, QA, summarization, and multilingual setting.
Authors: Ahmed G. A. H Ahmed, C. Okan Sakar
Abstract: This paper introduces DW-Bench, a new benchmark that evaluates large language models (LLMs) on graph-topology reasoning over data warehouse schemas, explicitly integrating both foreign-key (FK) and data-lineage edges. The benchmark comprises 1,046 automatically generated, verifiably correct questions across five schemas. Experiments show that tool-augmented methods substantially outperform static approaches but plateau on hard compositional subtypes.
Authors: Xiachong Feng, Yi Jiang, Xiaocheng Feng, Deyi Yin, Libo Qin, Yangfan Ye, Lei Huang, Weitao Ma, Yuxuan Gu, Chonghan Qin, Bing Qin, Lingpeng Kong
Abstract: Social intelligence, the ability to navigate complex interpersonal interactions, presents a fundamental challenge for language agents. Training such agents via reinforcement learning requires solving the credit assignment problem: determining how individual utterances contribute to multi-turn dialogue outcomes. Existing approaches directly employ language models to distribute episode-level rewards, yielding attributions that are retrospective and lack theoretical grounding. We propose SAVOIR (ShApley Value fOr SocIal RL), a novel principled framework grounded in cooperative game theory. Our approach combines two complementary principles: expected utility shifts evaluation from retrospective attribution to prospective valuation, capturing an utterance's strategic potential for enabling favorable future trajectories; Shapley values ensure fair credit distribution with axiomatic guarantees of efficiency, symmetry, and marginality. Experiments on the SOTOPIA benchmark demonstrate that SAVOIR achieves new state-of-the-art performance across all evaluation settings, with our 7B model matching or exceeding proprietary models including GPT-4o and Claude-3.5-Sonnet. Notably, even large reasoning models consistently underperform, suggesting social intelligence requires qualitatively different capabilities than analytical reasoning.
Authors: Santosh Ganji
Abstract: A major challenge for niche scientific and technical domains in leveraging coding agents is the lack of access to up-to-date, domain- specific knowledge. Foundational models often demonstrate limited reasoning capabilities in specialized fields and cannot inherently incorporate knowledge that evolves through ongoing research and experimentation. Materials scientists exploring novel compounds, communication engineers designing and evaluating new protocols, and bioengineering researchers conducting iterative experiments all face this limitation. These experts typically lack the resources to fine-tune large models or continuously embed new findings, creating a barrier to adopting AI-driven coding agents. To address this, we introduce a framework that gives coding agents instanta- neous access to research repositories and technical documentation, enabling real-time, context-aware operation. Our open-source im- plementation allows users to upload documents via doc-search.dev and includes zed-fork, which enforces domain-specific rules and workflows. Together, these tools accelerate the integration of coding agents into specialized scientific and technical workflows
Authors: David Billington
Abstract: Defeasible statements are statements that are likely, or probable, or usually true, but may occasionally be false. Plausible reasoning makes conclusions from statements that are either facts or defeasible statements without using numbers. So there are no probabilities or suchlike involved. Seventeen principles of logics that do plausible reasoning are suggested and several important plausible reasoning examples are considered. There are 14 necessary principles and 3 desirable principles, one of which is not formally stated. A first-order logic, called Plausible Logic (PL), is defined that satisfies all but two of the desirable principles and reasons correctly with all the examples. As far as we are aware, this is the only such logic. PL has 8 reasoning algorithms because, from a given plausible reasoning situation, there are different sensible conclusions. This article is a condensation of my book `Plausible Reasoning and Plausible Logic' (PRPL), which is to be submitted. Each section of this article corresponds to a chapter in PRPL, and vice versa. The proofs of all the results are in PRPL, so they are omitted in this article.
Authors: Kai Xi, Stephen Gould, Sylvie Thi\'ebaux
Abstract: Efficient construction of models capturing the preconditions and effects of actions is essential for applying AI planning in real-world domains. Extensive prior work has explored learning such models from high-level descriptions of state and/or action sequences. In this paper, we tackle a more challenging setting: learning lifted action models from sequences of state images, without action observation. We propose a deep learning framework that jointly learns state prediction, action prediction, and a lifted action model. We also introduce a mixed-integer linear program (MILP) to prevent prediction collapse and self-reinforcing errors among predictions. The MILP takes the predicted states, actions, and action model over a subset of traces and solves for logically consistent states, actions, and action model that are as close as possible to the original predictions. Pseudo-labels extracted from the MILP solution are then used to guide further training. Experiments across multiple domains show that integrating MILP-based correction helps the model escape local optima and converge toward globally consistent solutions.
Authors: Yishu Wei, Yi Lin, Adam Flanders, George Shih, Yifan Peng
Abstract: Accurate disease classification from radiology reports is essential for many applications. While supervised fine-tuning (SFT) of lightweight LLMs improves accuracy, it can degrade reasoning. We propose a two-stage approach: SFT on disease labels followed by Group Relative Policy Optimization (GRPO) to refine predictions by optimizing accuracy and format without reasoning supervision. Across three radiologist-annotated datasets, SFT outperformed baselines and GRPO further improved classification and enhanced reasoning recall and comprehensiveness.
Authors: Shashank Sharma, Janina Hoffmann, Vinay Namboodiri
Abstract: We introduce Options LLM (OLLM), a simple, general method that replaces the single next-token prediction of standard LLMs with a \textit{set of learned options} for the next token, indexed by a discrete latent variable. Instead of relying on temperature or sampling heuristics to induce diversity, OLLM models variation explicitly: a small latent space parametrizes multiple plausible next-token options which can be selected or searched by a downstream policy. Architecturally, OLLM is a lightweight "plug-in" that inserts two layers: an encoder and a decoder, before the output head, allowing almost any pretrained LLM to be converted with minimal additional parameters. We apply OLLM to a 1.7B-parameter backbone (only $1.56\%$ of parameters trainable) trained on OpenMathReasoning and evaluated on OmniMath. The SOTA LoRA-adapted baselines peak at $51\%$ final answer correctness, while OLLM's option set allows up to $\sim 70\%$ under optimal latent selection. We then train a compact policy in the latent space that emits latents to control generation. Operating in a low-dimensional option space makes reward optimization far more sample-efficient and substantially reduces common misalignments (e.g., language switching or degenerate reasoning), as the policy is constrained to options learned during SFT. Crucially, this alignment arises from model structure rather than additional KL or handcrafted alignment losses. Our results demonstrate that optionized next-token modeling enhances controllability, robustness, and efficiency in math reasoning, and highlight latent-space policy learning as a promising direction for reinforcement learning in LLMs.
Authors: Dahyun Jung, Jaewook Lee, Heuiseok Lim
Abstract: Large language models (LLMs) require frequent knowledge updates to reflect changing facts and mitigate hallucinations. To meet this demand, lifelong knowledge editing has emerged as a continual approach to modify specific pieces of knowledge without retraining the entire model. Existing parameter editing methods struggle with stability during sequential edits due to catastrophic forgetting. While retrieval-based approaches are proposed to alleviate this issue, their applicability remains limited across various datasets because of high training costs. To address these limitations and enhance scalability in lifelong settings, we propose LightEdit. Our framework first selects relevant knowledge from retrieved information to modify the query effectively. It then incorporates a decoding strategy to suppress the model's original knowledge probabilities, thereby enabling efficient edits based on the selected information. Extensive experiments on ZSRE, Counterfact, and RIPE benchmarks demonstrate that LightEdit outperforms existing lifelong knowledge editing methods. Furthermore, by minimizing training costs, LightEdit achieves cost-effective scalability, enabling easy adaptation to various datasets.
Authors: Masaki Uto
Abstract: Automated essay scoring (AES) is commonly evaluated on public benchmarks using quadratic weighted kappa (QWK). However, because benchmark labels are assigned by human raters and inevitably contain scoring errors, it remains unclear both what QWK is theoretically attainable and what level is practically sufficient for deployment. We therefore derive two dataset-specific QWK ceilings based on the reliability concept in classical test theory, which can be estimated from standard two-rater benchmarks without additional annotation. The first is the theoretical ceiling: the maximum QWK that an ideal AES model that perfectly predicts latent true scores can achieve under label noise. The second is the human-like ceiling: the QWK attainable by an AES model with human-level scoring error, providing a practical target when AES is intended to replace a single human rater. We further show that human--human QWK, often used as a ceiling reference, can underestimate the true ceiling. Simulation experiments validate the proposed ceilings, and experiments on real benchmarks illustrate how they clarify the current performance and remaining headroom of modern AES models.
Authors: Zhao Wang, Max Xiong, Jianxun Lian, Zhicheng Dou
Abstract: The rapid advancement and widespread adoption of Large Language Models (LLMs) have elevated the need for reliable AI-generated content (AIGC) detection, which remains challenging as models evolve. We introduce AIGC-text-bank, a comprehensive multi-domain dataset with diverse LLM sources and authorship scenarios, and propose REVEAL, a detection framework that generates interpretable reasoning chains before classification. Our approach uses a two-stage training strategy: supervised fine-tuning to establish reasoning capabilities, followed by reinforcement learning to improve accuracy, improve logical consistency, and reduce hallucinations. Extensive experiments show that REVEAL achieves state-of-the-art performance across multiple benchmarks, offering a robust and transparent solution for AIGC detection. The project is open-source at https://aka.ms/reveal
URLs: https://aka.ms/reveal
Authors: Zhiqin Yang, Zhenyuan Zhang, Xianzhang Jia, Jun Song, Wei Xue, Yonggang Zhang, Yike Guo
Abstract: Current AI agent frameworks have made remarkable progress in automating individual tasks, yet all existing systems serve a single user. Human productivity rests on the social and organizational relationships through which people coordinate, negotiate, and delegate. When agents move beyond performing tasks for one person to representing that person in collaboration with others, the infrastructure for cross-user agent collaboration is entirely absent, let alone the governance mechanisms needed to secure it. We argue that the next frontier for AI agents lies not in stronger individual capability, but in the digitization of human collaborative relationships. To this end, we propose a human-symbiotic agent paradigm. Each user owns a permanently bound agent system that collaborates on the owner's behalf, forming a network whose nodes are humans rather than agents. This paradigm rests on three governance primitives. A layered identity architecture separates a Manager Agent from multiple context-specific Identity Agents; the Manager Agent holds global knowledge but is architecturally isolated from external communication. Scoped authorization enforces per-identity access control and escalates boundary violations to the owner. Action-level accountability logs every operation against its owner's identity and authorization, ensuring full auditability. We instantiate this paradigm in ClawNet, an identity-governed agent collaboration framework that enforces identity binding and authorization verification through a central orchestrator, enabling multiple users to collaborate securely through their respective agents.
Authors: Yadong Li, Guoxin Wu, Haiping Hou, Biye Li
Abstract: Full-duplex speech interaction, as the most natural and intuitive mode of human communication, is driving artificial intelligence toward more human-like conversational systems. Traditional cascaded speech processing pipelines suffer from critical limitations, including accumulated latency, information loss, and error propagation across modules. To address these issues, recent efforts focus on the end-to-end audio large language models (LLMs) like GPT-4o, which primarily unify speech understanding and generation task. However, most of these models are inherently half-duplex, and rely on a suite of separate, task-specific front-end components, such as voice activity detection (VAD) and turn-taking detection (TD). In our development of speech assistant, we observed that optimizing the speech front-end is equally crucial as advancing the back-end unified model for achieving seamless, responsive interactions. To bridge this gap, we propose the first unified audio front-end LLM (UAF) tailored for full-duplex speech systems. Our model reformulates diverse audio front-end tasks into a single auto-regressive sequence prediction problem, including VAD, TD, speaker recognition (SR), automatic speech recognition (ASR) and question answer (QA). It takes streaming fixed-duration audio chunk (e.g., 600 ms) as input, leverages a reference audio prompt to anchor the target speaker at the beginning, and regressively generates discrete tokens encoding both semantic content and system-level state controls (e.g., interruption signals). Experiments demonstrate that our model achieves leading performance across multiple audio front-end tasks and significantly enhances response latency and interruption accuracy in real-world interaction scenarios.
Authors: Shuo Feng, Runlin Zhou, Yuyang Li, Guangcan Liu
Abstract: Industrial surface defect detection often suffers from limited defect samples, severe long-tailed distributions, and difficulties in accurately localizing subtle defects under complex backgrounds. To address these challenges, this paper proposes an unsupervised defect detection method that integrates a Denoising Diffusion Probabilistic Model (DDPM) with an asymmetric teacher-student architecture. First, at the data level, the DDPM is trained solely on normal samples. By introducing constant-variance Gaussian perturbations and Perlin noise-based masks, high-fidelity and physically consistent defect samples along with pixel-level annotations are generated, effectively alleviating the data scarcity problem. Second, at the model level, an asymmetric dual-stream network is constructed. The teacher network provides stable representations of normal features, while the student network reconstructs normal patterns and amplifies discrepancies between normal and anomalous regions. Finally, a joint optimization strategy combining cosine similarity loss and pixel-wise segmentation supervision is adopted to achieve precise localization of subtle defects. Experimental results on the MVTecAD dataset show that the proposed method achieves 98.4\% image-level AUROC and 98.3\% pixel-level AUROC, significantly outperforming existing unsupervised and mainstream deep learning methods. The proposed approach does not require large amounts of real defect samples and enables accurate and robust industrial defect detection and localization. \keywords{Industrial defect detection \and diffusion models \and data generation \and teacher-student architecture \and pixel-level localization}
Authors: Suhaib Abdurahman, Etsuko Ishii, Katerina Margatina, Divya Bhargavi, Monica Sunkara, Yi Zhang
Abstract: LLM-based multi-agent systems (MAS) show promise on complex tasks but remain prone to coordination failures such as goal drift, error cascades, and misaligned behaviors. We propose Explicit Trait Inference (ETI), a psychologically grounded method for improving coordination. ETI enables agents to infer and track partner characteristics along two established psychological dimensions--warmth (e.g., trust) and competence (e.g., skill)--from interaction histories to guide decisions. We evaluate ETI in controlled settings (economic games), where it reduces payoff loss by 45-77%, and in more realistic, complex multi-agent settings (MultiAgentBench), where it improves performance by 3-29% depending on the scenario and model, relative to a CoT baseline. Additional analysis shows that gains are closely linked to trait inference: ETI profiles predict agents' actions, and informative profiles drive improvements. These results highlight ETI as a lightweight and robust mechanism for improving coordination in diverse multi-agent settings, and provide the first systematic evidence that LLM agents can (i) reliably infer others' traits from interaction histories and (ii) leverage structured awareness of others' traits for coordination.
Authors: Mikako Bito, Keita Nishimoto, Kimitaka Asatani, Ichiro Sakata
Abstract: The conformity bias exhibited by large language models (LLMs) can pose a significant challenge to decision-making in LLM-based multi-agent systems (LLM-MAS). While many prior studies have treated "conformity" simply as a matter of opinion change, this study introduces the social psychological distinction between informational conformity and normative conformity in order to understand LLM conformity at the mechanism level. Specifically, we design new tasks to distinguish between informational conformity, in which participants in a discussion are motivated to make accurate judgments, and normative conformity, in which participants are motivated to avoid conflict or gain acceptance within a group. We then conduct experiments based on these task settings. The experimental results show that, among the six LLMs evaluated, up to five exhibited tendencies toward not only informational conformity but also normative conformity. Furthermore, intriguingly, we demonstrate that by manipulating subtle aspects of the social context, it may be possible to control the target toward which a particular LLM directs its normative conformity. These findings suggest that decision-making in LLM-MAS may be vulnerable to manipulation by a small number of malicious users. In addition, through analysis of internal vectors associated with informational and normative conformity, we suggest that although both behaviors appear externally as the same form of "conformity," they may in fact be driven by distinct internal mechanisms. Taken together, these results may serve as an initial milestone toward understanding how "norms" are implemented in LLMs and how they influence group dynamics.
Authors: Ali Al-Kaswan, Maksim Plotnikov, Maxim H\'ajek, Roland V\'izner, Arie van Deursen, Maliheh Izadi
Abstract: Large Language Model (LLM) agents are increasingly proposed for autonomous cybersecurity tasks, but their capabilities in realistic offensive settings remain poorly understood. We present DeepRed, an open-source benchmark for evaluating LLM-based agents on realistic Capture The Flag (CTF) challenges in isolated virtualized environments. DeepRed places an agent in a Kali attacker environment with terminal tools and optional web search, connected over a private network to a target challenge, and records full execution traces for analysis. To move beyond binary solved/unsolved outcomes, we introduce a partial-credit scoring method based on challenge-specific checkpoints derived from public writeups, together with an automated summarise-then-judge labelling pipeline for assigning checkpoint completion from logs. Using DeepRed, we benchmark ten commercially accessible LLMs on ten VM-based CTF challenges spanning different challenge categories. The results indicate that current agents remain limited: the best model achieves only 35% average checkpoint completion, performing strongest on common challenge types and weakest on tasks requiring non-standard discovery and longer-horizon adaptation.
Authors: Anjie Qiu, Donglin Wang, Sanket Partani, Andreas Weinand, Hans D. Schotten
Abstract: The emergence of sixth-generation (6G) technologies has introduced new challenges and opportunities for machine learning (ML) applications in Internet of Things (IoT) networks, particularly concerning energy efficiency. As model training and data transmission contribute significantly to energy consumption, optimizing these processes has become critical for sustainable system design. This study first conduct analysis on the energy consumption model for both centralized and decentralized architecture and then presents a testbed deployed within the German railway infrastructure, leveraging sensor data for ML-based predictive maintenance. A comparative analysis of distributed versus Centralized Learning (CL) architectures reveals that distributed models maintain competitive predictive accuracy (~90%) while reducing overall electricity consumption by up to 70%. These findings underscore the potential of distributed ML to improve energy efficiency in real-world IoT deployments, particularly by mitigating transmission-related energy costs.
Authors: Ziyang Wang, Jiangfeng Xiao, Chuan Xiao, Ruoxiang Li, Rui Mao, Jianbin Qin
Abstract: Large language models (LLMs) are expensive to serve because model parameters, attention computation, and KV caches impose substantial memory and latency costs. We present GRASPrune, a structured pruning framework applied after pretraining that jointly prunes FFN channels and KV head groups under a single global budget. Instead of learning importance scores without constraints and applying the budget only after training, GRASPrune learns lightweight gate scores with a projected straight-through estimator that enforces a hard mask satisfying the budget at every step while keeping the backbone weights frozen. After the mask is fixed, we calibrate scaling factors on the retained units to mitigate scale mismatch caused by pruning, and fold these factors into the pruned weights to obtain a smaller dense checkpoint with no extra parameters at inference. On LLaMA-2-7B, GRASPrune removes 50% of parameters and achieves 12.18 perplexity on WikiText-2 while maintaining competitive average zero-shot accuracy on five benchmarks, using four epochs on 512 unlabeled calibration sequences on a single NVIDIA A100 80GB GPU without any full model fine-tuning.
Authors: Vasundra Srininvasan
Abstract: Long-horizon enterprise agents make high-stakes decisions (loan underwriting, claims adjudication, clinical review, prior authorization) under lossy memory, multi-step reasoning, and binding regulatory constraints. Current evaluation reports a single task-success scalar that conflates distinct failure modes and hides whether an agent is aligned with the standards its deployment environment requires. We propose that long-horizon decision behavior decomposes into four orthogonal alignment axes, each independently measurable and failable: factual precision (FRP), reasoning coherence (RCS), compliance reconstruction (CRR), and calibrated abstention (CAR). CRR is a novel regulatory-grounded axis; CAR is a measurement axis separating coverage from accuracy. We exercise the decomposition on a controlled benchmark (LongHorizon-Bench) covering loan qualification and insurance claims adjudication with deterministic ground-truth construction. Running six memory architectures, we find structure aggregate accuracy cannot see: retrieval collapses on factual precision; schema-anchored architectures pay a scaffolding tax; plain summarization under a fact-preservation prompt is a strong baseline on FRP, RCS, EDA, and CRR; and all six architectures commit on every case, exposing a decisional-alignment axis the field has not targeted. The decomposition also surfaced a pre-registered prediction of our own, that summarization would fail factual recall, which the data reversed at large magnitude, an axis-level reversal aggregate accuracy would have hidden. Institutional alignment (regulatory reconstruction) and decisional alignment (calibrated abstention) are under-represented in the alignment literature and become load-bearing once decisions leave the laboratory. The framework transfers to any regulated decisioning domain via two steps: build a fact schema, and calibrate the CRR auditor prompt.
Authors: Kyuhee Kim, Auguste Poiroux, Antoine Bosselut
Abstract: Formal verification guarantees proof validity but not formalization faithfulness. For natural-language logical reasoning, where models construct axiom systems from scratch without library constraints, this gap between valid proofs and faithful translations is especially acute. We investigate whether frontier models exploit this gap when generating Lean 4 proofs, a behavior we term formalization gaming. We evaluate GPT-5 and DeepSeek-R1 on 303 first-order logic problems (203 from FOLIO, 100 from Multi-LogiEval), comparing unified generation against a two-stage pipeline that separates formalization from proving. Despite compilation rates of 87-99%, we find no evidence of systematic gaming in unified generation: models prefer reporting failure over forcing proofs, even under prompting designed to encourage it. However, unfaithfulness that evades our detection signals may still occur. The two-stage pipeline reveals two distinct modes of unfaithfulness: GPT-5 fabricates axioms during proof generation, a reactive fallback detectable via cross-stage comparison, while DeepSeek-R1 mistranslates premises during formalization, producing internally consistent outputs that evade detection entirely. These findings show that high compilation rates or accuracies should not be equated with faithful reasoning. Code and data are available at https://github.com/koreankiwi99/formalization-gaming.
Authors: Jianzhi Yan, Le Liu, Buzhou Tang, Yang Xiang, Dongning Sun, Zhiming Li
Abstract: Large language models (LLMs) have achieved substantial advances in logical reasoning, yet they continue to lag behind human-level performance. In-context learning provides a viable solution that boosts the model's performance via prompting its input with expert-curated, in-domain exemplars. However, in many real-world, expertise-scarce domains, such as low-resource scientific disciplines, emerging biomedical subfields, or niche legal jurisdictions, such high-quality in-domain demonstrations are inherently limited or entirely unavailable, thereby constraining the general applicability of these approaches. To mitigate this limitation, recent efforts have explored the retrieval of cross-domain samples as surrogate in-context demonstrations. Nevertheless, the resulting gains remain modest. This is largely attributable to the pronounced domain shift between source and target distributions, which impedes the model's ability to effectively identify and exploit underlying shared structures or latent reasoning patterns. Consequently, when relying solely on raw textual prompting, LLMs struggle to abstract and transfer such cross-domain knowledge in a robust and systematic manner. To address these issues, we propose CoDA, which employs a lightweight adapter to directly intervene in the intermediate hidden states. By combining feature-based distillation of CoT-enriched reference representations with Maximum Mean Discrepancy (MMD) for kernelized distribution matching, our method aligns the latent reasoning representation of the source and target domains. Extensive experimental results on multiple logical reasoning tasks across various model families validate the efficacy of CoDA by significantly outperforming the previous state-of-the-art baselines by a large margin.
Authors: Beining Wu, Fuyou Mao, Jiong Lin, Cheng Yang, Jiaxuan Lu, Yifu Guo, Siyu Zhang, Yifan Wu, Ying Huang, Fu Li
Abstract: Generative engines (GEs) are reshaping information access by replacing ranked links with citation-grounded answers, yet current Generative Engine Optimization (GEO) methods optimize each instance in isolation, unable to accumulate or transfer effective strategies across tasks and engines. We reframe GEO as a strategy learning problem and propose MAGEO, a multi-agent framework in which coordinated planning, editing, and fidelity-aware evaluation serve as the execution layer, while validated editing patterns are progressively distilled into reusable, engine-specific optimization skills. To enable controlled assessment, we introduce a Twin Branch Evaluation Protocol for causal attribution of content edits and DSV-CF, a dual-axis metric that unifies semantic visibility with attribution accuracy. We further release MSME-GEO-Bench, a multi-scenario, multi-engine benchmark grounded in real-world queries. Experiments on three mainstream engines show that MAGEO substantially outperforms heuristic baselines in both visibility and citation fidelity, with ablations confirming that engine-specific preference modeling and strategy reuse are central to these gains, suggesting a scalable learning-driven paradigm for trustworthy GEO. Code is available at https://github.com/Wu-beining/MAGEO
Authors: Yuli Chen, Shuhao Zhang, Fanshen Meng, Bo Cheng, Jiale Han, Qiang Tong, Xiulei Liu
Abstract: Depth pruning improves the deployment efficiency of large language models (LLMs) by identifying and removing redundant layers. A widely accepted standard for this identification process is to measure the similarity between layers using cosine distance. However, we find that methods relying solely on this one-dimensional heuristic can exhibit unpredictable performance and even catastrophic collapse across different architectures. To address this issue, we propose SimDiff, a novel layer importance criterion that jointly evaluates layers from two orthogonal perspectives: representational similarity and transformation difference. The difference is quantified using two distinct metrics: MSSD, which is sensitive to outliers and identifies layers that make decisive corrections, and MASD, which robustly measures a layer's average contribution. Extensive experiments on multiple models ranging from 0.5B to 13B parameters demonstrate that SimDiff significantly outperforms state-of-the-art baselines across various pruning ratios. Notably, our method retains over 91% of LLaMA2-7B's performance at a 25% pruning ratio and achieves up to a 1.49x inference speedup when pruning 12 layers on LLaMA3.1-8B. We also show that pruned models can be effectively recovered with minimal fine-tuning.
Authors: Mihir Shriniwas Arya, Avinash Anish, Aditya Ranjan
Abstract: Social deduction games such as Mafia present a unique AI challenge: players must reason under uncertainty, interpret incomplete and intentionally misleading information, evaluate human-like communication, and make strategic elimination decisions. Unlike deterministic board games, success in Mafia depends not on perfect information or brute-force search, but on inference, memory, and adaptability in the presence of deception. This work presents the design and evaluation of Revac-8, an AI agent developed for the Social Deduction track of the MindGames Arena competition, where it achieved first place. The final agent evolved from a simple two-stage reasoning system into a multi-module architecture that integrates memory-based player profiling, social-graph analysis of accusations and defenses, and dynamic tone selection for communication. These results highlight the importance of structured memory and adaptive communication for achieving strong performance in high-stakes social environments.
Authors: Farbod Zorriassatine, Ahmad Lotfi
Abstract: Agentic AI, with goal-directed, proactive, and autonomous decision-making capabilities, offers a compelling opportunity to address movement-related risks in human activity, including the persistent hazard of falls among elderly populations. Despite numerous approaches to fall mitigation through fall prediction and detection, existing systems have not yet functioned as universal solutions across care pathways and safety-critical environments. This is largely due to limitations in consistently handling real-world complexity, particularly poor context awareness, high false alarm rates, environmental noise, and data scarcity. We argue that fall detection and fall prediction can usefully be formulated as anomaly detection problems and more effectively addressed through an agentic AI system. More broadly, this perspective enables the early identification of subtle deviations in movement patterns associated with increased risk, whether arising from age-related decline, fatigue, or environmental factors. While technical requirements for immediate deployment are beyond the scope of this paper, we propose a conceptual framework that highlights potential value. This framework promotes a well-orchestrated approach to risk management by dynamically selecting relevant tools and integrating them into adaptive decision-making workflows, rather than relying on static configurations tailored to narrowly defined scenarios.
Authors: Zhihong Zhang, Jie Zhao, Xiaojian Huang, Jin Xu, Zhuodong Luo, Xin Liu, Jiansheng Wei, Xuejin Chen
Abstract: Multimodal reward models (MRMs) play a crucial role in aligning Multimodal Large Language Models (MLLMs) with human preferences. Training a good MRM requires high-quality multimodal preference data. However, existing preference datasets face three key challenges: lack of granularity in preference strength, textual style bias, and unreliable preference signals. Besides, existing open-source multimodal preference datasets suffer from substantial noise, yet there is a lack of effective and scalable curation methods to enhance their quality. To address these limitations, we propose \textbf{DT2IT-MRM}, which integrates a \textbf{D}ebiased preference construction pipeline, a novel reformulation of text-to-image (\textbf{T2I}) preference data, and an \textbf{I}terative \textbf{T}raining framework that curates existing multimodal preference datasets for \textbf{M}ultimodal \textbf{R}eward \textbf{M}odeling. Our experimental results show that DT2IT-MRM achieves new \textbf{state-of-the-art} overall performance on three major benchmarks: VL-RewardBench, Multimodal RewardBench, and MM-RLHF-RewardBench.
Authors: Syed Sajid Ullah, Amir Khan
Abstract: Construction workers are highly vulnerable to heat stress, yet tools that translate real-time physiological data into actionable safety intelligence remain scarce. This study addresses this gap by developing and evaluating deep learning models, specifically a baseline Long Short-Term Memory (LSTM) network and an attention-based LSTM, to predict heat stress among 19 workers in Saudi Arabia. Using Garmin Vivosmart 5 smartwatches to monitor metrics such as heart rate, HRV, and oxygen saturation, the attention-based model outperformed the baseline, achieving 95.40% testing accuracy and significantly reducing false positives and negatives. With precision, recall, and F1 scores of 0.982, this approach not only improves predictive performance but also offers interpretable results suitable for integration into IoT-enabled safety systems and BIM dashboards, advancing proactive, informatics-driven safety management in the construction industry.
Authors: Juliusz Janicki, Savvas Chamezopoulos, Evangelos Kanoulas, Georgios Tsatsaronis
Abstract: Large Language Models (LLMs) utilize large amounts of data for their training, some of which may come from copyrighted sources. Membership Inference Attacks (MIA) aim to detect those documents and whether they have been included in the training corpora of the LLMs. The black-box MIAs require a significant amount of data manipulation; therefore, their comparison is often challenging. We study state-of-the-art (SOTA) MIAs under the black-box assumptions and compare them to each other using a unified set of datasets to determine if any of them can reliably detect membership under SOTA LLMs. In addition, a new method, called the Familiarity Ranking, was developed to showcase a possible approach to black-box MIAs, thereby giving LLMs more freedom in their expression to understand their reasoning better. The results indicate that none of the methods are capable of reliably detecting membership in LLMs, as shown by an AUC-ROC of approximately 0.5 for all methods across several LLMs. The higher TPR and FPR for more advanced LLMs indicate higher reasoning and generalizing capabilities, showcasing the difficulty of detecting membership in LLMs using black-box MIAs.
Authors: Chuou Xu, Liya Ji, Qifeng Chen
Abstract: Reinforcement learning (RL) as post-training is crucial for enhancing the reasoning ability of large language models (LLMs) in coding and math. However, their capacity for visual semantic arithmetic, inferring relationships from images, remains underexplored. The classic text analogy "king"-"man"+"woman" = "queen" illustrates relational reasoning, yet replacing text with images of "king" and "man" significantly reduces performance because it requires commonsense knowledge and the extraction of concise concepts from irrelevant visual details. This capability is important for service and domestic robotics in unstructured environments, where robots must infer semantic relationships among objects, agents, and actions. In a kitchen, recognizing from images that "powder" and "cake" are related by "is made of" grounds symbolic relations in perception, enabling tool substitution, task generalization, and improved semantic reasoning. Prior work approaches semantic arithmetic by decoding image features after vector arithmetic, but suffers from modality gaps and lacks systematic evaluation. In this paper, we formulate two novel tasks, two-term subtraction and three-term operations, and construct the Image-Relation-Pair Dataset (IRPD) for benchmarking. We further propose Semantic Arithmetic Reinforcement Fine-Tuning (SAri-RFT), which post-trains large vision-language models (LVLMs) using a verifiable function and Group Relative Policy Optimization (GRPO). Our method achieves state-of-the-art results on IRPD and the real-world Visual7W-Telling dataset. By equipping LVLMs with robust cross-modal relational reasoning, this work advances domestic robots' ability to ground symbolic reasoning in perception, enhancing decision-making, tool adaptability, and human-robot interaction in complex environments. Datasets and source code are provided in the supplementary material.
Authors: Xue Xia, Chengkai Yao, Mingyu Tsoi, Xinjie Mao, Wenxuan Huang, Jiaqi Wei, Hao Wu, Cheng Tan, Lang Yu, Yuejin Yang, Siqi Sun, Zhangyang Gao
Abstract: Systematic ablations are essential to attribute performance gains in AI Virtual Cells, yet they are rarely performed because biological repositories are under-standardized and tightly coupled to domain-specific data and formats. While recent coding agents can translate ideas into implementations, they typically stop at producing code and lack a verifier that can reproduce strong baselines and rigorously test which components truly matter. We introduce AblateCell, a reproduce-then-ablate agent for virtual cell repositories that closes this verification gap. AblateCell first reproduces reported baselines end-to-end by auto-configuring environments, resolving dependency and data issues, and rerunning official evaluations while emitting verifiable artifacts. It then conducts closed-loop ablation by generating a graph of isolated repository mutations and adaptively selecting experiments under a reward that trades off performance impact and execution cost. Evaluated on three single-cell perturbation prediction repositories (CPA, GEARS, BioLORD), AblateCell achieves 88.9% (+29.9% to human expert) end-to-end workflow success and 93.3% (+53.3% to heuristic) accuracy in recovering ground-truth critical components. These results enable scalable, repository-grounded verification and attribution directly on biological codebases.
Authors: Anton Kolonin, Alexey Glushchenko, Evgeny Bochkov, Abhishek Saxena
Abstract: Evaluating the reasoning capabilities of Large Language Models (LLMs) for complex, quantitative financial tasks is a critical and unsolved challenge. Standard benchmarks often fail to isolate an agent's core ability to parse queries and orchestrate computations. To address this, we introduce a novel evaluation methodology and benchmark designed to rigorously measure an LLM agent's reasoning for financial time-series analysis. We apply this methodology in a large-scale empirical study using our framework, Time Series Augmented Generation (TSAG), where an LLM agent delegates quantitative tasks to verifiable, external tools. Our benchmark, consisting of 100 financial questions, is used to compare multiple SOTA agents (e.g., GPT-4o, Llama 3, Qwen2) on metrics assessing tool selection accuracy, faithfulness, and hallucination. The results demonstrate that capable agents can achieve near-perfect tool-use accuracy with minimal hallucination, validating the tool-augmented paradigm. Our primary contribution is this evaluation framework and the corresponding empirical insights into agent performance, which we release publicly to foster standardized research on reliable financial AI.
Authors: Josue Torres-Fonseca, Naihao Deng, Yinpei Dai, Shane Storks, Yichi Zhang, Rada Mihalcea, Casey Kennington, Joyce Chai
Abstract: Multimodal Large Language Models are increasingly adopted as autonomous agents in interactive environments, yet their ability to proactively address safety hazards remains insufficient. We introduce SafetyALFRED, built upon the embodied agent benchmark ALFRED, augmented with six categories of real-world kitchen hazards. While existing safety evaluations focus on hazard recognition through disembodied question answering (QA) settings, we evaluate eleven state-of-the-art models from the Qwen, Gemma, and Gemini families on not only hazard recognition, but also active risk mitigation through embodied planning. Our experimental results reveal a significant alignment gap: while models can accurately recognize hazards in QA settings, average mitigation success rates for these hazards are low in comparison. Our findings demonstrate that static evaluations through QA are insufficient for physical safety, thus we advocate for a paradigm shift toward benchmarks that prioritize corrective actions in embodied contexts. We open-source our code and dataset under https://github.com/sled-group/SafetyALFRED.git
Authors: Aya Cherigui, Florent Gu\'epin, Arnaud Legendre, Jean-Fran\c{c}ois Couchot
Abstract: Human mobility data are used in numerous applications, ranging from public health to urban planning. Human mobility is inherently sensitive, as it can contain information such as religious beliefs and political affiliations. Historically, it has been proposed to modify the information using techniques such as aggregation, obfuscation, or noise addition, to adequately protect privacy and eliminate concerns. As these methods come at a great cost in utility, new methods leveraging development in generative models, were introduced. The extent to which such methods answer the privacy-utility trade-off remains an open problem. In this paper, we introduced a first step towards solving it, by the introduction and application of a new framework for utility evaluation. Furthermore, we provide evidence that privacy evaluation remains a great challenge to consider and that it should be tackled through adversarial evaluation in accordance with the current EU regulation. We propose a new membership inference attack against a subcategory of generative models, even though this subcategory was deemed private due to its resistance over the trajectory user-linking problem.
Authors: Shuai Wang, Hongyi Zhu, Jia-Hong Huang, Yixian Shen, Chengxi Zeng, Stevan Rudinac, Monika Kackovic, Nachoem Wijnberg, Marcel Worring
Abstract: Understanding artworks requires multi-step reasoning over visual content and cultural, historical, and stylistic context. While recent multimodal large language models show promise in artwork explanation, they rely on implicit reasoning and internalized knowl- edge, limiting interpretability and explicit evidence grounding. We propose A-MAR, an Agent-based Multimodal Art Retrieval framework that explicitly conditions retrieval on structured reasoning plans. Given an artwork and a user query, A-MAR first decomposes the task into a structured reasoning plan that specifies the goals and evidence requirements for each step. Retrieval is then conditionedon this plan, enabling targeted evidence selection and supporting step-wise, grounded explanations. To evaluate agent-based multi- modal reasoning within the art domain, we introduce ArtCoT-QA. This diagnostic benchmark features multi-step reasoning chains for diverse art-related queries, enabling a granular analysis that extends beyond simple final answer accuracy. Experiments on SemArt and Artpedia show that A-MAR consistently outperforms static, non planned retrieval and strong MLLM baselines in final explanation quality, while evaluations on ArtCoT-QA further demonstrate its advantages in evidence grounding and multi-step reasoning ability. These results highlight the importance of reasoning-conditioned retrieval for knowledge-intensive multimodal understanding and position A-MAR as a step toward interpretable, goal-driven AI systems, with particular relevance to cultural industries. The code and data are available at: https://github.com/ShuaiWang97/A-MAR.
Authors: Mohamed Mostafa
Abstract: Over the past 15 years, the volume, richness and quality of data collected from the combined social networking platforms has increased beyond all expectation, providing researchers from a variety of disciplines to use it in their research. Perhaps more impactfully, it has provided the foundation for a range of new products and services, transforming industries such as advertising and marketing, as well as bringing the challenges of sharing personal data into the public consciousness. But how to make sense of the ever-increasing volume of big social data so that we can better understand and improve the user experience in increasingly complex, data-driven digital systems. This link with usability and the user experience of data-driven system bridges into the wider field of HCI, attracting interdisciplinary researchers as we see the demand for consumer technologies, software and systems, as well as the integration of social networks into our everyday lives. The fact that the data largely posted on social networks tends to be textual, provides a further link to linguistics, psychology and psycholinguistics to better understand the relationship between human behaviours offline and online. In this thesis, we present a novel conceptual framework based on a complex digital system using collected longitudinal datasets to predict system status based on the personality traits and emotions extracted from text posted by users. The system framework was built using a dataset collected from an online scholarship system in which 2000 students had their digital behaviour and social network behaviour collected for this study. We contextualise this research project with a wider review and critical analysis of the current psycholinguistics, artificial intelligence and human-computer interaction literature, which reveals a gap of mapping and understanding digital profiling against system status.
Authors: Geovana S. de Oliveira, Ana P. C. Silva, Fabricio Murai, Carlos H. G. Ferreira
Abstract: Vaccination remains a cornerstone of global public health, yet the COVID-19 pandemic exposed how online misinformation, political polarization, and declining institutional trust can undermine immunization efforts. Most of the prior computational studies that analyzed vaccine discourse on social platforms focus on English-language data, specific vaccines, or short time windows, impairing our understanding of long-term dynamics in high-impact, non-English contexts like Brazil, home to one of the world's most comprehensive immunization systems. We here present the largest longitudinal study of Brazil's vaccine discourse on YouTube, leveraging a semi-supervised stance detection framework that combines self-labeling and self-training to classify nearly 1.4 million comments. By integrating stance with temporal patterns, engagement metrics, and channel taxonomy (legacy media, science communicators, digital-native outlets), we map how pro- and anti-vaccine narratives evolve and circulate within a hybrid media ecosystem. Our results show that semi-supervised learning substantially improves stance classification robustness, enabling fine-grained tracking of public attitudes across Brazil's full immunization schedule. Polarization spikes during epidemiological crises, especially COVID-19, but becomes fragmented across vaccines and interaction patterns in the post-pandemic period. Notably, science communication and digital-native channels emerge as the primary loci of both supportive and oppositional engagement, revealing structural vulnerabilities in contemporary health communication. Thus, our work advances computational methods for large-scale stance modeling while offering actionable evidence for public health agencies, platform governance, and online information ecosystems.
Authors: Guchan Li, Rui Tian, Hongning Wang
Abstract: Large language models (LLMs) have demonstrated significant potential in formal theorem proving, yet state-of-the-art performance often necessitates prohibitive test-time compute via massive roll-outs or extended context windows. In this work, we address this scalability bottleneck by exploiting an informative structure in formal verification: the observation that compilers map a vast space of diverse proof attempts to a compact set of structured failure modes. We introduce a learning-to-refine framework that leverages this compression to perform efficient learning and proof exploration. We perform tree search that corrects errors locally conditioned on explicit verifier feedback, thereby circumventing the costs associated with accumulating a long history of proof attempts. Extensive evaluations show that our method consistently amplifies the reasoning capabilities of base provers across varying scales. Notably, our approach achieves state-of-the-art performance on PutnamBench among publicly reported $\sim$8B and $\sim$32B parameter models under comparable test-time budgets, offering a scalable paradigm for next-generation verifier-guided reasoning.
Authors: Lei Wang, Min Huang, Eduard Dragut
Abstract: Thematic analysis is difficult to scale: manual workflows are labor-intensive, while fully automated pipelines often lack controllability and transparent evaluation. We present \textbf{CentaurTA Studio}, a web-based system for self-improving human--agent collaboration in open coding and theme construction. The system integrates (1) a two-stage human feedback pipeline separating simulator drafting and expert validation, (2) persistent prompt optimization that distills validated feedback into reusable alignment principles, and (3) rubric-based evaluation with early stopping for process control. Across three domains, CentaurTA achieves the strongest performance in both Open Coding and Theme Construction, reaching up to 92.12\% accuracy and consistently outperforming baseline systems. Agreement between the rubric-based LLM judge and human annotators reaches substantial reliability (average $\kappa = 0.68$). Ablation studies show that removing the feedback loop reduces performance from 90\% to 81\%, while eliminating the Critic or early stopping degrades accuracy or increases interaction cost. The full system reaches peak performance within 10 iterative rounds (about 25 minutes), demonstrating improved efficiency over expert-only refinement.
Authors: Yunshu Bai, RuiHao Li, Hao Zhang, Chien Her Lim, Ming Yan, Mengtian Li
Abstract: Game UI implementation requires translating stylized mockups into interactive engine entities. However, current "Screenshot-to-Code" tools often struggle with the irregular geometries and deep visual hierarchies typical of game interfaces. To bridge this gap, we introduce SPRITE, a pipeline that transforms static screenshots into editable engine assets. By integrating Vision-Language Models (VLMs) with a structured YAML intermediate representation, SPRITE explicitly captures complex container relationships and non-rectangular layouts. We evaluated SPRITE against a curated Game UI benchmark and conducted expert reviews with professional developers to assess reconstruction fidelity and prototyping efficiency. Our findings demonstrate that SPRITE streamlines development by automating tedious coding and resolving complex nesting. By facilitating rapid in-engine iteration, SPRITE effectively blurs the boundaries between artistic design and technical implementation in game development. Project page: https://baiyunshu.github.io/sprite.github.io/
Authors: Jan H\r{u}la, David Adamczyk, Tom\'a\v{s} Filip, Martin Pavl\'i\v{c}ek, Petr Sos\'ik
Abstract: We introduce a two-dimensional (2D) early exit strategy that coordinates layer-wise and sentence-wise exiting for classification tasks in large language models. By processing input incrementally sentence-by-sentence while progressively activating deeper layers, our method achieves multiplicative computational savings that exceed those from optimizing either dimension independently. Experimental evaluation across four state-of-the-art LLMs (Llama 3.1, Llama 3.2, Gemma, Qwen; 3B-8B parameters) on three sentiment classification datasets demonstrates additional speed-ups of 1.4--2.3$\times$ over optimal layer-wise early exit for simpler tasks with vanilla models, with graceful degradation on complex multi-class problems. Fine-tuning reduces but does not eliminate this advantage. The approach is model-agnostic, requires only lightweight classification adapters, and is orthogonal to complementary efficiency methods such as quantization and pruning. Our findings indicate that 2D early exit strategies excel when semantic information accumulates predictably across input structure, suggesting possible applicability to sequence-processing tasks beyond sentiment classification.
Authors: Stephen Smith, Cormac Purcell, Gabriele Meoni, Roberto Del Prete, Zdenka Kuncic
Abstract: Damage caused by bushfires and volcanic eruptions escalates rapidly when detection is delayed, making fast and reliable early warning capabilities essential. Recent Earth Observation (EO) approaches have shown that thermal anomaly detection can be performed directly on decompressed Level-0 (L0) sensor data, avoiding computationally expensive preprocessing chains. However, direct exploitation of raw data remains challenging due to domain shift, sensor drift, radiometric inconsistencies, and the scarcity of labelled training samples. To address these challenges, this work proposes a Physics-Aware Neuromorphic Network (PANN) framework for onboard thermal anomaly detection. The proposed lightweight architecture, inspired by physical neural network principles and neuromorphic computing paradigms, is evaluated using two Sentinel-2 datasets: decompressed L0 with additional metadata (i.e. raw) and Level-1C (L1C). The PANN achieves a Matthews Correlation Coefficient (MCC) of $0.809$ on raw measurements, compared to $0.875$ when using ground-processed L1C products. The mean processing latency per L0 granule is $2.44 \pm 0.09~\mathrm{s}$, which is below the Sentinel-2 acquisition time of $3.6~\mathrm{s}$, demonstrating the feasibility of real-time, onboard processing. Furthermore, the projected execution time for the corresponding neuromorphic hardware instantiation is substantially lower at $0.1290 \pm 0.0002~\mathrm{s}$. Memory usage, including all necessary programs and packages, remains within realistic onboard constraints, with requirements of $0.673 \pm 0.007~\mathrm{Gb}$ for the software PANN and $0.393 \pm 0.004~\mathrm{Gb}$ for the estimated hardware realisation. Overall, these results indicate that PANN offers a promising pathway toward low-latency and resource-efficient onboard EO processing for thermal event detection.
Authors: Yang Yang, Zining Zhong, Jindong Li, Jiemin Wu, Kaishen Yuan, Wenshuo Chen, Menglin Yang, Yutao Yue
Abstract: LLM-driven program evolution can discover high-quality programs, but its cost and run-to-run variance hinder reliable progress. We propose TurboEvolve, a multi-island evolutionary framework that improves sample efficiency and robustness under fixed evaluation budgets. Inspired by the multiple-offspring strategy in evolutionary algorithms, TurboEvolve introduces verbalized Sampling, prompting the LLM to emit K diverse candidates with explicit self-assigned sampling weights, and an online scheduler that adapts K to expand exploration under stagnation and reduce overhead during steady progress. To exploit existing solution pools, we further propose "seed-pool injection," which clusters seeds and assigns them across islands with controlled perturbations and elitist preservation to balance diversity and refinement. Across multiple program-optimization benchmarks, TurboEvolve consistently achieves stronger performance at lower budgets and improves best-known solutions on several tasks.
