Authors: Imran Khan
Abstract: Large Language Models (LLMs) are increasingly being deployed as the reasoning engines for agentic AI systems, yet they exhibit a critical flaw: a rigid adherence to explicit rules that leads to decisions misaligned with human common sense and intent. This "rule-rigidity" is a significant barrier to building trustworthy autonomous agents. While prior work has shown that supervised fine-tuning (SFT) with human explanations can mitigate this issue, SFT is computationally expensive and inaccessible to many practitioners. To address this gap, we introduce the Rule-Intent Distinction (RID) Framework, a novel, low-compute meta-prompting technique designed to elicit human-aligned exception handling in LLMs in a zero-shot manner. The RID framework provides the model with a structured cognitive schema for deconstructing tasks, classifying rules, weighing conflicting outcomes, and justifying its final decision. We evaluated the RID framework against baseline and Chain-of-Thought (CoT) prompting on a custom benchmark of 20 scenarios requiring nuanced judgment across diverse domains. Our human-verified results demonstrate that the RID framework significantly improves performance, achieving a 95% Human Alignment Score (HAS), compared to 80% for the baseline and 75% for CoT. Furthermore, it consistently produces higher-quality, intent-driven reasoning. This work presents a practical, accessible, and effective method for steering LLMs from literal instruction-following to liberal, goal-oriented reasoning, paving the way for more reliable and pragmatic AI agents.
Authors: Wei Fan, Wenlin Yao, Zheng Li, Feng Yao, Xin Liu, Liang Qiu, Qingyu Yin, Yangqiu Song, Bing Yin
Abstract: Large language models (LLMs) augmented with multi-step reasoning and action generation abilities have shown promise in leveraging external tools to tackle complex tasks that require long-horizon planning. However, existing approaches either rely on implicit planning in the reasoning stage or introduce explicit planners without systematically addressing how to optimize the planning stage. As evidence, we observe that under vanilla reinforcement learning (RL), planning tokens exhibit significantly higher entropy than other action tokens, revealing uncertain decision points that remain under-optimized. To address this, we propose DeepPlanner, an end-to-end RL framework that effectively enhances the planning capabilities of deep research agents. Our approach shapes token-level advantage with an entropy-based term to allocate larger updates to high entropy tokens, and selectively upweights sample-level advantages for planning-intensive rollouts. Extensive experiments across seven deep research benchmarks demonstrate that DeepPlanner improves planning quality and achieves state-of-the-art results under a substantially lower training budget.
Authors: Simon Sinong Zhan, Yao Liu, Philip Wang, Zinan Wang, Qineng Wang, Zhian Ruan, Xiangyu Shi, Xinyu Cao, Frank Yang, Kangrui Wang, Huajie Shao, Manling Li, Qi Zhu
Abstract: We present Sentinel, the first framework for formally evaluating the physical safety of Large Language Model(LLM-based) embodied agents across the semantic, plan, and trajectory levels. Unlike prior methods that rely on heuristic rules or subjective LLM judgments, Sentinel grounds practical safety requirements in formal temporal logic (TL) semantics that can precisely specify state invariants, temporal dependencies, and timing constraints. It then employs a multi-level verification pipeline where (i) at the semantic level, intuitive natural language safety requirements are formalized into TL formulas and the LLM agent's understanding of these requirements is probed for alignment with the TL formulas; (ii) at the plan level, high-level action plans and subgoals generated by the LLM agent are verified against the TL formulas to detect unsafe plans before execution; and (iii) at the trajectory level, multiple execution trajectories are merged into a computation tree and efficiently verified against physically-detailed TL specifications for a final safety check. We apply Sentinel in VirtualHome and ALFRED, and formally evaluate multiple LLM-based embodied agents against diverse safety requirements. Our experiments show that by grounding physical safety in temporal logic and applying verification methods across multiple levels, Sentinel provides a rigorous foundation for systematically evaluating LLM-based embodied agents in physical environments, exposing safety violations overlooked by previous methods and offering insights into their failure modes.
Authors: Boyou Chen, Gerui Xu, Zifei Wang, Huizhong Guo, Ananna Ahmed, Zhaonan Sun, Zhen Hu, Kaihan Zhang, Shan Bao
Abstract: Vehicle crashes involve complex interactions between road users, split-second decisions, and challenging environmental conditions. Among these, two-vehicle crashes are the most prevalent, accounting for approximately 70% of roadway crashes and posing a significant challenge to traffic safety. Identifying Driver Hazardous Action (DHA) is essential for understanding crash causation, yet the reliability of DHA data in large-scale databases is limited by inconsistent and labor-intensive manual coding practices. Here, we present an innovative framework that leverages a fine-tuned large language model to automatically infer DHAs from textual crash narratives, thereby improving the validity and interpretability of DHA classifications. Using five years of two-vehicle crash data from MTCF, we fine-tuned the Llama 3.2 1B model on detailed crash narratives and benchmarked its performance against conventional machine learning classifiers, including Random Forest, XGBoost, CatBoost, and a neural network. The fine-tuned LLM achieved an overall accuracy of 80%, surpassing all baseline models and demonstrating pronounced improvements in scenarios with imbalanced data. To increase interpretability, we developed a probabilistic reasoning approach, analyzing model output shifts across original test sets and three targeted counterfactual scenarios: variations in driver distraction and age. Our analysis revealed that introducing distraction for one driver substantially increased the likelihood of "General Unsafe Driving"; distraction for both drivers maximized the probability of "Both Drivers Took Hazardous Actions"; and assigning a teen driver markedly elevated the probability of "Speed and Stopping Violations." Our framework and analytical methods provide a robust and interpretable solution for large-scale automated DHA detection, offering new opportunities for traffic safety analysis and intervention.
Authors: Xinlei Wang, Mingtian Tan, Jing Qiu, Junhua Zhao, Jinjin Gu
Abstract: Traditional time series analysis has long relied on pattern recognition, trained on static and well-established benchmarks. However, in real-world settings -- where policies shift, human behavior adapts, and unexpected events unfold -- effective analysis must go beyond surface-level trends to uncover the actual forces driving them. The recent rise of Large Language Models (LLMs) presents new opportunities for rethinking time series analysis by integrating multimodal inputs. However, as the use of LLMs becomes popular, we must remain cautious, asking why we use LLMs and how to exploit them effectively. Most existing LLM-based methods still employ their numerical regression ability and ignore their deeper reasoning potential. This paper argues for rethinking time series with LLMs as a reasoning task that prioritizes causal structure and explainability. This shift brings time series analysis closer to human-aligned understanding, enabling transparent and context-aware insights in complex real-world environments.