Authors: Han Xu, Zhiyong Qin, Di Shang, Jiahong Zhang, Xuerui Qiu, Bo Lei, Tiejun Huang, Bo Xu, Guoqi Li
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress but incur substantial computational overhead and energy consumption during inference, limiting deployment in resource-constrained environments. Spiking Neural Networks (SNNs), with their sparse event-driven computation, offer inherent energy efficiency advantages on neuromorphic hardware, yet extending them to MLLMs faces two key challenges: heterogeneous modalities make uniform spike encoding insufficient, and high-resolution image inputs amplify timestep unfolding overhead. We propose SpikeMLLM, the first spike-based framework for MLLMs, which unifies existing ANN quantization methods in the spiking representation space and incorporates Modality-Specific Temporal Scales (MSTS) guided by Modality Evolution Discrepancy (MED) and Temporally Compressed LIF (TC-LIF) for timestep compression from T=L-1 to T=log2(L)-1. Experiments on four representative MLLMs across diverse multimodal benchmarks show that SpikeMLLM maintains near-lossless performance under aggressive timestep compression (Tv/Tt=3/4), with average gaps of only 0.72% and 1.19% relative to the FP16 baseline on InternVL2-8B and Qwen2VL-72B. We further develop a dedicated RTL accelerator tailored to the spike-driven datapath, observing 9.06x higher throughput and 25.8x better power efficiency relative to an FP16 GPU baseline under a deployment-oriented co-design setting, suggesting the promise of algorithm-hardware co-design for efficient multimodal intelligence.
Authors: Samrendra Roy, Sajedul Talukder, Syed Bahauddin Alam
Abstract: Anomaly detection in nuclear industrial control systems (ICS) requires continuous, energy-efficient monitoring across multiple subsystems that are often deployed at different stages of plant commissioning. When a conventional neural network is sequentially trained to monitor new subsystems, it catastrophically forgets previously learned anomaly patterns, a safety-critical failure mode. We present the first spiking neural network (SNN)-based anomaly detection system with continual learning for nuclear ICS, addressing both challenges simultaneously. Our approach introduces spike-encoded asynchronous sensor fusion, a delta-based encoding that converts heterogeneous sensor streams into sparse spike trains at rates dictated by each sensor's natural dynamics, achieving 92.7% input sparsity. We evaluate five continual learning strategies, including sequential fine-tuning, Elastic Weight Consolidation (EWC), Synaptic Intelligence (SI), experience replay, and a hybrid EWC+Replay approach, on the HAI 21.03 nuclear ICS security dataset across three sequentially deployed subsystems (boiler, turbine, water treatment). The hybrid EWC+Replay method achieves an average F1 score of 0.979 with near-zero average forgetting (AF = 0.000 single seed; 0.035 +/- 0.039 across three seeds), while requiring 12.6x fewer operations (an estimated 2.5x in energy based on published hardware specifications) than an equivalent artificial neural network. The system detects all tested attacks with a mean latency of 0.6 seconds. These results demonstrate that neuromorphic computing offers a viable path toward always-on, energy-efficient, and adaptable safety monitoring for next-generation nuclear facilities.
Authors: Xudong Wang, Chaoning Zhang, Chenghao Li, Shuxu Chen, Qigan Sun, Jiaquan Zhang, Fachrina Dewi Puspitasari, Tae-Ho Kim, Jiwei Wei, Malu Zhang, Guoqing Wang, Yang Yang, Heng Tao Shen
Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in complex reasoning tasks, while recent prompting strategies such as Chain-of-Thought (CoT) have further elevated their performance in handling complex logical problems. Despite these advances, high-quality reasoning remains heavily reliant on manual static prompts and is sensitive to decoding configurations and task distributions, leading to performance fluctuations and limited transferability. Existing automatic prompt optimization methods typically adopt single-agent local search, failing to simultaneously optimize prompts and decoding hyperparameters within a unified framework to achieve stable global improvements. To address this limitation, we propose Agent-GWO, a dynamic prompt optimization framework for complex reasoning. Specifically, we unify prompt templates and decoding hyperparameters as inheritable agent configurations. By leveraging the leader-follower mechanism of the Grey Wolf Optimizer (GWO), we automatically select three leader agents ($\alpha$, $\beta$, and $\delta$) to guide the collaborative updates of the remaining agents, enabling iterative convergence toward robust optimal reasoning configurations that can be seamlessly integrated for inference. Extensive experiments on multiple mathematical and hybrid reasoning benchmarks across diverse LLM backbones show that Agent-GWO consistently improves accuracy and stability over existing prompt optimization methods. The code will be released publicly.
Authors: Haohui Mai, Xiaoyan Guo, Xiangyun Ding, Daifeng Li, Qiuchu Yu, Chenzhun Guo, Cong Wang, Jiacheng Zhao, Christos Kozyrakis, Binhang Yuan
Abstract: LLM-based coding agents can generate functionally correct GPU kernels, yet their performance remains far below hand-optimized libraries on critical computations such as matrix multiplication, attention, and Mixture-of-Experts (MoE). Peak GPU performance requires coordinated reasoning over tightly coupled optimizations, including tiling, shared-memory staging, software pipelining, and instruction scheduling, while existing agents rely on sparse pass/fail feedback, leaving them unable to diagnose global constraint violations. We present Argus, an agentic framework that addresses this through data-flow invariants: compile-time specifications encoding how data must be choreographed throughout kernel execution. Argus introduces a tile-based, Pythonic DSL exposing hardware instructions and compiler policies while hiding low-level representations. The DSL provides tag functions to propagate symbolic annotations through data and control flow, and tag assertions to enforce relational constraints at use sites. When violations occur, the compiler returns concrete counterexamples identifying the thread, data element, and program point, enabling dense, structured feedback for targeted fixes. Invariants are verified at compile time via abstract interpretation over a layout algebra and SMT solving, with zero runtime overhead. An in-context reinforcement learning planner learns to select optimizations and synthesize effective invariants, supported by a curated knowledge base of GPU optimization techniques. We evaluate Argus on the AMD MI300X GPU across GEMM, flash attention, and MoE kernels accounting for over 90% of GPU time in LLM inference. Generated kernels achieve 99-104% of state-of-the-art hand-optimized assembly throughput and are 2-1543x faster than existing agentic systems. Argus further generalizes to 200 KernelBench tasks, solving 100% of Level 1 and 90% of Level 2 problems.
Authors: Anthony Zador, Jean-Marc Fellous, Terrence Sejnowski, Gina Adam, James B Aimone, Akwasi Akwaboah, Yiannis Aloimonos, Carmen Amo Alonso, Chiara Bartolozzi, Michael J. Bennington, Michael Berry, Bing W. Brunton, Gert Cauwenberghs, Hillel J. Chiel, Tobi Delbruck, John Doyle, Jason Eshraghian, Ralph Etienne-Cummings, Cornelia Fermuller, Matthew Jacobsen, Ali A. Minai, Barbara Oakley, Alexander G. Ororbia II, Joe Paton, Blake Richards, Yulia Sandamirskaya, Abhronil Sengupta, Shihab Shamma, Michael P. Stryker, Seong Jong Yoo, Steven W. Zucker
Abstract: Neuroscience and Artificial Intelligence (AI) have made impressive progress in recent years but remain only loosely interconnected. Based on a workshop convened by the National Science Foundation in August 2025, we identify three fundamental capability gaps in current AI: the inability to interact with the physical world, inadequate learning that produces brittle systems, and unsustainable energy and data inefficiency. We describe the neuroscience principles that address each: co-design of body and controller, prediction through interaction, multi-scale learning with neuromodulatory control, hierarchical distributed architectures, and sparse event-driven computation. We present a research roadmap organized around these principles at near, mid, and long-term horizons. We argue that realizing this program requires a new generation of researchers trained across the boundary between neuroscience and engineering, and describe the institutional conditions: interdisciplinary training, hardware access, community standards, and ethics, needed to support them. We conclude that NeuroAI, neuroscience-informed artificial intelligence, has the potential to overcome limitations of current AI while deepening our understanding of biological neural computation.
Authors: Zhiyin Yu, Bo Zhang, Qibin Hou, Zhonghai Wu, Xiao Luo, Lei Bai
Abstract: Previous LLMs-based RL studies typically follow either supervised learning with high annotation costs, or unsupervised paradigms using voting or entropy-based rewards. However, their performance remains far from satisfactory due to the substantial annotation cost and issues such as model collapse or reward hacking. To address these issues, we introduce a new perspective inspired by cognitive learning theory and propose a novel approach called EasyRL. The core of EasyRL is to simulate the human cognitive acquisition curve by integrating reliable knowledge transfer from easy labeled data with a progressive divide-and-conquer strategy that tackles increasingly difficult unlabeled data. Specifically, we initialize a warm-up model using supervised RL with few-shot labeled data. This is followed by a divide-and-conquer pseudo-labeling strategy on difficult unlabeled data, combining consistency-based selection for low-uncertainty cases and reflection-based resolution for medium-uncertainty cases. Finally, difficulty-progressive self-training with iterative pseudo-labeling and RL further strengthens the model's reasoning capability. EasyRL provides a unified self-evolving framework that facilitates data-efficient post-training of LLMs. Experimental results on mathematical and scientific benchmarks demonstrate that EasyRL, using only 10% of easy labeled data, consistently outperforms state-of-the-art baselines.
Authors: Pronob Kumar Barman, Pronoy Kumar Barman, Plaban Kumar Barman, Rohan Mandar Salvi
Abstract: Predictive policing systems that allocate patrol resources based solely on predicted crime risk can unintentionally amplify racial disparities through feedback driven data bias. We present FASE, a Fairness Aware Spatiotemporal Event Graph framework, which integrates spatiotemporal crime prediction with fairness constrained patrol allocation and a closed loop deployment feedback simulator. We model Baltimore as a graph of 25 ZIP Code Tabulation Areas and use 139,982 Part 1 crime incidents from 2017 to 2019 at hourly resolution, producing a sparse feature tensor. The prediction module combines a spatiotemporal graph neural network with a multivariate Hawkes process to capture spatial dependencies and self exciting temporal dynamics. Outputs are modeled using a Zero Inflated Negative Binomial distribution, suitable for overdispersed and zero heavy crime counts. The model achieves a validation loss of 0.4800 and a test loss of 0.4857. Patrol allocation is formulated as a fairness constrained linear optimization problem that maximizes risk weighted coverage while enforcing a Demographic Impact Ratio constraint with deviation bounded by 0.05. Across six simulated deployment cycles, fairness remains within 0.9928 to 1.0262, and coverage ranges from 0.876 to 0.936. However, a persistent detection rate gap of approximately 3.5 percentage points remains between minority and non minority areas. This result shows that allocation level fairness constraints alone do not eliminate feedback induced bias in retraining data, highlighting the need for fairness interventions across the full pipeline.
Authors: Hang Yuan, Xiaolin Hu, Yan Wan, Menglin Gao, Wenzhe Yu, Cong Huang, Fei Xu, Qing Li, Christina Dan Wang, Zhou Yu, Kai Chen
Abstract: Text-driven controllable dance generation remains under-explored, primarily due to the severe scarcity of high-quality datasets and the inherent difficulty of articulating complex choreographies. Characterizing dance is particularly challenging owing to its intricate spatial dynamics, strong directionality, and the highly decoupled movements of distinct body parts. To overcome these bottlenecks, we bridge principles from dance studies, human anatomy, and biomechanics to propose \textit{Choreographic Syntax}, a novel theoretical framework with a tailored annotation system. Grounded in this syntax, we combine professional dance archives with high-fidelity motion capture data to construct \textbf{DanceFlow}, the most fine-grained dance dataset to date. It encompasses 41 hours of high-quality motions paired with 6.34 million words of detailed descriptions. At the model level, we introduce \textbf{DanceCrafter}, a tailored motion transformer built upon the Momentum Human Rig. To circumvent optimization instabilities, we construct a continuous manifold motion representation paired with a hybrid normalization strategy. Furthermore, we design an anatomy-aware loss to explicitly regulate the decoupled nature of body parts. Together, these adaptations empower DanceCrafter to achieve the high-fidelity and stable generation of complex dance sequences. Extensive evaluations and user studies demonstrate our state-of-the-art performance in motion quality, fine-grained controllability, and generation naturalness.
Authors: Satoru Utsunomiya, Masaru Isonuma, Junichiro Mori, Ichiro Sakata
Abstract: As generative AI faces intensifying legal challenges, the machine learning community has increasingly relied on post-hoc mitigation -- especially machine unlearning and inference-time guardrails -- to argue for compliance. This paper argues that such post-hoc mitigation methods cannot retroactively cure liability from unlawful acquisition and training, because compliance hinges on data lineage, not the outputs. Our argument has three parts. First, unauthorized copying/ingestion can be a legally complete completed act, and model weights may operate as fixed copies that retain training-derived expressive value, making later filtering beside the point for infringement. Second, contract and tort/unfair-competition rules -- via licenses, terms of service, and anti-free-riding principles -- can independently restrict access and use, often bypassing copyright defenses (e.g., fair use or TDM exceptions). Third, since value from protected inputs can persist in weights, remedies such as unjust enrichment and disgorgement may require stripping gains and, in some cases, reaching the model itself. We therefore argue for a shift from Post-Hoc Sanitization to verifiable Ex-Ante Process Compliance.
Authors: Xiangyu Wen, Yuang Zhao, Xiaoyu Xu, Lingjun Chen, Changran Xu, Shu Chi, Jianrong Ding, Zeju Li, Haomin Li, Li Jiang, Fangxin Liu, Qiang Xu
Abstract: The transition of agentic AI from brittle prototypes to production systems is stalled by a pervasive crisis of craft. We suggest that the prevailing orchestration paradigm-delegating the system control loop to large language models and merely patching with heuristic guardrails-is the root cause of this fragility. Instead, we propose Arbiter-K, a Governance-First execution architecture that reconceptualizes the underlying model as a Probabilistic Processing Unit encapsulated by a deterministic, neuro-symbolic kernel. Arbiter-K implements a Semantic Instruction Set Architecture (ISA) to reify probabilistic messages into discrete instructions. This allows the kernel to maintain a Security Context Registry and construct an Instruction Dependency Graph at runtime, enabling active taint propagation based on the data-flow pedigree of each reasoning node. By leveraging this mechanism, Arbiter-K precisely interdicts unsafe trajectories at deterministic sinks (e.g., high-risk tool calls or unauthorized network egress) and enables autonomous execution correction and architectural rollback when security policies are triggered. Evaluations on OpenClaw and NanoBot demonstrate that Arbiter-K enforces security as a microarchitectural property, achieving 76% to 95% unsafe interception for a 92.79% absolute gain over native policies. The code is publicly available at https://github.com/cure-lab/ArbiterOS.
Authors: Sravanth Kodavanti, Sowmya Vajrala, Srinivas Miriyala, Utsav Tiwari, Uttam Kumar, Utkarsh Kumar Mahawar, Achal Pratap Singh, Arya D, Narendra Mutyala, Vikram Nelvoy Rajendiran, Sharan Kumar Allur, Euntaik Lee, Dohyoung Kim, HyeonSu Lee, Gyusung Cho, JungBae Kim
Abstract: Deploying large language models (LLMs) on smartphones poses significant engineering challenges due to stringent constraints on memory, latency, and runtime flexibility. In this work, we present a hardware-aware framework for efficient on-device inference of a LLaMA-based multilingual foundation model supporting multiple use cases on Samsung Galaxy S24 and S25 devices with SM8650 and SM8750 Qualcomm chipsets respectively. Our approach integrates application-specific LoRAs as runtime inputs to a single frozen inference graph, enabling dynamic task switching without recompilation or memory overhead. We further introduce a multi-stream decoding mechanism that concurrently generates stylistic variations - such as formal, polite, or jovial responses - within a single forward pass, reducing latency by up to 6x. To accelerate token generation, we apply Dynamic Self-Speculative Decoding (DS2D), a tree-based strategy that predicts future tokens without requiring a draft model, yielding up to 2.3x speedup in decode time. Combined with quantization to INT4 and architecture-level optimizations, our system achieves 4-6x overall improvements in memory and latency while maintaining accuracy across 9 languages and 8 tasks. These results demonstrate practical feasibility of deploying multi-use-case LLMs on edge devices, advancing the commercial viability of Generative AI in mobile platforms.
Authors: Dongcheng Zhang, Yiqing Jiang
Abstract: Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own deployers. Real-world incidents illustrate the gap: Slack AI credential exfiltration (Aug 2024), Microsoft 365 Copilot calendar-injection leaks (Jan 2024), and a Meta agent unauthorized forum post exposing operational data (Mar 2026). We propose Owner-Harm, a formal threat model with eight categories of agent behavior damaging the deployer. We quantify the defense gap on two benchmarks: a compositional safety system achieves 100% TPR / 0% FPR on AgentHarm (generic criminal harm) yet only 14.8% (4/27; 95% CI: 5.9%-32.5%) on AgentDojo injection tasks (prompt-injection-mediated owner harm). A controlled generic-LLM baseline shows the gap is not inherent to owner-harm (62.7% vs. 59.3%, delta 3.4 pp) but arises from environment-bound symbolic rules that fail to generalize across tool vocabularies. On a post-hoc 300-scenario owner-harm benchmark, the gate alone achieves 75.3% TPR / 3.3% FPR; adding a deterministic post-audit verifier raises overall TPR to 85.3% (+10.0 pp) and Hijacking detection from 43.3% to 93.3%, demonstrating strong layer complementarity. We introduce the Symbolic-Semantic Defense Generalization (SSDG) framework relating information coverage to detection rate. Two SSDG experiments partially validate it: context deprivation amplifies the detection gap 3.4x (R = 3.60 vs. R = 1.06); context injection reveals structured goal-action alignment, not text concatenation, is required for effective owner-harm detection.
Authors: Jin Zhao, Marta Kne\v{z}evi\'c, Tanja K\"aser
Abstract: Large Language Models (LLMs) are increasingly used in education, yet their default helpfulness often conflicts with pedagogical principles. Prior work evaluates pedagogical quality via answer leakage-the disclosure of complete solutions instead of scaffolding-but typically assumes well-intentioned learners, leaving tutor robustness under student misuse largely unexplored. In this paper, we study scenarios where students behave adversarially and aim to obtain the correct answer from the tutor. We evaluate a broad set of LLM-based tutor models, including different model families, pedagogically aligned models, and a multi-agent design, under a range of adversarial student attacks. We adapt six groups of adversarial and persuasive techniques to the educational setting and use them to probe how likely a tutor is to reveal the final answer. We evaluate answer leakage robustness using different types of in-context adversarial student agents, finding that they often fail to carry out effective attacks. We therefore introduce an adversarial student agent that we fine-tune to jailbreak LLM-based tutors, which we propose as the core of a standardized benchmark for evaluating tutor robustness. Finally, we present simple but effective defense strategies that reduce answer leakage and strengthen the robustness of LLM-based tutors in adversarial scenarios.
Authors: Wentao Zhang, Yan Zhuang, ZhuHang Zheng, Mingfei Zhang, Jiawen Deng, Fuji Ren
Abstract: Existing jamming attacks on Retrieval-Augmented Generation (RAG) systems typically induce explicit refusals or denial-of-service behaviors, which are conspicuous and easy to detect. In this work, we formalize a subtler availability threat, termed soft failure, which degrades system utility by inducing fluent and coherent yet non-informative responses rather than overt failures. We propose Deceptive Evolutionary Jamming Attack (DEJA), an automated black-box attack framework that generates adversarial documents to trigger such soft failures by exploiting safety-aligned behaviors of large language models. DEJA employs an evolutionary optimization process guided by a fine-grained Answer Utility Score (AUS), computed via an LLM-based evaluator, to systematically degrade the certainty of answers while maintaining high retrieval success. Extensive experiments across multiple RAG configurations and benchmark datasets show that DEJA consistently drives responses toward low-utility soft failures, achieving SASR above 79\% while keeping hard-failure rates below 15\%, significantly outperforming prior attacks. The resulting adversarial documents exhibit high stealth, evading perplexity-based detection and resisting query paraphrasing, and transfer across model families to proprietary systems without retargeting.
Authors: Vin Bhaskara, Haicheng Wang
Abstract: Local prediction-error-based curiosity rewards focus on the current transition without considering the world model's cumulative prediction error across all visited transitions. We introduce Curiosity-Critic, which grounds its intrinsic reward in the improvement of this cumulative objective, and show that it reduces to a tractable per-step form: the difference between the current prediction error and the asymptotic error baseline of the current state transition. We estimate this baseline online with a learned critic co-trained alongside the world model; regressing a single scalar, the critic converges well before the world model saturates, redirecting exploration toward learnable transitions without oracle knowledge of the noise floor. The reward is higher for learnable transitions and collapses toward the baseline for stochastic ones, effectively separating epistemic (reducible) from aleatoric (irreducible) prediction error online. Prior prediction-error curiosity formulations, from Schmidhuber (1991) to learned-feature-space variants, emerge as special cases corresponding to specific approximations of this baseline. Experiments on a stochastic grid world show that Curiosity-Critic outperforms prediction-error and visitation-count baselines in convergence speed and final world model accuracy.
Authors: Mashrekur Rahman, Samuel J. Barrett, Christina Last
Abstract: Earth observation foundation models encode land surface information into dense embedding vectors, yet the geometric structure of these representations and its implications for downstream reasoning remain underexplored. We characterize the manifold geometry of Google AlphaEarth's 64-dimensional embeddings across 12.1 million Continental United States samples (2017--2023) and develop an agentic system that leverages this geometric understanding for environmental reasoning. The manifold is non-Euclidean: effective dimensionality is 13.3 (participation ratio) from 64 raw dimensions, with local intrinsic dimensionality of approximately 10. Tangent spaces rotate substantially, with 84\% of locations exceeding 60\textdegree{} and local-global alignment (mean$|\cos\theta| = 0.17$) approaching the random baseline of 0.125. Supervised linear probes indicate that concept directions rotate across the manifold, and compositional vector arithmetic using both PCA-derived and probe-derived directions yields poor precision. Retrieval instead produces physically coherent results, with local geometry predicting retrieval coherence ($R^2 = 0.32$). Building on this characterization, we introduce an agentic system with nine specialized tools that decomposes environmental queries into reasoning chains over a FAISS-indexed embedding database. A five-condition ablation (120 queries, three complexity tiers) shows that embedding retrieval dominates response quality ($\mu = 3.79 \pm 0.90$ vs.\ $3.03 \pm 0.77$ parametric-only; scale 1--5), with peak performance on multi-step comparisons ($\mu = 4.28 \pm 0.43$). A cross-model benchmark show that geometric tools reduce Sonnet 4.5's score by 0.12 points but improve Opus 4.6's by 0.07, with Opus achieving higher geometric grounding (3.38 vs.\ 2.64), suggesting that the value of geometric characterization scales with the reasoning capability of the consuming model.
Authors: Isaac David, Arthur Gervais
Abstract: Agentic security systems increasingly audit live targets with tool-using LLMs, but prior systems fix a single coordination topology, leaving unclear when additional agents help and when they only add cost. We treat topology choice as an empirical systems question. We introduce a controlled benchmark of 20 interactive targets (10 web/API and 10 binary), each exposing one endpoint-reachable ground-truth vulnerability, evaluated in whitebox and blackbox modes. The core study executes 600 runs over five architecture families, three model families, and both access modes, with a separate 60-run long-context pilot reported only in the appendix. On the completed core benchmark, detection-any reaches 58.0% and validated detection reaches 49.8%. MAS-Indep attains the highest validated detection rate (64.2%), while SAS is the strongest efficiency baseline at $0.058 per validated finding. Whitebox materially outperforms blackbox (67.0% vs. 32.7% validated detection), and web materially outperforms binary (74.3% vs. 25.3%). Bootstrap confidence intervals and paired target-level deltas show that the dominant effects are observability and domain, while some leading whitebox topologies remain statistically close. The main result is a non-monotonic cost-quality frontier: broader coordination can improve coverage, but it does not dominate once latency, token cost, and exploit-validation difficulty are taken into account.
Authors: Niraj Agarwal, Timothy A. Smith, Sergey Frolov, Laura C. Slivinski
Abstract: Machine learning emulators have shown extraordinary skill in forecasting atmospheric states, and their application to global ocean dynamics offers similar promise. Here, we adapt the GraphCast architecture into a dedicated ocean-only emulator, driven by prescribed atmospheric conditions, for medium-range predictions. The emulator is trained on NOAA's UFS-Replay dataset. Using a 24 hour time step, single initial condition, and without using autoregressive training, we produce an emulator that provides skillful forecasts for 10-15 day lead times. We further demonstrate the use of Mahalanobis distance as loss that improves the forecast skill compared to the Mean Squared Error loss by explicitly accounting for the correlations between tendencies of the target variables. Using spatial correlation analysis of the forecasted fields, we also show that the proposed correlation-aware loss acts as a statistical-dynamical regularizer for the slow, correlated dynamics of the global oceans, offering a better background forecast for downstream tasks like data assimilation.
Authors: Merkouris Papamichail, Konstantinos Varsos, Giorgos Flouris, Jo\~ao Marques-Silva
Abstract: Many neural network (NN) verification systems represent the network's input-output relation as a constraint program. Sound and complete, representations involve integer constraints, for simulating the activations. Recent works convexly relax the integer constraints, improving performance, at the cost of soundness. Convex relaxations consider outputs that are unreachable by the original network. We study the worst case divergence between the original network and its convex relaxations; both qualitatively and quantitatively. The relaxations' space forms a lattice, where the top element corresponds to a full relaxation, with every neuron linearized. The bottom element corresponds to the original network. We provide analytical upper and lower bounds for the $\ell_\infty$-distance between the fully relaxed and original outputs. This distance grows exponentially, w.r.t. the network's depth, and linearly w.r.t. the input's radius. The misclassification probability exhibits a step-like behavior, w.r.t. input radius. Our results are supported by experiments on MNIST, Fashion MNIST and random networks.
Authors: Valentina Kuskova, Dmitry Zaytsev, Michael Coppedge
Abstract: Nonlinear machine-learning models are increasingly used to discover causal relationships in time-series data, yet the interpretation of their outputs remains poorly understood. In particular, causal scores produced by regularized neural autoregressive models are often treated as analogues of regression coefficients, leading to misleading claims of statistical significance. In this paper, we argue that causal relevance in nonlinear time-series models should be evaluated through forecast necessity rather than coefficient magnitude, and we present a practical evaluation procedure for doing so. We present an interpretable evaluation framework based on systematic edge ablation and forecast comparison, which tests whether a candidate causal relationship is required for accurate prediction. Using Neural Additive Vector Autoregression as a case study model, we apply this framework to a real-world case study of democratic development, modeled as a multivariate time series of panel data - democracy indicators across 139 countries. We show that relationships with similar causal scores can differ dramatically in their predictive necessity due to redundancy, temporal persistence, and regime-specific effects. Our results demonstrate how forecast-necessity testing supports more reliable causal reasoning in applied AI systems and provides practical guidance for interpreting nonlinear time-series models in high-stakes domains.
Authors: Andrew Wang, Ellie Pavlick, Ritambhara Singh
Abstract: An active challenge in developing multimodal machine learning (ML) models for healthcare is handling missing modalities during training and deployment. As clinical datasets are inherently temporal and sparse in terms of modality presence, capturing the underlying predictive signal via diagnostic multimodal ML models while retaining model explainability remains an ongoing challenge. In this work, we address this by re-framing clinical diagnosis as an autoregressive sequence modeling task, utilizing causal decoders from large language models (LLMs) to model a patient's multimodal trajectory. We first introduce a missingness-aware contrastive pre-training objective that integrates multiple modalities in datasets with missingness in a shared latent space. We then show that autoregressive sequence modeling with transformer-based architectures outperforms baselines on the MIMIC-IV and eICU fine-tuning benchmarks. Finally, we use interpretability techniques to move beyond performance boosts and find that across various patient stays, removing modalities leads to divergent behavior that our contrastive pre-training mitigates. By abstracting clinical diagnosis as sequence modeling and interpreting patient stay trajectories, we develop a framework to profile and handle missing modalities while addressing the canonical desideratum of safe, transparent clinical AI.
Authors: Ahson Saiyed, Sabrina Sadiekh, Chirag Agarwal
Abstract: Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoencoders (SAEs) are widely used for interpretability, their robustness implications remain underexplored. We present a study of integrating pretrained SAEs into transformer residual streams at inference time, without modifying model weights or blocking gradients. Across four model families (Gemma, LLaMA, Mistral, Qwen) and two strong white-box attacks (GCG, BEAST) plus three black-box benchmarks, SAE-augmented models achieve up to a 5x reduction in jailbreak success rate relative to the undefended baseline and reduce cross-model attack transferability. Parametric ablations reveal (i) a monotonic dose-response relationship between L0 sparsity and attack success rate, and (ii) a layer-dependent defense-utility tradeoff, where intermediate layers balance robustness and clean performance. These findings are consistent with a representational bottleneck hypothesis: sparse projection reshapes the optimization geometry exploited by jailbreak attacks.
Authors: Seowung Leem, Lin Gu, Chenyu You, Kuang Gong, Ruogu Fang
Abstract: The retina provides a unique, noninvasive window into Alzheimer's disease (AD) and dementia, capturing early structural changes through morphometric features, while systemic and lifestyle risk factors reflect well-established contributors to disease susceptibility long before clinical symptom onset. However, current retinal analysis frameworks typically model imaging and risk factors separately, limiting their ability to capture joint multimodal patterns critical for early risk prediction. Moreover, existing methods rarely incorporate mechanisms to organize or align patients with similar retinal and clinical characteristics, constraining the learning of coherent cross-modal associations. To address these limitations, we introduce REVEAL (REtinal-risk Vision-Language Early Alzheimer's Learning), a framework that aligns color fundus photographs with individualized disease-specific risk profiles for predicting incident AD and dementia, on average 8 years before diagnosis (range: 1-11 years). Because real-world risk factors are structured questionnaire data, we translate them into clinically interpretable narratives compatible with pretrained vision-language models (VLMs). We further propose a group-aware contrastive learning (GACL) strategy that clusters patients with similar retinal morphometry and risk factors as positive pairs, strengthening multimodal alignment. This unified representation learning framework substantially outperforms state-of-the-art retinal imaging models paired with clinical text encoders, as well as general-purpose VLMs, demonstrating the value of jointly modeling retinal biomarkers and clinical risk factors. By providing a generalizable and noninvasive approach for early AD and dementia risk stratification, REVEAL has the potential to enable earlier intervention and improve preventive care at the population level.
Authors: Bibek Aryal, Gift Modekwe, Qiugang Lu
Abstract: Fault detection and diagnosis are critical for the optimal and safe operation of industrial processes. The correlations among sensors often display non-Euclidean structures where graph neural networks (GNNs) are widely used therein. However, for large-scale systems, local, global, and dynamic relations extensively exist among sensors, and traditional GNNs often overlook such complex and multi-level structures for various problems including the fault diagnosis. To address this issue, we propose a structure-aware multi-level temporal graph network with local-global feature fusion for industrial fault diagnosis. First, a correlation graph is dynamically constructed using Pearson correlation coefficients to capture relationships among process variables. Then, temporal features are extracted through long short-term memory (LSTM)-based encoder, whereas the spatial dependencies among sensors are learned by graph convolution layers. A multi-level pooling mechanism is used to gradually coarsen and learn meaningful graph structures, to capture higher-level patterns while keeping important fault related details. Finally, a fusion step is applied to combine both detailed local features and overall global patterns before the final prediction. Experimental evaluations on the Tennessee Eastman process (TEP) demonstrate that the proposed model achieves superior fault diagnosis performance, particularly for complex fault scenarios, outperforming various baseline methods.
Authors: Seyedali Mohammadi, Manas Gaur, Francis Ferraro
Abstract: Scientific feasibility assessment asks whether a claim is consistent with established knowledge and whether experimental evidence could support or refute it. We frame feasibility assessment as a diagnostic reasoning task in which, given a hypothesis, a model predicts feasible or infeasible and justifies its decision. We evaluate large language models (LLMs) under controlled knowledge conditions (hypothesis-only, with experiments, with outcomes, or both) and probe robustness by progressively removing portions of the experimental and/or outcome context. Across multiple LLMs and two datasets, providing outcome evidence is generally more reliable than providing experiment descriptions. Outcomes tend to improve accuracy beyond what internal knowledge alone provides, whereas experimental text can be brittle and may degrade performance when the context is incomplete. These findings clarify when experimental evidence benefits LLM-based feasibility assessment and when it introduces fragility.
Authors: Zijian Zeng, Fei Ding, Huiming Yang, Xianwei Li
Abstract: Vision-Language-Action (VLA) models fail systematically on long-horizon manipulation tasks despite strong short-horizon performance. We show that this failure is not resolved by extending context length alone in the current reactive execution setting; instead, it stems from three recurring execution-loop deficiencies: the memory gap, the verification gap, and the recovery gap. We present HELM, a model-agnostic framework that addresses these deficiencies with three components: an Episodic Memory Module (EMM) that retrieves key task history via CLIP-indexed keyframes, a learned State Verifier (SV) that predicts action failure before execution from observation, action, subgoal, and memory-conditioned context, and a Harness Controller (HC) that performs rollback and replanning. The SV is the core learning contribution: it consistently outperforms rule-based feasibility checks and ensemble uncertainty baselines, and its effectiveness depends critically on access to episodic memory. On LIBERO-LONG, HELM improves task success rate by 23.1 percentage points over OpenVLA (58.4% to 81.5%), while extending the context window to H=32 yields only a 5.4-point gain and same-budget LoRA adaptation remains 12.2 points below HELM. HELM also improves long-horizon performance on CALVIN and substantially boosts recovery success under controlled perturbations. Ablations and mechanism analyses isolate the contribution of each component, and we release LIBERO-Recovery as a perturbation-injection protocol for evaluating failure recovery in long-horizon manipulation.
Authors: Zhiyuan Jiang, Weihao Hong, Xinlei Guan, Tejaswi Dhandu, Miles Q. Li, Meng Xu, Kuan Huang, Umamaheswara Rao Tida, Bingyu Shen, Daehan Kwak, Boyang Li
Abstract: Vision-Language Models (VLMs) are increasingly deployed in settings where reliable visual grounding carries operational consequences, yet their behavior under progressively coercive prompt phrasing remains undercharacterized. Existing hallucination benchmarks predominantly rely on neutral prompts and binary detection, leaving open how both the incidence and the intensity of fabrication respond to graded linguistic pressure across structurally distinct task types. We present Ghost-100, a procedurally constructed benchmark of 800 synthetically generated images spanning eight categories across three task families: text-illegibility, time-reading, and object-absence, each designed under a negative-ground-truth principle that guarantees the queried target is absent, illegible, or indeterminate by construction. Every image is paired with five prompts drawn from a structured 5-Level Prompt Intensity Framework, holding the image and task identity fixed while varying only directive force, so that tone is isolated as the sole independent variable. We adopt a dual-track evaluation protocol: a rule-based H-Rate measuring the proportion of responses in which a model crosses from grounded refusal into unsupported positive commitment, and a GPT-4o-mini-judged H-Score on a 1-5 scale characterizing the confidence and specificity of fabrication once it occurs. We additionally release a three-stage automated validation workflow, which retrospectively confirms 717 of 800 images as strictly compliant. Evaluating nine open-weight VLMs, we find that H-Rate and H-Score dissociate substantially across model families, reading-style and presence-detection subsets respond to prompt pressure in qualitatively different ways, and several models exhibit non-monotonic sensitivity peaking at intermediate tone levels: patterns that aggregate metrics obscure.
Authors: Yuanbang Liang, Zhengwen Chen, Yu-Kun Lai
Abstract: Latent Diffusion Models (LDMs) achieve high-fidelity synthesis but suffer from latent space brittleness, causing discontinuous semantic jumps during editing. We introduce a Riemannian framework to diagnose this instability by analyzing the generative Jacobian, decomposing geometry into \textit{Local Scaling} (capacity) and \textit{Local Complexity} (curvature). Our study uncovers a \textbf{``Geometric Decoupling"}: while curvature in normal generation functionally encodes image detail, OOD generation exhibits a functional decoupling where extreme curvature is wasted on unstable semantic boundaries rather than perceptible details. This geometric misallocation identifies ``Geometric Hotspots" as the structural root of instability, providing a robust intrinsic metric for diagnosing generative reliability.
Authors: Alexandre L. M. Levada
Abstract: Principal Component Analysis (PCA) is a fundamental tool for representation learning, but its global linear formulation fails to capture the structure of data supported on curved manifolds. In contrast, manifold learning methods model nonlinearity but often sacrifice the spectral structure and stability of PCA. We propose \emph{Geodesic Tangent Space Aggregation PCA (GTSA-PCA)}, a geometric extension of PCA that integrates curvature awareness and geodesic consistency within a unified spectral framework. Our approach replaces the global covariance operator with curvature-weighted local covariance operators defined over a $k$-nearest neighbor graph, yielding local tangent subspaces that adapt to the manifold while suppressing high-curvature distortions. We then introduce a geodesic alignment operator that combines intrinsic graph distances with subspace affinities to globally synchronize these local representations. The resulting operator admits a spectral decomposition whose leading components define a geometry-aware embedding. We further incorporate semi-supervised information to guide the alignment, improving discriminative structure with minimal supervision. Experiments on real datasets show consistent improvements over PCA, Kernel PCA, Supervised PCA and strong graph-based baselines such as UMAP, particularly in small sample size and high-curvature regimes. Our results position GTSA-PCA as a principled bridge between statistical and geometric approaches to dimensionality reduction.
Authors: Konstantin F. Willeke, Polina Turishcheva, Alex Gilbert, Goirik Chakrabarty, Hasan A. Bedel, Paul G. Fahey, Yongrong Qiu, Marissa A. Weis, Michaela Vystr\v{c}ilov\'a, Taliah Muhammad, Lydia Ntanavara, Rachel E. Froebe, Kayla Ponder, Zheng Huan Tan, Emin Orhan, Erick Cobos, Sophia Sanborn, Katrin Franke, Fabian H. Sinz, Alexander S. Ecker, Andreas S. Tolias
Abstract: Scaling data and artificial neural networks has transformed AI, driving breakthroughs in language and vision. Whether similar principles apply to modeling brain activity remains unclear. Here we leveraged a dataset of 3.1 million neurons from the visual cortex of 73 mice across 323 sessions, totaling more than 150 billion neural tokens recorded during natural movies, images and parametric stimuli, and behavior. We train multi-modal, multi-task models that support three regimes flexibly at test time: neural prediction, behavioral decoding, neural forecasting, or any combination of the three. OmniMouse achieves state-of-the-art performance, outperforming specialized baselines across nearly all evaluation regimes. We find that performance scales reliably with more data, but gains from increasing model size saturate. This inverts the standard AI scaling story: in language and computer vision, massive datasets make parameter scaling the primary driver of progress, whereas in brain modeling -- even in the mouse visual cortex, a relatively simple system -- models remain data-limited despite vast recordings. The observation of systematic scaling raises the possibility of phase transitions in neural modeling, where larger and richer datasets might unlock qualitatively new capabilities, paralleling the emergent properties seen in large language models. Code available at https://github.com/enigma-brain/omnimouse.
Authors: Sinan G. Aksoy, Alexandra A. Sabrio, Erik VonKaenel, Lee Burke
Abstract: We propose a scalable, multifactorial experimental framework that systematically probes LLM sensitivity to subtle semantic changes in pairwise document comparison. We analogize this as a needle-in-a-haystack problem: a single semantically altered sentence (the needle) is embedded within surrounding context (the hay), and we vary the perturbation type (negation, conjunction swap, named entity replacement), context type (original vs. topically unrelated), needle position, and document length across all combinations, testing five LLMs on tens of thousands of document pairs. Our analysis reveals several striking findings. First, LLMs exhibit a within-document positional bias distinct from previously studied candidate-order effects: most models penalize semantic differences more harshly when they occur earlier in a document. Second, when the altered sentence is surrounded by topically unrelated context, it systematically lowers similarity scores and induces bipolarized scores that indicate either very low or very high similarity. This is consistent with an interpretive frame account in which topically-related context may allow models to contextualize and downweight the alterations. Third, each LLM produces a qualitatively distinct scoring distribution, a stable "fingerprint" that is invariant to perturbation type, yet all models share a universal hierarchy in how leniently they treat different perturbation types. Together, these results demonstrate that LLM semantic similarity scores are sensitive to document structure, context coherence, and model identity in ways that go beyond the semantic change itself, and that the proposed framework offers a practical, LLM-agnostic toolkit for auditing and comparing scoring behavior across current and future models.
Authors: Chris Cameron, Wangzheng Wang, Nikita Ivanov, Ashmita Bhattacharyya, Didier Ch\'etelat, Yingxue Zhang
Abstract: Looped transformers scale computational depth without increasing parameter count by repeatedly applying a shared transformer block and can be used for iterative refinement, where each loop rewrites a full fixed-size prediction in parallel. On difficult problems, such as those that require search-like computation, reaching a highly structured solution starting from noise can require long refinement trajectories. Learning such trajectories is challenging when training specifies only the target solution and provides no supervision over the intermediate refinement path. Diffusion models tackle this issue by corrupting data with varying magnitudes of noise and training the model to reverse it in a \textit{single step}. However, this process misaligns training and testing behaviour. We introduce Denoising Recursion Models, a method that similarly corrupts data with noise but trains the model to reverse the corruption over \textit{multiple} recursive steps. This strategy provides a tractable curriculum of intermediate states, while better aligning training with testing and incentivizing non-greedy, forward-looking generation. Through extensive experiments, we show this approach outperforms the Tiny Recursion Model (TRM) on ARC-AGI, where it recently achieved breakthrough performance.
Authors: Katherine Wang, Nadia Berthouze, Aneesha Singh
Abstract: AI systems are increasingly embedded in multi-user social environments, yet most alignment frameworks conceptualize interaction as a dyadic relationship between a single user and an AI system. Livestreaming platforms challenge this assumption: interaction unfolds among streamers and audiences in real time, producing dynamic affective and social feedback loops. In this paper, we introduce the Triadic Loop, a conceptual framework that reconceptualizes alignment in AI co-hosted livestreaming as a temporally reinforced process of bidirectional adaptation among three actors: streamer $\leftrightarrow$ AI co-host, AI co-host $\leftrightarrow$ audience, and streamer $\leftrightarrow$ audience. Unlike instruction-following paradigms, bidirectional alignment requires each actor to continuously reshape the others, meaning misalignment in any sub-loop can destabilize the broader system. Drawing on literature from multi-party interaction, collaborative AI, and relational agents, we articulate how AI co-hosts function not only as mediators but as performative participants and community members shaping collective meaning-making. We further propose "strategic misalignment" as a mechanism for sustaining community engagement and introduce three relational evaluation constructs grounded in established instruments. The framework contributes a model of dynamic multi-party alignment, an account of cross-loop reinforcement, and design implications for AI co-hosts that sustain social coherence in participatory media environments.
Authors: Wenpeng Xu
Abstract: GUI agents that control desktop computers via screenshot-and-click loops introduce a new class of vulnerability: the observation-to-action gap (mean 6.51 s on real OSWorld workloads) creates a Time-Of-Check, Time-Of-Use (TOCTOU) window during which an unprivileged attacker can manipulate the UI state. We formalize this as a Visual Atomicity Violation and characterize three concrete attack primitives: (A) Notification Overlay Hijack, (B) Window Focus Manipulation, and (C) Web DOM Injection. Primitive B, the closest desktop analog to Android Action Rebinding, achieves 100% action-redirection success rate with zero visual evidence at the observation time. We propose Pre-execution UI State Verification (PUSV), a lightweight three-layer defense that re-verifies the UI state immediately before each action dispatch: masked pixel SSIM at the click target (L1), global screenshot diff (L2a), and X Window snapshot diff (L2b). PUSV achieves 100% Action Interception Rate across 180 adversarial trials (135 Primitive A + 45 Primitive B) with zero false positives and < 0.1 s overhead. Against Primitive C (zero-visual-footprint DOM injection), PUSV reveals a structural blind spot (~0% AIR), motivating future OS+DOM defense-in-depth architectures. No single PUSV layer alone achieves full coverage; different primitives require different detection signals, validating the layered design.
Authors: Guoming Long, Shihai Wang, Hui Fang, Tao Chen
Abstract: Bug reports, encompassing a wide range of bug types, are crucial for maintaining software quality. However, the increasing complexity and volume of bug reports pose a significant challenge in sole manual identification and assignment to the appropriate teams for resolution, as dealing with all the reports is time-consuming and resource-intensive. In this paper, we introduce a cross-project framework, dubbed Mutualistic Neural Active Learning (MNAL), designed for automated and more effective identification of bug reports from GitHub repositories boosted by human-machine collaboration. MNAL utilizes a neural language model that learns and generalizes reports across different projects, coupled with active learning to form neural active learning. A distinctive feature of MNAL is the purposely crafted mutualistic relation between the machine learners (neural language model) and human labelers (developers) when enriching the knowledge learned. That is, the most informative human-labeled reports and their corresponding pseudo-labeled ones are used to update the model while those reports that need to be labeled by developers are more readable and identifiable, thereby enhancing the human-machine teaming therein. We evaluate MNAL using a large scale dataset against the SOTA approaches, baselines, and different variants. The results indicate that MNAL achieves up to 95.8% and 196.0% effort reduction in terms of readability and identifiability during human labeling, respectively, while resulting in a better performance in bug report identification. Additionally, our MNAL is model-agnostic since it is capable of improving the model performance with various underlying neural language models. To further verify the efficacy of our approach, we conducted a qualitative case study involving 10 human participants, who rate MNAL as being more effective while saving more time and monetary resources.
Authors: Junhao Dong, Yifei Zhang, Hao Zhu, Yew-Soon Ong, Piotr Koniusz
Abstract: Vision-Language Models (VLMs) can perform zero-shot classification but are susceptible to adversarial attacks. While robust fine-tuning improves their robustness, existing approaches align fixed text embeddings with an image embedding, sacrificing natural performance and robustness. A robustness degradation also occurs when a model faces adversarial attacks targeting superclasses (parent classes, e.g., mammal) in addition to their base (leaf) classes (e.g., cat). Thus, to enhance adversarial robustness and leverage the inherent hierarchical properties of class space, we propose a novel adversarial fine-tuning framework based on hierarchical embeddings and several levels of adversarially robust alignment of image-text modalities. Additional mechanisms place visual embeddings at the desired depth of hierarchy, and we provide a theoretical connection between the depth of embedding in the hierarchy and the maximum viable margin size. Our model naturally realizes several margin sizes, boosting generalization of adversaries for robustification. As various trees with different parent labels can share the same leaf labels, we also consider aligning over multiple trees to boost semantic variety. Experiments across several datasets are performed.
Authors: Yuefei Chen, Yihao Quan, Xiaodong Lin, Ruixiang Tang
Abstract: LLMs frequently generate fictitious yet convincing citations, often expressing high confidence even when the underlying reference is wrong. We study this failure across 9 models and 108{,}000 generated references, and find that author names fail far more often than other fields across all models and settings. Citation style has no measurable effect, while reasoning-oriented distillation degrades recall. Probes trained on one field transfer at near-chance levels to the others, suggesting that hallucination signals do not generalize across fields. Building on this finding, we apply elastic-net regularization with stability selection to neuron-level CETT values of Qwen2.5-32B-Instruct and identify a sparse set of field-specific hallucination neurons (FH-neurons). Causal intervention further confirms their role: amplifying these neurons increases hallucination, while suppressing them improves performance across fields, with larger gains in some fields. These results suggest a lightweight approach to detecting and mitigating citation hallucination using internal model signals alone.
Authors: Zhongying Wang, Kevin Lane, Levi Cai, Morteza Karimzadeh, Esther Rolf
Abstract: Supervised learning with Earth observation inputs is often limited by the sparsity of high-quality labeled or in-situ measured data to use as training labels. With the abundance of geographic data products, in many cases there are variables correlated with - but different from - the variable of interest that can be leveraged. We integrate such proxy variables within a geographic prior via a trainable location encoder and introduce a proxy consistency loss (PCL) formulation to imbue proxy data into the location encoder. The first key insight behind our approach is to use the location encoder as an agile and flexible way to learn from abundantly available proxy data which can be sampled independently of training label availability. Our second key insight is that we will need to regularize the location encoder appropriately to achieve performance and robustness with limited labeled data. Our experiments on air quality prediction and poverty mapping show that integrating proxy data implicitly through the location encoder outperforms using both as input to an observation encoder and fusion strategies that use frozen, pretrained location embeddings as a geographic prior. Superior performance for in-sample prediction shows that the PCL can incorporate rich information from the proxies, and superior out-of-sample prediction shows that the learned latent embeddings help generalize to areas without training labels.