Authors: Stephane Hatgis-Kessell, Logan Mondal Bhamidipaty, Emma Brunskill
Abstract: Human-designed reward functions for reinforcement learning (RL) agents are frequently misaligned with the humans' true, unobservable objectives, and thus act only as proxies. Optimizing for a misspecified proxy reward function often induces reward hacking, resulting in a policy misaligned with the human's true objectives. An alternative is to perform RL from human feedback, which involves learning a reward function from scratch by collecting human preferences over pairs of trajectories. However, building such datasets is costly. To address the limitations of both approaches, we propose Preference-Based Reward Repair (PBRR): an automated iterative framework that repairs a human-specified proxy reward function by learning an additive, transition-dependent correction term from preferences. A manually specified reward function can yield policies that are highly suboptimal under the ground-truth objective, yet corrections on only a few transitions may suffice to recover optimal performance. To identify and correct for those transitions, PBRR uses a targeted exploration strategy and a new preference-learning objective. We prove in tabular domains PBRR has a cumulative regret that matches, up to constants, that of prior preference-based RL methods. In addition, on a suite of reward-hacking benchmarks, PBRR consistently outperforms baselines that learn a reward function from scratch from preferences or modify the proxy reward function using other approaches, requiring substantially fewer preferences to learn high performing policies.
Authors: Qun Ma, Xiao Xue, Xuwen Zhang, Zihan Zhao, Yuwei Guo, Ming Zhang
Abstract: The advent of large language models (LLMs) has enabled agents to represent virtual humans in societal simulations, facilitating diverse interactions within complex social systems. However, existing LLM-based agents exhibit severe limitations in affective cognition: They fail to simulate the bounded rationality essential for bridging virtual and real-world services; They lack empirically validated integration mechanisms embedding emotions within agent decision architectures. This paper constructs an emotional cognition framework incorporating desire generation and objective management, designed to achieve emotion alignment between LLM-based agents and humans, modeling the complete decision-making process of LLM-based agents, encompassing state evolution, desire generation, objective optimization, decision generation, and action execution. This study implements the proposed framework within our proprietary multi-agent interaction environment. Experimental results demonstrate that agents governed by our framework not only exhibit behaviors congruent with their emotional states but also, in comparative assessments against other agent types, demonstrate superior ecological validity and generate decision outcomes that significantly more closely approximate human behavioral patterns.
Authors: Zehui Ling, Deshu Chen, Yichi Zhang, Yuchen Liu, Xigui Li, Xin Guo, Yuan Cheng
Abstract: Recent advances in Large Language Models (LLMs) demonstrate that chain-of-thought prompting and deep reasoning substantially enhance performance on complex tasks, and multi-agent systems can further improve accuracy by enabling model debates. However, applying deep reasoning to all problems is computationally expensive. To mitigate these costs, we propose a complementary agent system integrating small and large LLMs. The small LLM first generates an initial answer, which is then verified by the large LLM. If correct, the answer is adopted directly; otherwise, the large LLM performs in-depth reasoning. Experimental results show that, for simple problems, our approach reduces the computational cost of the large LLM by more than 50% with negligible accuracy loss, while consistently maintaining robust performance on complex tasks.
Authors: Joy Jia Yin Lim, Ye He, Jifan Yu, Xin Cong, Daniel Zhang-Li, Zhiyuan Liu, Huiqin Liu, Lei Hou, Juanzi Li, Bin Xu
Abstract: Personalized Learning Path Planning (PLPP) aims to design adaptive learning paths that align with individual goals. While large language models (LLMs) show potential in personalizing learning experiences, existing approaches often lack mechanisms for goal-aligned planning. We introduce Pxplore, a novel framework for PLPP that integrates a reinforcement-based training paradigm and an LLM-driven educational architecture. We design a structured learner state model and an automated reward function that transforms abstract objectives into computable signals. We train the policy combining supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO), and deploy it within a real-world learning platform. Extensive experiments validate Pxplore's effectiveness in producing coherent, personalized, and goal-driven learning paths. We release our code and dataset to facilitate future research.
Authors: Yufei He, Juncheng Liu, Yue Liu, Yibo Li, Tri Cao, Zhiyuan Hu, Xinxing Xu, Bryan Hooi
Abstract: A fundamental limitation of current AI agents is their inability to learn complex skills on the fly at test time, often behaving like "clever but clueless interns" in novel environments. This severely limits their practical utility. To systematically measure and drive progress on this challenge, we first introduce the Jericho Test-Time Learning (J-TTL) benchmark. J-TTL is a new evaluation setup where an agent must play the same game for several consecutive episodes, attempting to improve its performance from one episode to the next. On J-TTL, we find that existing adaptation methods like reflection, memory, or reinforcement learning struggle. To address the challenges posed by our benchmark, we present EvoTest, an evolutionary test-time learning framework that improves an agent without any fine-tuning or gradients-by evolving the entire agentic system after every episode. EvoTest has two roles: the Actor Agent, which plays the game, and the Evolver Agent, which analyzes the episode transcript to propose a revised configuration for the next run. This configuration rewrites the prompt, updates memory by logging effective state-action choices, tunes hyperparameters, and learns the tool-use routines. On our J-TTL benchmark, EvoTest consistently increases performance, outperforming not only reflection and memory-only baselines but also more complex online fine-tuning methods. Notably, our method is the only one capable of winning two games (Detective and Library), while all baselines fail to win any.
Authors: Jalal Khan, Manzoor Khan, Sherzod Turaev, Sumbal Malik, Hesham El-Sayed, Farman Ullah
Abstract: The driving environment perception has a vital role for autonomous driving and nowadays has been actively explored for its realization. The research community and relevant stakeholders necessitate the development of Deep Learning (DL) models and AI-enabled solutions to enhance autonomous vehicles (AVs) for smart mobility. There is a need to develop a model that accurately perceives multiple objects on the road and predicts the driver's perception to control the car's movements. This article proposes a novel utility-based analytical model that enables perception systems of AVs to understand the driving environment. The article consists of modules: acquiring a custom dataset having distinctive objects, i.e., motorcyclists, rickshaws, etc; a DL-based model (YOLOv8s) for object detection; and a module to measure the utility of perception service from the performance values of trained model instances. The perception model is validated based on the object detection task, and its process is benchmarked by state-of-the-art deep learning models' performance metrics from the nuScense dataset. The experimental results show three best-performing YOLOv8s instances based on mAP@0.5 values, i.e., SGD-based (0.832), Adam-based (0.810), and AdamW-based (0.822). However, the AdamW-based model (i.e., car: 0.921, motorcyclist: 0.899, truck: 0.793, etc.) still outperforms the SGD-based model (i.e., car: 0.915, motorcyclist: 0.892, truck: 0.781, etc.) because it has better class-level performance values, confirmed by the proposed perception model. We validate that the proposed function is capable of finding the right perception for AVs. The results above encourage using the proposed perception model to evaluate the utility of learning models and determine the appropriate perception for AVs.
Authors: Weiqi Guo, Guanjun Liu, Ziyuan Zhou
Abstract: Multi-Agent Deep Reinforcement Learning (MADRL) has shown potential for cooperative and competitive tasks such as autonomous driving and strategic gaming. However, models trained by MADRL are vulnerable to adversarial perturbations on states and actions. Therefore, it is essential to investigate the robustness of MADRL models from an attack perspective. Existing studies focus on either state-only attacks or action-only attacks, but do not consider how to effectively joint them. Simply combining state and action perturbations such as randomly perturbing states and actions does not exploit their potential synergistic effects. In this paper, we propose the State-Action Joint Attack (SAJA) framework that has a good synergistic effects. SAJA consists of two important phases: (1) In the state attack phase, a multi-step gradient ascent method utilizes both the actor network and the critic network to compute an adversarial state, and (2) in the action attack phase, based on the perturbed state, a second gradient ascent uses the critic network to craft the final adversarial action. Additionally, a heuristic regularizer measuring the distance between the perturbed actions and the original clean ones is added into the loss function to enhance the effectiveness of the critic's guidance. We evaluate SAJA in the Multi-Agent Particle Environment (MPE), demonstrating that (1) it outperforms and is more stealthy than state-only or action-only attacks, and (2) existing state or action defense methods cannot defend its attacks.
Authors: Yunxiao Zhao, Zhiqiang Wang, Xingtong Yu, Xiaoli Li, Jiye Liang, Ru Li
Abstract: Rationalization, a data-centric framework, aims to build self-explanatory models to explain the prediction outcome by generating a subset of human-intelligible pieces of the input data. It involves a cooperative game model where a generator generates the most human-intelligible parts of the input (i.e., rationales), followed by a predictor that makes predictions based on these generated rationales. Conventional rationalization methods typically impose constraints via regularization terms to calibrate or penalize undesired generation. However, these methods are suffering from a problem called mode collapse, in which the predictor produces correct predictions yet the generator consistently outputs rationales with collapsed patterns. Moreover, existing studies are typically designed separately for specific collapsed patterns, lacking a unified consideration. In this paper, we systematically revisit cooperative rationalization from a novel game-theoretic perspective and identify the fundamental cause of this problem: the generator no longer tends to explore new strategies to uncover informative rationales, ultimately leading the system to converge to a suboptimal game equilibrium (correct predictions v.s collapsed rationales). To solve this problem, we then propose a novel approach, Game-theoretic Policy Optimization oriented RATionalization (PORAT), which progressively introduces policy interventions to address the game equilibrium in the cooperative game process, thereby guiding the model toward a more optimal solution state. We theoretically analyse the cause of such a suboptimal equilibrium and prove the feasibility of the proposed method. Furthermore, we validate our method on nine widely used real-world datasets and two synthetic settings, where PORAT achieves up to 8.1% performance improvements over existing state-of-the-art methods.
Authors: Liesbeth Allein, Nataly Pineda-Casta\~neda, Andrea Rocci, Marie-Francine Moens
Abstract: How does a cause lead to an effect, and which intermediate causal steps explain their connection? This work scrutinizes the mechanistic causal reasoning capabilities of large language models (LLMs) to answer these questions through the task of implicit causal chain discovery. In a diagnostic evaluation framework, we instruct nine LLMs to generate all possible intermediate causal steps linking given cause-effect pairs in causal chain structures. These pairs are drawn from recent resources in argumentation studies featuring polarized discussion on climate change. Our analysis reveals that LLMs vary in the number and granularity of causal steps they produce. Although they are generally self-consistent and confident about the intermediate causal connections in the generated chains, their judgments are mainly driven by associative pattern matching rather than genuine causal reasoning. Nonetheless, human evaluations confirmed the logical coherence and integrity of the generated chains. Our baseline causal chain discovery approach, insights from our diagnostic evaluation, and benchmark dataset with causal chains lay a solid foundation for advancing future work in implicit, mechanistic causal reasoning in argumentation settings.
Authors: Timothy Wong, Tom Freeman, Joseph Feehily
Abstract: Effective assessment of mobile network coverage and the precise identification of service weak spots are paramount for network operators striving to enhance user Quality of Experience (QoE). This paper presents a novel framework for mobile coverage and weak spot analysis utilising crowdsourced QoE data. The core of our methodology involves coverage analysis at the individual cell (antenna) level, subsequently aggregated to the site level, using empirical geolocation data. A key contribution of this research is the application of One-Class Support Vector Machine (OC-SVM) algorithm for calculating mobile network coverage. This approach models the decision hyperplane as the effective coverage contour, facilitating robust calculation of coverage areas for individual cells and entire sites. The same methodology is extended to analyse crowdsourced service loss reports, thereby identifying and quantifying geographically localised weak spots. Our findings demonstrate the efficacy of this novel framework in accurately mapping mobile coverage and, crucially, in highlighting granular areas of signal deficiency, particularly within complex urban environments.
Authors: He Du, Bowen Li, Chengxing Xie, Chang Gao, Kai Chen, Dacheng Tao
Abstract: Reward models can significantly enhance the reasoning capabilities of large language models (LLMs), but they typically require extensive curated data and costly training. To mitigate these challenges, training-free approaches such as LLM-as-a-Judge leverage the intrinsic reasoning abilities of LLMs to evaluate responses, achieving promising results. Recent works have also indicated that model confidence can serve effectively as a reward metric, distinguishing between chain-of-thought (CoT) and non-CoT paths. However, the concept of using confidence as a reward has not been comprehensively studied. In this work, we systematically investigate Confidence-as-a-Reward (CRew), a simple yet powerful training-free method that utilizes token-level confidence in the model's final answers as a proxy for reward, especially suitable for close-ended tasks. Through extensive experiments on mathematical reasoning tasks, we demonstrate that CRew outperforms existing training-free reward approaches on the MATH500 and RewardMATH benchmarks, and even surpasses most trained reward models. We further identify a strong correlation between CRew scores and the actual reasoning performance of the model. Additionally, we find that CRew can effectively filter high-quality training data. Building upon these insights, we propose CRew-DPO, a training strategy that constructs preference data from confidence scores combined with correctness signals. Finetuning with CRew-DPO further enhances the model's judging capabilities and consistently outperforms existing self-training methods.
Authors: William Flanagan, Mukunda Das, Rajitha Ramanyake, Swaunja Maslekar, Meghana Manipuri, Joong Ho Choi, Shruti Nair, Shambhavi Bhusan, Sanjana Dulam, Mouni Pendharkar, Nidhi Singh, Vashisth Doshi, Sachi Shah Paresh
Abstract: As Generative Artificial Intelligence is adopted across the financial services industry, a significant barrier to adoption and usage is measuring model performance. Historical machine learning metrics can oftentimes fail to generalize to GenAI workloads and are often supplemented using Subject Matter Expert (SME) Evaluation. Even in this combination, many projects fail to account for various unique risks present in choosing specific metrics. Additionally, many widespread benchmarks created by foundational research labs and educational institutions fail to generalize to industrial use. This paper explains these challenges and provides a Risk Assessment Framework to allow for better application of SME and machine learning Metrics
Authors: Robert West, Ashton Anderson, Ece Kamar, Eric Horvitz
Abstract: As language models continue to rapidly improve, we can expect their actions and reasoning to become difficult or impossible for weaker agents and humans to follow, undermining interpretability and oversight. With an eye on long-term futures, we pursue methods that encourage models to produce solutions that remain intelligible to weaker collaborators. We formalize intelligibility as handoff robustness: a strong model's solution is intelligible to a weaker model if randomly handing off control to the weaker model along the solution path does not cause failure. Building on this criterion, we introduce tandem training for language models, a reinforcement learning (RL) paradigm in which rollout tokens are intermittently and randomly sampled from a frozen weak model rather than the strong model being trained. Because rollouts succeed only when the strong model's actions and reasoning process can be continued by the weak model -- when the two can co-construct a successful solution -- optimizing standard RL objectives with tandem training implicitly incentivizes both correctness and intelligibility. In the GSM8K math reasoning task, tandem training reliably teaches models to abandon jargon and adapt their language to weaker partners while keeping task accuracy high. Our results demonstrate a promising route to building AI systems that remain auditable by weaker agents, with implications for human--AI collaboration and multi-agent communication.