Authors: Vassilios Exarhakos, Jinghui Cheng, Jin L. C. Guo
Abstract: Current AI-assisted programming tools are predominantly linear and chat-based, which deviates from the iterative and branching nature of programming itself. Our preliminary study with developers using AI assistants suggested that they often struggle to explore alternatives, manage prompting sequences, and trace changes. Informed by these insights, we created EvoGraph, an IDE plugin that integrates AI interactions and code changes as a lightweight and interactive development graph. EvoGraph automatically records a branching AI-assisted coding history and allows developers to manipulate the graph to compare, merge, and revisit prior collaborative AI programming states. Our user study with 20 participants revealed that EvoGraph addressed developers' challenges identified in our preliminary study while imposing lower cognitive load. Participants also found the graph-based representation supported safe exploration, efficient iteration, and reflection on AI-generated changes. Our work highlights design opportunities for tools to help developers make sense of and act on their problem-solving progress in the emerging AI-mediated programming context.
Authors: Henry Fraser, Jessica M. Szczuka, Raffaele F. Ciriello
Abstract: A series of high-profile tragedies involving companion chatbots has triggered an unusually rapid regulatory response. Several jurisdictions, including Australia, California, and New York, have introduced enforceable regulation, while regulators elsewhere have signaled growing concern about risks posed by companion chatbots, particularly to children. In parallel, leading providers, notably OpenAI, appear to have strengthened their self-regulatory approaches. Drawing on legal textual analysis and insights from regulatory theory, psychology, and information systems research, this paper critically examines these recent interventions. We examine what is regulated and who is regulated, identifying regulatory targets, scope, and modalities. We classify interventions by method and priority, showing how emerging regimes combine "locks and blocks", such as access gating and content moderation, with measures addressing toxic relationship features and process-based accountability requirements. We argue that effective regulation of companion chatbots must integrate all three dimensions. More, however, is required. Current regimes tend to focus on discrete harms, narrow conceptions of vulnerability, or highly specified accountability processes, while failing to confront deeper power asymmetries between providers and users. Providers of companion chatbots increasingly control artificial intimacy at scale, creating unprecedented opportunities for control through intimacy. We suggest that a general, open-ended duty of care would be an important first step toward constraining that power and addressing a fundamental source of chatbot risk. The paper contributes to debates on companion chatbot regulation and is relevant to regulators, platform providers, and scholars concerned with digital intimacy, law and technology, and fairness, accountability, and transparency in sociotechnical systems.
Authors: Isaac Llorente-Saguer
Abstract: Harmful intent is geometrically recoverable from large language model residual streams: as a linear direction in most layers, and as angular deviation in layers where projection methods fail. Across 12 models spanning four architectural families (Qwen2.5, Qwen3.5, Llama-3.2, Gemma-3) and three alignment variants (base, instruction-tuned, abliterated), under single-turn, English evaluation, we characterise this geometry through six direction-finding strategies. Three succeed: a soft-AUC-optimised linear direction reaches mean AUROC 0.98 and TPR@1\%FPR 0.80; a class-mean probe reaches 0.98 and 0.71 at <1ms fitting cost; a supervised angular-deviation strategy reaches AUROC 0.96 and TPR of 0.61 along a representationally distinct direction ($73^\circ$ from projection-based solutions), uniquely sustaining detection in middle layers where projection methods collapse. Detection remains stable across alignment variants, including abliterated models from which refusal has been surgically removed: harmful intent and refusal behaviour are functionally dissociated features of the representation. A direction fitted on AdvBench transfers to held-out HarmBench and JailbreakBench with worst-case AUROC 0.96. The same picture holds at scale: across Qwen3.5 from 0.8B to 9B parameters, AUROC remains $\geq$0.98 and cross-variant transfer stays within 0.018 of own-direction performance This is consistent with a simple account: models acquire a linearly decodable representation of harmful intent as part of general language understanding, and alignment then shapes what they do with such inputs without reorganising the upstream recognition signal. As a practical consequence, AUROC in the 0.97+ regime can substantially overestimate operational detectability; TPR@$1\%$FPR should accompany AUROC in safety-adjacent evaluation.
Authors: Matthew V. Macfarlane, Cl\'ement Bonnet, Herke van Hoof, Levi H. S. Lelis
Abstract: A central challenge in program induction has long been the trade-off between symbolic and neural approaches. Symbolic methods offer compositional generalisation and data efficiency, yet their scalability is constrained by formalisms such as domain-specific languages (DSLs), which are labour-intensive to create and may not transfer to new domains. In contrast, neural networks flexibly learn from data but tend to generalise poorly in compositional and out-of-distribution settings. We bridge this divide with an instance of a Latent Adaptation Network architecture named Neural Language Interpreter (NLI), which learns its own discrete, symbolic-like programming language end-to-end. NLI autonomously discovers a vocabulary of primitive operations and uses a novel differentiable neural executor to interpret variable-length sequences of these primitives. This allows NLI to represent programs that are not bound to a constant number of computation steps, enabling it to solve more complex problems than those seen during training. To make these discrete, compositional program structures amenable to gradient-based optimisation, we employ the Gumbel-Softmax relaxation, enabling the entire model to be trained end-to-end. Crucially, this same differentiability enables powerful test-time adaptation. At inference, NLI's program inductor provides an initial program guess. This guess is then refined via gradient descent through the neural executor, enabling efficient search for the neural program that best explains the given data. We demonstrate that NLI outperforms in-context learning, test-time training, and continuous latent program networks on tasks that require combinatorial generalisation and rapid adaptation to unseen tasks. Our results establish a new path toward models that combine the compositionality of discrete languages with the gradient-based search and end-to-end learning of neural networks.
Authors: Mehul Agarwal, Aditya Aggarwal, Arnav Goel, Medha Hira, Anubha Gupta
Abstract: While multilingual large language models (LLMs) perform well on high-level tasks like translation and question answering, their ability to handle grammatical gender and morphological agreement remains underexplored. In morphologically rich languages, gender influences verb conjugation, pronouns, and even first-person constructions with explicit and implicit mentions of gender. We introduce MORPHOGEN, a morphologically grounded large-scale benchmark dataset for evaluating gender-aware generation in three typologically diverse grammatically gendered languages: French, Arabic, and Hindi. The core task, GENFORM, requires models to rewrite a first-person sentence in the opposite gender while preserving its meaning and structure. We construct a high-quality synthetic dataset spanning these three languages and benchmark 15 popular multilingual LLMs (2B-70B) on their ability to perform this transformation. Our results reveal significant gaps and interesting insights into how current models handle morphological gender. MORPHOGEN provides a focused diagnostic lens for gender-aware language modeling and lays the groundwork for future research on inclusive and morphology-sensitive NLP.
Authors: Faisal Alherran
Abstract: Despite growing interest in Quranic data research, existing Quran datasets remain limited in both scale and diversity. To address this gap, we present Tadabur, a large-scale Quran audio dataset. Tadabur comprises more than 1400+ hours of recitation audio from over 600 distinct reciters, providing substantial variation in recitation styles, vocal characteristics, and recording conditions. This diversity makes Tadabur a comprehensive and representative resource for Quranic speech research and analysis. By significantly expanding both the total duration and variability of available Quran data, Tadabur aims to support future research and facilitate the development of standardized Quranic speech benchmarks.
Authors: Yihuai Gao, Jinyun Liu, Shuang Li, Shuran Song
Abstract: Robotic manipulation tasks exhibit varying memory requirements, ranging from Markovian tasks that require no memory to non-Markovian tasks that depend on historical information spanning single or multiple interaction trials. Surprisingly, simply extending observation histories of a visuomotor policy often leads to a significant performance drop due to distribution shift and overfitting. To address these issues, we propose Gated Memory Policy (GMP), a visuomotor policy that learns both when to recall memory and what to recall. To learn when to recall memory, GMP employs a learned memory gate mechanism that selectively activates history context only when necessary, improving robustness and reactivity. To learn what to recall efficiently, GMP introduces a lightweight cross-attention module that constructs effective latent memory representations. To further enhance robustness, GMP injects diffusion noise into historical actions, mitigating sensitivity to noisy or inaccurate histories during both training and inference. On our proposed non-Markovian benchmark MemMimic, GMP achieves a 30.1% average success rate improvement over long-history baselines, while maintaining competitive performance on Markovian tasks in RoboMimic. All code, data and in-the-wild deployment instructions are available on our project website https://gated-memory-policy.github.io/.
Authors: Nathaniel S. Woodward, Zhiqi Gao, Yurii Kvasiuk, Kendrick M. Smith, Frederic Sala, Moritz M\"unchmeyer
Abstract: Despite the growing application of Large Language Models (LLMs) to theoretical physics, there is little academic exploration into how domain-specific physics reasoning ability develops while training these models. To investigate this, we perform the first academic fine-tuning study of small (7B-parameter) reasoning models dedicated specifically to theoretical physics. Because open-source verifiable training data required to train such capabilities is scarce, we developed a robust data generation pipeline that can both create synthetic problems and make existing human-authored problems suitable for model training. Selecting Quantum Field Theory (QFT) as our primary domain, we generated over 2,500 synthetic problems alongside a curated collection of human-adapted problems sourced from arXiv and standard pedagogical resources. We conduct both Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT) experiments, benchmarking performance gains as well as generalization to other physics domains. We perform an extensive analysis of model chains-of-though before and after fine-tuning, to understand how reasoning errors evolve during RL and SFT. Finally, we publicly release our data pipeline, verifiable QFT training data, and $\sim$200M tokens of QFT reasoning traces.
Authors: Ramtin Davoudi, Kartik Thakkar, Nazanin Donyapour, Tyler Derr, Hamid Karimi
Abstract: In this study, we present the first comprehensive evaluation of modern LLMs - including GPT-4, GPT-4o, GPT-3.5-Turbo, Gemini 1.5 Pro, DeepSeek-V3, Llama 3.2, and BERT - across three core social media analytics tasks on a Twitter (X) dataset: (I) Social Media Authorship Verification, (II) Social Media Post Generation, and (III) User Attribute Inference. For the authorship verification, we introduce a systematic sampling framework over diverse user and post selection strategies and evaluate generalization on newly collected tweets from January 2024 onward to mitigate "seen-data" bias. For post generation, we assess the ability of LLMs to produce authentic, user-like content using comprehensive evaluation metrics. Bridging Tasks I and II, we conduct a user study to measure real users' perceptions of LLM-generated posts conditioned on their own writing. For attribute inference, we annotate occupations and interests using two standardized taxonomies (IAB Tech Lab 2023 and 2018 U.S. SOC) and benchmark LLMs against existing baselines. Overall, our unified evaluation provides new insights and establishes reproducible benchmarks for LLM-driven social media analytics. The code and data are provided in the supplementary material and will also be made publicly available upon publication.
Authors: Weixiao Zhan, Yongcheng Jing, Leszek Rutkowski, Dacheng Tao
Abstract: Knowledge distillation (KD) transfers capabilities from large language models (LLMs) to smaller students, yet it can fail unpredictably and also underpins model leakage risks. Our analysis revealed several distillation traps: tail noise, off-policy instability, and, most fundamentally, the teacher-student gap, that distort training signals. These traps manifest as overconfident hallucinations, self-correction collapse, and local decoding degradation, causing distillation to fail. Motivated by these findings, we propose a post-hoc calibration method that, to the best of our knowledge, for the first time enables control over a teacher's distillability via reinforcement fine-tuning (RFT). Our objective combines task utility, KL anchor, and across-tokenizer calibration reward. This makes distillability a practical safety lever for foundation models, connecting robust teacher-student transfer with deployment-aware model protection. Experiments across math, knowledge QA, and instruction-following tasks show that students distilled from distillable calibrated teachers outperform SFT and KD baselines, while undistillable calibrated teachers retain their task performance but cause distilled students to collapse, offering a practical knob for both better KD and model IP protection.
Authors: Yunbo Long, Tejumade Afonja, Alexandra Brintrup, Mario Fritz
Abstract: While language models have been adapted for tabular data generation, two fundamental limitations remain: (1) static fine-tuning produces models that cannot learn from their own generated samples and adapt to self-correct, and (2) autoregressive objectives preserve local token coherence but neglect global statistical properties, degrading tabular quality. Reinforcement learning offers a potential solution but requires designing reward functions that balance competing objectives -- impractical for tabular data. To fill the gap, we introduce TabGRAA (Tabular Group-Relative Advantage Alignment), the first self-improving framework for tabular data generation via automated feedback. At each iteration, TabGRAA uses an \emph{automated quality signal} -- such as a two-sample distinguishability classifier or a distance-based reward -- to partition newly generated samples into high- and low-quality groups, then optimizes a group-relative advantage objective that reinforces realistic patterns while penalizing artifacts. The specific signal is a modular choice rather than a fixed component of the framework. This establishes a virtuous feedback cycle, where the quality signal is re-computed against newly \emph{generated synthetic} samples at each round; the language model is only fine-tuned on these self-generated signals, so no additional real record is exposed during alignment, mitigating data-leakage risk beyond the initial supervised fine-tuning. Experiments show TabGRAA outperforms existing methods in fidelity, utility, and privacy, while matching or exceeding diffusion-based synthesizers, advancing tabular synthesis from static statistical replication to dynamic, self-improving generation.
Authors: Yuan Zhuang, Yuexin Bian, Sihong He, Jie Feng, Qing Su, Songyang Han, Jonathan Petit, Shihao Ji, Yuanyuan Shi, Fei Miao
Abstract: Scaling critic capacity is a promising direction for enhancing off-policy reinforcement learning (RL). However, larger critics are prone to overfitting and unstable in replay-buffer-based bootstrap training. This paper leverages Low-Rank Adaptation (LoRA) as a structural-sparsity regularizer for off-policy critics. Our approach freezes randomly initialized base matrices and solely optimizes low-rank adapters, thereby constraining critic updates to a low-dimensional subspace. Built on top of SimbaV2, we further develop a LoRA formulation, compatible with SimbaV2, that preserves its hyperspherical normalization geometry under frozen-backbone training. We evaluate our method with SAC and FastTD3 on DeepMind Control locomotion and IsaacLab robotics benchmarks. LoRA consistently achieves lower critic loss during training and stronger policy performance. Extensive experiments demonstrate that adaptive low-rank updates provide a simple, scalable, and effective structural regularization for critic learning in off-policy RL.
Authors: Jiagao Hu, Daiguo Zhou, Danzhen Fu, Fuhao Li, Zepeng Wang, Fei Wang, Wenhua Liao, Jiayi Xie, Haiyang Sun
Abstract: Perception robustness under adverse weather remains a critical challenge for autonomous driving, with the core bottleneck being the scarcity of real-world video data in adverse weather. Existing weather generation approaches struggle to balance visual quality and annotation reusability. We present AutoAWG, a controllable Adverse Weather video Generation framework for Autonomous driving. Our method employs a semantics-guided adaptive fusion of multiple controls to balance strong weather stylization with high-fidelity preservation of safety-critical targets; leverages a vanishing point-anchored temporal synthesis strategy to construct training sequences from static images, thereby reducing reliance on synthetic data; and adopts masked training to enhance long-horizon generation stability. On the nuScenes validation set, AutoAWG significantly outperforms prior state-of-the-art methods: without first-frame conditioning, FID and FVD are relatively reduced by 50.0% and 16.1%; with first-frame conditioning, they are further reduced by 8.7% and 7.2%, respectively. Extensive qualitative and quantitative results demonstrate advantages in style fidelity, temporal consistency, and semantic--structural integrity, underscoring the practical value of AutoAWG for improving downstream perception in autonomous driving. Our code is available at: https://github.com/higherhu/AutoAWG
Authors: Zhenbang Du, Kejing Xia, Xinrui Zhong, Yonggan Fu, Nicolai Oswald, Binfei Ji, Brucek Khailany, Pavlo Molchanov, Yingyan Lin
Abstract: Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive generation by enabling parallel token prediction. However, practical dLLM decoding still suffers from high inference latency, which limits deployment. In this work, we observe that a substantial part of this inefficiency comes from recurring redundancy in the decoding process, including spatial redundancy caused by confidence clusters and positional ambiguity, and temporal redundancy caused by repeatedly remasking predictions that have already stabilized. Motivated by these patterns, we propose $R^2$-dLLM, a unified framework for reducing decoding redundancy from both inference and training perspectives. At inference time, we introduce training-free decoding rules that aggregate local confidence and token predictions, and finalize temporally stable tokens to avoid redundant decoding steps. We further propose a redundancy-aware supervised fine-tuning pipeline that aligns the model with efficient decoding trajectories and reduces reliance on manually tuned thresholds. Experiments demonstrate that $R^2$-dLLM consistently reduces the number of decoding steps by up to 75% compared to existing decoding strategies, while maintaining competitive generation quality across different models and tasks. These results validate that decoding redundancy is a central bottleneck in dLLMs, and that explicitly reducing it yields substantial practical efficiency gains.
Authors: Xiaoyang Liu, Zineng Dong, Yifan Bai, Yantao Li, Yuntian Liu, Tao Luo
Abstract: Statement autoformalization acts as a critical bridge between human mathematics and formal mathematics by translating natural language problems into formal language. While prior works have focused on data synthesis and diverse training paradigms to optimize end-to-end Large Language Models (LLMs), they typically treat formal code as flat sequences, neglecting the hierarchical logic inherent in mathematical statements. In this work, we introduce Decompose, Structure, and Repair (DSR), a neuro-symbolic framework that restructures autoformalization into a modular pipeline. DSR decomposes statements into logical components and maps them to structured operator trees, leveraging this topological blueprint to precisely localize and repair errors via sub-tree refinement. Furthermore, we introduce PRIME, a benchmark of 156 undergraduate and graduate-level theorems selected from canonical textbooks and expertly annotated in Lean 4. Experimental results demonstrate that DSR establishes a new state-of-the-art, consistently outperforming baselines under equivalent computational budgets. The datasets, model, and code will be released to the public soon.
Authors: Tao Fan, Guoqiang Ma, Yuanfeng Song, Lixin Fan, Kai Chen, Qiang Yang
Abstract: Federated fine-tuning of Large Language Models (LLMs) is obstructed by a trilemma of challenges: protecting LLMs intellectual property (IP), ensuring client privacy, and mitigating performance loss on heterogeneous data. Existing methods like Offsite-Tuning (OT) secure the LLMs IP by having clients train only lightweight adapters, yet our analysis reveals they suffer from a fundamental performance bottleneck, leaving a significant gap compared to centralized training. To bridge this gap, we introduce FedProxy, a new federated adaptation framework. FedProxy replaces weak adapters with a unified, powerful Proxy Small Language Model (SLM), compressed from the proprietary LLM, to serve as a high-fidelity surrogate for collaborative fine-tuning. Our framework systematically resolves the trilemma through a three-stage architecture: (i) Efficient Representation via server-guided compression to create a resource-friendly proxy; (ii) Robust Optimization through an interference-mitigating aggregation strategy to handle data heterogeneity; and (iii) Effortless Fusion via a training-free "plug-in" mechanism to integrate learned knowledge back into the LLM. Experiments show FedProxy significantly outperforms OT methods and approaches centralized performance, establishing a new benchmark for secure and high-performance federated LLM adaptation.
Authors: Julian Skifstad, Xinyue Annie Yang, Glen Chou
Abstract: Inference-time LLM alignment methods, particularly activation steering, offer an alternative to fine-tuning by directly modifying activations during generation. Existing methods, however, often rely on non-anticipative interventions that ignore how perturbations propagate through transformer layers and lack online error feedback, resulting in suboptimal, open-loop control. To address this, we show empirically that, despite the nonlinear structure of transformer blocks, layer-wise dynamics across multiple LLM architectures and scales are well-approximated by locally-linear models. Exploiting this property, we model LLM inference as a linear time-varying dynamical system and adapt the classical linear quadratic regulator to compute feedback controllers using layer-wise Jacobians, steering activations toward desired semantic setpoints in closed-loop with minimal computational overhead and no offline training. We also derive theoretical bounds on setpoint tracking error, enabling formal guarantees on steering performance. Using a novel adaptive semantic feature setpoint signal, our method yields robust, fine-grained behavior control across models, scales, and tasks, including state-of-the-art modulation of toxicity, truthfulness, refusal, and arbitrary concepts, surpassing baseline steering methods. Our code is available at: https://github.com/trustworthyrobotics/lqr-activation-steering
URLs: https://github.com/trustworthyrobotics/lqr-activation-steering
Authors: Arsalan Sharifnassab, Mohamed Elsayed, Kris De Asis, A. Rupam Mahmood, Richard S. Sutton
Abstract: In gradient-based learning, a step size chosen in parameter units does not produce a predictable per-step change in function output. This often leads to instability in the streaming setting (i.e., batch size=1), where stochasticity is not averaged out and update magnitudes can momentarily become arbitrarily big or small. Instead, we propose intentional updates: first specify the intended outcome of an update and then solve for the step size that approximately achieves it. This strategy has precedent in online supervised linear regression via Normalized Least Mean Squares algorithm, which selects a step size to yield a specified change in the function output proportional to the current error. We extend this principle to streaming deep reinforcement learning by defining appropriate intended outcomes: Intentional TD aims for a fixed fractional reduction of the TD error, and Intentional Policy Gradient aims for a bounded per-step change in the policy, limiting local KL divergence. We propose practical algorithms combining eligibility traces and diagonal scaling. Empirically, these methods yield state-of-the-art streaming performance, frequently performing on par with batch and replay-buffer approaches.
Authors: Hanjun Cho, Jay-Yoon Lee
Abstract: Existing QA benchmarks typically assume distinct documents with minimal overlap, yet real-world retrieval-augmented generation (RAG) systems operate on corpora such as financial reports, legal codes, and patents, where information is highly redundant and documents exhibit strong inter-document similarity. This mismatch undermines evaluation validity: retrievers can be unfairly undervalued even when they retrieve documents that provide sufficient evidence, because redundancy across documents is not accounted for in evaluation. On the other hand, retrievers that perform well on standard benchmarks often generalize poorly to real-world corpora with highly similar and redundant documents. We present RARE (Redundancy-Aware Retrieval Evaluation), a framework for constructing realistic benchmarks by (i) decomposing documents into atomic facts to enable precise redundancy tracking and (ii) enhancing LLM-based data generation with CRRF. RAG benchmark data usually requires multiple quality criteria, but LLMs often yield trivial outputs. CRRF scores criteria separately and fuses decisions by rank, improving the reliability of generated data. Applying RARE to Finance, Legal, and Patent corpora, we introduce RedQA, where a strong retriever baseline drops from 66.4% PerfRecall@10 on 4-hop General-Wiki to 5.0-27.9% PerfRecall@10 at 4-hop depth, revealing robustness gaps that current benchmarks fail to capture. RARE enables practitioners to build domain-specific RAG evaluations that faithfully reflect real-world deployment conditions.
Authors: Boyan Shi, Wei Chen, Shuyuan Zhao, Junfeng Shen, Shengnan Guo, Shaojiang Wang, Huaiyu Wan
Abstract: The combination of Mixture-of-Experts (MoE) and Low-Rank Adaptation (LoRA) has shown significant potential for enhancing the multi-task learning capabilities of Large Language Models. However, existing methods face two primary challenges: (1)Imprecise Routing in the current MoE-LoRA method fails to explicitly match input semantics with expert capabilities, leading to weak expert specialization. (2)Uniform weight fusion strategies struggle to provide adaptive update strengths, overlooking the varying complexity of different tasks. To address these limitations, we propose SAMoRA (Semantic-Aware Mixture of LoRA Experts), a novel parameter-efficient fine-tuning framework tailored for task-adaptive learning. Specifically, A Semantic-Aware Router is proposed to explicitly align textual semantics with the most suitable experts for precise routing. A Task-Adaptive Scaling mechanism is designed to regulate expert contributions based on specific task requirements dynamically. In addition, a novel regularization objective is proposed to jointly promote expert specialization and effective scaling. Extensive experiments on multiple multi-task benchmarks demonstrate that SAMoRA significantly outperforms the state-of-the-art methods and holds excellent task generalization capabilities. Code is available at https://github.com/boyan-code/SAMoRA
Authors: Abhinav Agarwal
Abstract: LLM-assisted defect discovery has a precision crisis: plausible-but-wrong reports overwhelm maintainers and degrade credibility for real findings. We present Refute-or-Promote, an inference-time reliability pattern combining Stratified Context Hunting (SCH) for candidate generation, adversarial kill mandates, context asymmetry, and a Cross-Model Critic (CMC). Adversarial agents attempt to disprove candidates at each promotion gate; cold-start reviewers are intended to reduce anchoring cascades; cross-family review can catch correlated blind spots that same-family review misses. Over a 31-day campaign across 7 targets (security libraries, the ISO C++ standard, major compilers), the pipeline killed roughly 79% of 171 candidates before advancing to disclosure (retrospective aggregate); on a consolidated-protocol subset (lcms2, wolfSSL; n=30), the prospective kill rate was 83%. Outcomes: 4 CVEs (3 public, 1 embargoed); LWG 4549 accepted to the C++ working paper; 5 merged C++ editorial PRs; 3 compiler conformance bugs; 8 merged security-related fixes without CVE; an RFC 9000 errata filed under committee review; and 1+ FIPS 140-3 normative compliance issues under coordinated disclosure -- all evaluated by external acceptance, not benchmarks. The most instructive failure: ten dedicated reviewers unanimously endorsed a non-existent Bleichenbacher padding oracle in OpenSSL's CMS module; it was killed only by a single empirical test, motivating the mandatory empirical gate. No vulnerability was discovered autonomously; the contribution is external structure that filters LLM agents' persistent false positives. As a preliminary transfer test beyond defect discovery, a simplified cross-family critique variant also solved five previously unsolved SymPy instances on SWE-bench Verified and one SWE-rebench hard task.
Authors: Aby Mammen Mathew
Abstract: Neural NLI models overfit dataset artifacts instead of truly reasoning. A hypothesis-only model gets 57.7% in SNLI, showing strong spurious correlations, and 38.6% of the baseline errors are the result of these artifacts. We propose Product-of-Experts (PoE) training, which downweights examples where biased models are overconfident. PoE nearly preserves accuracy (89.10% vs. 89.30%) while cutting bias reliance by 4.71% (bias agreement 49.85% to 45%). An ablation finds lambda = 1.5 that best balances debiasing and accuracy. Behavioral tests still reveal issues with negation and numerical reasoning.
Authors: Xuelin Zhang, Hong Chen, Yingjie Wang, Tieliang Gong, Bin Gu
Abstract: Semi-supervised learning with manifold regularization is a classical framework for jointly learning from both labeled and unlabeled data, where the key requirement is that the support of the unknown marginal distribution has the geometric structure of a Riemannian manifold. Typically, the Laplace-Beltrami operator-based manifold regularization can be approximated empirically by the Laplacian regularization associated with the entire training data and its corresponding graph Laplacian matrix. However, the graph Laplacian matrix depends heavily on the prespecified similarity metric and may lead to inappropriate penalties when dealing with redundant or noisy input variables. To address the above issues, this paper proposes a new \textit{Semi-Supervised Meta Additive Model (S$^2$MAM) based on a bilevel optimization scheme that automatically identifies informative variables, updates the similarity matrix, and simultaneously achieves interpretable predictions. Theoretical guarantees are provided for S$^2$MAM, including the computing convergence and the statistical generalization bound. Experimental assessments across 4 synthetic and 12 real-world datasets, with varying levels and categories of corruption, validate the robustness and interpretability of the proposed approach.
Authors: Andrei Andrusenko, Vladimir Bataev, Lilit Grigoryan, Nune Tadevosyan, Vitaly Lavrukhin, Boris Ginsburg
Abstract: Unification of automatic speech recognition (ASR) systems reduces development and maintenance costs, but training a single model to perform well in both offline and low-latency streaming settings remains challenging. We present a Unified ASR framework for Transducer (RNNT) training that supports both offline and streaming decoding within a single model, using chunk-limited attention with right context and dynamic chunked convolutions. To further close the gap between offline and streaming performance, we introduce an efficient Triton implementation of mode-consistency regularization for RNNT (MCR-RNNT), which encourages agreement across training modes. Experiments show that the proposed approach improves streaming accuracy at low latency while preserving offline performance and scaling to larger model sizes and training datasets. The proposed Unified ASR framework and the English model checkpoint are open-sourced.
Authors: Kun Wang, Cheng Qian, Miao Yu, Lilan Peng, Liang Lin, Jiaming Zhang, Tianyu Zhang, Yu Cheng, Yang Wang
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the feasibility of backdoors in MLLMs via fine-tuning data poisoning to manipulate inference, the underlying mechanisms of backdoor attacks remain opaque, complicating the understanding and mitigation. To bridge this gap, we propose ProjLens, an interpretability framework designed to demystify MLLMs backdoors. We first establish that normal downstream task alignment--even when restricted to projector fine--tuning--introduces vulnerability to backdoor injection, whose activation mechanism is different from that observed in text-only LLMs. Through extensive experiments across four backdoor variants, we uncover:(1) Low-Rank Structure: Backdoor injection updates appear overall full-rank and lack dedicated ``trigger neurons'', but the backdoor-critical parameters are encoded within a low-rank subspace of the projector;(2) Activation Mechanism: Both clean and poisoned embedding undergoes a semantic shift toward a shared direction aligned with the backdoor target, but the shifting magnitude scales linearly with the input norm, resulting in the distinct backdoor activation on poisoned samples. Our code is available at: https://anonymous.4open.science/r/ProjLens-8FD7
Authors: Feng Jiang, Yang Chen, Kyle Xu, Yuchen Liu, Haifeng Wang, Zhenhao Shen, Jasper Lu, Shengze Huang, Yuanfei Wang, Chen Xie, Ruihai Wu
Abstract: Recent advances in large-scale video world models have enabled increasingly realistic future prediction, raising the prospect of leveraging imagined videos for robot learning. However, visual realism does not imply physical plausibility, and behaviors inferred from generated videos may violate dynamics and fail when executed by embodied agents. Existing benchmarks begin to incorporate notions of physical plausibility, but they largely remain perception- or diagnostic-oriented and do not systematically evaluate whether predicted behaviors can be translated into executable actions that complete the intended task. To address this gap, we introduce RoboWM-Bench, a manipulation-centric benchmark for embodiment-grounded evaluation of video world models. RoboWM-Bench converts generated behaviors from both human-hand and robotic manipulation videos into embodied action sequences and validates them through robotic execution. The benchmark spans diverse manipulation scenarios and establishes a unified protocol for consistent and reproducible evaluation. Using RoboWM-Bench, we evaluate state-of-the-art video world models and find that reliably generating physically executable behaviors remains an open challenge. Common failure modes include errors in spatial reasoning, unstable contact prediction, and non-physical deformations. While finetuning on manipulation data yields improvements, physical inconsistencies still persist, suggesting opportunities for more physically grounded video generation for robots.
Authors: Jinglin Xu, Yi Li, Chuxiong Sun, Xiao Xu, Jiangmeng Li, Fanjiang Xu
Abstract: Multi-modal test-time adaptation (TTA) enhances the resilience of benchmark multi-modal models against distribution shifts by leveraging the unlabeled target data during inference. Despite the documented success, the advancement of multi-modal TTA methodologies has been impeded by a persistent limitation, i.e., the lack of explicit modeling of category-conditional distributions, which is crucial for yielding accurate predictions and reliable decision boundaries. Canonical Gaussian discriminant analysis (GDA) provides a vanilla modeling of category-conditional distributions and achieves moderate advancement in uni-modal contexts. However, in multi-modal TTA scenario, the inherent modality distribution asymmetry undermines the effectiveness of modeling the category-conditional distribution via the canonical GDA. To this end, we introduce a tailored probabilistic Gaussian model for multi-modal TTA to explicitly model the category-conditional distributions, and further propose an adaptive contrastive asymmetry rectification technique to counteract the adverse effects arising from modality asymmetry, thereby deriving calibrated predictions and reliable decision boundaries. Extensive experiments across diverse benchmarks demonstrate that our method achieves state-of-the-art performance under a wide range of distribution shifts. The code is available at https://github.com/XuJinglinn/AdaPGC.
Authors: Rania Elbadry, Sarfraz Ahmad, Ahmed Heakl, Dani Bouch, Momina Ahsan, Muhra AlMahri, Marwa Elsaid khalil, Yuxia Wang, Salem Lahlou, Sophia Ananiadou, Veselin Stoyanov, Jimin Huang, Xueqing Peng, Preslav Nakov, Zhuohan Xie
Abstract: English financial NLP has progressed rapidly through benchmarks for sentiment, document understanding, and financial question answering, while Arabic financial NLP remains comparatively under-explored despite strong practical demand for trustworthy finance and Islamic-finance assistants. We introduce SAHM, a document-grounded benchmark and instruction-tuning dataset for Arabic financial NLP and Shari'ah-compliant reasoning. SAHM contains 14,380 expert-verified instances spanning seven tasks: AAOIFI standards QA, fatwa-based QA/MCQ, accounting and business exams, financial sentiment analysis, extractive summarization, and event-cause reasoning, curated from authentic regulatory, juristic, and corporate sources. We evaluate 19 strong open and proprietary LLMs using task-specific metrics and rubric-based scoring for open-ended outputs, and find that Arabic fluency does not reliably translate to evidence-grounded financial reasoning: models are substantially stronger on recognition-style tasks than on generation and causal reasoning, with the largest gaps on event-cause reasoning. We release the benchmark, evaluation framework, and an instruction-tuned model to support future research on trustworthy Arabic financial NLP.
Authors: Roberto Martinez-Maldonado, Vanessa Echeverria, Jenna Hawes, YJ Kim, Zara Maddigan, Mikaela Milesi, Todd Nelson, Yi-Shan Tsai
Abstract: Education is not merely the transmission of information or the optimisation of individual performance; it is a fundamentally social, constructive, and relational practice. However, recent advances in generative artificial intelligence (GenAI) increasingly emphasise efficiency, automation, and individualised assistance, risking the weakening of relational learning processes. Despite growing adoption, AI in education (AIED) research has yet to fully articulate how AI can be designed in ways that sustain the social and ecological relationships through which learning occurs. In this paper, we re-centre education as relational and frame learner-AI interactions as context-specific relationships with clearly defined purposes and boundaries, rather than positioning them as substitutes for, or replacements of, human interaction. Grounded in participatory design practices and inspired by Indigenous worldviews (including Aboriginal Australian, Native American, and Mesoamerican traditions) that foreground reciprocity and relational accountability, we argue that meaningful educational AI should support learning with others rather than replace them. We advance this perspective by: i) conceptualising AIED as a relational design problem grounded in reciprocity; ii) articulating key tensions introduced by GenAI in education; and iii) outlining design directions that expand the AIED design space toward reciprocity, including when not to use AI, how to define pedagogical boundaries, and how to support responsible uses of AIED innovations that sustain communities and natural environments.
Authors: Yuanye Wu, Keyi Wang, Linqi Ye, Boyang Xing
Abstract: Learning diverse locomotion skills for humanoid robots in a unified reinforcement learning framework remains challenging due to the conflicting requirements of stability and dynamic expressiveness across different gaits. We present a multi-gait learning approach that enables a humanoid robot to master five distinct gaits -- walking, goose-stepping, running, stair climbing, and jumping -- using a consistent policy structure, action space, and reward formulation. The key contribution is a selective Adversarial Motion Prior (AMP) strategy: AMP is applied to periodic, stability-critical gaits (walking, goose-stepping, stair climbing) where it accelerates convergence and suppresses erratic behavior, while being deliberately omitted for highly dynamic gaits (running, jumping) where its regularization would over-constrain the motion. Policies are trained via PPO with domain randomization in simulation and deployed on a physical 12-DOF humanoid robot through zero-shot sim-to-real transfer. Quantitative comparisons demonstrate that selective AMP outperforms a uniform AMP policy across all five gaits, achieving faster convergence, lower tracking error, and higher success rates on stability-focused gaits without sacrificing the agility required for dynamic ones.
Authors: Yulai Zhang, Yinrong Zhang, Ting Wu, Linqi Ye
Abstract: Developing bipedal football robots in dynamiccombat environments presents challenges related to motionstability and deep coupling of multiple tasks, as well ascontrol switching issues between different states such as up-right walking and fall recovery. To address these problems,this paper proposes a modular reinforcement learning (RL)framework for achieving adaptive multi-task control. Firstly,this framework combines an open-loop feedforward oscilla-tor with a reinforcement learning-based feedback residualstrategy, effectively separating the generation of basic gaitsfrom complex football actions. Secondly, a posture-driven statemachine is introduced, clearly switching between the ballseeking and kicking network (BSKN) and the fall recoverynetwork (FRN), fundamentally preventing state interference.The FRN is efficiently trained through a progressive forceattenuation curriculum learning strategy. The architecture wasverified in Unity simulations of bipedal robots, demonstratingexcellent spatial adaptability-reliably finding and kicking theball even in restricted corner scenarios-and rapid autonomousfall recovery (with an average recovery time of 0.715 seconds).This ensures seamless and stable operation in complex multi-task environments.
Authors: Zhenghua Ma, G Abarajithan, Dimitrios Danopoulos, Olivia Weng, Francesco Restuccia, Ryan Kastner
Abstract: Extreme-edge scientific applications use machine learning models to analyze sensor data and make real-time decisions. Their stringent latency and throughput requirements demand small batch sizes and require that model weights remain fully on-chip. Spatial dataflow implementations are common for extreme-edge applications. Spatial dataflow works well for small networks, but it fails to scale to larger models due to inherent resource scaling limitations. AI Engines on modern FPGA SoCs offer a promising alternative with high compute density and additional on-chip memory. However, the architecture, programming model, and performance-scaling behavior of AI Engines differ fundamentally from those of the programmable logic, making direct comparison non-trivial and the benefits of using AI Engines unclear. This work addresses how and when extreme-edge scientific neural networks should be implemented on AI Engines versus programmable logic. We provide systematic architectural characterization and micro-benchmarking and introduce a latency-adjusted resource equivalence (LARE) metric that identifies when AI Engine implementations outperform programmable logic designs. We further propose spatial and API-level dataflow optimizations tailored to low-latency scientific inference. Finally, we demonstrate the successful deployment of end-to-end neural networks on AI Engines that cannot fit on programmable logic when using the hlsml toolchain.
Authors: Zikang Liu, Peilan Xu
Abstract: Generative answer engines expose content through selective citation rather than ranked retrieval, fundamentally altering how visibility is determined. This shift calls for new optimization methods beyond traditional search engine optimization. Existing generative engine optimization (GEO) approaches primarily rely on token-level text rewriting, offering limited interpretability and weak control over the trade-off between citation visibility and content quality. We propose FeatGEO, a feature-level, multi-objective optimization framework that abstracts webpages into interpretable structural, content, and linguistic properties. Instead of directly editing text, FeatGEO optimizes over this feature space and uses a language model to realize feature configurations into natural language, decoupling high-level optimization from surface-level generation. Experiments on GEO-Bench across three generative engines demonstrate that FeatGEO consistently improves citation visibility while maintaining or improving content quality, substantially outperforming token-level baselines. Further analyses show that citation behavior is more strongly influenced by document-level content properties than by isolated lexical edits, and that the learned feature configurations generalize across language models of different scales.
Authors: Isaiah Thompson, Tanmay Sen, Ritwik Bhattacharya
Abstract: Modern distributed systems generate massive volumes of log data that are critical for detecting anomalies and cyber threats. However, in real world settings, these logs are often distributed across multiple organizations and cannot be centralized due to privacy and security constraints. Existing log anomaly detection methods, including recent large language model (LLM) based approaches, largely rely on centralized training and are not suitable for such environments. In this paper, we propose DP-FLogTinyLLM, a privacy preserving federated framework for log anomaly detection using parameter efficient LLMs. Our approach enables collaborative learning without sharing raw log data by integrating federated optimization with differential privacy. To ensure scalability in resource constrained environments, we employ low rank adaptation (LoRA) for efficient fine tuning of Tiny LLMs at each client. Empirical results on the Thunderbird and BGL datasets show that the proposed framework matches the performance of centralized LLM based methods, while incurring additional computational overhead due to privacy mechanisms. Compared to existing federated baselines, DP-FLogTinyLLM consistently achieves higher precision and F1-score, with particularly strong gains on the Thunderbird dataset, highlighting its effectiveness in detecting anomalies while minimizing false positives.
Authors: Shuai Wu, Xue Li, Yanna Feng, Yufang Li, Zhijun Wang, Ran Wang
Abstract: As Large Language Models (LLMs) continue to evolve through alignment techniques such as Reinforcement Learning from Human Feedback (RLHF) and Constitutional AI, a growing and increasingly conspicuous phenomenon has emerged: the proliferation of verbal tics -- repetitive, formulaic linguistic patterns that pervade model outputs. These range from sycophantic openers ("That's a great question!", "Awesome!") to pseudo-empathetic affirmations ("I completely understand your concern", "I'm right here to catch you") and overused vocabulary ("delve", "tapestry", "nuanced"). In this paper, we present a systematic analysis of the verbal tic phenomenon across eight state-of-the-art LLMs: GPT-5.4, Claude Opus 4.7, Gemini 3.1 Pro, Grok 4.2, Doubao-Seed-2.0-pro, Kimi K2.5, DeepSeek V3.2, and MiMo-V2-Pro. Utilizing a custom evaluation framework for standardized API-based evaluation, we assess 10,000 prompts across 10 task categories in both English and Chinese, yielding 160,000 model responses. We introduce the Verbal Tic Index (VTI), a composite metric quantifying tic prevalence, and analyze its correlation with sycophancy, lexical diversity, and human-perceived naturalness. Our findings reveal significant inter-model variation: Gemini 3.1 Pro exhibits the highest VTI (0.590), while DeepSeek V3.2 achieves the lowest (0.295). We further demonstrate that verbal tics accumulate over multi-turn conversations, are amplified in subjective tasks, and show distinct cross-lingual patterns. Human evaluation (N = 120) confirms a strong inverse relationship between sycophancy and perceived naturalness (r = -0.87, p < 0.001). These results underscore the "alignment tax" of current training paradigms and highlight the urgent need for more authentic human-AI interaction frameworks.
Authors: Lin Sha, Haiyun Guo, Tao Wang, Cong Zhang, Min Huang, Jinqiao Wang, Qinghai Miao
Abstract: Vision-Language Models (VLMs) have become central to autonomous driving systems, yet their deployment is severely bottlenecked by the massive computational overhead of multi-view camera and multi-frame video input. Existing token pruning methods, primarily designed for single-image inputs, treat each frame or view in isolation and thus fail to exploit the inherent spatio-temporal redundancies in driving scenarios. To bridge this gap, we propose ST-Prune, a training-free, plug-and-play framework comprising two complementary modules: Motion-aware Temporal Pruning (MTP) and Ring-view Spatial Pruning (RSP). MTP addresses temporal redundancy by encoding motion volatility and temporal recency as soft constraints within the diversity selection objective, prioritizing dynamic trajectories and current-frame content over static historical background. RSP further resolves spatial redundancy by exploiting the ring-view camera geometry to penalize bilateral cross-view similarity, eliminating duplicate projections and residual background that temporal pruning alone cannot suppress. These two modules together constitute a complete spatio-temporal pruning process, preserving key scene information under strict compression. Validated across four benchmarks spanning perception, prediction, and planning, ST-Prune establishes new state-of-the-art for training-free token pruning. Notably, even at 90\% token reduction, ST-Prune achieves near-lossless performance with certain metrics surpassing the full-model baseline, while maintaining inference speeds comparable to existing pruning approaches.
Authors: Weijie Zhao, Mingquan Liu, Bolun Wang, Simo Wu, Nuobei Xie, Rui-Jie Zhu, Peng Zhou
Abstract: Scaling Transformers typically necessitates training larger models from scratch, as standard architectures struggle to expand without discarding learned representations. We identify the primary bottleneck in the attention mechanism's linear projections, which strictly confine feature extraction to fixed-dimensional subspaces, limiting both expressivity and incremental capacity. To address this, we introduce Nexusformer, which replaces linear $Q/K/V$ projections with a Nexus-Rank layer, a three-stage nonlinear mapping driven by dual activations in progressively higher dimensional spaces. This design overcomes the linearity constraint and enables lossless structured growth: new capacity can be injected along two axes via zero-initialized blocks that preserve pretrained knowledge. Experiments on language modeling and reasoning benchmarks demonstrate that Nexusformer matches Tokenformer's perplexity using up to 41.5\% less training compute during progressive scaling (240M to 440M). Furthermore, our analysis of growth dynamics reveals that zero initialization induces a stable convergence trajectory, allowing us to derive a geometric scaling law that accurately predicts performance across expansion scales.
Authors: Haoyang Chen, Yi Liu, Jianzhi Shao, Tao Zhang, Chengfu Huo, Wei Hu
Abstract: Thinking LLMs produce reasoning traces before answering. Prior activation steering work mainly targets on shaping these traces. It remains less understood how answer tokens actually read and integrate the reasoning to produce reliable outcomes. Focusing on quantitative reasoning, we analyze the answer-to-reasoning attention and observe a benign self-reading pattern aligned with correctness, characterized by a forward drift of the reading focus along the reasoning trace and a persistent concentration on key semantic anchors, whereas incorrect solutions exhibit diffuse and irregular attention pattern. We interpret this as internal certainty during answer decoding, where the model commits to a viable solution branch and integrates key evidence. Following this, we propose a training-free steering method driven by Self-Reading Quality (SRQ) scores combining geometric metrics for process control with semantic metrics for content monitoring. SRQ selects data to build steering vectors that guide inference toward benign self-reading and away from uncertain and disorganized reading. Experiments show that our method yields consistent accuracy gains.
Authors: Siqing Song, Chuang Wang, Yong Lang, Yi Yang, Xu-Yao Zhang
Abstract: Deploying large language models (LLMs) in resource-constrained environments is hindered by heavy computational and memory requirements. We present LBLLM, a lightweight binarization framework that achieves effective W(1+1)A4 quantization through a novel three-stage quantization strategy. The framework proceeds as follows: (1) initialize a high-quality quantized model via PTQ; (2) quantize binarized weights, group-wise bitmaps, and quantization parameters through layer-wise distillation while keeping activations in full precision; and (3) training learnable activation quantization factors to dynamically quantize activations to 4 bits. This decoupled design mitigates interference between weight and activation quantization, yielding greater training stability and better inference accuracy. LBLLM, trained only using 0.016B tokens with a single GPU, surpasses existing state-of-the-art binarization methods on W2A4 quantization settings across tasks of language modeling, commonsense QA, and language understanding. These results demonstrate that extreme low-bit quantization of LLMs can be both practical and highly effective without introducing any extra high-precision channels or rotational matrices commonly used in recent PTQ-based works, offering a promising path toward efficient LLM deployment in resource-limited situations.
Authors: Bo-Jyun Wang, Ying-Jia Lin, Hung-Yu Kao
Abstract: Small language models (SLMs), such as BART, can achieve summarization performance comparable to large language models (LLMs) via distillation. However, existing LLM-based ranking strategies for summary candidates suffer from instability, while classical metrics (e.g., ROUGE) are insufficient to rank high-quality summaries. To address these issues, we introduce \textbf{SCURank}, a framework that enhances summarization by leveraging \textbf{Summary Content Units (SCUs)}. Instead of relying on unstable comparisons or surface-level overlap, SCURank evaluates summaries based on the richness and semantic importance of information content. We investigate the effectiveness of SCURank in distilling summaries from multiple diverse LLMs. Experimental results demonstrate that SCURank outperforms traditional metrics and LLM-based ranking methods across evaluation measures and datasets. Furthermore, our findings show that incorporating diverse LLM summaries enhances model abstractiveness and overall distilled model performance, validating the benefits of information-centric ranking in multi-LLM distillation. The code for SCURank is available at https://github.com/IKMLab/SCURank.
Authors: Xiangmeng Wang, Qian Li, Haiyang Xia, Hao Miao, Qing Li, Guandong Xu
Abstract: Heterophily is a prevalent property of real-world graphs and is well known to impair the performance of homophilic Graph Neural Networks (GNNs). Prior work has attempted to adapt GNNs to heterophilic graphs through non-local neighbor extension or architecture refinement. However, the fundamental reasons behind misclassifications remain poorly understood. In this work, we take a novel perspective by examining recurring inductive subgraphs, empirically and theoretically showing that they act as spurious shortcuts that mislead GNNs and reinforce non-causal correlations in heterophilic graphs. To address this, we adopt a causal inference perspective to analyze and correct the biased learning behavior induced by shortcut inductive subgraphs. We propose a debiased causal graph that explicitly blocks confounding and spillover paths responsible for these shortcuts. Guided by this causal graph, we introduce Causal Disentangled GNN (CD-GNN), a principled framework that disentangles spurious inductive subgraphs from true causal subgraphs by explicitly blocking non-causal paths. By focusing on genuine causal signals, CD-GNN substantially improves the robustness and accuracy of node classification in heterophilic graphs. Extensive experiments on real-world datasets not only validate our theoretical findings but also demonstrate that our proposed CD-GNN outperforms state-of-the-art heterophily-aware baselines.
Authors: Pritam Kar, Gouri Lakshmi S, Saptarshi Bej
Abstract: Anomaly detection in medical imaging is essential for identifying rare pathological conditions, particularly when annotated abnormal samples are limited. We propose a hybrid anomaly detection framework that integrates self-supervised representation learning with manifold-based density estimation, a combination that remains largely unexplored in this domain. Medical images are first embedded into a latent feature space using pretrained, potentially domain-specific, backbones. These representations are then refined via Mean Shift Density Enhancement (MSDE), an iterative manifold-shifting procedure that moves samples toward regions of higher likelihood. Anomaly scores are subsequently computed using Gaussian density estimation in a PCA-reduced latent space, where Mahalanobis distance measures deviation from the learned normal distribution. The framework follows a one-class learning paradigm and requires only normal samples for training. Extensive experiments on seven medical imaging datasets demonstrate state-of-the-art performance. MSDE achieves the highest AUC on four datasets and the highest Average Precision on five datasets, including near-perfect performance on brain tumor detection (0.981 AUC/AP). These results underscore the potential of the proposed framework as a scalable clinical decision-support tool for early disease detection, screening in low-label settings, and robust deployment across diverse imaging modalities.
Authors: Gopal Krishna Shyam, Ila Chandrakar
Abstract: Crop yield prediction is one of the most important challenge, which is crucial to world food security and policy-making decisions. The conventional forecasting techniques are limited in their accuracy with reference to the fact that they utilize static data sources that do not reflect the dynamic and intricate relationships that exist between the variables of the environment over time [5,13]. This paper presents Attention-Based Multi-Modal Deep Learning Framework (ABMMDLF), which is suggested to be used in high-accuracy spatio-temporal crop yield prediction. The model we use combines multi-year satellite imagery, high-resolution time-series of meteorological data and initial soil properties as opposed to the traditional models which use only one of the aforementioned factors [12, 21]. The main architecture involves the use of Convolutional Neural Networks (CNN) to extract spatial features and a Temporal Attention Mechanism to adaptively weight important phenological periods targeted by the algorithm to change over time and condition on spatial features of images and video sequences. As can be experimentally seen, the proposed research work provides an R^2 score of 0.89, which is far better than the baseline models do.
Authors: Daniel M. Jimenez-Gutierrez, Enrique Zuazua, Georgios Kellaris, Joaquin Del Rio, Oleksii Sliusarenko, Xabi Uribe-Etxebarria
Abstract: Federated Learning (FL) enables collaborative model training among multiple parties without centralizing raw data. There are two main paradigms in FL: Horizontal FL (HFL), where all participants share the same feature space but hold different samples, and Vertical FL (VFL), where parties possess complementary features for the same set of samples. A prerequisite for VFL training is privacy-preserving entity alignment (PPEA), which establishes a common index of samples across parties (alignment) without revealing which samples are shared between them. Conventional private set intersection (PSI) achieves alignment but leaks intersection membership, exposing sensitive relationships between datasets. The standard private set union (PSU) mitigates this risk by aligning on the union of identifiers rather than the intersection. However, existing approaches are often limited to two parties or lack support for typo-tolerant matching. In this paper, we introduce the Sherpa.ai multi-party PSU protocol for VFL, a PPEA method that hides intersection membership and enables both exact and noisy matching. The protocol generalizes two-party approaches to multiple parties with low communication overhead and offers two variants: an order-preserving version for exact alignment and an unordered version tolerant to typographical and formatting discrepancies. We prove correctness and privacy, analyze communication and computational (exponentiation) complexity, and formalize a universal index mapping from local records to a shared index space. This multi-party PSU offers a scalable, mathematically grounded protocol for PPEA in real-world VFL deployments, such as multi-institutional healthcare disease detection, collaborative risk modeling between banks and insurers, and cross-domain fraud detection between telecommunications and financial institutions, while preserving intersection privacy.
Authors: Clara Lachenmaier, Hannah Bultmann, Sina Zarrie{\ss}
Abstract: Repair, an important resource for resolving trouble in human-human conversation, remains underexplored in human-LLM interaction. In this study, we investigate how LLMs engage in the interactive process of repair in multi-turn dialogues around solvable and unsolvable math questions. We examine whether models initiate repair themselves and how they respond to user-initiated repair. Our results show strong differences across models: reactions range from being almost completely resistant to (appropriate) repair attempts to being highly susceptible and easily manipulated. We further demonstrate that once conversations extend beyond a single turn, model behavior becomes more distinctive and less predictable across systems. Overall, our findings indicate that each tested LLM exhibits its own characteristic form of unreliability in the context of repair.
Authors: Florentina Voboril, Martin Gebser, Stefan Szeider, Alice Tarzariol
Abstract: Streamliner constraints reduce the search space of combinatorial problems by ruling out portions of the solution space. We adapt the StreamLLM approach, which uses Large Language Models (LLMs) to generate streamliners for Constraint Programming, to Answer Set Programming (ASP). Given an ASP encoding and a few small training instances, we prompt multiple LLMs to propose candidate constraints. Candidates that cause syntax errors, render satisfiable instances unsatisfiable, or degrade performance on all training instances are discarded. The surviving streamliners are evaluated together with the original encoding, and we report results for a virtual best encoding (VBE) that, for each instance, selects the fastest among the original encoding and its streamlined variants. On three ASP Competition benchmarks (Partner Units Problem, Sokoban, Towers of Hanoi), the VBE achieves speedups of up to 4--5x over the original encoding. Different LLMs produce semantically diverse constraints, not mere syntactic variations, indicating that the approach captures genuine problem structure.
Authors: Xianming Li, Zongxi Li, Tsz-fung Andrew Lee, Jing Li, Haoran Xie, Qing Li
Abstract: Parameter-efficient fine-tuning (PEFT) reduces the training cost of full-parameter fine-tuning for large language models (LLMs) by training only a small set of task-specific parameters while freezing the pretrained backbone. However, existing approaches, such as Low-Rank Adaptation (LoRA), achieve adaptation by inserting independent low-rank perturbations directly to individual weights, resulting in a local parameterization of adaptation. We propose ShadowPEFT, a centralized PEFT framework that instead performs layer-level refinement through a depth-shared shadow module. At each transformer layer, ShadowPEFT maintains a parallel shadow state and evolves it repeatedly for progressively richer hidden states. This design shifts adaptation from distributed weight-space perturbations to a shared layer-space refinement process. Since the shadow module is decoupled from the backbone, it can be reused across depth, independently pretrained, and optionally deployed in a detached mode, benefiting edge computing scenarios. Experiments on generation and understanding benchmarks show that ShadowPEFT matches or outperforms LoRA and DoRA under comparable trainable-parameter budgets. Additional analyses on shadow pretraining, cross-dataset transfer, parameter scaling, inference latency, and system-level evaluation suggest that centralized layer-space adaptation is a competitive and flexible alternative to conventional low-rank PEFT.
Authors: Peiqin Lin, Chenyang Lyu, Wenjiang Luo, Haotian Ye, Md Mehrab Hossain, Chunlan Ma, Shaoxiong Ji, Younes Samih, Bo Zeng, Fan Jiang, Yuanbin Cao, Dilda Duisenbek, Adrian Neo Sau Xun, Daria Pozdniakova, Liubou Misevich, Nevena Marinkovi\'c, Ngoc Gia Linh Nguyen, Thi Khanh Linh Do, Sarakmatak Sophy, Baotian Hu, Guanhua Chen, Gongbo Tang, Alham Fikri Aji, Longyue Wang, Weihua Luo
Abstract: Large language models (LLMs) are now deployed worldwide, inspiring a surge of benchmarks that measure their multilingual and multicultural abilities. However, these benchmarks prioritize generic language understanding or superficial cultural trivia, leaving the evaluation of grounded tasks -- where models must reason within real-world, context-rich scenarios -- largely unaddressed. To fill this gap, we present CulturALL, a comprehensive and challenging benchmark to assess LLMs' multilingual and multicultural competence on grounded tasks. CulturALL is built via a human--AI collaborative framework: expert annotators ensure appropriate difficulty and factual accuracy, while LLMs lighten the manual workload. By incorporating diverse sources, CulturALL ensures comprehensive scenario coverage. Each item is carefully designed to present a high level of difficulty, making CulturALL challenging. CulturALL contains 2,610 samples in 14 languages from 51 regions, distributed across 16 topics to capture the full breadth of grounded tasks. Experiments show that the best LLM achieves 44.48% accuracy on CulturALL, underscoring substantial room for improvement.
Authors: Abu Noman Md Sakib, Md. Main Oddin Chisty, Zijie Zhang
Abstract: The use of Large Language Models (LLMs) to support patients in addressing medical questions is becoming increasingly prevalent. However, most of the measures currently used to evaluate the performance of these models in this context only measure how closely a model's answers match semantically, and therefore do not provide a true indication of the model's medical accuracy or of the health equity risks associated with it. To address these shortcomings, we present a new evaluation framework for medical question answering called VB-Score (Verification-Based Score) that provides a separate evaluation of the four components of entity recognition, semantic similarity, factual consistency, and structured information completeness for medical question-answering models. We perform rigorous reviews of the performance of three well-known and widely used LLMs on 48 public health-related topics taken from high-quality, authoritative information sources. Based on our analyses, we discover a major discrepancy between the models' semantic and entity accuracy. Our assessments of the performance of all three models show that each of them has almost uniformly severe performance failures when evaluated against our criteria. Our findings indicate alarming performance disparities across various public health topics, with most of the models exhibiting 13.8% lower performance (compared to an overall average) for all the public health topics that relate to chronic conditions that occur in older and minority populations, which indicates the existence of what's known as condition-based algorithmic discrimination. Our findings also demonstrate that prompt engineering alone does not compensate for basic architectural limitations on how these models perform in extracting medical entities and raise the question of whether semantic evaluation alone is a sufficient measure of medical AI safety.
Authors: Guy Mor-Lan, Omer Goldman, Matan Eyal, Adi Mayrav Gilady, Sivan Eiger, Idan Szpektor, Avinatan Hassidim, Yossi Matias, Reut Tsarfaty
Abstract: Multilingual large language models (LLMs) have minimized the fluency gap between languages. This advancement, however, exposes models to the risk of biased behavior, as knowledge and norms may propagate across languages. In this work, we aim to quantify models' inter- and intra-lingual biases, via their ability to answer locale-ambiguous questions. To this end, we present LocQA, a test set containing 2,156 questions in 12 languages, referring to various locale-dependent facts such as laws, dates, and measurements. The questions do not contain indications of the locales they relate to, other than the querying language itself. LLMs' responses to LocQA locale-ambiguous questions thus reveal models' implicit priors. We used LocQA to evaluate 32 models, and detected two types of structural biases. Inter-lingually, we show a global bias towards answers relevant to the US-locale, even when models are asked in languages other than English. Moreover, we discovered that this global bias is exacerbated in models that underwent instruction tuning, compared to their base counterparts. Intra-lingually, we show that when multiple locales are relevant for the same language, models act as demographic probability engines, prioritizing locales with larger populations. Taken together, insights from LocQA may help in shaping LLMs' desired local behavior, and in quantifying the impact of various training phases on different kinds of biases.
Authors: Rajveer Singh Pall
Abstract: We introduce IndiaFinBench, to our knowledge the first publicly available evaluation benchmark for assessing large language model (LLM) performance on Indian financial regulatory text. Existing financial NLP benchmarks draw exclusively from Western financial corpora (SEC filings, US earnings reports, and English-language financial news), leaving a significant gap in coverage of non-Western regulatory frameworks. IndiaFinBench addresses this gap with 406 expert-annotated question-answer pairs drawn from 192 documents sourced from the Securities and Exchange Board of India (SEBI) and the Reserve Bank of India (RBI), spanning four task types: regulatory interpretation (174 items), numerical reasoning (92 items), contradiction detection (62 items), and temporal reasoning (78 items). Annotation quality is validated through a model-based secondary pass (kappa=0.918 on contradiction detection) and a 60-item human inter-annotator agreement evaluation (kappa=0.611; 76.7% overall agreement). We evaluate twelve models under zero-shot conditions, with accuracy ranging from 70.4% (Gemma 4 E4B) to 89.7% (Gemini 2.5 Flash). All models substantially outperform a non-specialist human baseline of 60.0%. Numerical reasoning is the most discriminative task, with a 35.9 percentage-point spread across models. Bootstrap significance testing (10,000 resamples) reveals three statistically distinct performance tiers. The dataset, evaluation code, and all model outputs are available at https://github.com/rajveerpall/IndiaFinBench
Authors: Xinlin Wang, Mats Brorsson
Abstract: Despite the impressive capabilities of large language models, their substantial computational costs, latency, and privacy risks hinder their widespread deployment in real-world applications. Small Language Models (SLMs) with fewer than 10 billion parameters present a promising alternative; however, their inherent limitations in knowledge and reasoning curtail their effectiveness. Existing research primarily focuses on enhancing SLMs through scaling laws or fine-tuning strategies while overlooking the potential of using agent paradigms, such as tool use and multi-agent collaboration, to systematically compensate for the inherent weaknesses of small models. To address this gap, this paper presents the first large-scale, comprehensive study of <10B open-source models under three paradigms: (1) the base model, (2) a single agent equipped with tools, and (3) a multi-agent system with collaborative capabilities. Our results show that single-agent systems achieve the best balance between performance and cost, while multi-agent setups add overhead with limited gains. Our findings highlight the importance of agent-centric design for efficient and trustworthy deployment in resource-constrained settings.
Authors: Feiyu Zhao, Yiming Chen, Wenhuan Lu, Daipeng Zhang, Xianghu Yue, Jianguo Wei
Abstract: Large Audio-Language Models (LALMs) have recently achieved strong performance across various audio-centric tasks. However, hallucination, where models generate responses that are semantically incorrect or acoustically unsupported, remains largely underexplored in the audio domain. Existing hallucination benchmarks mainly focus on text or vision, while the few audio-oriented studies are limited in scale, modality coverage, and diagnostic depth. We therefore introduce HalluAudio, the first large-scale benchmark for evaluating hallucinations across speech, environmental sound, and music. HalluAudio comprises over 5K human-verified QA pairs and spans diverse task types, including binary judgments, multi-choice reasoning, attribute verification, and open-ended QA. To systematically induce hallucinations, we design adversarial prompts and mixed-audio conditions. Beyond accuracy, our evaluation protocol measures hallucination rate, yes/no bias, error-type analysis, and refusal rate, enabling a fine-grained analysis of LALM failure modes. We benchmark a broad range of open-source and proprietary models, providing the first large-scale comparison across speech, sound, and music. Our results reveal significant deficiencies in acoustic grounding, temporal reasoning, and music attribute understanding, underscoring the need for reliable and robust LALMs.
Authors: Athikash Jeyaganthan, Kai Xu, Franziska Becker, Steffen Koch
Abstract: Qualitative coding relies on a researcher's application of codes to textual data. As coding proceeds across large datasets, interpretations of codes often shift (temporal drift), reducing the credibility of the analysis. Existing Computer-Assisted Qualitative Data Analysis (CAQDAS) tools provide support for data management but offer no workflow for real-time detection of these drifts. We present Co-Refine, an AI-augmented qualitative coding platform that delivers continuous, grounded feedback on coding consistency without disrupting the researcher's workflow. The system employs a three-stage audit pipeline: Stage 1 computes deterministic embedding-based metrics for mathematical consistency; Stage 2 grounds LLM verdicts within $\pm0.15$ of the deterministic scores; and Stage 3 produces code definitions from previous patterns to create a deepening feedback loop. Co-Refine demonstrates that deterministic scoring can effectively constrain LLM outputs to produce reliable, real-time audit signals for qualitative analysis.
Authors: Yusuf \c{C}elebi, Ya\u{g}{\i}z Asker, \"Ozay Ezerceli, Mahmoud ElHussieni, Selva Ta\c{s}, Reyhan Bayraktar, Fatma Bet\"ul Terzio\u{g}lu
Abstract: Fine-tuning Large Language Models (LLMs) remains structurally uncertain despite parameter-efficient methods such as Low-Rank Adaptation (LoRA), as the layer-specific roles of internal representations are poorly understood, leading to heuristic decisions about where adaptation should be applied. We model the evolution of hidden states as a high-dimensional geometric trajectory and propose using the Ramer-Douglas-Peucker (RDP) algorithm, a parameter-free and training-free polygon simplification method that preserves global structural transitions while eliminating locally redundant changes, to identify critical breakpoints along the representation path. Crucially, we use these geometric pivots not merely for analysis, but as a direct decision signal for determining which layers should be adapted during parameter-efficient fine-tuning. By integrating this geometry-aware layer selection strategy into LoRA fine-tuning of Qwen3-8B-Base, we achieve superior performance on MMLU-Math using only 13 RDP-selected layers (81.67%), significantly outperforming both full 36-layer adaptation (79.32%) and random 13-layer selection (75.56%), as well as the baseline Qwen3-8B-Base model (74.25%). These results demonstrate that leveraging the intrinsic geometry of representation trajectories provides a robust, interpretable, and training-free signal for optimizing layer selection during model adaptation.
Authors: Tommi Kerola, Yuya Masuda, Takashi Masuko, Toshiki Nakanishi, Daisuke Nishino, Kuniyuki Takahashi, Hanqin Wang, Yoshihiro Yamada
Abstract: We introduce PLaMo 2.1-VL, a lightweight Vision Language Model (VLM) for autonomous devices, available in 8B and 2B variants and designed for local and edge deployment with Japanese-language operation. Focusing on Visual Question Answering (VQA) and Visual Grounding as its core capabilities, we develop and evaluate the models for two real-world application scenarios: factory task analysis via tool recognition, and infrastructure anomaly detection. We also develop a large-scale synthetic data generation pipeline and comprehensive Japanese training and evaluation resources. PLaMo 2.1-VL outperforms comparable open models on Japanese and English benchmarks, achieving 61.5 ROUGE-L on JA-VG-VQA-500 and 85.2% accuracy on Japanese Ref-L4. For the two application scenarios, it achieves 53.9% zero-shot accuracy on factory task analysis, and fine-tuning on power plant data improves anomaly detection bbox + label F1-score from 39.7 to 64.9.
Authors: Haotian Ye, Haowei Lin, Jingyi Tang, Yizhen Luo, Caiyin Yang, Chang Su, Rahul Thapa, Rui Yang, Ruihua Liu, Zeyu Li, Chong Gao, Dachao Ding, Guangrong He, Miaolei Zhang, Lina Sun, Wenyang Wang, Yuchen Zhong, Zhuohao Shen, Di He, Jianzhu Ma, Stefano Ermon, Tongyang Li, Xiaowen Chu, James Zou, Yuzhi Xu
Abstract: Language models are increasingly used in scientific discovery to generate hypotheses, propose candidate solutions, implement systems, and iteratively refine them. At the core of these trial-and-error loops lies evaluation: the process of obtaining feedback on candidate solutions via verifiers, simulators, or task-specific scoring functions. While prior work has highlighted the importance of evaluation, it has not explicitly formulated the problem of how evaluation-driven discovery loops can be scaled up in a principled and effective manner to push the boundaries of scientific discovery, a problem this paper seeks to address. We introduce Simple Test-time Evaluation-driven Scaling (SimpleTES), a general framework that strategically combines parallel exploration, feedback-driven refinement, and local selection, revealing substantial gains unlocked by scaling evaluation-driven discovery loops along the right dimensions. Across 21 scientific problems spanning six domains, SimpleTES discovers state-of-the-art solutions using gpt-oss models, consistently outperforming both frontier-model baselines and sophisticated optimization pipelines. Particularly, we sped up the widely used LASSO algorithm by over 2x, designed quantum circuit routing policies that reduce gate overhead by 24.5%, and discovered new Erdos minimum overlap constructions that surpass the best-known results. Beyond novel discoveries, SimpleTES produces trajectory-level histories that naturally supervise feedback-driven learning. When post-trained on successful trajectories, models not only improve efficiency on seen problems but also generalize to unseen problems, discovering solutions that base models fail to uncover. Together, our results establish effective evaluation-driven loop scaling as a central axis for advancing LLM-driven scientific discovery, and provide a simple yet practical framework for realizing these gains.
Authors: Huayu Deng, Jinghui Zhong, Xiangming Zhu, Yunbo Wang, Xiaokang Yang
Abstract: High-fidelity measurements of continuum physical fields are essential for scientific discovery and engineering design but remain challenging under sparse and constrained sensing. Conventional reconstruction methods typically rely on fixed sensor layouts, which cannot adapt to evolving physical states. We propose LASER, a unified, closed-loop framework that formulates active sensing as a Partially Observable Markov Decision Process (POMDP). At its core, LASER employs a continuum field latent world model that captures the underlying physical dynamics and provides intrinsic reward feedback. This enables a reinforcement learning policy to simulate ''what-if'' sensing scenarios within a latent imagination space. By conditioning sensor movements on predicted latent states, LASER navigates toward potentially high-information regions beyond current observations. Our experiments demonstrate that LASER consistently outperforms static and offline-optimized strategies, achieving high-fidelity reconstruction under sparsity across diverse continuum fields.
Authors: Vasiliki Papanikou, Evaggelia Pitoura
Abstract: Graph representation learning has achieved notable success in encoding graph-structured data into latent vector spaces, enabling a wide range of downstream tasks. However, these node representations remain opaque and difficult to interpret. Existing explainability methods primarily focus on supervised settings or on explaining individual representation dimensions, leaving a critical gap in explaining the overall structure of node representations. In this paper, we propose TACENR (Task-Agnostic Contrastive Explanations for Node Representations), a local explanation method that identifies not only attribute features but also proximity and structural ones that contribute the most in the representation space. TACENR builds on contrastive learning, through which we learn a similarity function in the representation space, revealing which are the features that play an important role in the representation of a node. While our focus is on task-agnostic explanations, TACENR can be applied to supervised scenarios as well. Experimental results demonstrate that proximity and structural features play a significant role in shaping node representations and that our supervised variant performs comparably to existing task-specific approaches in identifying the most impactful features.
Authors: Seunghee Han, Jaewoong Lee, Jihan Kim
Abstract: Metal-organic frameworks (MOFs) are a major target of machine-learning-based property prediction, yet most models assume that a single framework representation maps to a single property value. This assumption becomes problematic for experimental MOFs, where samples reported as the same framework can exhibit different properties because of differences in crystallinity, phase purity, defects, and other sample-dependent factors. Here we introduce Experimental X-ray Diffraction Integrated Transformer (EXIT), a multimodal transformer for sample-aware prediction of MOF properties that combines MOFid with X-ray diffraction (XRD). In EXIT, MOFid encodes MOF identity, whereas XRD provides complementary information about the experimentally realized sample state. EXIT is pre-trained on one million hypothetical MOFs with simulated XRD to learn transferable representations, leading to improved downstream performance relative to existing approaches. EXIT is fine-tuned on literature-derived experimental datasets for surface area and pore volume prediction. Incorporating experimental XRD improves predictive performance relative to models without experimental XRD, and attention analysis and sample-level case studies further show that EXIT assigns different predictions to samples sharing the same MOF identity when their XRD patterns differ. These results establish a practical step from framework-aware to sample-aware MOF property prediction and highlight the value of incorporating experimental characterization into porous materials informatics.
Authors: Gerard Pons, Carlos Escolano, Besim Bilalli, Anna Queralt
Abstract: Knowledge Graph Embeddings (KGEs) support a wide range of downstream tasks over Knowledge Graphs (KGs). In practice, KGs evolve as new entities and facts are added, motivating Continual Knowledge Graph Embedding (CKGE) methods that update embeddings over time. Current CKGE approaches address catastrophic forgetting (i.e., the performance degradation on previously learned tasks) primarily by limiting changes to existing embeddings. However, we show that this view is incomplete. When new entities are introduced, their embeddings can interfere with previously learned ones, causing the model to predict them in place of previously correct answers. This phenomenon, which we call entity interference, has been largely overlooked and is not accounted for in current CKGE evaluation protocols. As a result, the assessment of catastrophic forgetting becomes misleading, and CKGE methods performance is systematically overestimated. To address this issue, we introduce a corrected CKGE evaluation protocol that accounts for entity interference. Through experiments on multiple benchmarks, we show that ignoring this effect can lead to performance overestimation of up to 25%, particularly in scenarios with significant entity growth. We further analyze how different CKGE methods and KGE models are affected by the different sources of forgetting, and introduce a catastrophic forgetting metric tailored to CKGE.
Authors: Yukai Feng, Zhiheng Wu, Zhengxing Wu, Junwen Gu, Junzhi Yu
Abstract: Traditional policy learning methods in cooperative pursuit face fundamental challenges in biomimetic underwater robots, where long-horizon decision making, partial observability, and inter-robot coordination require both expressiveness and stability. To address these issues, a novel framework called Mamba-based multi-agent group relative policy optimization (M$^{2}$GRPO) is proposed, which integrates a selective state-space Mamba policy with group-relative policy optimization under the centralized-training and decentralized-execution (CTDE) paradigm. Specifically, the Mamba-based policy leverages observation history to capture long-horizon temporal dependencies and exploits attention-based relational features to encode inter-agent interactions, producing bounded continuous actions through normalized Gaussian sampling. To further improve credit assignment without sacrificing stability, the group-relative advantages are obtained by normalizing rewards across agents within each episode and optimized through a multi-agent extension of GRPO, significantly reducing the demand for training resources while enabling stable and scalable policy updates. Extensive simulations and real-world pool experiments across team scales and evader strategies demonstrate that M$^{2}$GRPO consistently outperforms MAPPO and recurrent baselines in both pursuit success rate and capture efficiency. Overall, the proposed framework provides a practical and scalable solution for cooperative underwater pursuit with biomimetic robot systems.
Authors: Fan Li, Chonghuinan Wang, Lina Lei, Yuping Qiu, Jiaqi Xu, Jiaxiu Jiang, Xinran Qin, Zhikai Chen, Fenglong Song, Zhixin Wang, Renjing Pei, Wangmeng Zuo
Abstract: Common image editing tasks typically adopt powerful generative diffusion models as the leading paradigm for real-world content editing. Meanwhile, although reinforcement learning (RL) methods such as Diffusion-DPO and Flow-GRPO have further improved generation quality, efficiently applying Reinforcement Learning from Human Feedback (RLHF) to diffusion-based editing remains largely unexplored, due to a lack of scalable human-preference datasets and frameworks tailored to diverse editing needs. To fill this gap, we propose HP-Edit, a post-training framework for Human Preference-aligned Editing, and introduce RealPref-50K, a real-world dataset across eight common tasks and balancing common object editing. Specifically, HP-Edit leverages a small amount of human-preference scoring data and a pretrained visual large language model (VLM) to develop HP-Scorer--an automatic, human preference-aligned evaluator. We then use HP-Scorer both to efficiently build a scalable preference dataset and to serve as the reward function for post-training the editing model. We also introduce RealPref-Bench, a benchmark for evaluating real-world editing performance. Extensive experiments demonstrate that our approach significantly enhances models such as Qwen-Image-Edit-2509, aligning their outputs more closely with human preference.
Authors: Joshua Niemeijer, Alaa Eddine Ben Zekri, Reza Bahmanyar, Philipp M. Schm\"alzle, Houda Chaabouni-Chouayakh, Franz Kurz
Abstract: Understanding road scenes in a geometrically consistent, scene-centric representation is crucial for planning and mapping. We present GOLD-BEV, a framework that learns dense bird's-eye-view (BEV) semantic environment maps-including dynamic agents-from ego-centric sensors, using time-synchronized aerial imagery as supervision only during training. BEV-aligned aerial crops provide an intuitive target space, enabling dense semantic annotation with minimal manual effort and avoiding the ambiguity of ego-only BEV labeling. Crucially, strict aerial-ground synchronization allows overhead observations to supervise moving traffic participants and mitigates the temporal inconsistencies inherent to non-synchronized overhead sources. To obtain scalable dense targets, we generate BEV pseudo-labels using domain-adapted aerial teachers, and jointly train BEV segmentation with optional pseudo-aerial BEV reconstruction for interpretability. Finally, we extend beyond aerial coverage by learning to synthesize pseudo-aerial BEV images from ego sensors, which support lightweight human annotation and uncertainty-aware pseudo-labeling on unlabeled drives.
Authors: Alessandro G. Buda, Giuseppe Primiero, Leonardo Ceragioli, Melissa Antonelli
Abstract: Generative AI systems are known to amplify biases present in their training data. While several inference-time mitigation strategies have been proposed, they remain largely empirical and lack formal guarantees. In this paper we introduce CTLF, a branching-time logic designed to reason about bias in series of generative AI outputs. CTLF adopts a counting worlds semantics where each world represents a possible output at a given step in the generation process and introduces modal operators that allow us to verify whether the current output series respects an intended probability distribution over a protected attribute, to predict the likelihood of remaining within acceptable bounds as new outputs are generated, and to determine how many outputs are needed to remove in order to restore fairness. We illustrate the framework on a toy example of biased image generation, showing how CTLF formulas can express concrete fairness properties at different points in the output series.
Authors: Fanyu Wang, Xiaoxi Kang, Paul Burgess, Aashish Srivastava, Chetan Arora, Adnan Trakic, Lay-Ki Soon, Md Khalid Hossain, Lizhen Qu
Abstract: More than half of the global population struggles to meet their civil justice needs due to limited legal resources. While Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, significant challenges remain even at the foundational step of legal issue identification. To investigate LLMs' capabilities in this task, we constructed a dataset from 769 real-world Malaysian Contract Act court cases, using GPT-4o to extract facts and generate candidate legal issues, annotated by senior legal experts, which reveals a critical limitation: while LLMs generate diverse issue candidates, their precision remains inadequate (GPT-4o achieves only 62%). To address this gap, we propose LePREC (Legal Professional-inspired Reasoning Elicitation and Classification), a neuro-symbolic framework combining neural generation with structured statistical reasoning. LePREC consists of: (1) a neuro component leverages LLMs to transform legal descriptions into question-answer pairs representing diverse analytical factors, and (2) a symbolic component applies sparse linear models over these discrete features, learning explicit algebraic weights that identify the most informative reasoning factors. Unlike end-to-end neural approaches, LePREC achieves interpretability through transparent feature weighting while maintaining data efficiency through correlation-based statistical classification. Experiments show a 30-40% improvement over advanced LLM baselines, including GPT-4o and Claude, confirming that correlation-based factor-issue analysis offers a more data-efficient solution for relevance decisions.
Authors: Chengyun Wang, Liwei Chen, Nils Thuerey
Abstract: Understanding how complex systems respond to perturbations, such as whether they will remain stable or what their most sensitive patterns are, is a fundamental challenge across science and engineering. Traditional stability and receptivity (resolvent) analyses are powerful but rely on known equations and linearization, limiting their use in nonlinear or poorly modeled systems. Here, we introduce a data-driven framework that automatically identifies stability properties and optimal forcing responses from observation data alone, without requiring governing equations. By training a neural network as a dynamics emulator and using automatic differentiation to extract its Jacobian, we can compute eigenmodes and resolvent modes directly from data. We demonstrate the method on both canonical chaotic models and high-dimensional fluid flows, successfully identifying dominant instability modes and input-output structures even in strongly nonlinear regimes. By leveraging a neural network-based emulator, we readily obtain a nonlinear representation of system dynamics while additionally retrieving intricate dynamical patterns that were previously difficult to resolve. This equation-free methodology establishes a broadly applicable tool for analyzing complex, high-dimensional datasets, with immediate relevance to grand challenges in fields such as climate science, neuroscience, and fluid engineering.
Authors: Kelly McConvey, Dipto Das, Maya Ghai, Angelina Zhai, Rosa Lee, Shion Guha
Abstract: Fairness audits of institutional risk models are critical for understanding how deployed machine learning pipelines allocate resources. Drawing on multi-year collaboration with Centennial College, where our prior ethnographic work introduced the ASP-HEI Cycle, we present a replica-based audit of a deployed Early Warning System (EWS), replicating its model using institutional training data and design specifications. We evaluate disparities by gender, age, and residency status across the full pipeline (training data, model predictions, and post-processing) using standard fairness metrics. Our audit reveals systematic misallocation: younger, male, and international students are disproportionately flagged for support, even when many ultimately succeed, while older and female students with comparable dropout risk are under-identified. Post-processing amplifies these disparities by collapsing heterogeneous probabilities into percentile-based risk tiers. This work provides a replicable methodology for auditing institutional ML systems and shows how disparities emerge and compound across stages, highlighting the importance of evaluating construct validity alongside statistical fairness. It contributes one empirical thread to a broader program investigating algorithms, student data, and power in higher education.
Authors: Chengjun Pan, Shichun Liu, Jiahang Lin, Dingwei Zhu, Jiazheng Zhang, Shihan Dou, Songyang Gao, Zhenhua Han, Binghai Wang, Rui Zheng, Xuanjing Huang, Tao Gui, Yansong Feng
Abstract: Reinforcement learning (RL) for LLM post-training faces a fundamental design choice: whether to use a learned critic as a baseline for policy optimization. Classical theory favors critic-based methods such as PPO for variance reduction, yet critic-free alternatives like GRPO have gained widespread adoption due to their simplicity and competitive performance. We show that in sparse-reward settings, a learned critic can inject estimation noise that exceeds the state signal it captures, increasing rather than reducing advantage variance. By casting baseline selection as a Kalman filtering problem, we unify PPO and GRPO as two extremes of the Kalman gain and prove that explained variance (EV), computable from a single training batch, identifies the exact boundary: positive EV indicates the critic reduces variance, while zero or negative EV signals that it inflates variance. Building on this insight, we propose Explained Variance Policy Optimization (EVPO), which monitors batch-level EV at each training step and adaptively switches between critic-based and batch-mean advantage estimation, provably achieving no greater variance than the better of the two at every step. Across four tasks spanning classical control, agentic interaction, and mathematical reasoning, EVPO consistently outperforms both PPO and GRPO regardless of which fixed baseline is stronger on a given task. Further analysis confirms that the adaptive gating tracks critic maturation over training and that the theoretically derived zero threshold is empirically optimal.
Authors: Saket Maganti
Abstract: The consensus that GCN, GraphSAGE, GAT, and EvolveGCN outperform feature-only baselines on the Elliptic Bitcoin Dataset is widely cited but has not been rigorously stress-tested under a leakage-free evaluation protocol. We perform a seed-matched inductive-versus-transductive comparison and find that this consensus does not hold. Under a strictly inductive protocol, Random Forest on raw features achieves F1 = 0.821 and outperforms all evaluated GNNs, while GraphSAGE reaches F1 = 0.689 +/- 0.017. A paired controlled experiment reveals a 39.5-point F1 gap attributable to training-time exposure to test-period adjacency. Additionally, edge-shuffle ablations show that randomly wired graphs outperform the real transaction graph, indicating that the dataset's topology can be misleading under temporal distribution shift. Hybrid models combining GNN embeddings with raw features provide only marginal gains and remain substantially below feature-only baselines. We release code, checkpoints, and a strict-inductive protocol to enable reproducible, leakage-free evaluation.
Authors: Jianyang Gao, Yutong Gou, Yuexuan Xu, Jifan Shi, Yongyi Yang, Shuolin Li, Raymond Chi-Wing Wong, Cheng Long
Abstract: This technical note revisits the relationship between RaBitQ and TurboQuant under a unified comparison framework. We compare the two methods in terms of methodology, theoretical guarantees, and empirical performance, using a reproducible, transparent, and symmetric setup. Our results show that, despite the claimed advantage of TurboQuant, TurboQuant does not provide a consistent improvement over RaBitQ in directly comparable settings; in many tested configurations, it performs worse than RaBitQ. We further find that several reported runtime and recall results in the TurboQuant paper could not be reproduced from the released implementation under the stated configuration. Overall, this note clarifies the shared structure and genuine differences between the two lines of work, while documenting reproducibility issues in the experimental results reported by the TurboQuant paper.
Authors: Lekai Qian, Haoyu Gu, Jingwei Zhao, Ziyu Wang
Abstract: Tokenizing music to fit the general framework of language models is a compelling challenge, especially considering the diverse symbolic structures in which music can be represented (e.g., sequences, grids, and graphs). To date, most approaches tokenize symbolic music as sequences of musical events, such as onsets, pitches, time shifts, or compound note events. This strategy is intuitive and has proven effective in Transformer-based models, but it treats the regularity of musical time implicitly: individual tokens may span different durations, resulting in non-uniform time progression. In this paper, we instead consider whether an alternative tokenization is possible, where a uniform-length musical step (e.g., a beat) serves as the basic unit. Specifically, we encode all events within a single time step at the same pitch as one token, and group tokens explicitly by time step, which resembles a sparse encoding of a piano-roll representation. We evaluate the proposed tokenization on music continuation and accompaniment generation tasks, comparing it with mainstream event-based methods. Results show improved musical quality and structural coherence, while additional analyses confirm higher efficiency and more effective capture of long-range patterns with the proposed tokenization.
Authors: Alankrit Chona, Igor Kozlov, Ambuj Kumar
Abstract: We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model (LLM) agents perform the core SOC analyst task of threat hunting: given a database of raw Windows event logs with no guided questions or hints, identify the exact timestamps of malicious events. The benchmark wraps 106 real attack procedures from the OTRF Security-Datasets corpus - spanning 86 MITRE ATT&CK sub-techniques across 12 tactics - into a Gymnasium reinforcement-learning environment. Each episode presents the agent with an in-memory SQLite database of 75,000-135,000 log records produced by a deterministic campaign simulator that time-shifts and entity-obfuscates the raw recordings. The agent must iteratively submit SQL queries to discover malicious event timestamps and explicitly flag them, scored CTF-style against Sigma-rule-derived ground truth. Evaluating five frontier models - Claude Opus 4.6, GPT-5, Gemini 3.1 Pro, Kimi K2.5, and Gemini 3 Flash - on 26 campaigns covering 105 of 106 procedures, we find that all models fail dramatically: the best model (Claude Opus 4.6) submits correct flags for only 3.8% of malicious events on average, and no run across any model ever finds all flags. We define a passing score as >= 50% recall on every ATT&CK tactic - the minimum bar for unsupervised SOC deployment. No model passes: the leader clears this bar on 5 of 13 tactics and the remaining four on zero. These results suggest that current LLMs are poorly suited for open-ended, evidence-driven threat hunting despite strong performance on curated Q&A security benchmarks.
Authors: Hongwei Xu
Abstract: Teams of LLM agents increasingly collaborate on tasks spanning days or weeks: multi-day data-generation sprints where generator, reviewer, and auditor agents coordinate in real time on overlapping batches; specialists carrying findings forward across session restarts; product decisions compounding over many review rounds. This requires agents to share, evaluate, and combine each other's cognitive state in real time across sessions. We call this cross-session agent-to-agent cognitive collaboration, distinct from parallel agent execution. To enable it, three problems must be solved together. (P1) Each agent decides field by field what to accept from peers, not accept or reject whole messages. (P2) Every claim is traceable to source, so returning claims are recognised as echoes of the receiver's own prior thinking. (P3) Memory that survives session restarts is relevant because of how it was stored, not how it is retrieved. These are protocol-level properties at the semantic layer of agent communication, distinct from tool-access and task-delegation protocols at lower layers. We call this missing protocol layer "semantic infrastructure," and the Mesh Memory Protocol (MMP) specifies it. Four composable primitives work together: CAT7, a fixed seven-field schema for every Cognitive Memory Block (CMB); SVAF, which evaluates each field against the receiver's role-indexed anchors and realises P1; inter-agent lineage, carried as parents and ancestors of content-hash keys and realising P2; and remix, which stores only the receiver's own role-evaluated understanding of each accepted CMB, never the raw peer signal, realising P3. MMP is specified, shipped, and running in production across three reference deployments, where each session runs an autonomous agent as a mesh peer with its own identity and memory, collaborating with other agents across the network for collective intelligence.
Authors: Bobo Li, Rui Wu, Zibo Ji, Meishan Zhang, Hao Fei, Min Zhang, Mong-Li Lee, Wynne Hsu
Abstract: Large Language Model agents have rapidly evolved from static text generators into dynamic systems capable of executing complex autonomous workflows. To enhance reliability, multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing. While such role-playing effectively leverages domain expert knowledge, we find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry (AOA). Specifically, an agent acting as an actor (during self-reflection) tends to attribute failures to external factors, whereas an observer (during mutual auditing) attributes the same errors to internal faults. We quantify this using our new Ambiguous Failure Benchmark, which reveals that simply swapping perspectives triggers the AOA effect in over 20% of cases for most models. To tame this bias, we introduce ReTAS (Reasoning via Thesis-Antithesis-Synthesis), a model trained through dialectical alignment to enforce perspective-invariant reasoning. By integrating dialectical chain-of-thought with Group Relative Policy Optimization, ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus. Experiments demonstrate that ReTAS effectively mitigates attribution inconsistency and significantly improves fault resolution rates in ambiguous scenarios.
Authors: Yanshuo Wang, Yuan Xu, Xuesong Li, Jie Hong, Yizhou Wang, Chang Wen Chen, Wentao Zhu
Abstract: Egocentric assistants often rely on first-person view data to capture user behavior and context for personalized services. Since different users exhibit distinct habits, preferences, and routines, such personalization is essential for truly effective assistance. However, effectively integrating long-term user data for personalization remains a key challenge. To address this, we introduce EgoSelf, a system that includes a graph-based interaction memory constructed from past observations and a dedicated learning task for personalization. The memory captures temporal and semantic relationships among interaction events and entities, from which user-specific profiles are derived. The personalized learning task is formulated as a prediction problem where the model predicts possible future interactions from individual user's historical behavior recorded in the graph. Extensive experiments demonstrate the effectiveness of EgoSelf as a personalized egocentric assistant. Code is available at https://abie-e.github.io/EgoSelf/.
Authors: Jonas Waldendorf, Bashar Awwad Shiekh Hasan, Evgenii Tsymbalov
Abstract: Hallucinations in Speech Large Language Models (SpeechLLMs) pose significant risks, yet existing detection methods typically rely on gold-standard outputs that are costly or impractical to obtain. Moreover, hallucination detection methods developed for text-based LLMs do not directly capture audio-specific signals. We investigate four attention-derived metrics: AUDIORATIO, AUDIOCONSISTENCY, AUDIOENTROPY, and TEXTENTROPY, designed to capture pathological attention patterns associated with hallucination, and train lightweight logistic regression classifiers on these features for efficient inference-time detection. Across automatic speech recognition and speech-to-text translation tasks, evaluations on Qwen-2-Audio and Voxtral-3B show that our approach outperforms uncertainty-based and prior attention-based baselines on in-domain data, achieving improvements of up to +0.23 PR-AUC, and generalises to out-of-domain ASR settings. We further find that strong performance can be achieved with approximately 100 attention heads, improving out-of-domain generalisation compared to using all heads. While effectiveness is model-dependent and task-specific training is required, our results demonstrate that attention patterns provide a valuable tool for hallucination detection in SpeechLLMs.
Authors: Donghwan Lee
Abstract: Q-learning is one of the most fundamental algorithms in reinforcement learning. We analyze constant-stepsize Q-learning through a direct stochastic switching system representation. The key observation is that the Bellman maximization error can be represented exactly by a stochastic policy. Therefore, the Q-learning error admits a switched linear conditional-mean recursion with martingale-difference noise. The intrinsic drift rate is the joint spectral radius (JSR) of the direct switching family, which can be strictly smaller than the standard row-sum rate. Using this representation, we derive a finite-time final-iterate bound via a JSR-induced Lyapunov function and then give a computable quadratic-certificate version.
Authors: Wenqing Wu, Chengzhi Zhang, Yi Zhao, Tong Bao
Abstract: With the rapid advancement of Large Language Models (LLMs), the academic community has faced unprecedented disruptions, particularly in the realm of academic communication. The primary function of peer review is improving the quality of academic manuscripts, such as clarity, originality and other evaluation aspects. Although prior studies suggest that LLMs are beginning to influence peer review, it remains unclear whether they are altering its core evaluative functions. Moreover, the extent to which LLMs affect the linguistic form, evaluative focus, and recommendation-related signals of peer-review reports has yet to be systematically examined. In this study, we examine the changes in peer review reports for academic articles following the emergence of LLMs, emphasizing variations at fine-grained level. Specifically, we investigate linguistic features such as the length and complexity of words and sentences in review comments, while also automatically annotating the evaluation aspects of individual review sentences. We also use a maximum likelihood estimation method, previously established, to identify review reports that potentially have modified or generated by LLMs. Finally, we assess the impact of evaluation aspects mentioned in LLM-assisted review reports on the informativeness of recommendation for paper decision-making. The results indicate that following the emergence of LLMs, peer review texts have become longer and more fluent, with increased emphasis on summaries and surface-level clarity, as well as more standardized linguistic patterns, particularly reviewers with lower confidence score. At the same time, attention to deeper evaluative dimensions, such as originality, replicability, and nuanced critical reasoning, has declined.
Authors: Mircea Timpuriu, Mihaela-Claudia Cercel, Dumitru-Clementin Cercel
Abstract: The importance of clear and correct text in legal documents cannot be understated, and, consequently, a grammatical error correction tool meant to assist a professional in the law must have the ability to understand the possible errors in the context of a legal environment, correcting them accordingly, and implicitly needs to be trained in the same environment, using realistic legal data. However, the manually annotated data required by such a process is in short supply for languages such as Romanian, much less for a niche domain. The most common approach is the synthetic generation of parallel data; however, it requires a structured understanding of the Romanian grammar. In this paper, we introduce, to our knowledge, the first Romanian-language parallel dataset for the detection and correction of grammatical errors in the legal domain, RoLegalGEC, which aggregates 350,000 examples of errors in legal passages, along with error annotations. Moreover, we evaluate several neural network models that transform the dataset into a valuable tool for both detecting and correcting grammatical errors, including knowledge-distillation Transformers, sequence tagging architectures for detection, and a variety of pre-trained text-to-text Transformer models for correction. We consider that the set of models, together with the novel RoLegalGEC dataset, will enrich the resource base for further research on Romanian.
Authors: Kihyuk Lee
Abstract: This study compared repeated generation consistency of exercise prescription outputs across three large language models (LLMs), specifically GPT-4.1, Claude Sonnet 4.6, and Gemini 2.5 Flash, under temperature=0 conditions. Each model generated prescriptions for six clinical scenarios 20 times, yielding 360 total outputs analyzed across four dimensions: semantic similarity, output reproducibility, FITT classification, and safety expression. Mean semantic similarity was highest for GPT-4.1 (0.955), followed by Gemini 2.5 Flash (0.950) and Claude Sonnet 4.6 (0.903), with significant inter-model differences confirmed (H = 458.41, p < .001). Critically, these scores reflected fundamentally different generative behaviors: GPT-4.1 produced entirely unique outputs (100%) with stable semantic content, while Gemini 2.5 Flash showed pronounced output repetition (27.5% unique outputs), indicating that its high similarity score derived from text duplication rather than consistent reasoning. Identical decoding settings thus yielded fundamentally different consistency profiles, a distinction that single-output evaluations cannot capture. Safety expression reached ceiling levels across all models, confirming its limited utility as a differentiating metric. These results indicate that model selection constitutes a clinical rather than merely technical decision, and that output behavior under repeated generation conditions should be treated as a core criterion for reliable deployment of LLM-based exercise prescription systems.