Authors: Cecilia Di Florio, Huimin Dong, Antonino Rotolo
Abstract: Logic-based models can be used to build verification tools for machine learning classifiers employed in the legal field. ML classifiers predict the outcomes of new cases based on previous ones, thereby performing a form of case-based reasoning (CBR). In this paper, we introduce a modal logic of classifiers designed to formally capture legal CBR. We incorporate principles for resolving conflicts between precedents, by introducing into the logic the temporal dimension of cases and the hierarchy of courts within the legal system.
Authors: Evan Ellis, Vivek Myers, Jens Tuyls, Sergey Levine, Anca Dragan, Benjamin Eysenbach
Abstract: Assistive agents should not only take actions on behalf of a human, but also step out of the way and cede control when there are important decisions to be made. However, current methods for building assistive agents, whether via mimicking expert humans or via RL finetuning on an inferred reward, often encourage agents to complete tasks on their own rather than truly assisting the human attain their objectives. Additionally, these methods often require costly explicit human feedback to provide a training signal. We propose a new approach to tuning assistive language models based on maximizing the human's empowerment, their ability to effect desired changes in the environment. Our empowerment-maximizing method, Empower, only requires offline text data, providing a self-supervised method for fine-tuning language models to better assist humans. To study the efficacy of our approach, we conducted an 18-person user study comparing our empowerment assistant with a strong baseline. Participants preferred our assistant 78% of the time (p=0.015), with a 31% higher acceptance rate and 38% fewer suggestions. Additionally, we introduce a new environment for evaluating multi-turn code assistance using simulated humans. Using this environment, we show that agents trained with Empower increase the success rate of a simulated human programmer on challenging coding questions by an average of 192% over an SFT baseline. With this empowerment objective, we provide a framework for useful aligned AI agents at scale using only offline data without the need for any additional human feedback or verifiable rewards.
Authors: Ravi Pandya, Madison Bland, Duy P. Nguyen, Changliu Liu, Jaime Fern\'andez Fisac, Andrea Bajcsy
Abstract: Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-generation autonomous cars. In this context, safety is no longer about blocking harmful content, but about preempting downstream hazards like financial or physical harm. Yet, most AI guardrails continue to rely on output classification based on labeled datasets and human-specified criteria,making them brittle to new hazardous situations. Even when unsafe conditions are flagged, this detection offers no path to recovery: typically, the AI system simply refuses to act--which is not always a safe choice. In this work, we argue that agentic AI safety is fundamentally a sequential decision problem: harmful outcomes arise from the AI system's continually evolving interactions and their downstream consequences on the world. We formalize this through the lens of safety-critical control theory, but within the AI model's latent representation of the world. This enables us to build predictive guardrails that (i) monitor an AI system's outputs (actions) in real time and (ii) proactively correct risky outputs to safe ones, all in a model-agnostic manner so the same guardrail can be wrapped around any AI model. We also offer a practical training recipe for computing such guardrails at scale via safety-critical reinforcement learning. Our experiments in simulated driving and e-commerce settings demonstrate that control-theoretic guardrails can reliably steer LLM agents clear of catastrophic outcomes (from collisions to bankruptcy) while preserving task performance, offering a principled dynamic alternative to today's flag-and-block guardrails.
Authors: Shrey Pandit, Austin Xu, Xuan-Phi Nguyen, Yifei Ming, Caiming Xiong, Shafiq Joty
Abstract: Large language model (LLM)-based reasoning systems have recently achieved gold medal-level performance in the IMO 2025 competition, writing mathematical proofs where, to receive full credit, each step must be not only correct but also sufficiently supported. To train LLM-based reasoners in such challenging, open-ended settings, strong verifiers capable of catching step-level mistakes are necessary prerequisites. We introduce Hard2Verify, a human-annotated, step-level verification benchmark produced with over 500 hours of human labor. Hard2Verify is designed to rigorously assess step-level verifiers at the frontier: Verifiers must provide step-level annotations or identify the first error in responses generated by frontier LLMs for very recent, challenging, and open-ended math questions. We evaluate 29 generative critics and process reward models, demonstrating that, beyond a few standouts, open-source verifiers lag closed source models. We subsequently analyze what drives poor performance in step-level verification, the impacts of scaling verifier compute, as well as fundamental questions such as self-verification and verification-generation dynamics.
Authors: Shang Zhou, Zihan Zheng, Kaiyuan Liu, Zeyu Shen, Zerui Cheng, Zexing Chen, Hansen He, Jianzhu Yao, Huanzhi Mao, Qiuyang Mang, Tianfu Fu, Beichen Li, Dongruixuan Li, Wenhao Chai, Zhuang Liu, Aleksandra Korolova, Peter Henderson, Natasha Jaques, Pramod Viswanath, Saining Xie, Jingbo Shang
Abstract: Writing competitive programming problems is exacting. Authors must: set constraints, input distributions, and edge cases that rule out shortcuts; target specific algorithms (e.g., max-flow, dynamic programming, data structures); and calibrate complexity beyond the reach of most competitors. We argue that this makes for an ideal test of general large language model capabilities and study whether they can do this reliably. We introduce AutoCode, which uses multiple rounds of validation to yield competition-grade problem statements and test cases. On held-out problems, AutoCode test suites approach 99% consistency with official judgments, a significant improvement over current state-of-the-art methods like HardTests, which achieve less than 81%. Furthermore, starting with a random seed problem, AutoCode can create novel variants with reference and brute-force solutions. By cross-verifying these generated solutions against test cases, we can further filter out malformed problems. Our system ensures high correctness, as verified by human experts. AutoCode successfully produces novel problems judged by Grandmaster-level (top 0.3%) competitive programmers to be of contest quality.
Authors: Mahdi Cherakhloo, Arash Abbasi, Mohammad Saeid Sarafraz, Bijan Vosoughi Vahdat
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous languages; however, their effectiveness in low-resource languages like Persian requires thorough investigation. This paper presents a comprehensive benchmark of several open-source LLMs for Persian Natural Language Processing (NLP) tasks, utilizing both zero-shot and few-shot learning paradigms. We evaluate models across a range of tasks including sentiment analysis, named entity recognition, reading comprehension, and question answering, using established Persian datasets such as ParsiNLU and ArmanEmo. Our methodology encompasses rigorous experimental setups for both zero-shot and few-shot scenarios, employing metrics such as Accuracy, F1-score, BLEU, and ROUGE for performance evaluation. The results reveal that Gemma 2 consistently outperforms other models across nearly all tasks in both learning paradigms, with particularly strong performance in complex reasoning tasks. However, most models struggle with token-level understanding tasks like Named Entity Recognition, highlighting specific challenges in Persian language processing. This study contributes to the growing body of research on multilingual LLMs, providing valuable insights into their performance in Persian and offering a benchmark for future model development.