Authors: Shuhai Peng, Hui Lu, Jinjiang Liu, Liyang Chen, Guiping Zhong, Jiakui Li, Huimeng Wang, Haiyun Li, Liang Cao, Shiyin Kang, Zhiyong Wu
Abstract: While generative models have set new benchmarks for Target Speaker Extraction (TSE), their inherent reliance on global context precludes deployment in real-time applications. Direct adaptation to streaming scenarios often leads to catastrophic inference performance degradation due to the severe mismatch between training and streaming inference. To bridge this gap, we present the first autoregressive (AR) models tailored for streaming TSE. Our approach introduces a Chunk-wise Interleaved Splicing Paradigm that ensures highly efficient and stable streaming inference. To ensure the coherence between the extracted speech segments, we design a historical context refinement mechanism that mitigates boundary discontinuities by leveraging historical information. Experiments on Libri2Mix show that while AR generative baseline exhibits performance degradation at low latencies, our approach maintains 100% stability and superior intelligibility. Furthermore, our streaming results are comparable to or even surpass offline baselines. Additionally, our model achieves a Real-Time-Factor (RTF) of 0.248 on consumer-level GPUs. This work provides empirical evidence that AR generative backbones are viable for latency-sensitive applications through the Chunk-wise Interleaved Splicing Paradigm.
Authors: Tongxin Li
Abstract: Modern world models are becoming too complex to admit explicit dynamical descriptions. We study safety-critical contextual control, where a Planner must optimize a task objective using only feasibility samples from a black-box Simulator, conditioned on a context signal $\xi_t$. We develop a sample-based Penalized Predictive Control (PPC) framework grounded in online Riemannian optimization, in which the Simulator compresses the feasibility manifold into a score-based density $\hat{p}(u \mid \xi_t)$ that endows the action space with a Riemannian geometry guiding the Planner's gradient descent. The barrier curvature $\kappa(\xi_t)$, the minimum curvature of the conditional log-density $-\ln\hat{p}(\cdot\mid\xi_t)$, governs both convergence rate and safety margin, replacing the Lipschitz constant of the unknown dynamics. Our main result is a contextual safety bound showing that the distance from the true feasibility manifold is controlled by the score estimation error and a ratio that depends on $\kappa(\xi_t)$, both of which improve with richer context. Simulations on a dynamic navigation task confirm that contextual PPC substantially outperforms marginal and frozen density models, with the advantage growing after environment shifts.
Authors: Yanhui Chen, Baoyao Yang, Siqi Liu, Jingchao Wang
Abstract: SAM3 advances open-vocabulary semantic segmentation by introducing a prompt-driven mask generation paradigm. However, in multi-class open-vocabulary scenarios, masks generated independently from different category prompts lack a unified and inter-class comparable evidence scale, often resulting in overlapping coverage and unstable competition. Moreover, synonymous expressions of the same concept tend to activate inconsistent semantic and spatial evidence, leading to intra-class drift that exacerbates inter-class conflicts and compromises overall inference stability. To address these issues, we propose CoCo-SAM3 (Concept-Conflict SAM3), which explicitly decouples inference into intra-class enhancement and inter-class competition. Our method first aligns and aggregates evidence from synonymous prompts to strengthen concept consistency. It then performs inter-class competition on a unified comparable scale, enabling direct pixel-wise comparisons among all candidate classes. This mechanism stabilizes multi-class inference and effectively mitigates inter-class conflicts. Without requiring any additional training, CoCo-SAM3 achieves consistent improvements across eight open-vocabulary semantic segmentation benchmarks.
Authors: Lam Pham, Khoi Vu, Dat Tran, Phat Lam, Vu Nguyen, David Fischinger, Alexander Schindler, Martin Boyer, Son Le
Abstract: In this paper, we propose a deep-learning framework for environmental sound deepfake detection (ESDD) -- the task of identifying whether the sound scene and sound event in an input audio recording is fake or not. To this end, we conducted extensive experiments to explore how individual spectrograms, a wide range of network architectures and pre-trained models, ensemble of spectrograms or network architectures affect the ESDD task performance. The experimental results on the benchmark datasets of EnvSDD and ESDD-Challenge-TestSet indicate that detecting deepfake audio of sound scene and detecting deepfake audio of sound event should be considered as individual tasks. We also indicate that the approach of finetuning a pre-trained model is more effective compared with training a model from scratch for the ESDD task. Eventually, our best model, which was finetuned from the pre-trained WavLM model with the proposed three-stage training strategy, achieve the Accuracy of 0.98, F1 Score of 0.95, AuC of 0.99 on EnvSDD Test subset and the Accuracy of 0.88, F1 Score of 0.77, and AuC of 0.92 on ESDD-Challenge-TestSet dataset.
Authors: Robert Stanley, Avi Verma, Lillian Tsai, Konstantinos Kallas, Sam Kumar
Abstract: AI agents promise to serve as general-purpose personal assistants for their users, which requires them to have access to private user data (e.g., personal and financial information). This poses a serious risk to security and privacy. Adversaries may attack the AI model (e.g., via prompt injection) to exfiltrate user data. Furthermore, sharing private data with an AI agent requires users to trust a potentially unscrupulous or compromised AI model provider with their private data. This paper presents GAAP (Guaranteed Accounting for Agent Privacy), an execution environment for AI agents that guarantees confidentiality for private user data. Through dynamic and directed user prompts, GAAP collects permission specifications from users describing how their private data may be shared, and GAAP enforces that the agent's disclosures of private user data, including disclosures to the AI model and its provider, comply with these specifications. Crucially, GAAP provides this guarantee deterministically, without trusting the agent with private user data, and without requiring any AI model or the user prompt to be free of attacks. GAAP enforces the user's permission specification by tracking how the AI agent accesses and uses private user data. It augments Information Flow Control with novel persistent data stores and annotations that enable it to track the flow of private information both across execution steps within a single task, and also over multiple tasks separated in time. Our evaluation confirms that GAAP blocks all data disclosure attacks, including those that make other state-of-the-art systems disclose private user data to untrusted parties, without a significant impact on agent utility.
Authors: Yi Zhong, Buqiang Xu, Yijun Wang, Zifei Shan, Shuofei Qiao, Guozhou Zheng, Ningyu Zhang
Abstract: At present, executable visual workflows have emerged as a mainstream paradigm in real-world industrial deployments, offering strong reliability and controllability. However, in current practice, such workflows are almost entirely constructed through manual engineering: developers must carefully design workflows, write prompts for each step, and repeatedly revise the logic as requirements evolve-making development costly, time-consuming, and error-prone. To study whether large language models can automate this multi-round interaction process, we introduce Chat2Workflow, a benchmark for generating executable visual workflows directly from natural language, and propose a robust agentic framework to mitigate recurrent execution errors. Chat2Workflow is built from a large collection of real-world business workflows, with each instance designed so that the generated workflow can be transformed and directly deployed to practical workflow platforms such as Dify and Coze. Experimental results show that while state-of-the-art language models can often capture high-level intent, they struggle to generate correct, stable, and executable workflows, especially under complex or changing requirements. Although our agentic framework yields up to 5.34% resolve rate gains, the remaining real-world gap positions Chat2Workflow as a foundation for advancing industrial-grade automation. Code is available at https://github.com/zjunlp/Chat2Workflow.
Authors: Alex Cuellar, Michael Hagenow, Julie Shah
Abstract: Effective human-robot teaming is crucial for the practical deployment of robots in human workspaces. However, optimizing joint human-robot plans remains a challenge due to the difficulty of modeling individualized human capabilities and preferences. While prior research has leveraged the multi-cycle structure of domains like manufacturing to learn an individual's tendencies and adapt plans over repeated interactions, these techniques typically consider task-level and motion-level adaptation in isolation. Task-level methods optimize allocation and scheduling but often ignore spatial interference in close-proximity scenarios; conversely, motion-level methods focus on collision avoidance while ignoring the broader task context. This paper introduces RAPIDDS, a framework that unifies these approaches by modeling an individual's spatial behavior (motion paths) and temporal behavior (time required to complete tasks) over multiple cycles. RAPIDDS then jointly adapts task schedules and steers diffusion models of robot motions to maximize efficiency and minimize proximity accounting for these individualized models. We demonstrate the importance of this dual adaptation through an ablation study in simulation and a physical robot scenario using a 7-DOF robot arm. Finally, we present a user study (n=32) showing significant plan improvement compared to non-adaptive systems across both objective metrics, such as efficiency and proximity, and subjective measures, including fluency and user preference. See this paper's companion video at: https://youtu.be/55Q3lq1fINs.
Authors: Hunter L. Brown, Geoffrey Hollinger, Stefan Lee
Abstract: Reinforcement learning-based control policies have been frequently demonstrated to be more effective than analytical techniques for many manipulation tasks. Commonly, these methods learn neural control policies that predict end-effector pose changes directly from observed state information. For tasks like inserting delicate connectors which induce force constraints, pose-based policies have limited explicit control over force and rely on carefully tuned low-level controllers to avoid executing damaging actions. In this work, we present hybrid position-force control policies that learn to dynamically select when to use force or position control in each control dimension. To improve learning efficiency of these policies, we introduce Mode-Aware Training for Contact Handling (MATCH) which adjusts policy action probabilities to explicitly mirror the mode selection behavior in hybrid control. We validate MATCH's learned policy effectiveness using fragile peg-in-hole tasks under extreme localization uncertainty. We find MATCH substantially outperforms pose-control policies -- solving these tasks with up to 10% higher success rates and 5x fewer peg breaks than pose-only policies under common types of state estimation error. MATCH also demonstrates data efficiency equal to pose-control policies, despite learning in a larger and more complex action space. In over 1600 sim-to-real experiments, we find MATCH succeeds twice as often as pose policies in high noise settings (33% vs.~68%) and applies ~30% less force on average compared to variable impedance policies on a Franka FR3 in laboratory conditions.
Authors: Jake Lee
Abstract: The discretization of continuous numerical attributes remains a persistent computational bottleneck in the induction of decision trees, particularly as dataset dimensions scale. Building upon the recently proposed MSD-Splitting technique -- which bins continuous data using the empirical mean and standard deviation to dramatically improve the efficiency and accuracy of the C4.5 algorithm -- we introduce Adaptive MSD-Splitting (AMSD). While standard MSD-Splitting is highly effective for approximately symmetric distributions, its rigid adherence to fixed one-standard-deviation cutoffs can lead to catastrophic information loss in highly skewed data, a common artifact in real-world biomedical and financial datasets. AMSD addresses this by dynamically adjusting the standard deviation multiplier based on feature skewness, narrowing intervals in dense regions to preserve discriminative resolution. Furthermore, we integrate AMSD into ensemble methods, specifically presenting the Random Forest-AMSD (RF-AMSD) framework. Empirical evaluations on the Census Income, Heart Disease, Breast Cancer, and Forest Covertype datasets demonstrate that AMSD yields a 2-4% accuracy improvement over standard MSD-Splitting, while maintaining near-identical O(N) time complexity reductions compared to the O(N log N) exhaustive search. Our Random Forest extension achieves state-of-the-art accuracy at a fraction of standard computational costs, confirming the viability of adaptive statistical binning in large-scale ensemble learning architectures.
Authors: Jiaming Zhang, Meng Ding, Shaopeng Fu, Jingfeng Zhang, Di Wang
Abstract: Despite the remarkable success of Vision Transformers (ViTs) across a wide range of vision tasks, recent studies have revealed that they remain vulnerable to adversarial examples, much like Convolutional Neural Networks (CNNs). A common empirical defense strategy is adversarial training, yet the theoretical underpinnings of its robustness in ViTs remain largely unexplored. In this work, we present the first theoretical analysis of adversarial training under simplified ViT architectures. We show that, when trained under a signal-to-noise ratio that satisfies a certain condition and within a moderate perturbation budget, adversarial training enables ViTs to achieve nearly zero robust training loss and robust generalization error under certain regimes. Remarkably, this leads to strong generalization even in the presence of overfitting, a phenomenon known as \emph{benign overfitting}, previously only observed in CNNs (with adversarial training). Experiments on both synthetic and real-world datasets further validate our theoretical findings.
Authors: Jean Mercat, Sedrick Keh, Kushal Arora, Isabella Huang, Paarth Shah, Haruki Nishimura, Shun Iwase, Katherine Liu
Abstract: We present VLA Foundry, an open-source framework that unifies LLM, VLM, and VLA training in a single codebase. Most open-source VLA efforts specialize on the action training stage, often stitching together incompatible pretraining pipelines. VLA Foundry instead provides a shared training stack with end-to-end control, from language pretraining to action-expert fine-tuning. VLA Foundry supports both from-scratch training and pretrained backbones from Hugging Face. To demonstrate the utility of our framework, we train and release two types of models: the first trained fully from scratch through our LLM-->VLM-->VLA pipeline and the second built on the pretrained Qwen3-VL backbone. We evaluate closed-loop policy performance of both models on LBM Eval, an open-data, open-source simulator. We also contribute usability improvements to the simulator and the STEP analysis tools for easier public use. In the nominal evaluation setting, our fully-open from-scratch model is on par with our prior closed-source work and substituting in the Qwen3-VL backbone leads to a strong multi-task table top manipulation policy outperforming our baseline by a wide margin. The VLA Foundry codebase is available at https://github.com/TRI-ML/vla_foundry and all multi-task model weights are released on https://huggingface.co/collections/TRI-ML/vla-foundry. Additional qualitative videos are available on the project website https://tri-ml.github.io/vla_foundry.
URLs: https://github.com/TRI-ML/vla_foundry, https://huggingface.co/collections/TRI-ML/vla-foundry., https://tri-ml.github.io/vla_foundry.
Authors: Perry Dong, Alexander Swerdlow, Dorsa Sadigh, Chelsea Finn
Abstract: Some of the most performant reinforcement learning algorithms today can be prohibitively expensive as they use test-time scaling methods such as sampling multiple action candidates and selecting the best one. In this work, we propose FASTER, a method for getting the benefits of sampling-based test-time scaling of diffusion-based policies without the computational cost by tracing the performance gain of action samples back to earlier in the denoising process. Our key insight is that we can model the denoising of multiple action candidates and selecting the best one as a Markov Decision Process (MDP) where the goal is to progressively filter action candidates before denoising is complete. With this MDP, we can learn a policy and value function in the denoising space that predicts the downstream value of action candidates in the denoising process and filters them while maximizing returns. The result is a method that is lightweight and can be plugged into existing generative RL algorithms. Across challenging long-horizon manipulation tasks in online and batch-online RL, FASTER consistently improves the underlying policies and achieves the best overall performance among the compared methods. Applied to a pretrained VLA, FASTER achieves the same performance while substantially reducing training and inference compute requirements. Code is available at https://github.com/alexanderswerdlow/faster .
Authors: Boyu Chen, Yi Chen, Lu Qiu, Jerry Bai, Yuying Ge, Yixiao Ge
Abstract: Scaling humanoid foundation models is bottlenecked by the scarcity of robotic data. While massive egocentric human data offers a scalable alternative, bridging the cross-embodiment chasm remains a fundamental challenge due to kinematic mismatches. We introduce UniT (Unified Latent Action Tokenizer via Visual Anchoring), a framework that establishes a unified physical language for human-to-humanoid transfer. Grounded in the philosophy that heterogeneous kinematics share universal visual consequences, UniT employs a tri-branch cross-reconstruction mechanism: actions predict vision to anchor kinematics to physical outcomes, while vision reconstructs actions to filter out irrelevant visual confounders. Concurrently, a fusion branch synergies these purified modalities into a shared discrete latent space of embodiment-agnostic physical intents. We validate UniT across two paradigms: 1) Policy Learning (VLA-UniT): By predicting these unified tokens, it effectively leverages diverse human data to achieve state-of-the-art data efficiency and robust out-of-distribution (OOD) generalization on both humanoid simulation benchmark and real-world deployments, notably demonstrating zero-shot task transfer. 2) World Modeling (WM-UniT): By aligning cross-embodiment dynamics via unified tokens as conditions, it realizes direct human-to-humanoid action transfer. This alignment ensures that human data seamlessly translates into enhanced action controllability for humanoid video generation. Ultimately, by inducing a highly aligned cross-embodiment representation (empirically verified by t-SNE visualizations revealing the convergence of human and humanoid features into a shared manifold), UniT offers a scalable path to distill vast human knowledge into general-purpose humanoid capabilities.
Authors: Mario Tuci, Caner Korkmaz, Umut \c{S}im\c{s}ekli, Tolga Birdal
Abstract: Training modern neural networks often relies on large learning rates, operating at the edge of stability, where the optimization dynamics exhibit oscillatory and chaotic behavior. Empirically, this regime often yields improved generalization performance, yet the underlying mechanism remains poorly understood. In this work, we represent stochastic optimizers as random dynamical systems, which often converge to a fractal attractor set (rather than a point) with a smaller intrinsic dimension. Building on this connection and inspired by Lyapunov dimension theory, we introduce a novel notion of dimension, coined the `sharpness dimension', and prove a generalization bound based on this dimension. Our results show that generalization in the chaotic regime depends on the complete Hessian spectrum and the structure of its partial determinants, highlighting a complexity that cannot be captured by the trace or spectral norm considered in prior work. Experiments across various MLPs and transformers validate our theory while also providing new insights into the recently observed phenomenon of grokking.
Authors: Tian Yu Liu, Stefano Soatto
Abstract: The semantic similarity between sample expressions measures the distance between their latent 'meaning'. These meanings are themselves typically represented by textual expressions. We propose a novel approach whereby the semantic similarity among textual expressions is based not on other expressions they can be rephrased as, but rather based on the imagery they evoke. While this is not possible with humans, generative models allow us to easily visualize and compare generated images, or their distribution, evoked by a textual prompt. Therefore, we characterize the semantic similarity between two textual expressions simply as the distance between image distributions they induce, or 'conjure.' We show that by choosing the Jeffreys divergence between the reverse-time diffusion stochastic differential equations (SDEs) induced by each textual expression, this can be directly computed via Monte-Carlo sampling. Our method contributes a novel perspective on semantic similarity that not only aligns with human-annotated scores, but also opens up new avenues for the evaluation of text-conditioned generative models while offering better interpretability of their learnt representations.
Authors: Krisztian Balog, ChengXiang Zhai
Abstract: User simulation is an emerging interdisciplinary topic with multiple critical applications in the era of Generative AI. It involves creating an intelligent agent that mimics the actions of a human user interacting with an AI system, enabling researchers to model and analyze user behaviour, generate synthetic data for training, and evaluate interactive AI systems in a controlled and reproducible manner. Because of its broad scope, research on this topic currently remains scattered across artificial intelligence, human-computer interaction, information science, computational social science, and psychology. To address this fragmented landscape of current research, this article presents a foundational synthesis. We highlight the paradigm shift from traditional predictive models to modern generative approaches, and explicitly frame critical ethical considerations -- demonstrating how controlled simulation serves not merely as a risk vector for bias, but as a powerful, proactive tool to ensure fair representation and system safety. Furthermore, we establish the theoretical connection between user simulation and the pursuit of Artificial General Intelligence, arguing that realistic simulators are indispensable catalysts for overcoming critical data and evaluation bottlenecks and optimizing personalization. Ultimately, we propose a practical, self-sustaining innovation ecosystem bridging academia and industry to advance this increasingly important technology.
Authors: Xiaolong Liang, Y\`i N. W\'ang
Abstract: This paper presents a class of epistemic logics that captures the dynamics of acquiring knowledge and descending into oblivion, while incorporating concepts of group knowledge. The approach is grounded in a system of weighted models, introducing an ``epistemic skills'' metric to represent the epistemic capacities tied to knowledge updates. Within this framework, knowledge acquisition is modeled as a process of upskilling, whereas oblivion is represented as a consequence of downskilling. The framework further enables exploration of ``knowability'' and ``forgettability,'' defined as the potential to gain knowledge through upskilling and to lapse into oblivion through downskilling, respectively. Additionally, it supports a detailed analysis of the distinctions between epistemic de re and de dicto expressions. The computational complexity of the model checking and satisfiability problems is examined, offering insights into their theoretical foundations and practical implications.
Authors: Vojt\v{e}ch K\r{u}r, V\'it Musil, Vojt\v{e}ch \v{R}eh\'ak
Abstract: Adversarial Patrolling games form a subclass of Security games where a Defender moves between locations, guarding vulnerable targets. The main algorithmic problem is constructing a strategy for the Defender that minimizes the worst damage an Attacker can cause. We focus on the class of finite-memory (also known as regular) Defender's strategies that experimentally outperformed other competing classes. A finite-memory strategy can be seen as a positional strategy on a finite set of states. Each state consists of a pair of a location and a certain integer value--called memory. Existing algorithms improve the transitional probabilities between the states but require that the available memory size itself is assigned at each location manually. Choosing the right memory assignment is a well-known open and hard problem that hinders the usability of finite-memory strategies. We solve this issue by developing a general method that iteratively changes the memory assignment. Our algorithm can be used in connection with any black-box strategy optimization tool. We evaluate our method on various experiments and show its robustness by solving instances of various patrolling models.
Authors: Shashank Sharma, Janina Hoffmann, Vinay Namboodiri
Abstract: Hierarchical reinforcement learning (HRL) decomposes the policy into a manager and a worker, enabling long-horizon planning but introducing a performance gap on tasks requiring agility. We identify a root cause: in subgoal-based HRL, the manager's goal representation is typically learned without constraints on reachability or temporal distance from the current state, preventing precise local subgoal selection. We further show that the optimal subgoal distance is both task- and state-dependent: nearby subgoals enable precise control but amplify prediction noise, while distant subgoals produce smoother motion at the cost of geometric precision. We propose Multi-Resolution Skills (MRS), which learns multiple goal-prediction modules each specialized to a fixed temporal horizon, with a jointly trained meta-controller that selects among them based on the current state. MRS consistently outperforms fixed-resolution baselines and significantly reduces the performance gap between HRL and non-HRL state-of-the-art on DeepMind Control Suite, Gym-Robotics, and long-horizon AntMaze tasks. [Project page: https://sites.google.com/view/multi-res-skills/home]
Authors: William F. Shen, Xinchi Qiu, Nicola Cancedda, Nicholas D. Lane
Abstract: Adapting LLMs with new knowledge is increasingly important, but standard fine-tuning often erodes aligned epistemic abstention: the ability to acknowledge when the model does not know. This failure mode is especially concerning in high-stakes settings, where abstention is a critical safeguard against hallucination. We present SEAT, a preventive fine-tuning method that preserves epistemic abstention while maintaining strong knowledge acquisition. SEAT combines sparse tuning, which constrains global activation drift, with entity-perturbed KL regularization, which sharpens local epistemic boundaries and prevents spillover to neighboring knowledge. Crucially, SEAT requires no alignment data, explicit boundary probing, or post-hoc re-alignment, making it attractive for lightweight and privacy-sensitive adaptation. Across models and datasets, SEAT improves human-evaluated abstention on unknown queries by 18%-101% over the strongest baseline while retaining near-perfect target knowledge acquisition, and produces coherent, context-aware abstentions after tuning. Further analyses show that both components are essential, that SEAT more cleanly separates known from unknown queries in representation space, and that it preserves downstream utility. These results identify preservation of epistemic abstention as a core objective for safe knowledge adaptation.
Authors: Ge Chang, Jinbo Su, Jiacheng Liu, Pengfei Yang, Yuhao Shang, Huiwen Zheng, Hongli Ma, Yan Liang, Yuanchun Li, Yunxin Liu
Abstract: Large Language Models (LLMs) integrated with Retrieval-Augmented Generation (RAG) techniques have exhibited remarkable performance across a wide range of domains. However, existing RAG approaches primarily operate on unstructured data and demonstrate limited capability in handling structured knowledge such as knowledge graphs. Meanwhile, current graph retrieval methods fundamentally struggle to capture holistic graph structures while simultaneously facing precision control challenges that manifest as either critical information gaps or excessive redundant connections, collectively undermining reasoning performance. To address this challenge, we propose GRAIL: Graph-Retrieval Augmented Interactive Learning, a framework designed to interact with large-scale graphs for retrieval-augmented reasoning. Specifically, GRAIL integrates LLM-guided random exploration with path filtering to establish a data synthesis pipeline, where a fine-grained reasoning trajectory is automatically generated for each task. Based on the synthesized data, we then employ a two-stage training process to learn a policy that dynamically decides the optimal actions at each reasoning step. The overall objective of precision-conciseness balance in graph retrieval is decoupled into fine-grained process-supervised rewards to enhance data efficiency and training stability. In practical deployment, GRAIL adopts an interactive retrieval paradigm, enabling the model to autonomously explore graph paths while dynamically balancing retrieval breadth and precision. Extensive experiments have shown that GRAIL achieves an average accuracy improvement of 21.01% and F1 improvement of 22.43% on three knowledge graph question-answering datasets. Our source code and datasets is available at https://github.com/Changgeww/GRAIL.
Authors: Yumeng Fu, Jiayin Zhu, Lingling Zhang, Wenjun Wu, Bo Zhao, Shaoxuan Ma, Yushun Zhang, Jun Liu
Abstract: Geometry problem solving (GPS) poses significant challenges for Multimodal Large Language Models (MLLMs) in diagram comprehension, knowledge application, long-step reasoning, and auxiliary line construction. However, current benchmarks lack fine-grained evaluation for long-step problems necessitating auxiliary construction. To address these limitations, we present GeoLaux, a fine-grained annotated dataset comprising 2186 calculation and proof problems. It features long-step reasoning (with an average solution length of 6.51 steps, maximum of 24 steps) and auxiliary line construction (required in 41.8% of problems). Building on the dataset, we conduct a comprehensive five-dimensional evaluation of 23 leading MLLMs. The evaluation yields three pivotal findings: First, models perform significantly worse on long-step problems compared to short-step ones, with 18 models exhibiting a performance drop of over 50%. Second, it is crucial to enhance models' understanding, awareness, and proficiency in auxiliary line construction, which is vital for overall geometric reasoning. Third, limited answer hints effectively improve process correctness, whereas explicit answers lead models to neglect intermediate reasoning steps. These findings position GeoLaux both to benchmark MLLMs geometry reasoning abilities and to guide their improvement. Data and code are available at https://github.com/Candice-yu/GeoLaux
Authors: Xiao Liang, Bangxin Li, Zixuan Chen, Hanyue Zheng, Zhi Ma, Di Wang, Cong Tian, Quan Wang
Abstract: The technical complexity of research papers often limits their reach, necessitating more accessible formats like scientific videos to disseminate key insights through engaging narration. However, existing automated methods primarily focus on static posters or slide presentations that remain template-bound and linear. Shifting to audience-adaptive video synthesis requires addressing non-linear narrative orchestration and the joint synchronization of disparate multimodal assets. We introduce VideoAgent, a modular framework that redefines scientific video synthesis as an intent-driven planning problem. By decoupling content understanding from multimodal synthesis, VideoAgent adaptively interleaves static slides with dynamic animations to match the semantic density of the narration. We further propose SciVidEval, a benchmark evaluating multimodal quality and pedagogical utility through automated metrics and human knowledge transfer studies. Extensive experiments demonstrate that VideoAgent effectively conveys complex technical logic with high narrative fidelity and communicative impact.
Authors: Vincent Siu, Nathan W. Henry, Nicholas Crispino, Yang Liu, Dawn Song, Chenguang Wang
Abstract: Current safety evaluations of language models rely on benchmark-based assessments that may miss localized vulnerabilities. We present RepIt, a simple and data-efficient framework for isolating concept-specific representations in LM activations. While existing steering methods already achieve high attack success rates through broad interventions, RepIt enables a more concerning capability: selective suppression of refusal on targeted concepts while preserving refusal elsewhere. Across five frontier LMs, RepIt produces evaluation-evading model organisms with semantic backdoors, answering questions related to weapons of mass destruction while still scoring as safe on standard benchmarks. We find the edit of the steering vector localizes to just 100-200 residual dimensions, and robust concept vectors can be extracted from as few as a dozen examples on a single RTX A6000, highlighting how targeted, hard-to-detect modifications can exploit evaluation blind spots with minimal resources. Through demonstrating precise concept disentanglement, this work exposes vulnerabilities in current safety evaluation practices and demonstrates a need for more comprehensive, representation aware assessments.
Authors: Wenda Xie, Chao Guo, Yanqing Jing, Junle Wang, Yisheng Lv, Fei-Yue Wang
Abstract: Although LLMs have been widely adopted for creative content generation, a single-pass process often struggles to produce high-quality long narratives. How to effectively revise and improve long narrative scripts like scriptwriters remains a significant challenge, as it demands a comprehensive understanding of the entire context to identify global structural issues and local detailed flaws, as well as coordinating revisions at multiple granularities and locations. Direct modifications by LLMs typically introduce inconsistencies between local edits and the overall narrative requirements. To address these issues, we propose Dramaturge, a task and feature oriented divide-and-conquer approach powered by hierarchical multiple LLM agents. It consists of a Global Review stage to grasp the overall storyline and structural issues, a Scene-level Review stage to pinpoint detailed scene and sentence flaws, and a Hierarchical Coordinated Revision stage that coordinates and integrates structural and detailed improvements throughout the script. The top-down task flow ensures that high-level strategies guide local modifications, maintaining contextual consistency. The review and revision workflow follows a coarse-to-fine iterative process, continuing through multiple rounds until no further substantive improvements can be made. Comprehensive experiments show that Dramaturge significantly outperforms all baselines in terms of script-level overall quality and scene-level details. Our approach is plug-and-play and can be easily integrated into existing methods to improve the generated scripts.
Authors: Zhen Zhu, Yiming Gong, Yao Xiao, Yaoyao Liu, Derek Hoiem
Abstract: How can we teach large multimodal models (LMMs) new skills without erasing prior abilities? We study sequential fine-tuning on five target skills while monitoring general ability on eight held-out benchmarks across three model families. Surprisingly, we find that performance lost on held-out tasks after fine-tuning on one skill can partly recover when the model is subsequently tuned on a different skill. We trace this behavior to a measurable shift in the output token distribution, manifested through a simple counting-bias probe that shows the shift co-varies with forgetting. Guided by this insight, we identify two simple, robust tuning recipes that learn strongly while limiting drift: (i) updating only the self-attention projection layers (SA Proj., $\Delta$ learning +24.9 / $\Delta$ held-out forgetting -0.6), and (ii) updating only the MLP Gate&Up while freezing the Down projection (+30.5 / -2.1). Both substantially outperform full-LLM tuning (+31.8 / -23.3) in the learning-forgetting trade-off. We also compare against common forgetting mitigation methods: Learning without Forgetting (LwF), LoRA, Mixture-of-Experts, and weight-space interpolation (WiSE-FT), and find that our selective tuning recipes match or exceed their learning-stability balance while remaining simpler, requiring no replay, auxiliary parameters, or per-stage tuning. These results hold across LLaVA-OneVision, LLaVA-NeXT, and Qwen2.5-VL, confirming that the key to teaching LMMs new skills without forgetting lies in controlling output distribution shift by choosing which components to tune. Code will be made available.
Authors: Jiayi Mao, Liqun Li, Yanjie Gao, Zegang Peng, Shilin He, Chaoyun Zhang, Si Qin, Samia Khalid, Qingwei Lin, Saravan Rajmohan, Sitaram Lanka, Dongmei Zhang
Abstract: Effective incident management in large-scale IT systems relies on troubleshooting guides (TSGs), but their manual execution is slow and error-prone. While recent advances in LLMs offer promise for automating incident management tasks, existing LLM-based solutions lack specialized support for several key challenges, including managing TSG quality issues, interpreting complex control flow, handling data-intensive queries, and exploiting execution parallelism. We first conducted an empirical study on 92 real-world TSGs, and, guided by our findings, we present StepFly, a novel end-to-end agentic framework for troubleshooting guide automation. Our approach features a three-stage workflow: the first stage provides a comprehensive guide together with a tool, TSG Mentor, to assist site reliability engineers (SREs) in improving TSG quality; the second stage performs offline preprocessing using LLMs to extract structured execution directed acyclic graphs (DAGs) from unstructured TSGs and to create dedicated Query Preparation Plugins (QPPs); and the third stage executes online using a DAG-guided scheduler-executor framework with a memory system to ensure correct workflow and support parallel execution of independent steps. Our empirical evaluation on a collection of real-world TSGs and incidents demonstrates that StepFly achieves a ~94% success rate on GPT-4.1, outperforming baselines with less time and token consumption. Furthermore, it achieves a remarkable execution time reduction of 32.9% to 70.4% for parallelizable TSGs. Our code and sample data are publicly available at https://github.com/microsoft/StepFly.
Authors: Boxuan Wang, Zhuoyun Li, Xinmiao Huang, Xiaowei Huang, Yi Dong
Abstract: This paper primarily demonstrates a method to quantitatively assess the alignment between multi-step, structured reasoning in large language models and human preferences. We introduce the Alignment Score, a semantic-level metric that compares a model-produced chain of thought traces with a human-preferred reference by constructing semantic-entropy-based matrices over intermediate steps and measuring their divergence. Our analysis shows that Alignment Score tracks task accuracy across models and hop depths, and peaks at 2-hop reasoning. Empirical results further indicate that misalignment at greater reasoning depths is driven mainly by alignment errors such as thematic shift and redundant reasoning. Viewing chain sampling as drawing from a distribution over reasoning paths, we empirically demonstrate a strong and consistent correlation between Alignment Score and accuracy, readability, and coherence, supporting its use as a diagnostic signal. The code is available.
Authors: Xiqiao Xiong, Ouxiang Li, Zhuo Liu, Moxin Li, Wentao Shi, Fengbin Zhu, Qifan Wang, Fuli Feng
Abstract: Large language models have seen widespread adoption, yet they remain vulnerable to multi-turn jailbreak attacks, threatening their safe deployment. This has led to the task of training automated multi-turn attackers to probe model safety vulnerabilities. However, existing approaches typically rely on turn-level optimization, which is insufficient for learning long-term attack strategies. To bridge this gap, we formulate this task as a multi-turn reinforcement learning problem, directly optimizing the harmfulness of the final-turn response as the outcome reward. To address the sparse supervision of the outcome reward, we introduce TROJail, which employs two process rewards to evaluate the utility of intermediate prompts and integrate them into advantage estimation. These rewards (1) penalize overly harmful prompts that trigger the model's refusal mechanism, and (2) encourage steering the semantic relevance of responses toward the targeted harmful content. Experimental results show improved attack success rates across multiple models and benchmarks, highlighting the effectiveness of our approach. The code is available at https://github.com/xxiqiao/TROJail. Warning: This paper contains examples of harmful content.
Authors: Xiang Cheng, Yulan Hu, Xiangwen Zhang, Lu Xu, Lide Tan, Zheng Pan, Xin Li, Yong Liu
Abstract: Travel planning is a natural real-world task to test large language models' (LLMs) planning and tool-use abilities. Although prior work has studied LLM performance on travel planning, existing settings still differ from real-world needs, mainly due to limited domain coverage, insufficient modeling of users' implicit preferences in multi-turn conversations, and a lack of evaluation of agents' capability boundaries. To mitigate these gaps, we propose $\textbf{TravelBench}$, a benchmark for $\textit{truly real-world}$ travel planning. We collect user queries, user preferences, and tools from real scenarios, and construct three subtasks -- $\textit{Single-Turn}$, $\textit{Multi-Turn}$, and $\textit{Unsolvable}$ -- to evaluate agents' three core capabilities in real settings: (1) solving problems independently, (2) interacting with users to elicit implicit preferences, and (3) recognizing the capability boundaries. To enable stable tool invocation and reproducible evaluation, we cache real tool-call results and build a sandbox environment which integrates ten travel-related tools, enabling agents to combine these tools to solve most practical travel planning problems. We evaluate multiple LLMs on TravelBench and find that even advanced models exhibit imbalanced performance across different capabilities. Our further systematic verification demonstrates the stability of the proposed benchmark. TravelBench provides a practical and reproducible benchmark to advance research on LLM agents for real-world travel planning.
Authors: Basab Jha, Firoj Paudel, Ujjwal Puri, Ethan Henkel, Zhang Yuting, Mateusz Kowalczyk, Mei Huang, Choi Donghyuk, Wang Junhao
Abstract: We demonstrate SAGE-32B, a 32 billion parameter language model that focuses on agentic reasoning and long range planning tasks. Unlike chat models that aim for general conversation fluency, SAGE-32B is designed to operate in an agentic loop, emphasizing task decomposition, tool usage, and error recovery. The model is initialized from the Qwen2.5-32B pretrained model and fine tuned using Iterative Distillation, a two stage training process that improves reasoning performance through rigorously tested feedback loops. SAGE-32B also introduces an inverse reasoning approach, which uses a meta cognition head to forecast potential failures in the planning process before execution. On agentic reasoning benchmarks including MMLU-Pro, AgentBench, and MATH-500, SAGE-32B achieves higher success rates in multi tool usage scenarios compared to similarly sized baseline models, while remaining competitive on standard reasoning evaluations. Model weights are publicly released at https://huggingface.co/sagea-ai/sage-reasoning-32b
Authors: Dongyi Lv, Qiuyu Ding, Heng-Da Xu, Zhaoxu Sun, Zhi Wang, Feng Xiong, Mu Xu
Abstract: Generative recommendation with large language models (LLMs) reframes prediction as sequence generation, yet existing LLM-based recommenders remain limited in leveraging geographic signals that are crucial in mobility and local-services scenarios. Here, we present Reasoning Over Space (ROS), a framework that utilizes geography as a vital decision variable within the reasoning process. ROS introduces a Hierarchical Spatial Semantic ID (SID) that discretizes coarse-to-fine locality and POI semantics into compositional tokens, and endows LLM with a three-stage Mobility Chain-of-Thought (CoT) paradigm that models user personality, constructs an intent-aligned candidate space, and performs locality informed pruning. We further align the model with real world geography via spatial-guided Reinforcement Learning (RL). Experiments on three widely used location-based social network (LBSN) datasets show that ROS achieves over 10% relative gains in hit rate over strongest LLM-based baselines and improves cross-city transfer, despite using a smaller backbone model.
Authors: William Walden, Miriam Wanner
Abstract: Hint-based faithfulness evaluations have established that Large Reasoning Models (LRMs) may not say what they think: they do not always volunteer information about how key parts of the input (e.g. answer hints) influence their reasoning. Yet, these evaluations also fail to specify what models should do when confronted with hints or other unusual prompt content -- even though versions of such instructions are standard security measures (e.g. for countering prompt injections). Here, we study faithfulness under this more realistic setting in which models are explicitly alerted to the possibility of unusual inputs. We find that such instructions can yield strong results on faithfulness metrics from prior work. However, results on new, more granular metrics proposed in this work paint a mixed picture: although models may acknowledge the presence of hints, they will often deny intending to use them -- even when permitted to use hints and even when it can be demonstrated that they are using them. Our results thus raise broader challenges for CoT monitoring and interpretability.
Authors: Ant\'onio Loison, Quentin Mac\'e, Antoine Edy, Victor Xing, Tom Balough, Gabriel Moreira, Bo Liu, Manuel Faysse, C\'eline Hudelot, Gautier Viaud
Abstract: Retrieval-Augmented Generation (RAG) pipelines must address challenges beyond simple single-document retrieval, such as interpreting visual elements (tables, charts, images), synthesizing information across documents, and providing accurate source grounding. Existing benchmarks fail to capture this complexity, often focusing on textual data, single-document comprehension, or evaluating retrieval and generation in isolation. We introduce ViDoRe v3, a comprehensive multimodal RAG benchmark featuring multi-type queries over visually rich document corpora. It covers 10 datasets across diverse professional domains, comprising ~26,000 document pages paired with 3,099 human-verified queries, each available in 6 languages. Through 12,000 hours of human annotation effort, we provide high-quality annotations for retrieval relevance, bounding box localization, and verified reference answers. Our evaluation of state-of-the-art RAG pipelines reveals that visual retrievers outperform textual ones, late-interaction models and textual reranking substantially improve performance, and hybrid or purely visual contexts enhance answer generation quality. However, current models still struggle with non-textual elements, open-ended queries, and fine-grained visual grounding. To encourage progress in addressing these challenges, the benchmark is released under a commercially permissive license at https://hf.co/vidore.
URLs: https://hf.co/vidore.
Authors: Shiyu Liu, Yongjing Yin, Jianhao Yan, Yunbo Tang, Qinggang Zhang, Bei Li, Xin Chen, Jingang Wang, Xunliang Cai, Jinsong Su
Abstract: RL-based agentic search enables LLMs to solve complex questions via dynamic planning and external search. While this approach significantly enhances accuracy with agent policies optimized via large-scale reinforcement learning, we identify a critical gap in reliability: these agents fail to recognize their reasoning boundaries and rarely admit ``I DON'T KNOW'' (IDK) even when evidence is insufficient or reasoning reaches its limit. The lack of reliability often leads to plausible but unreliable answers, introducing significant risks in many real-world scenarios. To this end, we propose Boundary-Aware Policy Optimization (BAPO), a novel RL framework designed to cultivate reliable boundary awareness without compromising accuracy. BAPO introduces two key components: (i) a group-based boundary-aware reward that encourages an IDK response only when the reasoning reaches its limit, and (ii) an adaptive reward modulator that strategically suspends this reward during early exploration, preventing the model from exploiting IDK as a shortcut. Extensive experiments on four benchmarks demonstrate that BAPO substantially enhances the overall reliability of agentic search.
Authors: Meiru Zhang, Zaiqiao Meng, Nigel Collier
Abstract: Despite scaling to massive context windows, Large Language Models (LLMs) struggle with multi-hop reasoning due to inherent position bias, which causes them to overlook information at certain positions. Whether these failures stem from an inability to locate evidence (recognition failure) or integrate it (synthesis failure) is unclear. We introduce Multi-Focus Attention Instruction (MFAI), a semantic probe to disentangle these mechanisms by explicitly steering attention towards selected positions. Across 5 LLMs on two multi-hop QA tasks (MuSiQue and NeoQA), we identify the "Weakest Link Effect": in our 18-document, 3-bucket setting, multi-hop reasoning performance collapses to the level of the least visible evidence, governed by absolute position rather than the linear distance between facts. While matched MFAI resolves recognition bottlenecks, improving accuracy by up to 11.49% in low-visibility positions, misleading MFAI yields divergent effects modulated by task topology: entity-centric tasks with vertical reasoning chains are vulnerable, whereas event-centric tasks with horizontal evidence structures are more resilient. Finally, we demonstrate that thinking models utilizing System-2 reasoning effectively locate and integrate the required information, matching gold-only baselines even in noisy, long-context settings. Supplementary experiments on 2WikiMultiHopQA, extended 3-4 hop counts, and a 32B model confirm these findings generalize across datasets, reasoning depths, and model scales.
Authors: Chiyuan Fu, Lyuhao Chen, Yunze Xiao, Weihao Xuan, Carlos Busso, Mona Diab
Abstract: LLM agents are increasingly used for social simulation, yet emotion is often treated as a transient cue, causing emotional amnesia and weak long-horizon continuity. We present Sentipolis, a framework for emotionally stateful agents that integrates continuous Pleasure-Arousal-Dominance (PAD) representation, dual-speed emotion dynamics, and emotion--memory coupling. Across thousands of interactions over multiple base models and evaluators, Sentipolis improves emotionally grounded behavior, boosting communication, and emotional continuity. Gains are model-dependent: believability increases for higher-capacity models but can drop for smaller ones, and emotion-awareness can mildly reduce adherence to social norms, reflecting a human-like tension between emotion-driven behavior and rule compliance in social simulation. Network-level diagnostics show reciprocal, moderately clustered, and temporally stable relationship structures, supporting the study of cumulative social dynamics such as alliance formation and gradual relationship change.
Authors: Edward Y. Chang
Abstract: Large language models may answer causal questions correctly for the wrong reasons, substituting associational shortcuts P(Y|X) for the interventional query P(Y|do(X)). Current RL methods reward what the model answers but not why, reinforcing these shortcuts until distribution shift exposes them. We introduce Epistemic Regret Minimization (ERM), a framework that identifies causal reasoning flaws from reasoning traces, with no ground-truth labels. On CausalT5K (N=1,360, 6 frontier LLMs), models bifurcate: compliant models already correct under outcome-only reprompting, but reasoning-heavy models (GPT-4 Turbo, GPT-5.2, Claude Sonnet 3.5) resist outcome-only correction yet respond significantly to ERM's targeted causal critique. Ablation on 4,054 scenarios confirms causal content, not prompt structure alone, drives correction for stubborn models (p=0.006), and a scenario-blind judge argues against answer leakage. Cross-benchmark evaluation on CLadder confirms Rung Collapse generalizes beyond CausalT5K. We extend ERM to cross-episode RL, where interventional evidence accumulates into a reward signal for open-domain problems lacking ground-truth verifiers. A separation theorem proves outcome-only RL cannot distinguish correct from flawed causal models in confounded environments, and preliminary experiments across four LLMs show epistemic reward carries signal where outcome reward does not. This establishes signal existence, not yet policy improvement.
Authors: Luise Ge, Yongyan Zhang, Yevgeniy Vorobeychik
Abstract: The use of large language models either as decision support systems, or in agentic workflows, is rapidly transforming the digital ecosystem. However, the understanding of LLM decision-making under uncertainty remains limited. We study LLM risky choices along two dimensions: (1) prospect representation (based on an explicit representation or outcome history) and (2) decision rationale (explanation). Our study, which involves 20 frontier and open LLMs, is complemented by a matched human subjects experiment, which provides one reference point, while an expected payoff maximizing rational agent model provides another. We find that LLMs cluster into two categories: reasoning models (RMs) and conversational models (CMs). RMs tend towards rational behavior, are insensitive to the order of prospects, gain/loss framing, and explanations, and behave similarly whether prospects are explicit or presented via a history of outcomes. CMs are significantly less rational, slightly more human-like, sensitive to prospect ordering, framing, and explanation, and exhibit a large description-history gap. Paired comparisons of open LLMs suggest that a key factor differentiating RMs and CMs is training for mathematical reasoning.
Authors: Jingxuan Chen, Mohammad Taher Pilehvar, Jose Camacho-Collados
Abstract: Users often rely on Large Language Models (LLMs) for processing multiple documents or performing analysis over a number of instances. For example, analysing the overall sentiment of a number of movie reviews requires an LLM to process the sentiment of each review individually in order to provide a final aggregated answer. While LLM performance on such individual tasks is generally high, there has been little research on how LLMs perform when dealing with multi-instance inputs. In this paper, we perform a comprehensive evaluation of the multi-instance processing (MIP) ability of LLMs for tasks in which they excel individually. The results show that all LLMs follow a pattern of slight performance degradation for small numbers of instances (approximately 20-100), followed by a performance collapse on larger instance counts. Crucially, our analysis shows that while context length is associated with this degradation, the number of instances has a stronger effect on the final results. This finding suggests that when optimising LLM performance for MIP, attention should be paid to both context length and, in particular, instance count.
Authors: Thanh Luong Tuan
Abstract: Enterprise adoption of Large Language Models (LLMs) is constrained by hallucination, domain drift, and the inability to enforce regulatory compliance at the reasoning level. We present a neurosymbolic architecture implemented within the Foundation AgenticOS (FAOS) platform that addresses these limitations through ontology-constrained neural reasoning. Our approach introduces a three-layer ontological framework--Role, Domain, and Interaction ontologies--that provides formal semantic grounding for LLM-based enterprise agents. We formalize the concept of asymmetric neurosymbolic coupling, wherein symbolic ontological knowledge constrains agent inputs (context assembly, tool discovery, governance thresholds) while proposing mechanisms for extending this coupling to constrain agent outputs (response validation, reasoning verification, compliance checking). We evaluate the architecture through a controlled experiment (600 runs across five industries: FinTech, Insurance, Healthcare, Vietnamese Banking, and Vietnamese Insurance), finding that ontology-coupled agents significantly outperform ungrounded agents on Metric Accuracy (p < .001, W = .460), Regulatory Compliance (p = .003, W = .318), and Role Consistency (p < .001, W = .614), with improvements greatest where LLM parametric knowledge is weakest--particularly in Vietnam-localized domains. Our contributions include: (1) a formal three-layer enterprise ontology model, (2) a taxonomy of neurosymbolic coupling patterns, (3) ontology-constrained tool discovery via SQL-pushdown scoring, (4) a proposed framework for output-side ontological validation, (5) empirical evidence for the inverse parametric knowledge effect that ontological grounding value is inversely proportional to LLM training data coverage of the domain, and (6) a production system serving 21 industry verticals with 650+ agents.
Authors: Zhengyang Qi, Charles Dickens, Derek Pham, Amanda Dsouza, Armin Parchami, Frederic Sala, Paroma Varma
Abstract: Rubric-based evaluation is widely used in LLM benchmarks and training pipelines for open-ended, less verifiable tasks. While prior work has demonstrated the effectiveness of rubrics using downstream signals such as reinforcement learning outcomes, there remains no principled way to diagnose how a rubric itself fails from such aggregated or downstream signals alone. To address this gap, we introduce RIFT: RubrIc Failure mode Taxonomy, a taxonomy for systematically characterizing failure modes in rubric composition and design. RIFT consists of eight failure modes organized into three high-level categories: Reliability Failures, Content Validity Failures, and Consequential Validity Failures. RIFT is developed using grounded theory by iteratively annotating rubrics drawn from five diverse data sources spanning general instruction following, code generation, creative writing, and expert-level deep research, until no new failure modes are identified. We evaluate the consistency of the taxonomy by measuring agreement among independent human annotators, observing fair agreement overall (87% pairwise agreement and 0.64 average Cohen's kappa). Finally, to support scalable diagnosis, we propose automated rubric quality metrics and show that they align with human failure-mode annotations, achieving up to 0.925 F1.
Authors: Xue Liu, Xin Ma, Yuxin Ma, Yongchang Peng, Duo Wang, Zhoufutu Wen, Ge Zhang, Kaiyuan Zhang, Xinyu Chen, Yida Ding, Tianci He, Jiani Hou, Liang Hu, Ziyun Huang, Yongzhe Hui, Jianpeng Jiao, Chennan Ju, Yingru Kong, Yiran Li, Jiashuo Liu, Mengyun Liu, Luyao Ma, Fei Ni, Yiqing Ni, Pengbo Niu, Yueyan Qiu, Yanle Ren, Xinyu Shen, Zilin Shi, Zaiyuan Wang, Wenjie Yue, Chun Zhang, Shiyu Zhang, Xinyi Zhang, Kaiwen Zhao, Zhenwei Zhu, Shanshan Wu, Qi Zhao, Wenhao Huang
Abstract: As Large Language Models (LLMs) exhibit plateauing performance on conventional benchmarks, a pivotal challenge persists: evaluating their proficiency in complex, open-ended tasks characterizing genuine expert-level cognition. Existing frameworks suffer from narrow domain coverage, reliance on generalist tasks, or self-evaluation biases. To bridge this gap, we present XpertBench, a high-fidelity benchmark engineered to assess LLMs across authentic professional domains. XpertBench consists of 1,346 meticulously curated tasks across 80 categories, spanning finance, healthcare, legal services, education, and dual-track research (STEM and Humanities). These tasks are derived from over 1,000 submissions by domain experts--including researchers from elite institutions and practitioners with extensive clinical or industrial experience--ensuring superior ecological validity. Each task uses detailed rubrics with mostly 15-40 weighted checkpoints to assess professional rigor. To facilitate scalable yet human-aligned assessment, we introduce ShotJudge, a novel evaluation paradigm that employs LLM judges calibrated with expert few-shot exemplars to mitigate self-rewarding biases. Our empirical evaluation of state-of-the-art LLMs reveals a pronounced performance ceiling: even leading models achieve a peak success rate of only ~66%, with a mean score around 55%. Models also exhibit domain-specific divergence, showing non-overlapping strengths in quantitative reasoning versus linguistic synthesis.. These findings underscore a significant "expert-gap" in current AI systems and establish XpertBench as a critical instrument for navigating the transition from general-purpose assistants to specialized professional collaborators.
Authors: Hao Yan, Yuliang Liu, Xingchen Liu, Yuyi Zhang, Minghui Liao, Jihao Wu, Wei Chen, Xiang Bai
Abstract: Existing Multimodal Large Language Models (MLLMs) suffer from significant performance degradation on the long document understanding task as document length increases. This stems from two fundamental challenges: 1) a low Signal-to-Noise Ratio (SNR), with crucial evidence buried in irrelevant pages; and 2) supervision scarcity, as datasets offering only final short answers provide a weak learning signal. In this paper, we address these challenges by proposing a paradigm that requires the model to execute a structured Analysis, Localization and Reasoning workflow. To instill this capability, we design a two-stage training framework: we first perform Supervised Fine-Tuning on high-quality data generated via an efficient knowledge distillation strategy. Subsequently, we employ an Evidence-aware Group Relative Policy Optimization which jointly optimizes for both evidence localization and answer accuracy. Additionally, we introduce a Evidence-Guided Resolution Allocation strategy to mitigate memory constraints of training on multi-pages documents. Extensive experiments demonstrate that DocSeeker achieves superior performance on both in-domain and out-of-domain tasks. We show it robustly generalizes from short-page training to ultra-long documents and is naturally synergistic with visual Retrieval-Augmented Generation systems, serving as a solid foundation for their implementation.
Authors: Wentao Zhang, Zhe Zhao, Haibin Wen, Yingcheng Wu, Ming Yin, Bo An, Mengdi Wang
Abstract: Recent advances in LLM based agent systems have shown promise in tackling complex, long horizon tasks. However, existing agent protocols (e.g., A2A and MCP) under specify cross entity lifecycle and context management, version tracking, and evolution safe update interfaces, which encourages monolithic compositions and brittle glue code. We introduce Autogenesis Protocol (AGP), a self evolution protocol that decouples what evolves from how evolution occurs. Its Resource Substrate Protocol Layer (RSPL) models prompts, agents, tools, environments, and memory as protocol registered resources with explicit state, lifecycle, and versioned interfaces. Its Self Evolution Protocol Layer (SEPL) specifies a closed loop operator interface for proposing, assessing, and committing improvements with auditable lineage and rollback. Building on AGP, we present Autogenesis System (AGS), a self-evolving multi-agent system that dynamically instantiates, retrieves, and refines protocol-registered resources during execution. We evaluate AGS on multiple challenging benchmarks that require long horizon planning and tool use across heterogeneous resources. The results demonstrate consistent improvements over strong baselines, supporting the effectiveness of agent resource management and closed loop self evolution. The code is available at https://github.com/DVampire/Autogenesis.
Authors: Valentin Kriegmair, Dirk U. Wulff
Abstract: As large language models (LLMs) are increasingly integrated into daily life, in roles ranging from high-stakes decision support to companionship, understanding their behavioral dispositions becomes critical. A growing literature uses psychometric inventories and cognitive paradigms to profile LLM dispositions. However, these approaches cannot determine whether behavioral differences reflect stable, stimulus-specific individuality or global response biases and stochastic noise. Here, we apply crossed random-effects models -- widely used in psychometrics to separate systematic effects -- to 74.9 million ratings provided by 10 open-weight LLMs for over 100,000 words across 14 psycholinguistic norms. On average, 16.9% of variance is attributable to stimulus-specific individuality, robustly exceeding a statistical null model. Cross-norm prediction analyses reveal this individuality as a coherent fingerprint, unique to each model. These results identify individual differences among LLMs that cannot be attributed to response biases or stochastic noise. We term these differences machine individuality.
Authors: Xinyu Zhu, Yuzhu Cai, Zexi Liu, Cheng Wang, Fengyang Li, Wenkai Jin, Wanxu Liu, Zehao Bing, Bingyang Zheng, Jingyi Chai, Shuo Tang, Rui Ye, Yuwen Du, Xianghe Pang, Yaxin Du, Tingjia Miao, Yuzhi Zhang, Ruoxue Liao, Zhaohan Ding, Linfeng Zhang, Yanfeng Wang, Weinan E, Siheng Chen
Abstract: The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. While the scientific method is inherently iterative, existing agent frameworks are predominantly static, narrowly scoped, and lack the capacity to learn from trial and error. To bridge this gap, we present EvoMaster, a foundational evolving agent framework engineered specifically for Agentic Science at Scale. Driven by the core principle of continuous self-evolution, EvoMaster empowers agents to iteratively refine hypotheses, self-critique, and progressively accumulate knowledge across experimental cycles, faithfully mirroring human scientific inquiry. Crucially, as a domain-agnostic base harness, EvoMaster is exceptionally easy to scale up -- enabling developers to build and deploy highly capable, self-evolving scientific agents for arbitrary disciplines in approximately 100 lines of code. Built upon EvoMaster, we incubated the SciMaster ecosystem across domains such as machine learning, physics, and general science. Evaluations on four authoritative benchmarks (Humanity's Last Exam, MLE-Bench Lite, BrowseComp, and FrontierScience) demonstrate that EvoMaster achieves state-of-the-art scores of 41.1%, 75.8%, 73.3%, and 53.3%, respectively. It comprehensively outperforms the general-purpose baseline OpenClaw with relative improvements ranging from +159% to +316%, robustly validating its efficacy and generality as the premier foundational framework for the next generation of autonomous scientific discovery. EvoMaster is available at https://github.com/sjtu-sai-agents/EvoMaster.
Authors: Yifan Song, Xingjian Tao, Zhicheng Yang, Yihong Luo, Jing Tang
Abstract: Graph-based Retrieval-Augmented Generation (GraphRAG) enhances LLMs by structuring corpus into graphs to facilitate multi-hop reasoning. While recent lightweight approaches reduce indexing costs by leveraging Named Entity Recognition (NER), they rely strictly on structural co-occurrence, failing to capture latent semantic connections between disjoint entities. To address this, we propose EHRAG, a lightweight RAG framework that constructs a hypergraph capturing both structure and semantic level relationships, employing a hybrid structural-semantic retrieval mechanism. Specifically, EHRAG constructs structural hyperedges based on sentence-level co-occurrence with lightweight entity extraction and semantic hyperedges by clustering entity text embeddings, ensuring the hypergraph encompasses both structural and semantic information. For retrieval, EHRAG performs a structure-semantic hybrid diffusion with topic-aware scoring and personalized pagerank (PPR) refinement to identify the top-k relevant documents. Experiments on four datasets show that EHRAG outperforms state-of-the-art baselines while maintaining linear indexing complexity and zero token consumption for construction. Code is available at https://github.com/yfsong00/EHRAG.
Authors: Lingfeng Zhang, Yongan Sun, Jinpeng Hu, Hui Ma, Yang Ying, Kuien Liu, Zenglin Shi, Meng Wang
Abstract: Recent advancements in large language models (LLMs) have empowered autonomous web agents to execute natural language instructions directly on real-world webpages. However, existing agents often struggle with complex tasks involving dynamic interactions and long-horizon execution due to rigid planning strategies and hallucination-prone reasoning. To address these limitations, we propose WebUncertainty, a novel autonomous agent framework designed to tackle dual-level uncertainty in planning and reasoning. Specifically, we design a Task Uncertainty-Driven Adaptive Planning Mechanism that adaptively selects planning modes to navigate unknown environments. Furthermore, we introduce an Action Uncertainty-Driven Monte Carlo tree search (MCTS) Reasoning Mechanism. This mechanism incorporates the Confidence-induced Action Uncertainty (ConActU) strategy to quantify both aleatoric uncertainty (AU) and epistemic uncertainty (EU), thereby optimizing the search process and guiding robust decision-making. Experimental results on the WebArena and WebVoyager benchmarks demonstrate that WebUncertainty achieves superior performance compared to state-of-the-art baselines.
Authors: Terry Leitch
Abstract: We present a systematic evaluation of large language model families -- spanning both proprietary cloud APIs and locally-hosted open-source models -- on two purpose-built benchmarks for System Dynamics AI assistance: the \textbf{CLD Leaderboard} (53 tests, structured causal loop diagram extraction) and the \textbf{Discussion Leaderboard} (interactive model discussion, feedback explanation, and model building coaching). On CLD extraction, cloud models achieve 77--89\% overall pass rates; the best local model reaches 77\% (Kimi~K2.5~GGUF~Q3, zero-shot engine), matching mid-tier cloud performance. On Discussion, the best local models achieve 50--100\% on model building steps and 47--75\% on feedback explanation, but only 0--50\% on error fixing -- a category dominated by long-context prompts that expose memory limits in local deployments. A central contribution of this paper is a systematic analysis of \textit{model type effects} on performance: we compare reasoning vs.\ instruction-tuned architectures, GGUF (llama.cpp) vs.\ MLX (mlx\_lm) backends, and quantization levels (Q3 / Q4\_K\_M / MLX-3bit / MLX-4bit / MLX-6bit) across the same underlying model families. We find that backend choice has larger practical impact than quantization level: mlx\_lm does not enforce JSON schema constraints, requiring explicit prompt-level JSON instructions, while llama.cpp grammar-constrained sampling handles JSON reliably but causes indefinite generation on long-context prompts for dense models. We document the full parameter sweep ($t$, $p$, $k$) for all local models, cleaned timing data (stuck requests excluded), and a practitioner guide for running 671B--123B parameter models on Apple~Silicon.
Authors: Kevin Murphy
Abstract: We present BLF (Bayesian Linguistic Forecaster), an agentic system for binary forecasting that achieves state-of-the-art performance on the ForecastBench benchmark. The system is built on three ideas. (1) A linguistic belief state: a semi-structured representation combining numerical probability estimates with natural-language evidence summaries, updated by the LLM at each step of an iterative tool-use loop. This contrasts with the common approach of appending all retrieved evidence to an ever-growing context. (2) Hierarchical multi-trial aggregation: running $K$ independent trials and combining them using logit-space shrinkage with a data-dependent prior. (3) Hierarchical calibration: Platt scaling with a hierarchical prior, which avoids over-shrinking extreme predictions for sources with skewed base rates. On 400 backtesting questions from the ForecastBench leaderboard, BLF outperforms all the top public methods, including Cassi, GPT-5, Grok~4.20, and Foresight-32B. Ablation studies show that the structured belief state is almost as impactful as web search access, and that shrinkage aggregation and hierarchical calibration each provide significant additional gains. In addition, we develop a robust back-testing framework with a leakage rate below 1.5\%, and use rigorous statistical methodology to compare different methods while controlling for various sources of noise.
Authors: Ming Li, Zhiyong Sun, Siep Weiland
Abstract: This paper revisits a classical challenge in the design of stabilizing controllers for nonlinear systems with a norm-bounded input constraint. By extending Lin-Sontag's universal formula and introducing a generic (state-dependent) scaling term, a unifying controller design method is proposed. The incorporation of this generic scaling term gives a unified controller and enables the derivation of alternative universal formulas with various favorable properties, which makes it suitable for tailored control designs to meet specific requirements and provides versatility across different control scenarios. Additionally, we present a constructive approach to determine the optimal scaling term, leading to an explicit solution to an optimization problem, named optimization-based universal formula. The resulting controller ensures asymptotic stability, satisfies a norm-bounded input constraint, and optimizes a predefined cost function. Finally, the essential properties of the unified controllers are analyzed, including smoothness, continuity at the origin, stability margin, and inverse optimality. Simulations validate the approach, showcasing its effectiveness in addressing a challenging stabilizing control problem of a nonlinear system.
Authors: Bo Shu, Yiting Zhang, Saisai Hu, Dong Shu
Abstract: This report investigates the history and impact of Generative Models and Connected and Automated Vehicles (CAVs), two groundbreaking forces pushing progress in technology and transportation. By focusing on the application of generative models within the context of CAVs, the study aims to unravel how this integration could enhance predictive modeling, simulation accuracy, and decision-making processes in autonomous vehicles. This thesis discusses the benefits and challenges of integrating generative models and CAV technology in transportation. It aims to highlight the progress made, the remaining obstacles, and the potential for advancements in safety and innovation.
Authors: Pooneh Mousavi, Jarod Duret, Darius Petermann, Artem Ploujnikov, Luca Della Libera, Anastasia Kuznetsova, Cem Subakan, Mirco Ravanelli
Abstract: Discrete audio tokens have recently gained considerable attention for their potential to bridge audio and language processing, enabling multimodal language models that can both generate and understand audio. However, preserving key information such as phonetic content, speaker identity, and paralinguistic cues remains a major challenge. Identifying the optimal tokenizer and configuration is further complicated by inconsistent evaluation settings across existing studies. To address this, we introduce the Discrete Audio and Speech Benchmark (DASB), a comprehensive framework for benchmarking discrete audio tokens across speech, general audio, and music domains on a range of discriminative and generative tasks. Our results show that discrete representations are less robust than continuous ones and require careful tuning of factors such as model architecture, data size, learning rate, and capacity. Semantic tokens generally outperform acoustic tokens, but a gap remains between discrete tokens and continuous features, highlighting the need for further research. DASB codes, evaluation setup, and leaderboards are publicly available at https://poonehmousavi.github.io/DASB-website/.
Authors: Tianheng Ling, Chao Qian, Gregor Schiele
Abstract: Executing flow estimation using Deep Learning (DL)-based soft sensors on resource-limited IoT devices has demonstrated promise in terms of reliability and energy efficiency. However, its application in the field of wastewater flow estimation remains underexplored due to: (1) a lack of available datasets, (2) inconvenient toolchains for on-device AI model development and deployment, and (3) hardware platforms designed for general DL purposes rather than being optimized for energy-efficient soft sensor applications. This study addresses these gaps by proposing an automated, end-to-end solution for wastewater flow estimation using a prototype IoT device.
Authors: Chao Qian, Christopher Cichiwskyj, Tianheng Ling, Gregor Schiele
Abstract: In the rapidly evolving Internet of Things (IoT) domain, we concentrate on enhancing energy efficiency in Deep Learning accelerators on FPGA-based heterogeneous platforms, aligning with the principles of sustainable computing. Instead of focusing on the inference phase, we introduce innovative optimizations to minimize the overhead of the FPGA configuration phase. By fine-tuning configuration parameters correctly, we achieved a 40.13-fold reduction in configuration energy. Moreover, augmented with power-saving methods, our Idle-Waiting strategy outperformed the traditional On-Off strategy in duty-cycle mode for request periods up to 499.06 ms. Specifically, at a 40 ms request period within a 4147 J energy budget, this strategy extends the system lifetime to approximately 12.39x that of the On-Off strategy. Empirically validated through hardware measurements and simulations, these optimizations provide valuable insights and practical methods for achieving energy-efficient and sustainable deployments in IoT.
Authors: Christoph Riedl, Eric Bogert
Abstract: Feedback from artificial intelligence (AI) is increasingly easy to access and research has already established that people learn from it. But individuals choose when and how to seek such feedback, and more engaged and motivated individuals may seek it more, creating an illusion of effectiveness that masks self-selection. We investigate how the endogenous choice to seek AI feedback shapes both individual learning and collective outcomes. Using data from over five years and 52,000 individuals on an online chess platform, we show that motivated and higher-skilled individuals self-select into AI feedback use-and use it more productively. This self-selection creates an illusion of AI effectiveness: apparent learning gains disappear once endogenous motivation is accounted for. This same selection mechanism drives two population-level consequences. Because motivated, higher-skilled individuals benefit disproportionately, AI access widens the skill gap. And because individuals exposed to centralized AI feedback converge on common input from a centralized AI source, intellectual diversity declines. Leveraging 42 platform-level natural experiments, we show this diversity reduction is causal. Self-selection into AI use thus connects individual-level learning dynamics to collective-level consequences-a micro-macro linkage with implications for organizational learning, human capital development, and the design of AI-augmented work.
Authors: Young-Jin Park, Carson Sobolewski, Navid Azizan
Abstract: DETR and its variants have emerged as promising architectures for object detection, offering an end-to-end prediction pipeline. In practice, however, DETRs generate hundreds of predictions that far outnumber the actual objects present in an image. This raises a critical question: which of these predictions could be trusted? This is particularly important for safety-critical applications, such as in autonomous vehicles. Addressing this concern, we provide empirical and theoretical evidence that predictions within the same image play distinct roles, resulting in varying reliability levels. Our analysis reveals that DETRs employ an optimal specialist strategy: one prediction per object is trained to be well-calibrated, while the remaining predictions are trained to suppress their foreground confidence to near zero, even when maintaining accurate localization. We show that this strategy emerges as the loss-minimizing solution to the Hungarian matching, fundamentally shaping DETRs' outputs. While selecting the well-calibrated predictions is ideal, they are unidentifiable at inference time. This means that any post-processing algorithm poses a risk of outputting a set of predictions with mixed calibration levels. Therefore, practical deployment necessitates a joint evaluation of both the model's calibration quality and the effectiveness of the post-processing algorithm. However, we demonstrate that existing metrics like average precision and expected calibration error are inadequate for this task. To address this issue, we further introduce Object-level Calibration Error (OCE): This object-centric design penalizes both retaining suppressed predictions and missed ground truth foreground objects, making OCE suitable for both evaluating models and identifying reliable prediction subsets. Finally, we present a post hoc uncertainty quantification framework that predicts per-image model accuracy.
Authors: Chao Wang, Lingling Li, Licheng Jiao, Jiaxuan Zhao, Fang Liu, Shuyuan Yang
Abstract: The iterative search process of evolutionary algorithms (EAs) encapsulates optimization knowledge within historical populations and fitness evaluations. Effective utilization of this knowledge is crucial for facilitating knowledge transfer and online adaptation. However, current research typically addresses these goals in isolation and faces distinct limitations: evolutionary sequential transfer optimization often suffers from incomplete utilization of prior knowledge, while adaptive strategies, utilizing real-time knowledge, are limited to tailoring specific evolutionary operators. To simultaneously achieve these two capabilities, we introduce the Optimization Knowledge Adaptation Evolutionary Model (OKAEM), a unified learnable evolutionary framework capable of adaptively updating parameters based on available optimization knowledge. By parameterizing evolutionary operators via attention mechanisms, OKAEM enables learnable update rules that facilitate the utilization of optimization knowledge via two phases: pre-training to integrate extensive prior knowledge for efficient transfer, and adaptive optimization to dynamically update parameters based on real-time knowledge. Experimental results confirm that OKAEM significantly outperforms state-of-the-art sequential transfer methods across 12 transfer scenarios via pre-training, and surpasses advanced learnable EAs solely through its self-tuning mechanism in prior-free settings. Beyond demonstrating practical utility in prompt tuning for vision-language models, ablation studies validate the necessity of the learnable components, while visualization analyses reveal the model's capacity to autonomously discover interpretable evolutionary principles. The code can be accessed at https://gitee.com/Anonymity_Paper/code-of-okaem.
Authors: Weicheng Zhu, Haoxu Huang, Huanze Tang, Rushabh Musthyala, Boyang Yu, Long Chen, Emilio Vega, Thomas O'Donnell, Seena Dehkharghani, Jennifer A. Frontera, Arjun V. Masurkar, Kara Melmed, Narges Razavian
Abstract: Head computed tomography (CT) imaging is a widely-used imaging modality with multitudes of medical indications, particularly in assessing pathology of the brain, skull, and cerebrovascular system. It is commonly the first-line imaging in neurologic emergencies given its rapidity of image acquisition, safety, cost, and ubiquity. Deep learning models may facilitate detection of a wide range of diseases. However, the scarcity of high-quality labels and annotations, particularly among less common conditions, significantly hinders the development of powerful models. To address this challenge, we introduce FM-CT: a Foundation Model for Head CT for generalizable disease detection, trained using self-supervised learning. Our approach pre-trains a deep learning model on a large, diverse dataset of 361,663 non-contrast 3D head CT scans without the need for manual annotations, enabling the model to learn robust, generalizable features. To investigate the potential of self-supervised learning in head CT, we employed both discrimination with self-distillation and masked image modeling, and we construct our model in 3D rather than at the slice level (2D) to exploit the structure of head CT scans more comprehensively and efficiently. The model's downstream classification performance is evaluated using internal and three external datasets, encompassing both in-distribution (ID) and out-of-distribution (OOD) data. Our results demonstrate that the self-supervised foundation model significantly improves performance on downstream diagnostic tasks compared to models trained from scratch and previous 3D CT foundation models on scarce annotated datasets. This work highlights the effectiveness of self-supervised learning in medical imaging and sets a new benchmark for head CT image analysis in 3D, enabling broader use of artificial intelligence for head CT-based diagnosis.
Authors: Baiyu Chen, Wilson Wongso, Zechen Li, Yonchanok Khaokaew, Hao Xue, Flora Salim
Abstract: The goal of creating intelligent, human-centered wearable systems for continuous activity understanding faces a fundamental trade-off: Egocentric video-based models capture rich semantic information and have demonstrated strong performance in human activity recognition (HAR), but their high power consumption, privacy concerns, and dependence on lighting limit their feasibility for continuous on-device recognition. In contrast, inertial measurement unit (IMU) sensors offer an energy-efficient, privacy-preserving alternative, yet lack large-scale annotated datasets, leading to weaker generalization. To bridge this gap, we propose COMODO, a cross-modal self-supervised distillation framework that transfers semantic knowledge from video to IMU without requiring labels. COMODO leverages a pretrained and frozen video encoder to construct a dynamic instance queue to align the feature distributions of video and IMU embeddings. This enables the IMU encoder to inherit rich semantic structure from video while maintaining its efficiency for real-world applications. Experiments on multiple egocentric HAR datasets show that COMODO consistently improves downstream performance, matching or surpassing fully supervised models, and demonstrating strong cross-dataset generalization. Benefiting from its simplicity and flexibility, COMODO is compatible with diverse pretrained video and time-series models, offering the potential to leverage more powerful teacher and student foundation models in future ubiquitous computing research. The code is available at this repository: https://github.com/cruiseresearchgroup/COMODO.
Authors: Zeping Liu, Ni Lao, Zhangyu Wang, Junfeng Jiao, Gengchen Mai
Abstract: Vision Transformer (ViT) has been widely used in computer vision tasks with excellent results by providing representations for a whole image or image patches. However, ViT lacks detailed localized image representations at arbitrary positions when applied to geospatial tasks that involve multiple geospatial data modalities, such as overhead remote sensing (RS) data, ground-level imagery, and geospatial vector data. Here high-resolution localized representations are vital for modeling geospatial relationships and alignments across modalities. We proposed to solve this representation problem with an implicit neural representation (INR) module extending ViT with Neural Implicit Local Interpolation, which produces a continuous RS image representation covering arbitrary location in the RS image. Based on the INR module, we introduce GAIR, a novel location-aware self-supervised learning (SSL) objective integrating overhead RS data, street view (SV) imagery, and their geolocation metadata. GAIR utilizes three factorized neural encoders to project different modalities into the embedding space, and the INR module is used to further align these representations geographically, which are trained with contrastive learning objectives from unlabeled data. We evaluate GAIR across 9 geospatial tasks and 22 datasets spanning RS image-based, SV image-based, and location embedding-based benchmarks. Experimental results demonstrate that GAIR outperforms state-of-the-art geo-foundation models (GeoFM) and alternative SSL training objectives (e.g., MoCo V3 and MAE) that do not use fine-grained geo-aligned spatial representations. Our results highlight the effectiveness of GAIR in learning generalizable geospatial representations across tasks, spatial scales, and temporal contexts. The project code is available at https://github.com/zpl99/GAIR.
Authors: Hyunjong Ok, Suho Yoo, Jaeho Lee
Abstract: Spoken dialogue systems powered by large language models have demonstrated remarkable abilities in understanding human speech and generating appropriate spoken responses. However, these systems struggle with end-turn detection (ETD) -- the ability to distinguish between user turn completion and hesitation. This limitation often leads to premature or delayed responses, disrupting the flow of spoken conversations. In this paper, we introduce the ETD Dataset, the first public dataset for end-turn detection. The ETD dataset consists of both synthetic speech data generated with text-to-speech models and real-world speech data collected from web sources. We also propose SpeculativeETD, a novel collaborative inference framework that balances efficiency and accuracy to improve real-time ETD in resource-constrained environments. Our approach jointly employs a lightweight GRU-based model, which rapidly detects the non-speaking units in real-time on local devices, and a high-performance Wav2vec-based model running on the server to make a more challenging classification of distinguishing turn ends from mere pauses. Experiments demonstrate that the proposed SpeculativeETD significantly improves ETD accuracy while keeping the required computations low. Datasets and code will be available after the review.
Authors: Jenny Ma, Riya Sahni, Karthik Sreedhar, Lydia B. Chilton
Abstract: Multi-agent large language model simulations have the potential to model complex human behaviors and interactions. If the mechanics are set up properly, unanticipated and valuable social dynamics can surface. However, it is challenging to consistently enforce simulation mechanics while still allowing for notable and emergent dynamics. We present AgentDynEx, an AI system that helps set up simulations from user-specified mechanics and dynamics. AgentDynEx uses LLMs to guide users through a Configuration Matrix to identify core mechanics and define milestones to track dynamics. It also introduces a method called \textit{nudging}, where the system dynamically reflects on simulation progress and gently intervenes if it begins to deviate from intended outcomes. A technical evaluation found that nudging enables simulations to have more complex mechanics and maintain its notable dynamics compared to simulations without nudging. We discuss the importance of nudging as a technique for balancing mechanics and dynamics of multi-agent simulations.
Authors: Jinsheng Yuan, Yuhang Hao, Weisi Guo, Yun Wu, Chongyan Gu
Abstract: Federated Learning (FL) has the potential for simultaneous global learning amongst a large number of parallel agents, enabling emerging AI such as LLMs to be trained across demographically diverse data. Central to this being efficient is the ability for FL to perform sparse gradient updates and remote direct memory access at the central server. Most of the research in FL security focuses on protecting data privacy at the edge client or in the communication channels between the client and server. Client-facing attacks on the server are less well investigated as the assumption is that a large collective of clients offer resilience. Here, we show that by attacking certain clients that lead to a high frequency repetitive memory update in the server, we can remote initiate a rowhammer attack on the server memory. For the first time, we do not need backdoor access to the server, and a reinforcement learning (RL) attacker can learn how to maximize server repetitive memory updates by manipulating the client's sensor observation. The consequence of the remote rowhammer attack is that we are able to achieve bit flips, which can corrupt the server memory. We demonstrate the feasibility of our attack using a large-scale FL automatic speech recognition (ASR) systems with sparse updates, our adversarial attacking agent can achieve around 70% repeated update rate (RUR) in the targeted server model, effectively inducing bit flips on server DRAM. The security implications are that can cause disruptions to learning or may inadvertently cause elevated privilege. This paves the way for further research on practical mitigation strategies in FL and hardware design.
Authors: Shijun Li, Hilaf Hasson, Joydeep Ghosh
Abstract: Agents powered by advanced large language models (LLMs) have demonstrated impressive capabilities across diverse complex applications. Recently, Multi-Agent Systems (MAS), wherein multiple agents collaborate and communicate with each other, have exhibited enhanced capabilities in complex tasks, such as high-quality code generation and arithmetic reasoning. However, the development of such systems often relies on handcrafted methods, and the literature on systematic design and optimization of LLM-based MAS remains limited. In this work, we introduce OMAC, a general framework designed for holistic optimization of LLM-based MAS. Specifically, we identify five key optimization dimensions for MAS, encompassing both agent functionality and collaboration structure. Building upon these dimensions, we first propose a general algorithm, utilizing two actors termed the Semantic Initializer and the Contrastive Comparator, to optimize any single dimension. Then, we present an algorithm for joint optimization across multiple dimensions. Extensive experiments demonstrate the superior performance of OMAC on code generation, arithmetic reasoning, and general reasoning tasks against state-of-the-art approaches.
Authors: Ahmed Heakl, Gustavo Bertolo Stahl, Sarim Hashmi, Seung Hun Eddie Han, Mukul Ranjan, Arina Kharlamova, Salman Khan, Abdulrahman Mahmoud
Abstract: Cross-architecture GPU code transpilation is essential for unlocking low-level hardware portability, yet no scalable solution exists. We introduce CASS, the first dataset and model suite for source- and assembly-level GPU translation (CUDA <--> HIP, SASS <--> RDNA3). CASS contains 60k verified host-device code pairs, enabling learning-based translation across both ISA and runtime boundaries. We generate each sample using our automated pipeline that scrapes, translates, compiles, and aligns GPU programs across vendor stacks. Leveraging CASS, we train a suite of domain-specific translation models that achieve 88.2% accuracy on CUDA -> HIP and 69.1% on SASS -> RDNA3, outperforming commercial baselines including GPT-5.1, Claude-4.5, and Hipify by wide margins. Generated code matches native performance in 85% of cases, preserving both runtime and memory behavior. To support rigorous evaluation, we introduce CASS-Bench, a curated benchmark spanning 18 GPU domains with ground-truth execution. All data, models, and evaluation tools will be released as open source to support progress in GPU compiler tooling, binary compatibility, and LLM-guided code translation.
Authors: Hengzhi Li, Justin Zhang, Brendon Jiang, Alexander Naehu, Regan Song, Megan Tjandrasuwita, Chanakya Ekbote, Steven-Shine Chen, Adithya Balachandran, Wei Dai, Rebecca Chang, Paul Pu Liang
Abstract: Puzzlehunts are a genre of complex, multi-step puzzles lacking well-defined problem definitions. In contrast to conventional reasoning benchmarks consisting of tasks with clear instructions and constrained environments, puzzlehunts requires discovering the underlying problem structure from multimodal evidence and iterative reasoning, mirroring real-world domains such as scientific discovery, exploratory data analysis, or investigative problem-solving. Despite progress in foundation models, their performance on open-ended settings remains largely untested. We introduce PuzzleWorld, a comprehensive benchmark of 667 puzzlehunt-style problems designed to assess step-by-step, open-ended, and creative multimodal reasoning. Each puzzle is annotated with the final solution, detailed reasoning traces, and cognitive skill labels, enabling holistic benchmarking and fine-grained diagnostic analysis. Most state-of-the-art models achieve only 1-4% final answer accuracy. On PuzzleWorld, the best model solves only 18% of puzzles and reaches 40% stepwise accuracy, matching human puzzle novices but falling significantly behind puzzle enthusiasts. To demonstrate the value of our reasoning annotations, we show that fine-tuning a small model on reasoning traces boosts stepwise accuracy from 4% to 11%, which translates to improvements in downstream visual reasoning tasks. Our detailed error analysis reveals that current models exhibit myopic reasoning, are bottlenecked by the limitations of language-based inference, and lack sketching capabilities crucial for visual and spatial reasoning. We release PuzzleWorld at https://github.com/MIT-MI/PuzzleWorld to support future work on building more general, open-ended, and creative reasoning systems.
Authors: Davis Brown, Mahdi Sabbaghi, Luze Sun, Alexander Robey, George J. Pappas, Eric Wong, Hamed Hassani
Abstract: Existing language model safety evaluations focus on overt attacks and low-stakes tasks. In reality, an attacker can easily subvert existing safeguards by requesting help on small, benign-seeming tasks across many independent queries. Because the individual queries do not appear harmful, the attack is hard to detect. However, when combined, these fragments uplift misuse by helping the attacker complete hard and dangerous tasks. Toward identifying defenses against such strategies, we develop Benchmarks for Stateful Defenses (BSD), a data generation pipeline that automates evaluations of covert attacks and corresponding defenses. Using this pipeline, we curate two new datasets that are consistently refused by frontier models and are too difficult for weaker open-weight models. This enables us to evaluate decomposition attacks, which are found to be effective misuse enablers, and to highlight stateful defenses as a promising countermeasure.
Authors: Jiaqi Tang, Yu Xia, Yi-Feng Wu, Yuwei Hu, Yuhui Chen, Qing-Guo Chen, Xiaogang Xu, Xiangyu Wu, Hao Lu, Yanqing Ma, Shiyin Lu, Qifeng Chen
Abstract: The advent of autonomous agents is transforming interactions with Graphical User Interfaces (GUIs) by employing natural language as a powerful intermediary. Despite the predominance of Supervised Fine-Tuning (SFT) methods in current GUI agents for achieving spatial localization, these methods face substantial challenges due to their limited capacity to accurately perceive positional data. Existing strategies, such as reinforcement learning, often fail to assess positional accuracy effectively, thereby restricting their utility. In response, we introduce Location Preference Optimization (LPO), a novel approach that leverages locational data to optimize interaction preferences. LPO uses information entropy to predict interaction positions by focusing on zones rich in information. Besides, it further introduces a dynamic location reward function based on physical distance, reflecting the varying importance of interaction positions. Supported by Group Relative Preference Optimization (GRPO), LPO facilitates an extensive exploration of GUI environments and significantly enhances interaction precision. Comprehensive experiments demonstrate LPO's superior performance, achieving SOTA results across both offline benchmarks and real-world online evaluations. Our code will be made publicly available soon, at https://github.com/jqtangust/LPO.
Authors: Chenyuan Wu, Pengfei Zheng, Ruiran Yan, Shitao Xiao, Xin Luo, Yueze Wang, Wanli Li, Xiyan Jiang, Yexin Liu, Junjie Zhou, Ze Liu, Ziyi Xia, Chaofan Li, Haoge Deng, Jiahao Wang, Kun Luo, Bo Zhang, Defu Lian, Xinlong Wang, Zhongyuan Wang, Tiejun Huang, Zheng Liu
Abstract: In this work, we introduce OmniGen2, a versatile and open-source generative model designed to provide a unified solution for diverse generation tasks, including text-to-image, image editing, and in-context generation. Unlike OmniGen v1, OmniGen2 features two distinct decoding pathways for text and image modalities, utilizing unshared parameters and a decoupled image tokenizer. This design enables OmniGen2 to build upon existing multimodal understanding models without the need to re-adapt VAE inputs, thereby preserving the original text generation capabilities. To facilitate the training of OmniGen2, we developed comprehensive data construction pipelines, encompassing image editing and in-context generation data. Additionally, we introduce a reflection mechanism tailored for image generation tasks and curate a dedicated reflection dataset based on OmniGen2. Despite its relatively modest parameter size, OmniGen2 achieves competitive results on multiple task benchmarks, including text-to-image and image editing. To further evaluate in-context generation, also referred to as subject-driven tasks, we introduce a new benchmark named OmniContext. OmniGen2 achieves state-of-the-art performance among open-source models in terms of consistency. We will release our models, training code, datasets, and data construction pipeline to support future research in this field. Project Page: https://vectorspacelab.github.io/OmniGen2; GitHub Link: https://github.com/VectorSpaceLab/OmniGen2
URLs: https://vectorspacelab.github.io/OmniGen2;, https://github.com/VectorSpaceLab/OmniGen2
Authors: Matthew Stephenson, Alex Newcombe, Eric Piette, Dennis Soemers
Abstract: We present an efficient and generalised procedure to accurately identify the best (or near best) performing algorithm for each sub-task in a multi-problem domain. Our approach treats this as a set of best arm identification problems for multi-armed bandits, where each bandit corresponds to a specific task and each arm corresponds to a specific algorithm or agent. We propose an optimistic selection process based on a chosen confidence interval, that ranks each arm across all bandits in terms of their potential to influence our overall simple regret. We evaluate the performance of our approach on two of the most popular general game playing domains, the General Video Game AI (GVGAI) framework and the Ludii general game playing system, with the goal of selecting a high-performing agent for each game using a limited number of available trials. Compared to previous best arm identification algorithms for multi-armed bandits, our results demonstrate a substantial performance improvement in terms of average simple regret and average probability of error. This novel approach can be used to significantly improve the quality and accuracy of agent evaluation procedures for general game frameworks, as well as other multi-task domains with high algorithm runtimes.
Authors: Christian Bongiorno, Efstratios Manolakis, Rosario Nunzio Mantegna
Abstract: We develop a rotation-invariant neural network that provides the global minimum-variance portfolio by jointly learning how to lag-transform historical returns and marginal volatilities and how to regularise the eigenvalues of large equity covariance matrices. This explicit mathematical mapping offers clear interpretability of each module's role, so the model cannot be regarded as a pure black box. The architecture mirrors the analytical form of the global minimum-variance solution yet remains agnostic to dimension, so a single model can be calibrated on panels of a few hundred stocks and applied, without retraining, to one thousand US equities, a cross-sectional jump that indicates robust generalization capability. The loss function is the future short-term realized minimum variance and is optimized end-to-end on real returns. In out-of-sample tests from January 2000 to December 2024, the estimator delivers systematically lower realized volatility, smaller maximum drawdowns, and higher Sharpe ratios than the best competitors, including state-of-the-art non-linear shrinkage, and these advantages persist across both short and long evaluation horizons despite the model's training focus is short-term. Furthermore, although the model is trained end-to-end to produce an unconstrained minimum-variance portfolio, we show that its learned covariance representation can be used in general optimizers under long-only constraints with virtually no loss in its performance advantage over competing estimators. These advantages persist when the strategy is executed under a highly realistic implementation framework that models market orders at the auctions, empirical slippage, exchange fees, and financing charges for leverage, and they remain stable during episodes of acute market stress.
Authors: Yihao Ding, Siwen Luo, Yue Dai, Yanbei Jiang, Zechuan Li, Qiang Sun, Geoffrey Martin, Wei Liu, Yifan Peng
Abstract: Visually Rich Document Understanding (VRDU) has become a pivotal area of research, driven by the need to automatically interpret documents that contain intricate visual, textual, and structural elements. Recently, Multimodal Large Language Models (MLLMs) have demonstrated significant promise in this domain, including both OCR-based and OCR-free approaches for information extraction from document images. This survey reviews recent advances in MLLM-based VRDU, highlighting emerging trends and promising research directions with a focus on two key aspects: (1) techniques for representing and integrating textual, visual, and layout features; (2) training paradigms, including pretraining, instruction tuning, and training strategies. Moreover, we address challenges such as data scarcity, handling multi-page and multilingual documents, and integrating emerging trends such as Retrieval-Augmented Generation and agentic frameworks. Our analysis offers a roadmap for advancing MLLM-based VRDU toward more scalable, reliable, and adaptable systems.
Authors: Zengyang Li, Yimeng Li, Binbin Huang, Peng Liang, Ran Mo, Hui Liu, Yutao Ma
Abstract: Multilingual programming, which involves using multiple programming languages (PLs) in a single project, is increasingly common due to its benefits. However, it introduces cross-language bugs (CLBs), which arise from interactions between different PLs and are difficult to detect by single-language bug detection tools. This paper investigates the potential of pre-trained code language models (CodeLMs) in CLB detection. We developed CLCFinder, a cross-language code identification tool, and constructed a CLB dataset involving three PL combinations (Python-C/C++, Java-C/C++, and Python-Java) with nine interaction types. We fine-tuned 13 CodeLMs on this dataset and evaluated their performance, analyzing the effects of dataset size, token sequence length, and code comments. Results show that all 13 CodeLMs exhibited varying degrees of performance improvement after fine-tuning, with UniXcoder-base achieving the best F1 score (0.7407). Notably, within our experimental setup, small CodeLMs tended to performe better than large ones. CodeLMs fine-tuned on single-language bug datasets performed poorly on CLB detection, demonstrating the distinction between CLBs and single-language bugs. Additionally, increasing the fine-tuning dataset size significantly improved performance, while longer token sequences did not necessarily improve the model performance. The impact of code comments varied across models. Some fine-tuned CodeLMs' performance was improved, while others showed degraded performance.
Authors: ZeKe Xiao, Qin Wang, Yuekang Li, Shiping Chen
Abstract: Smart contracts are important for digital finance, yet they are hard to patch once deployed. Prior work has mainly explored LLMs for smart contract vulnerability detection, leaving end-to-end automated exploit generation (AEG) much less understood. We study that gap with \textsc{ReX}, an execution-grounded framework that links LLM-based exploit synthesis to the Foundry stack for end-to-end generation, compilation, execution, and validation. Five recent LLMs are evaluated across eight common vulnerability classes, supported by a curated dataset of 38{+} real incident PoCs and three automation aids: prompt refactoring, a compiler feedback loop, and templated test harnesses. Results indicate that current frontier LLMs can often produce deterministic PoCs for single-contract vulnerabilities, but remain weak on cross-contract attacks; outcomes depend mainly on the model and bug type, while code structure and prompt tuning contribute less in our setting. The study also surfaces important boundary conditions of LLM-driven AEG, including gaps between oracle-validated exploitability and real-world economic attacks, pointing to the need for stronger defenses and more realistic evaluation.
Authors: Xianren Zhang, Shreyas Prasad, Di Wang, Qiuhai Zeng, Suhang Wang, Wenbo Yan, Mat Hans
Abstract: Web agents have shown great promise in performing many tasks on ecommerce website. To assess their capabilities, several benchmarks have been introduced. However, current benchmarks in the e-commerce domain face two major problems. First, they primarily focus on product search tasks (e.g., Find an Apple Watch), failing to capture the broader range of functionalities offered by real-world e-commerce platforms such as Amazon, including account management and gift card operations. Second, existing benchmarks typically evaluate whether the agent completes the user query, but ignore the potential risks involved. In practice, web agents can make unintended changes that negatively impact the user account or status. For instance, an agent might purchase the wrong item, delete a saved address, or incorrectly configure an auto-reload setting. To address these gaps, we propose a new benchmark called Amazon-Bench. To generate user queries that cover a broad range of tasks, we propose a data generation pipeline that leverages webpage content and interactive elements (e.g., buttons, check boxes) to create diverse, functionality-grounded user queries covering tasks such as address management, wish list management, and brand store following. To improve the agent evaluation, we propose an automated evaluation framework that assesses both the performance and the safety of web agents. We systematically evaluate different agents, finding that current agents struggle with complex queries and pose safety risks. These results highlight the need for developing more robust and reliable web agents.
Authors: Deepro Choudhury, Sinead Williamson, Adam Goli\'nski, Ning Miao, Freddie Bickford Smith, Michael Kirchhof, Yizhe Zhang, Tom Rainforth
Abstract: We propose a general-purpose approach for improving the ability of large language models (LLMs) to intelligently and adaptively gather information from a user or other external source using the framework of sequential Bayesian experimental design (BED). This enables LLMs to act as effective multi-turn conversational agents and interactively interface with external environments. Our approach, which we call BED-LLM (Bayesian experimental design with large language models), is based on iteratively choosing questions or queries that maximize the expected information gain (EIG) with respect to a variable of interest given the responses gathered previously. We show how this EIG can be formulated (and then estimated) in a principled way using a probabilistic model derived from the LLM's predictive distributions and provide detailed insights into key decisions in its construction and updating procedure. We find that BED-LLM achieves substantial gains in performance across a wide range of tests based on the 20 Questions game and using the LLM to actively infer user preferences, compared to purely prompting-based design generation and other adaptive design strategies.
Authors: Tomoki Yamagami, Etsuo Segawa, Takatomo Mihana, Andr\'e R\"ohm, Atsushi Uchida, Ryoichi Horisaki
Abstract: Quantum reinforcement learning has emerged as a framework combining quantum computation with sequential decision-making, and applications to the multi-armed bandit (MAB) problem have been reported. The graph bandit problem extends the MAB setting by introducing spatial constraints, where the accessibility of arms is restricted by graph connectivity, yet quantum approaches to this setting remain limited. In this paper, we formulate best-arm identification in graph bandits and propose a quantum algorithmic framework, termed Quantum Spatial Best-Arm Identification (QSBAI), which is applicable to general graph structures. This framework uses quantum walks to encode superpositions over graph-constrained actions, thereby extending amplitude amplification and generalizing the quantum BAI algorithm via Szegedy's walk framework. We focus our theoretical analysis on complete and bipartite graphs, deriving the maximal success probability of identifying the best arm and the time step at which it is achieved. Our results clarify how quantum-walk-based search can be adapted to structurally constrained decision problems and provide a foundation for quantum best-arm identification in graph-structured environments.