Authors: Soheil Hashtarkhani, Rezaur Rashid, Christopher L Brett, Lokesh Chinthala, Fekede Asefa Kumsa, Janet A Zink, Robert L Davis, David L Schwartz, Arash Shaban-Nejad
Abstract: Electronic health records contain inconsistently structured or free-text data, requiring efficient preprocessing to enable predictive health care models. Although artificial intelligence-driven natural language processing tools show promise for automating diagnosis classification, their comparative performance and clinical reliability require systematic evaluation. The aim of this study is to evaluate the performance of 4 large language models (GPT-3.5, GPT-4o, Llama 3.2, and Gemini 1.5) and BioBERT in classifying cancer diagnoses from structured and unstructured electronic health records data. We analyzed 762 unique diagnoses (326 International Classification of Diseases (ICD) code descriptions, 436free-text entries) from 3456 records of patients with cancer. Models were tested on their ability to categorize diagnoses into 14predefined categories. Two oncology experts validated classifications. BioBERT achieved the highest weighted macro F1-score for ICD codes (84.2) and matched GPT-4o in ICD code accuracy (90.8). For free-text diagnoses, GPT-4o outperformed BioBERT in weighted macro F1-score (71.8 vs 61.5) and achieved slightly higher accuracy (81.9 vs 81.6). GPT-3.5, Gemini, and Llama showed lower overall performance on both formats. Common misclassification patterns included confusion between metastasis and central nervous system tumors, as well as errors involving ambiguous or overlapping clinical terminology. Although current performance levels appear sufficient for administrative and research use, reliable clinical applications will require standardized documentation practices alongside robust human oversight for high-stakes decision-making.
Authors: Shanshan Xu, Santosh T. Y. S. S, Barbara Plank
Abstract: Human Label Variation (HLV) refers to legitimate disagreement in annotation that reflects the genuine diversity of human perspectives rather than mere error. For decades, HLV in NLP was dismissed as noise to be discarded, and only slowly over the last decade has it been reframed as a signal for improving model robustness. With the rise of large language models (LLMs), where post-training on human feedback has become central to model alignment, the role of HLV has become increasingly consequential. Yet current preference-learning datasets routinely aggregate multiple annotations into a single label, thereby flattening diverse perspectives into a false universal agreement and erasing precisely the pluralism of human values that alignment aims to preserve. In this position paper, we argue that preserving HLV as an embodiment of human pluralism must be treated as a Selbstzweck - a goal it self when designing AI systems. We call for proactively incorporating HLV into preference datasets and outline actionable steps towards it.
Authors: Rajarshi Ghosh, Abhay Gupta, Hudson McBride, Anurag Vaidya, Faisal Mahmood
Abstract: Large language models (LLMs) are increasingly deployed in clinical decision support, yet subtle demographic cues can influence their reasoning. Prior work has documented disparities in outputs across patient groups, but little is known about how internal reasoning shifts under controlled demographic changes. We introduce MEDEQUALQA, a counterfactual benchmark that perturbs only patient pronouns (he/him, she/her, they/them) while holding critical symptoms and conditions (CSCs) constant. Each clinical vignette is expanded into single-CSC ablations, producing three parallel datasets of approximately 23,000 items each (69,000 total). We evaluate a GPT-4.1 model and compute Semantic Textual Similarity (STS) between reasoning traces to measure stability across pronoun variants. Our results show overall high similarity (mean STS >0.80), but reveal consistent localized divergences in cited risk factors, guideline anchors, and differential ordering, even when final diagnoses remain unchanged. Our error analysis highlights certain cases in which the reasoning shifts, underscoring clinically relevant bias loci that may cascade into inequitable care. MEDEQUALQA offers a controlled diagnostic setting for auditing reasoning stability in medical AI.
Authors: Junyao Huang, Rumin Situ
Abstract: Traditional pet emotion recognition from vocalizations, based on discrete classification, struggles with ambiguity and capturing intensity variations. We propose a continuous Valence-Arousal (VA) model that represents emotions in a two-dimensional space. Our method uses an automatic VA label generation algorithm, enabling large-scale annotation of 42,553 pet vocalization samples. A multi-task learning framework jointly trains VA regression with auxiliary tasks (emotion, body size, gender) to enhance prediction by improving feature learning. Our Audio Transformer model achieves a validation Valence Pearson correlation of r = 0.9024 and an Arousal r = 0.7155, effectively resolving confusion between discrete categories like "territorial" and "happy." This work introduces the first continuous VA framework for pet vocalization analysis, offering a more expressive representation for human-pet interaction, veterinary diagnostics, and behavioral training. The approach shows strong potential for deployment in consumer products like AI pet emotion translators.
Authors: Michele Loi, Marcello Di Bello, Nicol\`o Cangiotti
Abstract: The growing philosophical literature on algorithmic fairness has examined statistical criteria such as equalized odds and calibration, causal and counterfactual approaches, and the role of structural and compounding injustices. Yet an important dimension has been overlooked: whether the evidential value of an algorithmic output itself depends on structural injustice. Our paradigmatic pair of examples contrasts a predictive policing algorithm, which relies on historical crime data, with a camera-based system that records ongoing offenses, both designed to guide police deployment. In evaluating the moral acceptability of acting on a piece of evidence, we must ask not only whether the evidence is probative in the actual world, but also whether it would remain probative in nearby worlds without the relevant injustices. The predictive policing algorithm fails this test, but the camera-based system passes it. When evidence fails the test, it is morally problematic to use it punitively, more so than evidence that passes the test.
Authors: Thomas Gschwind, Shramona Chakraborty, Nitin Gupta, Sameep Mehta
Abstract: ETL (Extract, Transform, Load) tools such as IBM DataStage allow users to visually assemble complex data workflows, but configuring stages and their properties remains time consuming and requires deep tool knowledge. We propose a system that translates natural language descriptions into executable workflows, automatically predicting both the structure and detailed configuration of the flow. At its core lies a Classifier-Augmented Generation (CAG) approach that combines utterance decomposition with a classifier and stage-specific few-shot prompting to produce accurate stage predictions. These stages are then connected into non-linear workflows using edge prediction, and stage properties are inferred from sub-utterance context. We compare CAG against strong single-prompt and agentic baselines, showing improved accuracy and efficiency, while substantially reducing token usage. Our architecture is modular, interpretable, and capable of end-to-end workflow generation, including robust validation steps. To our knowledge, this is the first system with a detailed evaluation across stage prediction, edge layout, and property generation for natural-language-driven ETL authoring.