Authors: Chung-En Johnny Yu, Brian Jalaian, Nathaniel D. Bastian
Abstract: Large Vision-Language Models (LVLMs) exhibit strong multimodal capabilities but remain vulnerable to hallucinations from intrinsic errors and adversarial attacks from external exploitations, limiting their reliability in real-world applications. We present ORCA, an agentic reasoning framework that improves the factual accuracy and adversarial robustness of pretrained LVLMs through inference-time structured inference reasoning with a suite of small vision models (less than 3B parameters). ORCA operates via an Observe-Reason-Critique-Act loop, querying multiple visual tools with evidential questions, validating cross-model inconsistencies, and refining predictions iteratively without access to model internals or retraining. ORCA also stores intermediate reasoning traces, which supports auditable decision-making. Though designed primarily to mitigate object-level hallucinations, ORCA also exhibits emergent adversarial robustness without requiring adversarial training or defense mechanisms. We evaluate ORCA across three settings: (1) clean images on hallucination benchmarks, (2) adversarially perturbed images without defense, and (3) adversarially perturbed images with defense applied. On the POPE hallucination benchmark, ORCA improves standalone LVLMs performance by +3.64% to +40.67% across different subsets. Under adversarial perturbations on POPE, ORCA achieves an average accuracy gain of +20.11% across LVLMs. When combined with defense techniques on adversarially perturbed AMBER images, ORCA further improves standalone LVLM performance, with gains ranging from +1.20% to +48.00% across metrics. These results demonstrate that ORCA offers a promising path toward building more reliable and robust multimodal systems.
Authors: Chung-En Johnny Yu, Brian Jalaian, Nathaniel D. Bastian
Abstract: Building robust vision systems for high-stakes domains such as remote sensing requires stronger visual reasoning than what single-pass inference typically provides; yet, retraining large models is often computationally expensive and data intensive. We present Visual Reasoning Agent (VRA), a training-free agentic visual reasoning framework that orchestrates off-the-shelf large vision-language models (LVLMs) with a large reasoning model (LRM) through an iterative Think-Critique-Act loop for cross-model verification, self-critique, and recursive refinement. On the remote sensing benchmark VRSBench VQA dataset, VRA consistently outperforms multiple standalone LVLM baselines and achieves up to 40.67\% improvement on challenging question types spanning both perception and reasoning tasks. In addition, integrating three LVLMs with VRA improves the overall accuracy of the standalone LVLMs from 52.8% to 78.8%, demonstrating the effectiveness of agentic reasoning with increased inference-time compute.
Authors: Pin-Yen Chiu, I-Sheng Fang, Jun-Cheng Chen
Abstract: Recent advances in diffusion models have significantly improved image and video synthesis. In addition, several concept control methods have been proposed to enable fine-grained, continuous, and flexible control over free-form text prompts. However, these methods not only require intensive training time and GPU memory usage to learn the sliders or embeddings but also need to be retrained for different diffusion backbones, limiting their scalability and adaptability. To address these limitations, we introduce Text Slider, a lightweight, efficient and plug-and-play framework that identifies low-rank directions within a pre-trained text encoder, enabling continuous control of visual concepts while significantly reducing training time, GPU memory consumption, and the number of trainable parameters. Furthermore, Text Slider supports multi-concept composition and continuous control, enabling fine-grained and flexible manipulation in both image and video synthesis. We show that Text Slider enables smooth and continuous modulation of specific attributes while preserving the original spatial layout and structure of the input. Text Slider achieves significantly better efficiency: 5$\times$ faster training than Concept Slider and 47$\times$ faster than Attribute Control, while reducing GPU memory usage by nearly 2$\times$ and 4$\times$, respectively.
Authors: Yixin Wan, Xingrun Chen, Kai-Wei Chang
Abstract: Advancements in Large language models (LLMs) have enabled a variety of downstream applications like story and interview script generation. However, recent research raised concerns about culture-related fairness issues in LLM-generated content. In this work, we identify and systematically investigate LLMs' insider-outsider bias, a phenomenon where models position themselves as "insiders" of mainstream cultures during generation while externalizing less dominant cultures. We propose the InsideOut benchmark with 4,000 generation prompts and three evaluation metrics to quantify this bias through a culturally situated interview script generation task, in which an LLM is positioned as a reporter interviewing local people across 10 diverse cultures. Empirical evaluation on 5 state-of-the-art LLMs reveals that while models adopt insider tones in over 88% US-contexted scripts on average, they disproportionately default to "outsider" stances for non-Western cultures. To mitigate these biases, we propose 2 inference-time methods: a baseline prompt-based Fairness Intervention Pillars (FIP) method, and a structured Mitigation via Fairness Agents (MFA) framework consisting of a Single-Agent (MFA-SA), a Hierarchical-Agent (MFA-HA), and an autonomous Agentic Planning (MFA-Plan) pipeline. Empirical results demonstrate that agent-based MFA methods achieve outstanding and robust performance in mitigating the insider-outsider bias: For instance, on the Cultural Alignment Gap (CAG) metric, MFA-SA reduces bias in Llama model by 89.70 % and MFA-HA mitigates bias in Qwen by 82.54%. These findings showcase the effectiveness of agent-based methods as a promising direction for mitigating biases in generative LLMs.
Authors: Chenxiang Zhang, Alexander Theus, Damien Teney, Antonio Orvieto, Jun Pang, Sjouke Mauw
Abstract: Model merging combines independent solutions with different capabilities into a single one while maintaining the same inference cost. Two popular approaches are linear interpolation, which simply averages multiple model weights, and task arithmetic, which combines task vectors obtained by the difference between finetuned and base models. While useful in practice, what properties make merging effective are poorly understood. This paper explores how the optimization dynamics affect the loss landscape geometry and its impact on merging success. We show that a single quantity -- the effective noise scale -- unifies the impact of different optimizer components on model merging. Across architectures and datasets, merging success is a non-monotonic function of the effective noise scale, with a distinct optimum. Decomposing this quantity, we find that larger learning rates, stronger weight decay, smaller batch sizes, and data augmentation all independently modulate the effective noise scale and exhibit the same qualitative trend. Unlike prior work connecting optimizer noise to the flatness or generalization of individual minima, we show that it also affects the global loss landscape, predicting when independently trained solutions can be successfully merged. Our findings broaden the understanding of how optimization shapes the loss landscape geometry and its consequences for model merging, suggesting that training dynamics could be further manipulated to improve model merging.
Authors: Olayiwola Arowolo, Jochen L. Cremer
Abstract: AC Optimal Power Flow (ACOPF) is computationally intensive for large-scale grids, often requiring prohibitive solution times with conventional solvers. Machine learning offers significant speedups, but existing models struggle with scalability and topology flexibility. To address these challenges, we propose a Hybrid Heterogeneous Message Passing Neural Network (HH-MPNN) that integrates a heterogeneous graph neural network (GNN) with a scalable transformer and physics-informed positional encodings. Our architecture explicitly models distinct power system components to capture local features while using global attention for long-range dependencies. Evaluated on diverse benchmarks, including PGLearn and GridFM-DataKit datasets, HH-MPNN achieves less than 1% optimality gap on default topologies across grid sizes from 14 to 2,000 buses. For N-1 contingencies, our approach demonstrates zero-shot N-1 generalization with less than 3% optimality gap on several test cases despite training only on default topologies. We further develop an approach that ensures robust N-1 generalization to high-impact contingencies through targeted augmentation of the training data, showing that exhaustive simulation is unnecessary for topologically flexible models. Finally, size generalization experiments demonstrate that pre-training on small grids significantly improves performance on large-scale systems. Achieving computational speedups of up to 5,000 times compared to interior point solvers, these results advance practical, generalizable machine learning for real-time power system operations.
Authors: Abdulwahab Felemban, Yahia Battach, Faizan Farooq Khan, Yuqian Fu, Xuhui Liu, Yesmeen M. Khattab, Yousef A. Radwan, Xiang Li, Fabio Marchese, Sara Beery, Burton H. Jones, Francesca Benzoni, Mohamed Elhoseiny
Abstract: Coral reefs are rapidly declining under anthropogenic pressures (e.g., climate change), creating an urgent need for scalable and automated monitoring. Progress in data-driven coral analysis, however, is constrained by the scarcity of large-scale datasets with fine-grained labels that are taxonomically consistent across sites and studies. To address this gap, we introduce ReefNet, a large-scale public coral reef image dataset with point-level annotations mapped to the World Register of Marine Species (WoRMS) taxonomy. ReefNet aggregates imagery from 76 curated CoralNet sources and an additional reef site from Al-Wajh (Red Sea), totaling approximately 925K genus-level hard coral annotations. Through expert-driven verification and targeted filtering, we derive a high-confidence benchmark subset with 92% expert agreement over 39 hard-coral label classes, enabling reliable evaluation under realistic label noise and strong class imbalance. Beyond dataset construction, we establish a comprehensive benchmark spanning zero-shot, cross-domain few-shot adaptation, within-source evaluation, and cross-source transfer to the Al-Wajh dataset. Experiments with state-of-the-art vision-language models (VLMs), multimodal large language models (MLLMs), and vision-only backbones reveal substantial degradation in zero-shot and extremely few-shot regimes, while adaptation with in-domain supervision yields large gains yet still leaves a persistent gap under cross-source shift and on long-tail genera. These results highlight fundamental challenges in applying general-purpose multimodal models to biodiversity monitoring and underscore the importance of large-scale, taxonomically grounded, high-quality datasets. ReefNet serves as both a benchmark and a training resource for advancing fine-grained coral reef understanding.
Authors: George Ma, Anurag Koul, Qi Chen, Yawen Wu, Sachit Kuhar, Yu Yu, Aritra Sengupta, Varun Kumar, Murali Krishna Ramanathan
Abstract: Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs and cross-file dependencies are crucial. Retrieval-augmented methods mitigate this by injecting repository context at inference time. The low inference-time latency budget affects either retrieval quality or the added latency adversely impacts user experience. We address this limitation with SpecAgent, an agent that improves both latency and code-generation quality by proactively exploring repository files during indexing and constructing speculative context that anticipates future edits in each file. This indexing-time asynchrony allows thorough context computation, masking latency, and the speculative nature of the context improves code-generation quality. Additionally, we identify the problem of future context leakage in existing benchmarks, which can inflate reported performance. To address this, we construct a synthetic, leakage-free benchmark that enables a more realistic evaluation of our agent against baselines. Experiments show that SpecAgent consistently achieves absolute gains of 9-11% (48-58% relative) compared to the best-performing baselines, while significantly reducing inference latency.
Authors: Koki Shibata, Tianheng Ling, Chao Qian, Tomokazu Matsui, Hirohiko Suwa, Keiichi Yasumoto, Gregor Schiele
Abstract: The growing demand for smart home interfaces has increased interest in non-intrusive sensing methods like vibration-based gesture recognition. While prior studies demonstrated feasibility, they often rely on complex preprocessing and large Neural Networks (NNs) requiring costly high-performance hardware, resulting in high energy usage and limited real-world deployability. This study proposes an energy-efficient solution deploying compact NNs on low-power Field-Programmable Gate Arrays (FPGAs) to enable real-time gesture recognition with competitive accuracy. We adopt a series of optimizations: (1) We replace complex spectral preprocessing with raw waveform input, eliminating complex on-board preprocessing while reducing input size by 21x without sacrificing accuracy. (2) We design two lightweight architectures (1D-CNN and 1D-SepCNN) tailored for embedded FPGAs, reducing parameters from 369 million to as few as 216 while maintaining comparable accuracy. (3) With integer-only quantization and automated RTL generation, we achieve seamless FPGA deployment. A ping-pong buffering mechanism in 1D-SepCNN further improves deployability under tight memory constraints. (4) We extend a hardware-aware search framework to support constraint-driven model configuration selection, considering accuracy, deployability, latency, and energy consumption. Evaluated on two swipe-direction datasets with multiple users and ordinary tables, our approach achieves low-latency, energy-efficient inference on the AMD Spartan-7 XC7S25 FPGA. Under the PS data splitting setting, the selected 6-bit 1D-CNN reaches 0.970 average accuracy across users with 9.22 ms latency. The chosen 8-bit 1D-SepCNN further reduces latency to 6.83 ms (over 53x CPU speedup) with slightly lower accuracy (0.949). Both consume under 1.2 mJ per inference, demonstrating suitability for long-term edge operation.
Authors: Cesare Barbera, Lorenzo Perini, Giovanni De Toni, Andrea Passerini, Andrea Pugnana
Abstract: Developing trustworthy Machine Learning (ML) models requires their predicted probabilities to be well-calibrated, meaning they should reflect true-class frequencies. Among calibration notions in multiclass classification, strong calibration is the most stringent, as it requires all predicted probabilities to be simultaneously calibrated across all classes. However, existing approaches to multiclass calibration lack a notion of distance among inputs, which makes them vulnerable to proximity bias: predictions in sparse regions of the feature space are systematically miscalibrated. In this work, we address this main shortcoming by introducing a local perspective on multiclass calibration. First, we formally define multiclass local calibration and establish its relationship with strong calibration. Second, we theoretically analyze the pitfalls of existing evaluation metrics when applied to multiclass local calibration. Third, we propose a practical method to enhance local calibration in Neural Networks, which enforces alignment between predicted probabilities and local estimates of class frequencies using the Jensen-Shannon distance. Finally, we empirically validate our approach against existing multiclass calibration techniques.
Authors: Zaishuo Xia, Yukuan Lu, Xinyi Li, Yifan Xu, Yubei Chen
Abstract: A world model is an internal model that simulates how the world evolves. Given past observations and actions, it predicts the future physical state of both the embodied agent and its environment. Accurate world models are essential for enabling agents to think, plan, and reason effectively in complex, dynamic settings. However, existing world models often focus on random generation of open worlds, but neglect the need for high-fidelity modeling of deterministic scenarios (such as fixed-map mazes and static space robot navigation). In this work, we take a step toward building a truly accurate world model by addressing a fundamental yet open problem: constructing a model that can fully clone a deterministic 3D world. 1) Through diagnostic experiment, we quantitatively demonstrate that high-fidelity cloning is feasible and the primary bottleneck for long-horizon fidelity is the geometric structure of the latent representation, not the dynamics model itself. 2) Building on this insight, we show that applying temporal contrastive learning principle as a geometric regularization can effectively curate a latent space that better reflects the underlying physical state manifold, demonstrating that contrastive constraints can serve as a powerful inductive bias for stable world modeling; we call this approach Geometrically-Regularized World Models (GRWM). At its core is a lightweight geometric regularization module that can be seamlessly integrated into standard autoencoders, reshaping their latent space to provide a stable foundation for effective dynamics modeling. By focusing on representation quality, GRWM offers a simple yet powerful pipeline for improving world model fidelity.
Authors: Daniel Agyei Asante, Md Mokarram Chowdhury, Yang Li
Abstract: Large language models (LLMs) have driven major advances across domains, yet their massive size hinders deployment in resource-constrained settings. Low-rank factorization addresses this challenge by compressing models to effectively reduce their computation and memory consumption while maintaining accuracy. While these compressed models boast benign performance and system-level advantages, their trustworthiness implications remain poorly understood. In this paper, we present the first comprehensive study of how low-rank factorization affects LLM trustworthiness across privacy, adversarial robustness, ethics, and fairness, complemented by an explainability-driven analysis of the internal mechanisms behind these trust-related changes. We evaluate multiple LLMs of different sizes and architectures compressed with various low-rank factorization algorithms, revealing key insights: (1)low-rank factorization preserves training data privacy but weakens the protection of personally identifiable information during conversations; (2)adversarial robustness is generally enhanced under compression; (3)ethics degrades in zero-shot prompting but partially recovers in few-shot prompting; (4)fairness declines under compression. Beyond compression, we investigate how model scale and fine-tuning affect trustworthiness. Additionally, to move beyond black-box analysis, we employ a gradient-based attribution to identify which layers of LLMs contribute most to adversarial robustness.
Authors: Fanlong Zeng, Wensheng Gan
Abstract: Covariate distribution shift occurs when certain structural features present in the test set are absent from the training set. It is a common type of out-of-distribution (OOD) problem, frequently encountered in real-world graph data with complex structures. Existing research has revealed that most out-of-the-box graph neural networks (GNNs) fail to account for covariate shifts. Furthermore, we observe that existing methods aimed at addressing covariate shifts often fail to fully leverage the rich information contained within the latent space. Motivated by the potential of the latent space, we introduce a new method called MPAIACL for More Powerful Adversarial Invariant Augmentation using Contrastive Learning. MPAIACL leverages contrastive learning to unlock the full potential of vector representations by harnessing their intrinsic information. Through extensive experiments, MPAIACL demonstrates its robust generalization and effectiveness, as it performs well compared with other baselines across various public OOD datasets. The code is publicly available at https://github.com/flzeng1/MPAIACL.
Authors: Xiao Zhan, Guangzhi Sun, Jose Such, Phil Woodland
Abstract: Audio Large language models (LLMs) are increasingly deployed in the real world, where they inevitably capture speech from unintended nearby bystanders, raising privacy risks that existing benchmarks and defences did not consider. We introduce SH-Bench, the first benchmark designed to evaluate selective hearing: a model's ability to attend to an intended main speaker while refusing to process or reveal information about incidental bystander speech. SH-Bench contains 3,968 multi-speaker audio mixtures, including both real-world and synthetic scenarios, paired with 77k multiple-choice questions that probe models under general and selective operating modes. In addition, we propose Selective Efficacy (SE), a novel metric capturing both multi-speaker comprehension and bystander-privacy protection. Our evaluation of state-of-the-art open-source and proprietary LLMs reveals substantial bystander privacy leakage, with strong audio understanding failing to translate into selective protection of bystander privacy. To mitigate this gap, we also present Bystander Privacy Fine-Tuning (BPFT), a novel training pipeline that teaches models to refuse bystander-related queries without degrading main-speaker comprehension. We show that BPFT yields substantial gains, achieving an absolute 47% higher bystander accuracy under selective mode and an absolute 16% higher SE compared to Gemini 2.5 Pro, which is the best audio LLM without BPFT. Together, SH-Bench and BPFT provide the first systematic framework for measuring and improving bystander privacy in audio LLMs.
Authors: Guoqiang Zou, Wanyu Wang, Hao Zheng, Longxiang Yin, Yinhe Han
Abstract: Existing memory management techniques severely hinder efficient Large Language Model serving on accelerators constrained by poor random-access bandwidth.While static pre-allocation preserves memory contiguity,it incurs significant overhead due to worst-case provisioning.Conversely,fine-grained paging mitigates this overhead but relies on HBM's high random-access tolerance, making it unsuitable for LPDDR systems where non-sequential access rapidly degrades bandwidth. Furthermore, prior works typically assume static distributions and HBM characteristics, thereby failing to resolve the critical fragmentation and bandwidth constraints inherent to LPDDR hardware. We present ODMA, an on-demand memory allocation strategy tailored for random-access-constrained accelerators, such as the Cambricon MLU series.ODMA advances generation-length prediction by addressing two critical limitations in production workloads: (i) distribution drift that invalidates static bucket boundaries, and (ii) performance fragility under heavy-tailed request patterns. ODMA integrates a lightweight length predictor with adaptive bucket partitioning and a fallback safety pool. Bucket boundaries are dynamically recalibrated via online histograms to maximize utilization, while the safety pool ensures robustness against prediction errors. On Alpaca and Google-NQ benchmarks, ODMA improves S3's prediction accuracy from 98.60% to 99.55% and 82.68% to 93.36%, respectively. Deployment with DeepSeek-R1-Distill-Qwen-7B on Cambricon MLU370-X4 accelerators demonstrates that ODMA increases KV-cache utilization by up to 19.25% (absolute) and throughput (TPS) by 23-27% over static baselines, validating the efficacy of predictor-driven contiguous allocation for LPDDR-class devices.
Authors: Shuzheng Si, Qingyi Wang, Haozhe Zhao, Yuzhuo Bai, Guanqiao Chen, Kangyang Luo, Gang Chen, Fanchao Qi, Minjia Zhang, Baobao Chang, Maosong Sun
Abstract: Recognizing whether outputs from large language models (LLMs) contain faithfulness hallucination is crucial for real-world applications, e.g., retrieval-augmented generation and summarization. In this paper, we introduce FaithLens, a cost-efficient and effective faithfulness hallucination detection model that can jointly provide binary predictions and corresponding explanations to improve trustworthiness. To achieve this, we first synthesize training data with explanations via advanced LLMs and apply a well-defined data filtering strategy to ensure label correctness, explanation quality, and data diversity. Subsequently, we fine-tune the model on these well-curated training data as a cold start and further optimize it with rule-based reinforcement learning, using rewards for both prediction correctness and explanation quality. Results on 12 diverse tasks show that the 8B-parameter FaithLens outperforms advanced models such as GPT-5.2 and o3. Also, FaithLens can produce high-quality explanations, delivering a distinctive balance of trustworthiness, efficiency, and effectiveness.
Authors: Qiushi Han, David Simchi-Levi, Renfei Tan, Zishuo Zhao
Abstract: We study a sequential mechanism design problem in which a principal seeks to elicit truthful reports from multiple rational agents while starting with no prior knowledge of agents' beliefs. We introduce Distributionally Robust Adaptive Mechanism (DRAM), a general framework combining insights from both mechanism design and online learning to jointly address truthfulness and cost-optimality. Throughout the sequential game, the mechanism estimates agents' beliefs and iteratively updates a distributionally robust linear program with shrinking ambiguity sets to reduce payments while preserving truthfulness. Our mechanism guarantees truthful reporting with high probability while achieving $\tilde{O}(\sqrt{T})$ cumulative regret, and we establish a matching lower bound showing that no feasible adaptive mechanism can asymptotically do better. The framework generalizes to plug-in estimators, supporting structured priors and delayed feedback. To our knowledge, this is the first adaptive mechanism under general settings that maintains truthfulness and achieves optimal regret when incentive constraints are unknown and must be learned.
Authors: Rachmad Vidya Wicaksana Putra, Pasindu Wickramasinghe, Muhammad Shafique
Abstract: Large Language Models (LLMs) have been emerging as prominent AI models for solving many natural language tasks due to their high performance (e.g., accuracy) and capabilities in generating high-quality responses to the given inputs. However, their large computational cost, huge memory footprints, and high processing power/energy make it challenging for their embedded deployments. Amid several tinyLLMs, recent works have proposed spike-driven language models (SLMs) for significantly reducing the processing power/energy of LLMs. However, their memory footprints still remain too large for low-cost and resource-constrained embedded devices. Manual quantization approach may effectively compress SLM memory footprints, but it requires a huge design time and compute power to find the quantization setting for each network, hence making this approach not-scalable for handling different networks, performance requirements, and memory budgets. To bridge this gap, we propose QSLM, a novel framework that performs automated quantization for compressing pre-trained SLMs, while meeting the performance and memory constraints. To achieve this, QSLM first identifies the hierarchy of the given network architecture and the sensitivity of network layers under quantization, then employs a tiered quantization strategy (e.g., global-, block-, and module-level quantization) while leveraging a multi-objective performance-and-memory trade-off function to select the final quantization setting. Experimental results indicate that our QSLM reduces memory footprint by up to 86.5%, reduces power consumption by up to 20%, maintains high performance across different tasks (i.e., by up to 84.4% accuracy of sentiment classification on the SST-2 dataset and perplexity score of 23.2 for text generation on the WikiText-2 dataset) close to the original non-quantized model while meeting the performance and memory constraints.
Authors: Janvijay Singh, Dilek Hakkani-T\"ur
Abstract: Large language models solve complex tasks by generating long reasoning chains, achieving higher accuracy at the cost of increased computational cost and reduced ability to isolate functionally relevant reasoning. Prior work on compact reasoning shortens such chains through probabilistic sampling, heuristics, or supervision from frontier models, but offers limited insight into whether models internally encode token-level functional importance for answer generation. We address this gap diagnostically and propose greedy pruning, a likelihood-preserving deletion procedure that iteratively removes reasoning tokens whose removal minimally degrades model likelihood under a specified objective, yielding length-controlled reasoning chains. We evaluate pruned reasoning in a distillation framework and show that students trained on pruned chains outperform a frontier-model-supervised compression baseline at matched reasoning lengths. Finally, our analysis reveals systematic pruning patterns and shows that attention scores can predict greedy pruning ranks, further suggesting that models encode a nontrivial functional importance structure over reasoning tokens.
Authors: Yuhan Wu, Huan Zhang, Wei Cheng, Chen Shen, Jingyue Yang, Wei Hu
Abstract: Code translation across multiple programming languages is essential yet challenging due to two vital obstacles: scarcity of parallel data paired with executable test oracles, and optimization imbalance when handling diverse language pairs. We propose BootTrans, a bootstrapping method that resolves both obstacles. Its key idea is to leverage the functional invariance and cross-lingual portability of test suites, adapting abundant pivot-language unit tests to serve as universal verification oracles for multilingual reinforcement learning (RL) training. Our method introduces a dual-pool architecture with seed and exploration pools to progressively expand training data via execution-guided experience collection. Furthermore, we design a language-aware weighting mechanism that dynamically prioritizes harder translation directions based on relative performance across sibling languages, mitigating optimization imbalance. Extensive experiments on the HumanEval-X and TransCoder-Test benchmarks demonstrate substantial improvements over baseline LLMs across all translation directions, with ablation studies validating the effectiveness of both bootstrapping and weighting components.
Authors: Yunrui Gu, Zhenzhe Gao, Cong Kong, Jiawei Du, Zhaoxia Yin
Abstract: Medical hyperspectral imaging (MHSI) has shown strong potential for disease diagnosis by capturing spectral-spatial information of tissues. While deep learning has substantially improved MHSI classification accuracy, its robustness remains limited due to the well-known trade-off between accuracy and robustness in Deep Neural Networks (DNNs). This issue is particularly critical in MHSI, where reliable prediction depends on local tissue relationships and multiscale spectral-spatial structures. A practical way to improve robustness is to identify the most unstable adversarial examples and incorporate them into adversarial training. However, existing attack methods do not sufficiently exploit these MHSI-specific properties, leading to suboptimal attack effectiveness and limited value for robustness enhancement. To address this gap, we propose a structured adversarial attack framework for MHSI that progressively models its local spectral-spatial dependencies and multiscale hierarchical representations. The proposed method generates anatomically consistent perturbations by modeling neighborhood dependencies and hierarchical spectral-spatial features. Experiments on the brain and choledoch datasets show that our method more effectively degrades lesion-related classification performance in critical tumor regions than existing baselines while maintaining low perturbation magnitude. These results reveal a clinically relevant robustness weakness in current MHSI models and provide stronger adversarial samples for developing targeted defense strategies.
Authors: Yichen Jiang, Jiakang Yuan, Chongjun Tu, Peng Ye, Tao Chen
Abstract: Effectively processing long contexts remains a fundamental yet unsolved challenge for large language models (LLMs). Existing single-LLM-based methods primarily reduce the context window or optimize the attention mechanism, but they often encounter additional computational costs or constrained expanded context length. While multi-agent-based frameworks can mitigate these limitations, they remain susceptible to the accumulation of errors and the propagation of hallucinations. In this work, we draw inspiration from the Long Short-Term Memory (LSTM) architecture to design a Multi-Agent System called LSTM-MAS, emulating LSTM's hierarchical information flow and gated memory mechanisms for long-context understanding. Specifically, LSTM-MAS organizes agents in a chained architecture, where each node comprises a worker agent for segment-level comprehension, a filter agent for redundancy reduction, a judge agent for continuous error detection, and a manager agent for globally regulates information propagation and retention, analogous to LSTM and its input gate, forget gate, constant error carousel unit, and output gate. These novel designs enable controlled information transfer and selective long-term dependency modeling across textual segments, which can effectively avoid error accumulation and hallucination propagation. We conducted an extensive evaluation of our method. Compared with the previous best multi-agent approach, CoA, our model achieves improvements of 97.97%, 65.75%, 122.19%, 39.61% and 10.80% on Narrative QA, Qasper, HotpotQA, 2WikiMQA and MuSiQue, respectively.
Authors: Hyunjong Ok, Jaeho Lee
Abstract: Large language models exhibit surprising sensitivity to the structure of the prompt, but the mechanisms underlying this sensitivity remain poorly understood. In this work, we conduct an in-depth investigation on a striking case: in multiple-choice question answering, placing context before the questions and options (CQO) outperforms the reverse order (QOC) by over 14%p, consistently over a wide range of models and datasets. Through systematic architectural analysis, we identify causal attention as the core mechanism: in QOC prompts, the causal mask prevents option tokens from attending to context, creating an information bottleneck where context becomes invisible to options.
Authors: Yuxing Chen, Guoqing Luo, Zijun Wu, Lili Mou
Abstract: Large Language Models (LLMs) exhibit social biases, which can lead to harmful stereotypes and unfair outcomes. We propose \textbf{Multi-Persona Thinking (MPT)}, a simple inference-time framework that reduces social bias by encouraging reasoning from multiple perspectives. MPT guides the model to consider contrasting social identities, such as male and female, together with a neutral viewpoint. These viewpoints then interact through an iterative reasoning process to identify and correct biased judgments. This design transforms the potential weakness of persona assignment into a mechanism to mitigate bias. We evaluate MPT on two widely used bias benchmarks with both open-source and closed-source models. Our results show that MPT achieves a lower bias than the existing prompting-based methods while maintaining the core reasoning ability.
Authors: Akila Sampath, Vandana Janeja, Jianwu Wang
Abstract: Quantifying the causal relationship between sea ice thickness and sea surface height (SSH) is essential for understanding the mechanisms driving polar climate change and global sea-level rise. Conventional deep learning models often struggle with treatment effect estimation in climate settings due to time-varying confounding and the lack of physical constraints. To address these challenges, we propose the Knowledge-Guided Causal Model Variational Autoencoder (KGCM-VAE) to quantify the effect of SSH on sea ice thickness. The framework leverages established physical relationships between SSH and surface velocity to generate physically grounded, time-varying continuous treatments, where each treatment value can change at every time step within a sequence. The model also incorporates Maximum Mean Discrepancy (MMD) to balance treated and control distributions in the latent space, mitigating observed confounding bias. Using synthetic data, we evaluated the model's ability to predict sea ice thickness responses under hypothetical SSH forcing scenarios, demonstrating that KGCM-VAE achieves superior PEHE compared to state-of-the-art baselines. Ablation studies further confirm that MMD consistently enhances treatment effect estimation over the base model. Additionally, we conducted a real-world case study to examine the sensitivity of physical parameters to specific treatments and to compare these findings with an existing modeling study.
Authors: Zhaoyan Gong, Zhiqiang Liu, Songze Li, Xiaoke Guo, Yuanxiang Liu, Xinle Deng, Zhizhen Liu, Lei Liang, Huajun Chen, Wen Zhang
Abstract: Temporal Knowledge Graph Question Answering (TKGQA) is inherently challenging, as it requires sophisticated reasoning over dynamic facts with multi-hop dependencies and complex temporal constraints. Existing methods rely on fixed workflows and expensive closed-source APIs, limiting flexibility and scalability. We propose Temp-R1, the first autonomous end-to-end agent for TKGQA trained through reinforcement learning. To address cognitive overload in single-action reasoning, we expand the action space with specialized internal actions alongside external action. To prevent shortcut learning on simple questions, we introduce reverse curriculum learning that trains on difficult questions first, forcing the development of sophisticated reasoning before transferring to easier cases. Our 8B-parameter Temp-R1 achieves state-of-the-art performance on MultiTQ and TimelineKGQA, improving 19.8% over strong baselines on complex questions. Our work establishes a new paradigm for autonomous temporal reasoning agents. The code is available at https://github.com/zjukg/Temp-R1.
Authors: Zichao Wei
Abstract: Why do neural networks fail to generalize addition from 16-digit to 32-digit numbers, while a child who learns the rule can apply it to arbitrarily long sequences? We argue that this failure is not an engineering problem but a violation of physical postulates. Drawing inspiration from physics, we identify three constraints that any generalizing system must satisfy: (1) Locality -- information propagates at finite speed; (2) Symmetry -- the laws of computation are invariant across space and time; (3) Stability -- the system converges to discrete attractors that resist noise accumulation. From these postulates, we derive -- rather than design -- the Spatiotemporal Evolution with Attractor Dynamics (SEAD) architecture: a neural cellular automaton where local convolutional rules are iterated until convergence. Experiments on three tasks validate our theory: (1) Parity -- demonstrating perfect length generalization via light-cone propagation; (2) Addition -- achieving scale-invariant inference from L=16 to L=1 million with 100% accuracy, exhibiting input-adaptive computation; (3) Rule 110 -- learning a Turing-complete cellular automaton without trajectory divergence. Our results suggest that the gap between statistical learning and logical reasoning can be bridged -- not by scaling parameters, but by respecting the physics of computation.
Authors: Ding Xia, Xinyue Gui, Mark Colley, Fan Gao, Zhongyi Zhou, Dongyuan Li, Renhe Jiang, Takeo Igarashi
Abstract: Automated vehicles lack natural communication channels with other road users, making external Human-Machine Interfaces (eHMIs) essential for conveying intent and maintaining trust in shared environments. However, most eHMI studies rely on developer-crafted message-action pairs, which are difficult to adapt to diverse and dynamic traffic contexts. A promising alternative is to use Large Language Models (LLMs) as action designers that generate context-conditioned eHMI actions, yet such designers lack perceptual verification and typically depend on fixed prompts or costly human-annotated feedback for improvement. We present See2Refine, a human-free, closed-loop framework that uses vision-language model (VLM) perceptual evaluation as automated visual feedback to improve an LLM-based eHMI action designer. Given a driving context and a candidate eHMI action, the VLM evaluates the perceived appropriateness of the action, and this feedback is used to iteratively revise the designer's outputs, enabling systematic refinement without human supervision. We evaluate our framework across three eHMI modalities (lightbar, eyes, and arm) and multiple LLM model sizes. Across settings, our framework consistently outperforms prompt-only LLM designers and manually specified baselines in both VLM-based metrics and human-subject evaluations. Results further indicate that the improvements generalize across modalities and that VLM evaluations are well aligned with human preferences, supporting the robustness and effectiveness of See2Refine for scalable action design.
Authors: Xinyi Wen, Lena Hegemann, Xiaofu Jin, Shuai Ma, Antti Oulasvirta
Abstract: Aligning text-to-image generation with user intent remains challenging, as users frequently provide ambiguous inputs and struggle with model idiosyncrasies. We propose Adaptive Prompt Elicitation (APE), a technique that adaptively poses visual queries to help users refine prompts without extensive writing. Our technical contribution is a formulation of interactive intent inference under an information-theoretic framework. APE represents latent user intent as interpretable feature requirements using language model priors, adaptively generates visual queries, and compiles elicited requirements into effective prompts. Evaluation on IDEA-Bench and DesignBench shows that APE achieves stronger alignment with improved efficiency. A user study with 128 participants on user-defined tasks demonstrates 19.8% higher perceived alignment without increased workload. Our work contributes a principled approach to prompting that offers an effective and efficient complement to the prevailing prompt-based interaction paradigm with text-to-image models.
Authors: Seungbin Park, Peilin Wang, Ryan Pennell, Emily S. Weg, Himanshu Nagar, Timothy McClure, Mert R. Sabuncu, Daniel Margolis, Heejong Kim
Abstract: Purpose: To investigate whether an AI-based method can detect subtle inter-fraction changes in MR-Linac images acquired during radiotherapy and explore the broader potential of MRLinac imaging. Methods: This retrospective study included longitudinal 0.35T MR-Linac images from 761 patients. To identify temporal changes, we employed a deep learning model using temporal ordering via pairwise comparison, previously shown effective for longitudinal imaging studies. The model was trained using first-to-last fraction pairs (F1-FL) and all pairs (All-pairs). Performance was assessed using quantitative metrics (accuracy and AUC) and compared against a radiologist's performance. Qualitative evaluation was performed using saliency maps, which identify anatomical regions associated with temporal imaging changes. Results: The F1-FL model demonstrated high performance (AUC=0.99, accuracy=0.95) and outperformed the radiologist in temporal ordering task. The All-pairs model also showed high performance (AUC=0.97, accuracy=0.91). Regions contributing to predictions included the prostate, bladder, and pubic symphysis. The performance was correlated to fractional intervals and was reduced for non-radiation-exposed timepoints (Sim and F1), suggesting that observed changes may reflect both temporal variation and radiation exposure. Conclusion: MR-Linac imaging appears capable of capturing subtle changes during prostate radiotherapy that can be detected by AI models, even over approximately two-day intervals. The model's high performance, together with quantitative and qualitative analyses, supports a potential role for MR-Linac in clinical applications beyond image guidance.
Authors: Freja H{\o}gholm Petersen, Jesper Sandvig Mariegaard, Rocco Palmitessa, Allan P. Engsig-Karup
Abstract: While proper orthogonal decomposition (POD)-based surrogates are widely explored for hydrodynamic applications, the use of Koopman autoencoders for real-world coastal-ocean modelling remains relatively limited. This paper introduces a flexible Koopman autoencoder formulation that incorporates meteorological forcings and boundary conditions, and systematically compares its performance against POD-based surrogates. The Koopman autoencoder employs a learned linear temporal operator in latent space, enabling eigenvalue regularization to promote temporal stability. This strategy is evaluated alongside temporal unrolling techniques for achieving stable and accurate long-term predictions. The models are assessed on three test cases spanning distinct dynamical regimes, with prediction horizons up to one year at 30-minute temporal resolution. Across all cases, the reduced order surrogates with temporal unrolling achieve high accuracy with relative root-mean-squared-errors of 0.0068-0.14 and $R^2$-values of 0.61-0.995, where prediction errors are largest for current velocities, and smallest for water surface elevations. In two of the three cases, the Koopman Autoencoder have higher accuracy than the POD-based surrogates. Comparing to in-situ observations, the surrogate yields -0.64% to 12% increase in water surface elevation prediction error when compared to prediction errors of the physics-based model. These error levels, corresponding to a few centimeters, are acceptable for many practical applications, while inference speed-ups of 300-1400x enables workflows such as ensemble forecasting and long climate simulations for coastal-ocean modelling.
Authors: Peter Holderrieth, Douglas Chen, Luca Eyring, Ishin Shah, Giri Anantharaman, Yutong He, Zeynep Akata, Tommi Jaakkola, Nicholas Matthew Boffi, Max Simchowitz
Abstract: Flow and diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and brittle, a challenge commonly called reward alignment. We argue that efficient reward alignment should be a property of the generative model itself, not an afterthought, and redesign the model for adaptability. We propose "Diamond Maps", stochastic flow map models that enable efficient and accurate alignment to arbitrary rewards at inference time. Diamond Maps amortize many simulation steps into a single-step sampler, like flow maps, while preserving the stochasticity required for optimal reward alignment. This design makes search, Sequential Monte Carlo, and guidance scalable by enabling efficient and consistent estimation of the value function. Our experiments show that Diamond Maps can be learned efficiently via distillation from GLASS Flows, achieve stronger reward alignment performance, and scale better than existing methods. Our results point toward a practical route to generative models that can be rapidly adapted to arbitrary preferences and constraints at inference time.
Authors: Zhenxing Ming, Yaoqi Huang, Julie Stephany Berrio, Mao Shan, Stewart Worrall
Abstract: The prediction of 3D semantic occupancy enables autonomous vehicles (AVs) to perceive the fine-grained geometric and semantic scene structure for safe navigation and decision-making. Existing methods mainly rely on either voxel-based representations, which incur redundant computation over empty regions, or on object-centric Gaussian primitives, which are limited in modeling complex, non-convex, and asymmetric structures. In this paper, we present TFusionOcc, a T-primitive-based object-centric multi-sensor fusion framework for 3D semantic occupancy prediction. Specifically, we introduce a family of Students t-distribution-based T-primitives, including the plain T-primitive, T-Superquadric, and deformable T-Superquadric with inverse warping, where the deformable T-Superquadric serves as the key geometry-enhancing primitive. We further develop a unified probabilistic formulation based on the Students t-distribution and the T-mixture model (TMM) to jointly model occupancy and semantics, and design a tightly coupled multi-stage fusion architecture to effectively integrate camera and LiDAR cues. Extensive experiments on nuScenes show state-of-the-art performance, while additional evaluations on nuScenes-C demonstrate strong robustness under most corruption scenarios. The code will be available at: https://github.com/DanielMing123/TFusionOcc
Authors: Fumitaka Iwaki, Tatsuji Takahashi
Abstract: In the field of natural language processing, some studies have attempted sentiment analysis on text by handling emotions as explanatory or response variables. One of the most popular emotion models used in this context is the wheel of emotion proposed by Plutchik. This model schematizes human emotions in a circular structure, and represents them in two or three dimensions. However, the validity of Plutchik's wheel of emotion has not been sufficiently examined. This study investigated the validity of the wheel by creating and analyzing a semantic networks of emotion words. Through our experiments, we collected data of similarity and association of ordered pairs of emotion words, and constructed networks using these data. We then analyzed the structure of the networks through community detection, and compared it with that of the wheel of emotion. The results showed that each network's structure was, for the most part, similar to that of the wheel of emotion, but locally different.
Authors: Sieun Hyeon, Jusang Oh, Sunghwan Steve Cho, Jaeyoung Do
Abstract: Recent advances in Large Language Models (LLMs) have significantly improved table understanding tasks such as Table Question Answering (TableQA), yet challenges remain in ensuring reliability, scalability, and efficiency, especially in resource-constrained or privacy-sensitive environments. In this paper, we introduce MATA, a multi-agent TableQA framework that leverages multiple complementary reasoning paths and a set of tools built with small language models. MATA generates candidate answers through diverse reasoning styles for a given table and question, then refines or selects the optimal answer with the help of these tools. Furthermore, it incorporates an algorithm designed to minimize expensive LLM agent calls, enhancing overall efficiency. MATA maintains strong performance with small, open-source models and adapts easily across various LLM types. Extensive experiments on two benchmarks of varying difficulty with ten different LLMs demonstrate that MATA achieves state-of-the-art accuracy and highly efficient reasoning while avoiding excessive LLM inference. Our results highlight that careful orchestration of multiple reasoning pathways yields scalable and reliable TableQA. The code is available at https://github.com/AIDASLab/MATA.
Authors: Rong Fu, Xiaowen Ma, Kun Liu, Wangyu Wu, Ziyu Kong, Jia Yee Tan, Tailong Luo, Xianda Li, Zeli Su, Youjin Wang, Yongtai Liu, Simon Fong
Abstract: Deploying expressive learning models directly on programmable dataplanes promises line-rate, low-latency traffic analysis but remains hindered by strict hardware constraints and the need for predictable, auditable behavior. Chimera introduces a principled framework that maps attention-oriented neural computations and symbolic constraints onto dataplane primitives, enabling trustworthy inference within the match-action pipeline. Chimera combines a kernelized, linearized attention approximation with a two-layer key-selection hierarchy and a cascade fusion mechanism that enforces hard symbolic guarantees while preserving neural expressivity. The design includes a hardware-aware mapping protocol and a two-timescale update scheme that together permit stable, line-rate operation under realistic dataplane budgets. The paper presents the Chimera architecture, a hardware mapping strategy, and empirical evidence showing that neuro-symbolic attention primitives can achieve high-fidelity inference within the resource envelope of commodity programmable switches.
Authors: Spandan Garg, Yufan Huang
Abstract: While significant progress has been made in automating various aspects of software development through coding agents, there is still significant room for improvement in their bug fixing capabilities. Debugging and investigation of runtime behavior remains largely a manual, developer-driven process. Popular coding agents typically rely on either static analysis of the code or iterative test-fix cycles, which is akin to trial and error debugging. We posit that there is a wealth of rich runtime information that developers routinely access while debugging code, which agents are currently deprived of due to design limitations. Despite how prevalent debuggers are in modern IDEs and command-line tools, they have surprisingly not made their way into coding agents. In this work, we introduce Debug2Fix, a novel framework that incorporates interactive debugging as a core component of a software engineering agent via a subagent architecture. We incorporate debuggers for Java and Python into our agent framework and evaluate against GitBug-Java and SWE-Bench-Live and achieve >20% improvement in performance compared to the baseline for certain models. Furthermore, using our framework, we're able to make weaker models like GPT-5 and Claude Haiku 4.5 match or exceed the performances of stronger models like Claude Sonnet 4.5, showing that better tool design is often just as important as switching to a more expensive model. Finally, we conduct systematic ablations demonstrating the importance of both the subagent architecture and debugger integration.
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: Niu Lian, Yuting Wang, Hanshu Yao, Jinpeng Wang, Bin Chen, Yaowei Wang, Min Zhang, Shu-Tao Xia
Abstract: While multimodal large language models have demonstrated impressive short-term reasoning, they struggle with long-horizon video understanding due to limited context windows and static memory mechanisms that fail to mirror human cognitive efficiency. Existing paradigms typically fall into two extremes: vision-centric methods that incur high latency and redundancy through dense visual accumulation, or text-centric approaches that suffer from detail loss and hallucination via aggressive captioning. To bridge this gap, we propose MM-Mem, a pyramidal multimodal memory architecture grounded in Fuzzy-Trace Theory. MM-Mem structures memory hierarchically into a Sensory Buffer, Episodic Stream, and Symbolic Schema, enabling the progressive distillation of fine-grained perceptual traces (verbatim) into high-level semantic schemas (gist). Furthermore, to govern the dynamic construction of memory, we derive a Semantic Information Bottleneck objective and introduce SIB-GRPO to optimize the trade-off between memory compression and task-relevant information retention. In inference, we design an entropy-driven top-down memory retrieval strategy. Extensive experiments across 4 benchmarks confirm that MM-Mem achieves state-of-the-art performance on both offline and streaming tasks, demonstrating robust generalization and validating the effectiveness of cognition-inspired memory organization. Code and associated configurations are publicly available at https://github.com/EliSpectre/MM-Mem.
Authors: Ansh Nagda, Prabhakar Raghavan, Abhradeep Thakurta
Abstract: We present improved lower bounds for nine classical Ramsey numbers: $\mathbf{R}(3, 13)$ is increased from $60$ to $61$, $\mathbf{R}(3, 18)$ from $99$ to $100$, $\mathbf{R}(4, 13)$ from $138$ to $139$, $\mathbf{R}(4, 14)$ from $147$ to $148$, $\mathbf{R}(4, 15)$ from $158$ to $159$, $\mathbf{R}(4, 16)$ from $170$ to $174$, $\mathbf{R}(4, 18)$ from $205$ to $209$, $\mathbf{R}(4, 19)$ from $213$ to $219$, and $\mathbf{R}(4, 20)$ from $234$ to $237$. These results were achieved using AlphaEvolve, an LLM-based code mutation agent. Beyond these new results, we successfully recovered lower bounds for all Ramsey numbers known to be exact, and matched the best known lower bounds across many other cases. These include bounds for which previous work does not detail the algorithms used. Virtually all known Ramsey lower bounds are derived computationally, with bespoke search algorithms each delivering a handful of results. AlphaEvolve is a single meta-algorithm yielding search algorithms for all of our results.
Authors: Denys Katkalo, Andrii Rohovyi, Toby Walsh
Abstract: In recent years, RAPTOR based algorithms have been considered the state-of-the-art for path-finding with unlimited transfers without preprocessing. However, this status largely stems from the evolution of routing research, where Dijkstra-based solutions were superseded by timetable-based algorithms without a systematic comparison. In this work, we revisit classical Dijkstra-based approaches for public transit routing with unlimited transfers and demonstrate that Time-Dependent Dijkstra (TD-Dijkstra) outperforms MR. However, efficient TD-Dijkstra implementations rely on filtering dominated connections during preprocessing, which assumes passengers can always switch to a faster connection. We show that this filtering is unsound when stops have buffer times, as it cannot distinguish between seated passengers who may continue without waiting and transferring passengers who must respect the buffer. To address this limitation, we introduce Transfer Aware Dijkstra (TAD), a modification that scans entire trip sequences rather than individual edges, correctly handling buffer times while maintaining performance advantages over MR. Our experiments on London and Switzerland networks show that we can achieve a greater than two time speed-up over MR while producing optimal results on both networks with and without buffer times.