Authors: Thao Pham
Abstract: As large language model (LLM) agents are deployed autonomously in diverse contexts, evaluating their capacity for strategic deception becomes crucial. While recent research has examined how AI systems scheme against human developers, LLM-to-LLM scheming remains underexplored. We investigate the scheming ability and propensity of frontier LLM agents through two game-theoretic frameworks: a Cheap Talk signaling game and a Peer Evaluation adversarial game. Testing four models (GPT-4o, Gemini-2.5-pro, Claude-3.7-Sonnet, and Llama-3.3-70b), we measure scheming performance with and without explicit prompting while analyzing scheming tactics through chain-of-thought reasoning. When prompted, most models, especially Gemini-2.5-pro and Claude-3.7-Sonnet, achieved near-perfect performance. Critically, models exhibited significant scheming propensity without prompting: all models chose deception over confession in Peer Evaluation (100% rate), while models choosing to scheme in Cheap Talk succeeded at 95-100% rates. These findings highlight the need for robust evaluations using high-stakes game-theoretic scenarios in multi-agent settings.
Authors: Md. Nayeem, Md Shamse Tabrej, Kabbojit Jit Deb, Shaonti Goswami, Md. Azizul Hakim
Abstract: Automatic Speech Recognition (ASR) has undergone a profound transformation over the past decade, driven by advances in deep learning. This survey provides a comprehensive overview of the modern era of ASR, charting its evolution from traditional hybrid systems, such as Gaussian Mixture Model-Hidden Markov Models (GMM-HMMs) and Deep Neural Network-HMMs (DNN-HMMs), to the now-dominant end-to-end neural architectures. We systematically review the foundational end-to-end paradigms: Connectionist Temporal Classification (CTC), attention-based encoder-decoder models, and the Recurrent Neural Network Transducer (RNN-T), which established the groundwork for fully integrated speech-to-text systems. We then detail the subsequent architectural shift towards Transformer and Conformer models, which leverage self-attention to capture long-range dependencies with high computational efficiency. A central theme of this survey is the parallel revolution in training paradigms. We examine the progression from fully supervised learning, augmented by techniques like SpecAugment, to the rise of self-supervised learning (SSL) with foundation models such as wav2vec 2.0, which drastically reduce the reliance on transcribed data. Furthermore, we analyze the impact of largescale, weakly supervised models like Whisper, which achieve unprecedented robustness through massive data diversity. The paper also covers essential ecosystem components, including key datasets and benchmarks (e.g., LibriSpeech, Switchboard, CHiME), standard evaluation metrics (e.g., Word Error Rate), and critical considerations for real-world deployment, such as streaming inference, on-device efficiency, and the ethical imperatives of fairness and robustness. We conclude by outlining open challenges and future research directions.
Authors: Hieu Le Duc, Leo Liberti
Abstract: During 2024 and 2025 the discussion about the theorem-proving capabilities of large language models started reporting interesting success stories, mostly to do with difficult exercises (such as problems from the International Mathematical Olympiad), but also with conjectures [Feldman & Karbasi, arXiv:2509.18383v1] formulated for the purpose of verifying whether the artificial intelligence could prove it. In this paper we report a theorem proving feat achieved by ChatGPT by using a protocol involving different prover and verifier instances of the gpt-5 model working collaboratively. To make sure that the produced proofs do not suffer from hallucinations, the final proof is formally verified by the lean proof assistant, and the conformance of premises and conclusion of the lean code is verified by a human. Our methodology was able to solve five out of six 2025 IMO problems, and close a third of the sixty-six number theory conjectures in [Cohen, Journal of Integer Sequences, 2025].
Authors: Alex Dantart
Abstract: This paper presents a comprehensive governance framework for AI systems in the legal sector, designed to ensure verifiable compliance with the EU AI Act. The framework integrates a normative mapping of the regulation to technical controls, a forensic architecture for RAG/LLM systems, and an evaluation system with metrics weighted by legal risk. As a primary contribution, we present rag-forense, an open-source implementation of the framework, accompanied by an experimental protocol to demonstrate compliance. -- Este art\'iculo presenta un marco integral de gobernanza para sistemas de IA en el sector legal, dise\~nado para garantizar el cumplimiento verificable del Reglamento de IA de la UE (AI Act). El marco integra una cartograf\'ia normativa de la ley a controles t\'ecnicos, una arquitectura forense para sistemas RAG/LLM y un sistema de evaluaci\'on con m\'etricas ponderadas por el riesgo jur\'idico. Como principal contribuci\'on, se presenta rag-forense, una implementaci\'on de c\'odigo abierto del marco, acompa\~nada de un protocolo experimental para demostrar la conformidad.
Authors: Taicheng Guo, Hai Wang, ChaoChun Liu, Mohsen Golalikhani, Xin Chen, Xiangliang Zhang, Chandan K. Reddy
Abstract: Multi-turn Text-to-SQL aims to translate a user's conversational utterances into executable SQL while preserving dialogue coherence and grounding to the target schema. However, most existing systems only regard this task as a simple text translation task and follow a short-horizon paradigm, generating a query per turn without execution, explicit verification, and refinement, which leads to non-executable or incoherent outputs. We present MTSQL-R1, an agentic training framework for long-horizon multi-turn Text-to-SQL. We cast the task as a Markov Decision Process (MDP) in which an agent interacts with (i) a database for execution feedback and (ii) a persistent dialogue memory for coherence verification, performing an iterative propose to execute -> verify -> refine cycle until all checks pass. Experiments on COSQL and SPARC demonstrate that MTSQL-R1 consistently outperforms strong baselines, highlighting the importance of environment-driven verification and memory-guided refinement for conversational semantic parsing. Full recipes (including code, trained models, logs, reasoning trajectories, etc.) will be released after the internal review to contribute to community research.
Authors: Alistair Brash, Junyi Lu, Bruce Stephen, Blair Brown, Robert Atkinson, Craig Michie, Fraser MacIntyre, Christos Tachtatzis
Abstract: Limited visibility of power distribution network power flows at the low voltage level presents challenges to both distribution network operators from a planning perspective and distribution system operators from a congestion management perspective. Forestalling these challenges through scenario analysis is confounded by the lack of realistic and coherent load data across representative distribution feeders. Load profiling approaches often rely on summarising demand through typical profiles, which oversimplifies the complexity of substation-level operations and limits their applicability in specific power system studies. Sampling methods, and more recently generative models, have attempted to address this through synthesising representative loads from historical exemplars; however, while these approaches can approximate load shapes to a convincing degree of fidelity, the co-behaviour between substations, which ultimately impacts higher voltage level network operation, is often overlooked. This limitation will become even more pronounced with the increasing integration of low-carbon technologies, as estimates of base loads fail to capture load diversity. To address this gap, a Conditional Diffusion model for synthesising daily active and reactive power profiles at the low voltage distribution substation level is proposed. The evaluation of fidelity is demonstrated through conventional metrics capturing temporal and statistical realism, as well as power flow modelling. The results show synthesised load profiles are plausible both independently and as a cohort in a wider power systems context. The Conditional Diffusion model is benchmarked against both naive and state-of-the-art models to demonstrate its effectiveness in producing realistic scenarios on which to base sub-regional power distribution network planning and operations.