Authors: Andrii Rohovyi, Abdallah Abuaisha, Toby Walsh
Abstract: Routing algorithms for public transport, particularly the widely used RAPTOR and its variants, often face performance bottlenecks during the transfer relaxation phase, especially on dense transfer graphs, when supporting unlimited transfers. This inefficiency arises from iterating over many potential inter-stop connections (walks, bikes, e-scooters, etc.). To maintain acceptable performance, practitioners often limit transfer distances or exclude certain transfer options, which can reduce path optimality and restrict the multimodal options presented to travellers. This paper introduces Early Pruning, a low-overhead technique that accelerates routing algorithms without compromising optimality. By pre-sorting transfer connections by duration and applying a pruning rule within the transfer loop, the method discards longer transfers at a stop once they cannot yield an earlier arrival than the current best solution. Early Pruning can be integrated with minimal changes to existing codebases and requires only a one-time preprocessing step. The technique preserves Pareto-optimality in extended-criteria settings whenever the additional optimization criteria are monotonically non-decreasing in transfer duration. Across multiple state-of-the-art RAPTOR-based solutions, including RAPTOR, ULTRA-RAPTOR, McRAPTOR, BM-RAPTOR, ULTRA-McRAPTOR, and UBM-RAPTOR and tested on the Switzerland and London transit networks, we achieved query time reductions of up to 57\%. This approach provides a generalizable improvement to the efficiency of transit pathfinding algorithms.
Authors: Xi Jiang, Yue Guo, Jian Li, Yong Liu, Bin-Bin Gao, Hanqiu Deng, Jun Liu, Heng Zhao, Chengjie Wang, Feng Zheng
Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive success in natural visual understanding, yet they consistently underperform in industrial anomaly detection (IAD). This is because MLLMs trained mostly on general web data differ significantly from industrial images. Moreover, they encode each image independently and can only compare images in the language space, making them insensitive to subtle visual differences that are key to IAD. To tackle these issues, we present AD-Copilot, an interactive MLLM specialized for IAD via visual in-context comparison. We first design a novel data curation pipeline to mine inspection knowledge from sparsely labeled industrial images and generate precise samples for captioning, VQA, and defect localization, yielding a large-scale multimodal dataset Chat-AD rich in semantic signals for IAD. On this foundation, AD-Copilot incorporates a novel Comparison Encoder that employs cross-attention between paired image features to enhance multi-image fine-grained perception, and is trained with a multi-stage strategy that incorporates domain knowledge and gradually enhances IAD skills. In addition, we introduce MMAD-BBox, an extended benchmark for anomaly localization with bounding-box-based evaluation. The experiments show that AD-Copilot achieves 82.3% accuracy on the MMAD benchmark, outperforming all other models without any data leakage. In the MMAD-BBox test, it achieves a maximum improvement of $3.35\times$ over the baseline. AD-Copilot also exhibits excellent generalization of its performance gains across other specialized and general-purpose benchmarks. Remarkably, AD-Copilot surpasses human expert-level performance on several IAD tasks, demonstrating its potential as a reliable assistant for real-world industrial inspection. All datasets and models will be released for the broader benefit of the community.
Authors: Zifan Xu, Ran Gong, Maria Vittoria Minniti, Ahmet Salih Gundogdu, Eric Rosen, Kausik Sivakumar, Riedana Yan, Zixing Wang, Di Deng, Peter Stone, Xiaohan Zhang, Karl Schmeckpeper
Abstract: Learning generalizable and robust behavior cloning policies requires large volumes of high-quality robotics data. While human demonstrations (e.g., through teleoperation) serve as the standard source for expert behaviors, acquiring such data at scale in the real world is prohibitively expensive. This paper introduces ExpertGen, a framework that automates expert policy learning in simulation to enable scalable sim-to-real transfer. ExpertGen first initializes a behavior prior using a diffusion policy trained on imperfect demonstrations, which may be synthesized by large language models or provided by humans. Reinforcement learning is then used to steer this prior toward high task success by optimizing the diffusion model's initial noise while keep original policy frozen. By keeping the pretrained diffusion policy frozen, ExpertGen regularizes exploration to remain within safe, human-like behavior manifolds, while also enabling effective learning with only sparse rewards. Empirical evaluations on challenging manipulation benchmarks demonstrate that ExpertGen reliably produces high-quality expert policies with no reward engineering. On industrial assembly tasks, ExpertGen achieves a 90.5% overall success rate, while on long-horizon manipulation tasks it attains 85% overall success, outperforming all baseline methods. The resulting policies exhibit dexterous control and remain robust across diverse initial configurations and failure states. To validate sim-to-real transfer, the learned state-based expert policies are further distilled into visuomotor policies via DAgger and successfully deployed on real robotic hardware.
Authors: Tianyi Huang, Ying Kai Deng
Abstract: In factual question answering, many errors are not failures of access but failures of commitment: the system retrieves relevant evidence, yet still settles on the wrong answer. We present CounterRefine, a lightweight inference-time repair layer for retrieval-grounded question answering. CounterRefine first produces a short answer from retrieved evidence, then gathers additional support and conflicting evidence with follow-up queries conditioned on that draft answer, and finally applies a restricted refinement step that outputs either KEEP or REVISE, with proposed revisions accepted only if they pass deterministic validation. In effect, CounterRefine turns retrieval into a mechanism for testing a provisional answer rather than merely collecting more context. On the full SimpleQA benchmark, CounterRefine improves a matched GPT-5 Baseline-RAG by 5.8 points and reaches a 73.1 percent correct rate, while exceeding the reported one-shot GPT-5.4 score by roughly 40 points. These findings suggest a simple but important direction for knowledgeable foundation models: beyond accessing evidence, they should also be able to use that evidence to reconsider and, when necessary, repair their own answers.
Authors: Subina Khanal, Seshu Tirupathi, Merim Dzaferagic, Marco Ruffini, Torben Bach Pedersen
Abstract: Time series foundation models (TSFMs) require diverse, real-world datasets to adapt across varying domains and temporal frequencies. However, current large-scale datasets predominantly focus on low-frequency time series with sampling intervals, i.e., time resolution, in the range of seconds to years, hindering their ability to capture the nuances of high-frequency time series data. To address this limitation, we introduce a novel dataset that captures millisecond-resolution wireless and traffic conditions from an operational 5G wireless deployment, expanding the scope of TSFMs to incorporate high-frequency data for pre-training. Further, the dataset introduces a new domain, wireless networks, thus complementing existing more general domains like energy and finance. The dataset also provides use cases for short-term forecasting, with prediction horizons spanning from 1 millisecond (1 step) to 96 milliseconds (96 steps). By benchmarking traditional machine learning models and TSFMs on predictive tasks using this dataset, we demonstrate that most TSFM model configurations perform poorly on this new data distribution in both zero-shot and fine-tuned settings. Our work underscores the importance of incorporating high-frequency datasets during pre-training and forecasting to enhance architectures, fine-tuning strategies, generalization, and robustness of TSFMs in real-world applications.
Authors: Andrea Marinoni, Erik Cambria, Weisi Lin, Mauro Dalla Mura, Jocelyn Chanussot, Edoardo Ragusa, 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: Runze Sun, Yu Zheng, Zexuan Xiong, Zhongjin Qu, Lei Chen, Jie Zhou, Jiwen Lu
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: Zhiyuan Cheng, Longying Lai, Yue Liu
Abstract: Retrieval-Augmented Generation (RAG) systems for financial document question answering typically follow a chunk-based paradigm: documents are split into fragments, embedded into vector space, and retrieved via similarity search. While effective in general settings, this approach suffers from cross-document chunk confusion in structurally homogeneous corpora such as regulatory filings. Semantic File Routing (SFR), which uses LLM structured output to route queries to whole documents, reduces catastrophic failures but sacrifices the precision of targeted chunk retrieval. We identify this robustness-precision trade-off through controlled evaluation on the FinDER benchmark (1,500 queries across five groups): SFR achieves higher average scores (6.45 vs. 6.02) and fewer failures (10.3% vs. 22.5%), while chunk-based retrieval (CBR) yields more perfect answers (13.8% vs. 8.5%). To resolve this trade-off, we propose Hybrid Document-Routed Retrieval (HDRR), a two-stage architecture that uses SFR as a document filter followed by chunk-based retrieval scoped to the identified document(s). HDRR eliminates cross-document confusion while preserving targeted chunk precision. Experimental results demonstrate that HDRR achieves the best performance on every metric: an average score of 7.54 (25.2% above CBR, 16.9% above SFR), a failure rate of only 6.4%, a correctness rate of 67.7% (+18.7 pp over CBR), and a perfect-answer rate of 20.1% (+6.3 pp over CBR, +11.6 pp over SFR). HDRR resolves the trade-off by simultaneously achieving the lowest failure rate and the highest precision across all five experimental groups.
Authors: Arezoo Borji, Gernot Kronreif, Bernhard Angermayr, Francisco Mario Calisto, Ali Abbasian Ardakani, Wolfgang Birkfellner, Inna Servetnyk, Yinyin Yuan, Sepideh Hatamikia
Abstract: Breast cancer is a highly heterogeneous disease with diverse molecular profiles. The PAM50 gene signature is widely recognized as a standard for classifying breast cancer into intrinsic subtypes, enabling more personalized treatment strategies. In this study, we introduce a novel optimization-driven deep learning framework that aims to reduce reliance on costly molecular assays by directly predicting PAM50 subtypes from H&E-stained whole-slide images (WSIs). Our method jointly optimizes patch informativeness, spatial diversity, uncertainty, and patch count by combining the non-dominated sorting genetic algorithm II (NSGA-II) with Monte Carlo dropout-based uncertainty estimation. The proposed method can identify a small but highly informative patch subset for classification. We used a ResNet18 backbone for feature extraction and a custom CNN head for classification. For evaluation, we used the internal TCGA-BRCA dataset as the training cohort and the external CPTAC-BRCA dataset as the test cohort. On the internal dataset, an F1-score of 0.8812 and an AUC of 0.9841 using 627 WSIs from the TCGA-BRCA cohort were achieved. The performance of the proposed approach on the external validation dataset showed an F1-score of 0.7952 and an AUC of 0.9512. These findings indicate that the proposed optimization-guided, uncertainty-aware patch selection can achieve high performance and improve the computational efficiency of histopathology-based PAM50 classification compared to existing methods, suggesting a scalable imaging-based replacement that has the potential to support clinical decision-making.
Authors: Shuai Wu, Xue Li, Yanna Feng, Yufang Li, Zhijun Wang
Abstract: Large Language Models (LLMs), particularly those employing Mixture-of-Experts (MoE) architectures, have achieved remarkable capabilities across diverse natural language processing tasks. However, these models frequently suffer from hallucinations -- generating plausible but factually incorrect content -- and exhibit systematic biases that are amplified by uneven expert activation during inference. In this paper, we propose the Council Mode, a novel multi-agent consensus framework that addresses these limitations by dispatching queries to multiple heterogeneous frontier LLMs in parallel and synthesizing their outputs through a dedicated consensus model. The Council pipeline operates in three phases: (1) an intelligent triage classifier that routes queries based on complexity, (2) parallel expert generation across architecturally diverse models, and (3) a structured consensus synthesis that explicitly identifies agreement, disagreement, and unique findings before producing the final response. We implement and evaluate this architecture within an open-source AI workspace. Our comprehensive evaluation across multiple benchmarks demonstrates that the Council Mode achieves a 35.9% relative reduction in hallucination rates on the HaluEval benchmark and a 7.8-point improvement on TruthfulQA compared to the best-performing individual model, while maintaining significantly lower bias variance across domains. We provide the mathematical formulation of the consensus mechanism, detail the system architecture, and present extensive empirical results with ablation studies.
Authors: Yiming Mao, Zixi Yu, Weixin Mao, Yinhao Li, Qirui Hu, Zihan Lan, Minzhao Zhu, Hua Chen
Abstract: Long-horizon robotic manipulation remains challenging for reinforcement learning (RL) because sparse rewards provide limited guidance for credit assignment. Practical policy improvement thus relies on richer intermediate supervision, such as dense progress rewards, which are costly to obtain and ill-suited to non-monotonic behaviors such as backtracking and recovery. To address this, we propose Advantage Reward Modeling (ARM), a framework that shifts from hard-to-quantify absolute progress to estimating relative advantage. We introduce a cost-effective tri-state labeling strategy -- Progressive, Regressive, and Stagnant -- that reduces human cognitive overhead while ensuring high cross-annotator consistency. By training on these intuitive signals, ARM enables automated progress annotation for both complete demonstrations and fragmented DAgger-style data. Integrating ARM into an offline RL pipeline allows for adaptive action-reward reweighting, effectively filtering suboptimal samples. Our approach achieves a 99.4% success rate on a challenging long-horizon towel-folding task, demonstrating improved stability and data efficiency over current VLA baselines with near-zero human intervention during policy training.
Authors: Haocheng Tang, Xingyu Dang, Junmei Wang
Abstract: Optical Chemical Structure Recognition (OCSR) is critical for converting 2D molecular diagrams from printed literature into machine-readable formats. While Vision-Language Models have shown promise in end-to-end OCR tasks, their direct application to OCSR remains challenging, and direct full-parameter supervised fine-tuning often fails. In this work, we adapt DeepSeek-OCR-2 for molecular optical recognition by formulating the task as image-conditioned SMILES generation. To overcome training instabilities, we propose a two-stage progressive supervised fine-tuning strategy: starting with parameter-efficient LoRA and transitioning to selective full-parameter fine-tuning with split learning rates. We train our model on a large-scale corpus combining synthetic renderings from PubChem and realistic patent images from USPTO-MOL to improve coverage and robustness. Our fine-tuned model, MolSeek-OCR, demonstrates competitive capabilities, achieving exact matching accuracies comparable to the best-performing image-to-sequence model. However, it remains inferior to state-of-the-art image-to-graph modelS. Furthermore, we explore reinforcement-style post-training and data-curation-based refinement, finding that they fail to improve the strict sequence-level fidelity required for exact SMILES matching.
Authors: Hengshuai Yao, Xing Chen, Ahmed Murtadha, Guan Wang
Abstract: Adapting LLMs to new domains causes forgetting because standard methods (e.g., full fine-tuning, LoRA) inject new directions into the weight space. We show that forgetting is governed by one algebraic property: whether the update preserves the column span of the pretrained weight matrix (Proposition 1). We propose GAIN, the simplest multiplicative alternative (W_new = S * W), which satisfies this by construction and can be absorbed into existing weights for zero inference cost. Across five models (774M to 70B) adapted sequentially over eight domains, GAIN improves earlier-domain perplexity by 7-13%, while LoRA degrades it by 18-36%. GAIN matches replay-augmented LoRA without storing prior data and dominates EWC on the forgetting-adaptation Pareto front. While LoRA can only reduce forgetting by sacrificing in-domain adaptation, GAIN achieves both with no domain boundaries and no regularization. The principle generalises: (IA)^3, an independent multiplicative method, also improves earlier domains.
Authors: Zhixiong Zhao, Zukang Xu, Zhixuan Chen, Dawei Yang
Abstract: Mixture-of-Experts (MoE) based large language models (LLMs) offer strong performance but suffer from high memory and computation costs. Weight binarization provides extreme efficiency, yet existing binary methods designed for dense LLMs struggle with MoE-specific issues, including cross-expert redundancy, task-agnostic importance estimation, and quantization-induced routing shifts. To this end, we propose MoBiE, the first binarization framework tailored for MoE-based LLMs. MoBiE is built on three core innovations: 1. using joint SVD decomposition to reduce cross-expert redundancy; 2. integrating global loss gradients into local Hessian metrics to enhance weight importance estimation; 3. introducing an error constraint guided by the input null space to mitigate routing distortion. Notably, MoBiE achieves these optimizations while incurring no additional storage overhead, striking a balance between efficiency and model performance. Extensive experiments demonstrate that MoBiE consistently outperforms state-of-the-art binary methods across multiple MoE-based LLMs and benchmarks. For example, on Qwen3-30B-A3B, MoBiE reduces perplexity by 52.2$\%$, improves average zero-shot performance by 43.4$\%$, achieves over 2 $\times$ inference speedup, and further shortens quantization time. The code is available at https://github.com/Kishon-zzx/MoBiE.
Authors: Tanzim Ahad, Ismail Hossain, Md Jahangir Alam, Sai Puppala, Yoonpyo Lee, Syed Bahauddin Alam, Sajedul Talukder
Abstract: We introduce Semantic Intent Fragmentation (SIF), an attack class against LLM orchestration systems where a single, legitimately phrased request causes an orchestrator to decompose a task into subtasks that are individually benign but jointly violate security policy. Current safety mechanisms operate at the subtask level, so each step clears existing classifiers -- the violation only emerges at the composed plan. SIF exploits OWASP LLM06:2025 through four mechanisms: bulk scope escalation, silent data exfiltration, embedded trigger deployment, and quasi-identifier aggregation, requiring no injected content, no system modification, and no attacker interaction after the initial request. We construct a three-stage red-teaming pipeline grounded in OWASP, MITRE ATLAS, and NIST frameworks to generate realistic enterprise scenarios. Across 14 scenarios spanning financial reporting, information security, and HR analytics, a GPT-20B orchestrator produces policy-violating plans in 71% of cases (10/14) while every subtask appears benign. Three independent signals validate this: deterministic taint analysis, chain-of-thought evaluation, and a cross-model compliance judge with 0% false positives. Stronger orchestrators increase SIF success rates. Plan-level information-flow tracking combined with compliance evaluation detects all attacks before execution, showing the compositional safety gap is closable.
Authors: Mehdi Fatan Serj, C. Alejandro Parraga, Xavier Otazu
Abstract: We introduce an unsupervised visual representation learning system based entirely on local plasticity rules, without labels, backpropagation, or global error signals. The model is a VisNet-inspired hierarchical architecture combining opponent color inputs, multi-frequency Gabor and wavelet feature streams, competitive normalization with lateral inhibition, saliency modulation, associative memory, and a feedback loop. All representation learning occurs through continuous local plasticity applied to unlabeled image streams over 300 epochs. Performance is evaluated using a fixed linear probe trained only at readout time. The system achieves 80.1 percent accuracy on CIFAR-10 and 47.6 percent on CIFAR-100, improving over a Hebbian-only baseline. Ablation studies show that anti-Hebbian decorrelation, free-energy inspired plasticity, and associative memory are the main contributors, with strong synergistic effects. Even without learning, the fixed architecture alone reaches 61.4 percent on CIFAR-10, indicating that plasticity, not only inductive bias, drives most of the performance. Control analyses show that independently trained probes match co-trained ones within 0.3 percentage points, and a nearest-class-mean classifier achieves 78.3 percent without gradient-based training, confirming the intrinsic structure of the learned features. Overall, the system narrows but does not eliminate the performance gap to backpropagation-trained CNNs (5.7 percentage points on CIFAR-10, 7.5 percentage points on CIFAR-100), demonstrating that structured local plasticity alone can learn strong visual representations from raw unlabeled data.
Authors: Augustus Haoyang Li
Abstract: We present THEIA, a 2.75M modular neural architecture that learns the complete Kleene three-valued logic (K3) truth table from task data without external symbolic inference or hand-encoded K3 gate primitives. Across 5 seeds, THEIA achieves all 39 K3 rules at >99% per-rule accuracy. K3 learnability is not the central finding: Transformer baselines also reach >99% on all 39 rules, and flat MLPs match THEIA on Phase-1 accuracy within 0.04pp. The central findings are two properties of the learned system. (1) Uncertainty-verdict asymmetric propagation. The network preserves Has-Unknown at every upstream boundary (80.0/91.1/90.8/99.7% across Arith/Order/Set/Logic vs. ~52% majority) while final-verdict decodability stays at or below a 73.4% U-vs-non-U oracle reference under linear and nonlinear MLP probes. Activation patching on non-absorbent T->U configurations flips 4,898/4,898 OR pairs (4,719/4,719 AND) across 5 seeds, ruling out residual shortcuts. (2) Reliability spectrum under discretized end-to-end training, on task structures decomposable along the engine boundaries. A mod-3 sequential composition task generalizes from 5- to 500-step eval at 99.96+-0.04% (5 seeds). Under identical Gumbel-softmax training, flat MLPs collapse to chance by 50 steps; a 2x2 ResMLP depth x expansion grid reaches >=99% on only 3/20 (config, seed) trials; a pre-LN Transformer reaches 99.24+-0.34%. The 500-step figure is dominated by straight-through discretization preventing 0.999^500 compounding; the architectural separator is sustaining Phase-1 accuracy under Phase-3 end-to-end Gumbel training, where flat MLPs fail. Auxiliary: under matched optimizer settings THEIA reaches 12/12 Kleene coverage 6.5x faster than a parameter-comparable 8L Transformer; the ratio narrows to ~3.6x under Transformer-standard tuning. We did not perform a THEIA-optimal sweep; ratios are specific-config, not asymptotic.
Authors: Olga Chetverina
Abstract: Standard subword tokenization methods fragment numbers inconsistently, causing large language models (LLMs) to lose positional and decimal structure - a primary driver of errors in arithmetic and scientific reasoning. We introduce Triadic Suffix Tokenization (TST), a deterministic scheme that partitions digits into three-digit triads and annotates each triad with an explicit magnitude marker. Critically, the scheme defines a fixed, one-to-one mapping between suffixes and orders of magnitude for the integer part (thousands, millions, billions, etc.) and a parallel system of replicated markers for fractional depth (tenths, thousandths, millionths, etc.). Unlike approaches that rely on positional inference, this method provides a consistent gradient signal, which should ensure stable convergence. Two implementation variants are proposed: (1) a vocabulary-based approach that adds at most 10,000 fixed tokens to an existing vocabulary, covering 33 orders of magnitude ($10^{-15}$ to $10^{18}$); and (2) a suffix-marker approach that uses a small set of special tokens to denote magnitude dynamically. Both variants preserve exact digits while making order-of-magnitude relationships transparent at the token level. While we focus on 3-digit groups (Triadic), the framework is inherently scalable to any group size for precise vocabulary optimization. Furthermore, it allows for linear vocabulary expansion to accommodate arbitrary precision and range. TST is architecture-agnostic and can be integrated as a drop-in preprocessing step. Experimental validation is deferred to future work.
Authors: Ryan Faulkner, Anushka Deshpande, David Guzman Piedrahita, Joel Z. Leibo, Zhijing Jin
Abstract: Governing common-pool resources requires agents to develop enduring strategies through cooperation and self-governance to avoid collective failure. While foundation models have shown potential for cooperation in these settings, existing multi-agent research provides little insight into whether structured leadership and election mechanisms can improve collective decision making. The lack of such a critical organizational feature ubiquitous in human society presents a significant shortcoming of the current methods. In this work we aim to directly address whether leadership and elections can support improved social welfare and cooperation through multi-agent simulation with LLMs. We present our open-source framework that simulates leadership through elected personas and candidate-driven agendas and carry out an empirical study of LLMs under controlled governance conditions. Our experiments demonstrate that having elected leadership improves social welfare scores by 55.4% and survival time by 128.6% across a range of high performing LLMs. Through the construction of an agent social graph we compute centrality metrics to assess the social influence of leader personas and also analyze rhetorical and cooperative tendencies revealed through a sentiment analysis on leader utterances. This work lays the foundation for further study of election mechanisms in multi-agent systems toward navigating complex social dilemmas.
Authors: Taehun Kim, Hyeryun Park, Hyeonhoon Lee, Yushin Lee, Kyungsang Kim, Hyung-Chul Lee
Abstract: Clinical data-driven research requires clinical expertise, programming skills, access to patient data, and extensive documentation, creating barriers and slowing the pace for clinicians and external researchers. To address this, we developed the Clinical Agentic Research Intelligence System (CARIS) that automates the workflow: research planning, literature search, cohort construction, Institutional Review Board (IRB) documentation, Vibe Machine Learning (ML), and report generation, with human-in-the-loop refinement. CARIS integrates Large Language Models (LLMs) with modular tools through the Model Context Protocol (MCP), enabling natural language-driven research without coding while allowing users to access only outputs. We evaluated CARIS on three heterogeneous datasets with distinct clinical tasks, where it completed planning and IRB documentation within four iterations, supported Vibe ML, and generated reports, achieving 96% completeness in LLM-based evaluation and 82% in human evaluation. CARIS demonstrates potential to reduce documentation burden and technical barriers, accelerating data-driven clinical research across public and private data environments.
Authors: Jiaqi Zhu, Shaofeng Cai, Jie Chen, Fang Deng, Beng Chin Ooi, Wenqiao Zhang
Abstract: Online anomaly detection (OAD) plays a pivotal role in real-time analytics and decision-making for evolving data streams. However, existing methods often rely on costly retraining and rigid decision boundaries, limiting their ability to adapt both effectively and efficiently to concept drift in dynamic environments. To address these challenges, we propose DyMETER, a dynamic concept adaptation framework for OAD that unifies on-the-fly parameter shifting and dynamic thresholding within a single online paradigm. DyMETER first learns a static detector on historical data to capture recurring central concepts, and then transitions to a dynamic mode to adapt to new concepts as drift occurs. Specifically, DyMETER employs a novel dynamic concept adaptation mechanism that leverages a hypernetwork to generate instance-aware parameter shifts for the static detector, thereby enabling efficient and effective adaptation without retraining or fine-tuning. To achieve robust and interpretable adaptation, DyMETER introduces a lightweight evolution controller to estimate instance-level concept uncertainty for adaptive updates. Further, DyMETER employs a dynamic threshold optimization module to adaptively recalibrates the decision boundary by maintaining a candidate window of uncertain samples, which ensures continuous alignment with evolving concepts. Extensive experiments demonstrate that DyMETER significantly outperforms existing OAD approaches across a wide spectrum of application scenarios.
Authors: Alexandra Dragomir, Ioana Pintilie, Antonio Barbalau, Marius Dragoi, Florin Brad, Cristian Daniel Paduraru, Alexandru Tifrea, Elena Burceanu, Radu Tudor Ionescu
Abstract: Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by sequentially learning a low-rank update matrix for each task. To mitigate catastrophic forgetting, state-of-the-art approaches impose constraints on new adapters with respect to the previous ones, by targeting either subspace or coordinate-wise interference. In this paper, we propose JumpLoRA, a novel framework to adaptively induce sparsity in the Low-Rank Adaptation (LoRA) blocks through the use of JumpReLU gating. The method achieves dynamic parameter isolation, which helps prevent task interference. We demonstrate that our method is highly modular and compatible with LoRA-based CL approaches. Specifically, it significantly boosts the performance of IncLoRA and outperforms the leading state-of-the-art CL method, ELLA.
Authors: Matteo Casserini, Alessandro Facchini, Andrea Ferrario
Abstract: As autonomous coding agents become deeply embedded in software development workflows, their high operational velocity introduces a critical oversight challenge: the accumulating divergence between agentic actions and architectural intent. We term this process agentic entropy: a systemic drift that traditional code diff-based and HCXAI methods fail to capture, as they address local outputs rather than global agentic behaviour. To close this gap, we propose a process-oriented explainability framework that exposes how agentic decisions unfold across time, tool calls, and architectural boundaries. Built around three pillars (conformity seeding, reasoning monitoring, and a causal graph interface) our approach provides intent-level telemetry that complements, rather than replaces, existing review practices. We demonstrate its relevance across two user profiles: lay users engaged in vibe coding, who gain structural visibility otherwise masked by functional success; and professional developers, who gain richer contextual grounding for code review without increased overhead. By treating cognitive drift as a first-class concern alongside code quality, our framework supports the minimum level of human comprehension required for agentic oversight to remain substantive.
Authors: Jeanne McClure, Gregg Gerdau
Abstract: Global corporate AI investment reached $252.3 billion in 2024, yet only 6% of firms report significant earnings impact. This article argues that AI project failure is fundamentally an organizational learning problem rather than a technology deficit. Drawing on a systematic synthesis of 19 large-scale industry and academic sources, including surveys of nearly 10,000 organizational leaders, we identify two categories of failure: organizational (culture, leadership alignment, governance, and human-AI learning deficits) and technical (semantic bottlenecks and output management challenges). We introduce the Siloed-Integrated-Orchestrated (SIO) progression model, which maps enterprise AI capability across five pillars -- Culture & Leadership, Human Capital & Operations, Data Architecture, Systems Infrastructure, and Governance & Regulatory Compliance -- and provides prescriptive guidance for advancing between stages. The implications challenge organizations to reframe AI investment as capability development rather than technology procurement.
Authors: Nirmalendu Prakash, Narmeen Fatimah Oozeer, Xin Su, Phillip Howard, Shaan Shah, Zoe Wanying He, Shuang Wu, Shivam Raval, Roy Ka-Wei Lee, Meenakshi Khosla, Amir Abdullah
Abstract: CLIP retrieval is typically framed as a pointwise similarity problem in a shared embedding space. While CLIP achieves strong global cross-modal alignment, many retrieval failures arise from local geometric inconsistencies: nearby items are incorrectly ordered, leading to systematic confusions (e.g., pentagon vs. hexagon) and produces diffuse, weakly controlled result sets. Prior work largely optimizes for point wise relevance or finetuning to mitigate these problems. We instead view retrieval as a problem of neighborhood alignment. Our work introduces (1) neighborhood-level re-ranking via Hungarian matching, which rewards structural consistency; (2) query-conditioned local steering, where directions derived from contrastive neighborhoods around the query reshape retrieval. We show that these techniques improve retrieval performance on attribute-binding and compositional retrieval tasks. Together, these methods operate on local neighborhoods but serve different roles: re-ranking rewards alignment whereas local steering controls neighborhood structure. This shows that retrieval quality and controllability depend critically on local structure, which can be exploited at inference time without retraining.
Authors: Divya Shyamal, Marta Kne\v{z}evi\'c, Lan Tran, Chanakya Ekbote, Vijay Lingam, Paul Pu Liang
Abstract: Test-time scaling (TTS) improves large language models (LLMs) by allocating additional compute at inference time. In practice, TTS is often achieved through parallel scaling: generating multiple candidate responses and selecting the best via a Best-of-N (BoN) strategy. Its effectiveness therefore hinges on the scoring function. Learned scorers such as process reward models (PRMs) can be strong, but they are expensive to train and run. Lightweight confidence heuristics based on token log-probabilities are much cheaper, yet we find that they often perform substantially worse. To improve on lightweight confidence heuristics without incurring the full cost of stronger learned scorers, we introduce SCATR, a simple and efficient BoN ranking method that learns a lightweight scorer from a small calibration set using hidden representations from the base model. Across coding and mathematical reasoning benchmarks, SCATR improves over prior confidence-based baselines by up to 9%. Relative to LoRA fine-tuning on the same calibration data, it achieves comparable accuracy with up to 8000x fewer trainable parameters and much lower compute, reducing training and inference latency by up to 150x and 1000x, respectively. SCATR is also competitive with strong PRM baselines, and in several settings improves accuracy by up to 7.8% on math and 4.2% on coding while enabling up to 1000x faster inference. Overall, SCATR offers a strong accuracy-efficiency trade-off for scalable test-time selection.
Authors: Seungmin Lee, Jeonghwan Lee, Hyunkuk Lim, Sejoon Kim, Mingi Sung
Abstract: Recent text embedding models are often adapted to specialized domains via contrastive pre-finetuning (PFT) on a naive collection of scattered, heterogeneous tasks. However, this approach often introduces task-induced bias alongside domain knowledge, leading to uncontrolled representation shifts that distort the pretrained embedding geometry and cause substantial performance degradation. To address this issue, we propose REZE, a representation regularization framework that explicitly controls representation shift during embedding pre-finetuning. REZE operates on the relations of anchor-positive pairs and decomposes them in an eigenspace. It then measures task-wise dispersion along each eigencomponent to identify task-variant directions and applies adaptive soft-shrinkage to suppress task-induced noise while preserving task-invariant semantic structure, without inference-time overhead. Experiments across multiple embedding backbones and specialized benchmarks show that REZE outperforms standard pre-finetuning and isotropy-oriented post-hoc regularization in most settings, remaining stable where existing PFT variants collapse. Embedding space analyses further confirm that REZE induces controlled shifts aligned with the original embedding manifold, underscoring representation shift control as a key principle for robust embedding pre-finetuning under heterogeneous supervision.
Authors: Tiankai Yang, Yi Nian, Xinyuan Li, Ruiyao Xu, Kaize Ding, Yue Zhao
Abstract: Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful ones. Most preference-based safety alignment methods collapse safety into a single scalar that is applied uniformly to every preference pair. The result is a model that looks safe on average but stays relatively unsafe on a minority of harm categories. We cast safety alignment as a per-category constrained optimization problem and derive Cat-DPO, a direct-preference-optimization algorithm with a separate adaptive safety margin for each harm category. The margin tightens when the model still produces unsafe responses on a category and relaxes once the model catches up, so the training signal tracks each category's current difficulty rather than averaging under one global rate. Across two LLM backbones and six preference-learning baselines, Cat-DPO improves aggregate helpfulness and harmlessness and compresses per-category safety variance and the best-to-worst gap, offering a drop-in per-category refinement of direct preference safety alignment.
Authors: Vasileios Toulatzis, Sofia Theodoridou, Ioannis Fudos
Abstract: Ancient inscriptions frequently suffer missing or corrupted regions from fragmentation, erosion, or other damage, hindering reading, and analysis. We review prior image restoration methods and their applicability to inscription image recovery, then introduce MESA (Multi-Exemplar, Style-Aware) -an image-level restoration method that uses well-preserved exemplar inscriptions (from the same epigraphic monument, material, or similar letterforms) to guide reconstruction of damaged text. MESA encodes VGG19 convolutional features as Gram matrices to capture exemplar texture, style, and stroke structure; for each neural network layer it selects the exemplar minimizing Mean-Squared Displacement (MSD) to the damaged input. Layer-wise contribution weights are derived from Optical Character Recognition-estimated character widths in the exemplar set to bias filters toward scales matching letter geometry, and a training mask preserves intact regions so synthesis is restricted to damaged areas. We also summarize prior network architectures and exemplar and single-image synthesis, inpainting, and Generative Adversarial Network (GAN) approaches, highlighting limitations that MESA addresses. Comparative experiments demonstrate the advantages of MESA. Finally, we provide a practical roadmap for choosing restoration strategies given available exemplars and metadata.
Authors: Donghwan Lee
Abstract: Dynamic programming is one of the most fundamental methodologies for solving Markov decision problems. Among its many variants, Q-value iteration (Q-VI) is particularly important due to its conceptual simplicity and its classical contraction-based convergence guarantee. Despite the central role of this contraction property, it does not fully reveal the geometric structure of the Q-VI trajectory. In particular, when one is interested not only in the final limit $Q^*$ but also in when the induced greedy policy becomes effectively optimal, the standard contraction argument provides only a coarse characterization. To formalize this notion, we denote by $\mathcal X^*$ the set of $Q$-functions whose corresponding tie-broken greedy policies are optimal, referred to as the practically optimal solution set (POS). In this paper, we revisit discounted Q-VI through the lens of switching system theory and derive new geometric insights into its behavior. In particular, we show that although Q-VI does not reach $Q^*$ in finite time in general, it identifies the optimal action class in finite time. Furthermore, we prove that the distance from the iterate to a particular subset of $\mathcal X^*$ decays exponentially at a rate governed by the joint spectral radius (JSR) of a restricted switching family. This rate can be strictly faster than the standard $\gamma$ rate when the restricted JSR is strictly smaller than $\gamma$, while the convergence of the entire $Q$-function to $Q^*$ can still be dominated by the slower $\gamma$ mode, where $\gamma$ denotes the discount factor. These results reveal a two-stage geometric behavior of Q-VI: a fast convergence toward $\mathcal X_1$, followed by a slower convergence toward $Q^*$ in general.
Authors: Haokun Lin, Xinle Jia, Haobo Xu, Bingchen Yao, Xianglong Guo, Yichen Wu, Zhichao Lu, Ying Wei, Qingfu Zhang, Zhenan Sun
Abstract: The MXFP4 microscaling format, which partitions tensors into blocks of 32 elements sharing an E8M0 scaling factor, has emerged as a promising substrate for efficient LLM inference, backed by native hardware support on NVIDIA Blackwell Tensor Cores. However, activation outliers pose a unique challenge under this format: a single outlier inflates the shared block scale, compressing the effective dynamic range of the remaining elements and causing significant quantization error. Existing rotation-based remedies, including randomized Hadamard and learnable rotations, are data-agnostic and therefore unable to specifically target the channels where outliers concentrate. We propose DuQuant++, which adapts the outlier-aware fine-grained rotation of DuQuant to the MXFP4 format by aligning the rotation block size with the microscaling group size (B{=}32). Because each MXFP4 group possesses an independent scaling factor, the cross-block variance issue that necessitates dual rotations and a zigzag permutation in the original DuQuant becomes irrelevant, enabling DuQuant++ to replace the entire pipeline with a single outlier-aware rotation, which halves the online rotation cost while simultaneously smoothing the weight distribution. Extensive experiments on the LLaMA-3 family under MXFP4 W4A4 quantization show that DuQuant++ consistently achieves state-of-the-art performance. Our code is available at https://github.com/Hsu1023/DuQuant-v2.
Authors: Zichao Wei
Abstract: Can syntactic processing emerge spontaneously from purely local interaction? We present a concrete instance on a minimal system: an 18,658-parameter two-dimensional neural cellular automaton (NCA), supervised by nothing more than a 1-bit boundary signal, is trained on the membership problem of an arithmetic-expression grammar. After training, its internal $L \times L$ grid spontaneously self-organizes into an ordered, spatially extended representation that we name Proto-CKY. This representation satisfies three operational criteria for syntactic processing: expressive power beyond the regular languages, structural generalization beyond the training distribution, and an internal organization quantitatively aligned with grammatical structure (Pearson $r \approx 0.71$). It emerges independently on four context-free grammars and regenerates spontaneously after perturbation. Proto-CKY is functionally aligned with the CKY algorithm but formally distinct from it: it is a physical prototype, a concrete instantiation of a mathematical ideal on a physical substrate, and the systematic distance between the two carries information about the substrate itself.
Authors: Yuyan Zhou, Jiarui Yu, Hande Dong, Zhezheng Hao, Hong Wang, Jianqing Zhang, Qiang Lin
Abstract: Recently, latent reasoning has been introduced into large language models (LLMs) to leverage rich information within a continuous space. However, without stochastic sampling, these methods inevitably collapse to deterministic inference, failing to discover diverse reasoning paths. To bridge the gap, we inject controllable stochasticity into latent reasoning via Gumbel-Softmax, restoring LLMs' exploratory capacity and enhancing their compatibility with Reinforcement Learning (RL). Building on this, we propose \textbf{\underline{L}}atent R\textbf{\underline{e}}asoning \textbf{\underline{P}}olicy \textbf{\underline{O}}ptimization~(\textbf{LEPO}), a novel framework that applies RL directly to continuous latent representations. Specifically, in rollout stage, LEPO maintains stochasticity to enable diverse trajectory sampling, while in optimization stage, LEPO constructs a unified gradient estimation for both latent representations and discrete tokens. Extensive experiments show that LEPO significantly outperforms existing RL methods for discrete and latent reasoning.
Authors: Nuo Chen, Yicheng Tong, Yuzhe Yang, Yufei He, Xueyi Zhang, Qingyun Zou, Qian Wang, Bingsheng He
Abstract: Multi-agent systems (MAS) are increasingly used for open-ended idea generation, driven by the expectation that collective interaction will broaden the exploration diversity. However, when and why such collaboration truly expands the solution space remains unclear. We present a systematic empirical study of diversity in MAS-based ideation across three bottom-up levels: model intelligence, agent cognition, and system dynamics. At the model level, we identify a compute efficiency paradox, where stronger, highly aligned models yield diminishing marginal diversity despite higher per-sample quality. At the cognition level, authority-driven dynamics suppress semantic diversity compared to junior-dominated groups. At the system level, group-size scaling yields diminishing returns and dense communication topologies accelerate premature convergence. We characterize these outcomes as collective failures emerging from structural coupling, a process where interaction inadvertently contracts agent exploration and triggers diversity collapse. Our analysis shows that this collapse arises primarily from the interaction structure rather than inherent model insufficiency, highlighting the importance of preserving independence and disagreement when designing MAS for creative tasks. Our code is available at https://github.com/Xtra-Computing/MAS_Diversity.
Authors: Yunjia Xi, Menghui Zhu, Jianghao Lin, Bo Chen, Ruiming Tang, Yong Yu, Weinan Zhang
Abstract: Recently, large language models (LLMs) have advanced recommendation systems (RSs), and recent works have begun to explore how to integrate LLMs into industrial RSs. While most approaches deploy LLMs offline to generate and pre-cache augmented representations for RSs, high-dimensional representations from LLMs introduce substantial storage and computational costs. Thus, it is crucial to compress LLM representations effectively. However, we identify a counterintuitive phenomenon during representation compression: Mid-layer Representation Advantage (MRA), where representations from middle layers of LLMs outperform those from final layers in recommendation tasks. This degraded final layer renders existing compression methods, which typically compress on the final layer, suboptimal. We interpret this based on modularity theory that LLMs develop spontaneous internal functional modularity and force the final layer to specialize in the proxy training task. Thus, we propose \underline{M}odul\underline{a}r \underline{R}epresentation \underline{C}ompression (MARC) to explicitly control the modularity of LLMs. First, Modular Adjustment explicitly introduces compression and task adaptation modules, enabling the LLM to operate strictly as a representation-learning module. Next, to ground each module to its specific task, Modular Task Decoupling uses information constraints and different network structures to decouple tasks. Extensive experiments validate that MARC addresses MRA and produces efficient representations. Notably, MARC achieved a 2.82% eCPM lift in an online A/B test within a large-scale commercial search advertising scenario.
Authors: Sua Lee, Sanghee Park, Jinbae Im
Abstract: Multimodal Large Language Models (MLLMs) have been increasingly used as automatic evaluators-a paradigm known as MLLM-as-a-Judge. However, their reliability and vulnerabilities to biases remain underexplored. We find that many MLLM judges fail to reliably integrate key visual or textual cues, yielding unreliable evaluations when evidence is missing or mismatched, and exhibiting instability under semantically irrelevant perturbations. To address this, we systematically define Compositional Bias in MLLM-as-a-Judge systems and introduce MM-JudgeBias, a benchmark for evaluating it. MM-JudgeBias introduces controlled perturbations across Query, Image, and Response, and evaluates model behavior via two complementary metrics: Bias-Deviation (BD) for sensitivity and Bias-Conformity (BC) for stability. Our dataset of over 1,800 curated and refined multimodal samples, drawn from 29 source benchmarks, enables a fine-grained diagnosis of nine bias types across diverse tasks and domains. Experiments on 26 state-of-the-art MLLMs reveal systematic modality neglect and asymmetric evaluation tendencies, underscoring the need for more reliable judges.
Authors: Sungeun An, Swanand Ravindra Kadhe, Shailja Thakur, Chad DeLuca, Hima Patel
Abstract: Benchmarks are often used as a standard to understand LLM capabilities in different domains. However, aggregate benchmark scores provide limited insight into compositional skill gaps of LLMs and how to improve them. To make these weaknesses visible, we propose Scaffolded Task Design (STaD) framework. STaD generates controlled variations of benchmark tasks based on the concept of scaffolding, which introduces structured, incremental support in a step-by-step manner. Rather than inspecting failures individually, this approach enables systematic and scalable probing of model behavior by identifying the specific reasoning skill compositions they lack. Treating the LLM as a black box, our experiments on six models of varying sizes reveal multiple failure points in three reasoning benchmarks and highlight each model's unique and distinct skill gaps.
Authors: Yixuan Wang, Yue Huang, Hong Qian, Yunzhao Wei, Yifei Ding, Wenkai Wang, Zhi Liu, Zhongjing Huang, Aimin Zhou, Jiajun Guo
Abstract: Creativity has become a core competence in the era of LLMs and human-AI collaboration, underpinning innovation in real-world problem solving. Crucially, the systematic improvement of creativity necessitates scientifically valid assessment instruments. Psychometric research recognizes context-based assessment as an effective way to measure creative thinking. However, high-quality expert-designed contexts remain scarce. Existing LLM-based generators often struggle with insufficient assessment cues, weak narrative coherence, limited stylistic diversity, and poor support for creative thinking. To address these challenges, we propose AlphaContext, an evolutionary tree-based psychometric context generator for creativity assessment. First, the HyperTree Outline Planner formalizes expert-designed outlining as a rule-guided hypertree and performs top-down hierarchical planning. The MCTS-based Context Generator fills the outline via MCTS to balance global structure and local quality. Then, the Evolutionary Context Optimizer evolves contexts with MAP-Elites by repeatedly updating niche elites to jointly improve diversity and quality. Finally, the Assessment-Guided Evolution Refiner simulates virtual participants with diverse styles and recycles weak contexts for further evolution. Experiments show that AlphaContext yields an average improvement of 8% over competitive methods across 6 quality metrics.
Authors: Jun Chen, Umberto Biccari, Junmin Wang
Abstract: We propose a computational framework for replacing the repeated numerical solution of differential Riccati equations in finite-horizon Linear Quadratic Regulator (LQR) problems by a learned operator surrogate. Instead of solving a nonlinear matrix-valued differential equation for each new system instance, we construct offline an approximation of the associated solution operator mapping time-dependent system parameters to the Riccati trajectory. The resulting model enables fast online evaluation of approximate optimal feedbacks across a wide class of systems, thereby shifting the computational burden from repeated numerical integration to a one-time learning stage. From a theoretical perspective, we establish control-theoretic guarantees for this operator-based approximation. In particular, we derive bounds quantifying how operator approximation errors propagate to feedback performance, trajectory accuracy, and cost suboptimality, and we prove that exponential stability of the closed-loop system is preserved under sufficiently accurate operator approximation. These results provide a framework to assess the reliability of data-driven approximations in optimal control. On the computational side, we design tailored DeepONet architectures for matrix-valued, time-dependent problems and introduce a progressive learning strategy to address scalability with respect to the system dimension. Numerical experiments on both time-invariant and time-varying LQR problems demonstrate that the proposed approach achieves high accuracy and strong generalization across a wide range of system configurations, while delivering substantial computational speedups compared to classical solvers. The method offers an effective and scalable alternative for parametric and real-time optimal control applications.
Authors: Liubomyr Horbatko
Abstract: Modern sequence modeling is dominated by two families: Transformers, whose self-attention can access arbitrary elements of the visible sequence, and structured state-space models, which propagate information through an explicit recurrent state. These mechanisms face different limitations on long contexts: when attention is diffuse, the influence of individual tokens is diluted across the effective support, while recurrent state propagation can lose long-range sensitivity unless information is actively preserved. As a result, both mechanisms face challenges in preserving and selectively retrieving information over long contexts. We propose Sessa, a decoder that places attention inside a recurrent feedback path. This creates many attention-based paths through which past tokens can influence future states, rather than relying on a single attention read or a single recurrent chain. We prove that, under explicit assumptions and matched regimes, Sessa admits power-law memory tails $O(\ell^{-\beta})$ for $0 < \beta < 1$, with slower decay than in the corresponding Transformer and Mamba-style baselines. We further give an explicit construction that achieves this power-law rate. Under the same assumptions, Sessa is the only model class among those considered that realizes flexible selective retrieval, including profiles whose influence does not decay with distance. Consistent with this theoretical advantage, across matched experiments, Sessa achieves the strongest performance on long-context benchmarks while remaining competitive with Transformer and Mamba-style baselines on short-context language modeling.