Authors: T\'eo Guichoux, Th\'eodor Lemerle, Shivam Mehta, Jonas Beskow, Gustave Eje Henter, Laure Soulier, Catherine Pelachaud, Nicolas Obin
Abstract: Human communication is multimodal, with speech and gestures tightly coupled, yet most computational methods for generating speech and gestures synthesize them sequentially, weakening synchrony and prosody alignment. We introduce Gelina, a unified framework that jointly synthesizes speech and co-speech gestures from text using interleaved token sequences in a discrete autoregressive backbone, with modality-specific decoders. Gelina supports multi-speaker and multi-style cloning and enables gesture-only synthesis from speech inputs. Subjective and objective evaluations demonstrate competitive speech quality and improved gesture generation over unimodal baselines.
Authors: Kon Woo Kim (National Institute of Informatics, Japan), Rezarta Islamaj (National Library of Medicine, USA), Jin-Dong Kim (Joint Support-Center for Data Science Research, Japan), Florian Boudin (Japanese-French Laboratory of Informatics, CNRS, Nantes University, Japan), Akiko Aizawa (National Institute of Informatics, Japan)
Abstract: This study investigates how existing annotation guidelines can be repurposed to instruct large language model (LLM) annotators for text annotation tasks. Traditional guidelines are written for human annotators who internalize training, while LLMs require explicit, structured instructions. We propose a moderation-oriented guideline repurposing method that transforms guidelines into clear directives for LLMs through an LLM moderation process. Using the NCBI Disease Corpus as a case study, our experiments show that repurposed guidelines can effectively guide LLM annotators, while revealing several practical challenges. The results highlight the potential of this workflow to support scalable and cost-effective refinement of annotation guidelines and automated annotation.
Authors: Anil Yaman, Shen Tian, Bj\"orn Lindstr\"om
Abstract: Cumulative cultural evolution enables human societies to generate increasingly complex knowledge and technology over generations. While social learning transmits innovations between individuals and generations, the cognitive processes that generate these innovations remain poorly understood. Here, we demonstrate that semantic knowledge-structured associations between concepts and their functions-provides cognitive scaffolding for cumulative innovation by guiding exploration toward plausible and meaningful actions. We tested this hypothesis using a cultural evolutionary agent-based model and a large-scale behavioural experiment (N = 1,243), in which individuals performed a task requiring the combination of items into novel innovations. Across both approaches, semantic knowledge and social learning interact synergistically to enhance innovation. Behaviorally, participants without access to semantic knowledge performed no better than chance, even when social learning was available, and relied on shallow exploration strategies. These findings suggest that semantic knowledge is a key cognitive process enabling human cumulative culture.
Authors: Qianben Chen, Jingyi Cao, Jiayu Zhang, Tianrui Qin, Xiaowan Li, King Zhu, Dingfeng Shi, He Zhu, Minghao Liu, Xiaobo Liang, Ge Zhang, Jian Yang, Yuchen Eleanor Jiang, Wangchunshu Zhou
Abstract: Large language models split into two families: reasoning-centric LLMs, which strengthen internal chain-of-thought reasoning but cannot invoke external tools, and agentic LLMs, which learn to interact with environments and leverage tools but often lag in deep reasoning. This divide arises from fundamentally different training objectives, leading to mismatched strengths and inefficiency on simple queries, where both families tend to overthink or over-call tools. In this work, we present Adaptive Agent Foundation Model (A\textsuperscript{2}FM), a unified framework that follows a route-then-align principle: the model first learns task-aware routing and then aligns mode-specific trajectories under a shared backbone. To address the inefficiency gap, we introduce a third mode-instant-that handles simple queries directly, preventing unnecessary reasoning or tool calls while complementing the agentic and reasoning modes. To jointly enhance accuracy and efficiency, we propose Adaptive Policy Optimization (APO), which enforces adaptive sampling across modes and applies a cost-regularized reward. On the 32B scale, A\textsuperscript{2}FM achieves 13.4\% on BrowseComp, 70.4\% on AIME25, and 16.7\% on HLE, setting new SOTA among comparable models and performing competitively with frontier LLMs across agentic, reasoning, and general benchmarks. Notably, the adaptive execution achieves a cost of pass of only \$0.00487 per correct answer-cutting cost by 45.2\% relative to reasoning and 33.5\% relative to agentic, thus delivering substantially higher cost efficiency while maintaining comparable accuracy.
Authors: Yingjia Wan, Haochen Tan, Xiao Zhu, Xinyu Zhou, Zhiwei Li, Qingsong Lv, Changxuan Sun, Jiaqi Zeng, Yi Xu, Jianqiao Lu, Yinhong Liu, Zhijiang Guo
Abstract: Evaluating the factuality of long-form generations from Large Language Models (LLMs) remains challenging due to accuracy issues and costly human assessment. Prior efforts attempt this by decomposing text into claims, searching for evidence, and verifying claims, but suffer from critical drawbacks: (1) inefficiency due to complex pipeline components unsuitable for long LLM outputs, and (2) ineffectiveness stemming from inaccurate claim sets and insufficient evidence collection of one-line snippets. To address these limitations, we propose \name, a fast and strong evaluation framework that achieves the highest alignment with human evaluation and efficiency among existing baselines. \name first employs chunk-level claim extraction integrated with confidence-based pre-verification, significantly reducing the cost of web searching and inference calling while ensuring reliability. For searching and verification, it collects document-level evidence from crawled webpages and selectively retrieves it during verification, addressing the evidence insufficiency problem in previous pipelines. Extensive experiments based on an aggregated and manually annotated benchmark demonstrate the reliability of \name in both efficiently and effectively evaluating the factuality of long-form LLM generations. Code and benchmark data is available at https://github.com/Yingjia-Wan/FastFact.
Authors: Jesse Atuhurra, Iqra Ali, Tomoya Iwakura, Hidetaka Kamigaito, Tatsuya Hiraoka
Abstract: Vision Language Models (VLMs) are pivotal for advancing perception in intelligent agents. Yet, evaluation of VLMs remains limited to predominantly English-centric benchmarks in which the image-text pairs comprise short texts. To evaluate VLM fine-grained abilities, in four languages under long-text settings, we introduce a novel multilingual benchmark VLURes featuring eight vision-and-language tasks, and a pioneering unrelatedness task, to probe the fine-grained Visual and Linguistic Understanding capabilities of VLMs across English, Japanese, and low-resource languages, Swahili, and Urdu. Our datasets, curated from web resources in the target language, encompass ten diverse image categories and rich textual context, introducing valuable vision-language resources for Swahili and Urdu. By prompting VLMs to generate responses and rationales, evaluated automatically and by native speakers, we uncover performance disparities across languages and tasks critical to intelligent agents, such as object recognition, scene understanding, and relationship understanding. We conducted evaluations of ten VLMs with VLURes. The best performing model, GPT-4o, achieves an overall accuracy of 90.8% and lags human performance by 6.7%, though the gap is larger for open-source models. The gap highlights VLURes' critical role in developing intelligent agents to tackle multi-modal visual reasoning.
Authors: Mahamodul Hasan Mahadi, Md. Nasif Safwan, Souhardo Rahman, Shahnaj Parvin, Aminun Nahar, Kamruddin Nur
Abstract: Developing AI systems capable of nuanced ethical reasoning is critical as they increasingly influence human decisions, yet existing models often rely on superficial correlations rather than principled moral understanding. This paper introduces Ethic-BERT, a BERT-based model for ethical content classification across four domains: Commonsense, Justice, Virtue, and Deontology. Leveraging the ETHICS dataset, our approach integrates robust preprocessing to address vocabulary sparsity and contextual ambiguities, alongside advanced fine-tuning strategies like full model unfreezing, gradient accumulation, and adaptive learning rate scheduling. To evaluate robustness, we employ an adversarially filtered "Hard Test" split, isolating complex ethical dilemmas. Experimental results demonstrate Ethic-BERT's superiority over baseline models, achieving 82.32% average accuracy on the standard test, with notable improvements in Justice and Virtue. In addition, the proposed Ethic-BERT attains 15.28% average accuracy improvement in the HardTest. These findings contribute to performance improvement and reliable decision-making using bias-aware preprocessing and proposed enhanced AI model.
Authors: Jan Miller
Abstract: The Efficient Adaptive Transformer (EAT) framework unifies three adaptive efficiency techniques - progressive token pruning, sparse attention, and dynamic early exiting - into a single, reproducible architecture for input-adaptive inference. EAT provides an open-source benchmarking pipeline that automates data processing, timing, and ablation across GLUE tasks (SST-2, QQP, MNLI). Although this empirical study finds that combining these mechanisms can increase latency in shallow six-layer models, it demonstrates that EAT achieves slightly higher accuracy than the optimized DistilBERT baseline on SST-2, illustrating the potential of dynamic computation for latency-sensitive NLP. The main contribution is the open, end-to-end reproducible framework - complete with scripts, CSV logging, and analysis utilities - intended to serve as a community tool for further research on adaptive transformers.
Authors: Robin Staab, Jasper Dekoninck, Maximilian Baader, Martin Vechev
Abstract: Large language models (LLMs) are now widely deployed in user-facing applications, reaching hundreds of millions worldwide. As they become integrated into everyday tasks, growing reliance on their outputs raises significant concerns. In particular, users may unknowingly be exposed to model-inherent biases that systematically disadvantage or stereotype certain groups. However, existing bias benchmarks continue to rely on templated prompts or restrictive multiple-choice questions that are suggestive, simplistic, and fail to capture the complexity of real-world user interactions. In this work, we address this gap by introducing a counterfactual bias evaluation framework that automatically generates realistic, open-ended questions over sensitive attributes such as sex, race, or religion. By iteratively mutating and selecting bias-inducing questions, our approach systematically explores areas where models are most susceptible to biased behavior. Beyond detecting harmful biases, we also capture distinct response dimensions that are increasingly relevant in user interactions, such as asymmetric refusals and explicit acknowledgment of bias. Leveraging our framework, we construct CAB, a human-verified benchmark spanning diverse topics, designed to enable cross-model comparisons. Using CAB, we analyze a range of LLMs across multiple bias dimensions, revealing nuanced insights into how different models manifest bias. For instance, while GPT-5 outperforms other models, it nonetheless exhibits persistent biases in specific scenarios. These findings underscore the need for continual improvements to ensure fair model behavior.
Authors: Mohammed Hilal Al-Kharusi, Khizar Hayat, Khalil Bader Al Ruqeishi, Haroon Rashid Lone
Abstract: The sacred practice of Quranic recitation (Tajweed), governed by precise phonetic, prosodic, and theological rules, faces significant pedagogical challenges in the modern era. While digital technologies promise unprecedented access to education, automated tools for recitation evaluation have failed to achieve widespread adoption or pedagogical efficacy. This literature review investigates this critical gap, conducting a comprehensive analysis of academic research, web platforms, and commercial applications developed over the past two decades. Our synthesis reveals a fundamental misalignment in prevailing approaches that repurpose Automatic Speech Recognition (ASR) architectures, which prioritize lexical recognition over qualitative acoustic assessment and are plagued by data dependency, demographic biases, and an inability to provide diagnostically useful feedback. Critiquing these data--driven paradigms, we argue for a foundational paradigm shift towards a knowledge-centric computational framework. Capitalizing on the immutable nature of the Quranic text and the precisely defined rules of Tajweed, we propose that a robust evaluator must be architected around anticipatory acoustic modeling based on canonical rules and articulation points (Makhraj), rather than relying on statistical patterns learned from imperfect and biased datasets. This review concludes that the future of automated Quranic evaluation lies in hybrid systems that integrate deep linguistic knowledge with advanced audio analysis, offering a path toward robust, equitable, and pedagogically sound tools that can faithfully support learners worldwide.
Authors: Masoud Makrehchi
Abstract: Artificial Intelligence (AI) has emerged as both a continuation of historical technological revolutions and a potential rupture with them. This paper argues that AI must be viewed simultaneously through three lenses: \textit{risk}, where it resembles nuclear technology in its irreversible and global externalities; \textit{transformation}, where it parallels the Industrial Revolution as a general-purpose technology driving productivity and reorganization of labor; and \textit{continuity}, where it extends the fifty-year arc of computing revolutions from personal computing to the internet to mobile. Drawing on historical analogies, we emphasize that no past transition constituted a strict singularity: disruptive shifts eventually became governable through new norms and institutions. We examine recurring patterns across revolutions -- democratization at the usage layer, concentration at the production layer, falling costs, and deepening personalization -- and show how these dynamics are intensifying in the AI era. Sectoral analysis illustrates how accounting, law, education, translation, advertising, and software engineering are being reshaped as routine cognition is commoditized and human value shifts to judgment, trust, and ethical responsibility. At the frontier, the challenge of designing moral AI agents highlights the need for robust guardrails, mechanisms for moral generalization, and governance of emergent multi-agent dynamics. We conclude that AI is neither a singular break nor merely incremental progress. It is both evolutionary and revolutionary: predictable in its median effects yet carrying singularity-class tail risks. Good outcomes are not automatic; they require coupling pro-innovation strategies with safety governance, ensuring equitable access, and embedding AI within a human order of responsibility.
Authors: Hancheng Ye, Zhengqi Gao, Mingyuan Ma, Qinsi Wang, Yuzhe Fu, Ming-Yu Chung, Yueqian Lin, Zhijian Liu, Jianyi Zhang, Danyang Zhuo, Yiran Chen
Abstract: Multi-agent large language model (LLM) systems are increasingly adopted for complex language processing tasks that require communication and coordination among agents. However, these systems often suffer substantial overhead from repeated reprocessing of overlapping contexts across agents. In typical pipelines, once an agent receives a message from its predecessor, the full context-including prior turns-must be reprocessed from scratch, leading to inefficient processing. While key-value (KV) caching is an effective solution for avoiding redundant computation in single-agent settings where prefixes remain unchanged, it cannot be directly reused in multi-agent scenarios due to diverging prefixes introduced by agent-specific context extensions. We identify that the core challenge lies in the offset variance of KV-caches across agents. To address this, we propose KVCOMM, a training-free framework that enables efficient prefilling in multi-agent inference by reusing KV-caches and aligning cache offsets of overlapping contexts under diverse prefix contexts. KVCOMM estimates and adjusts KV-caches for shared content by referencing a pool of cached examples-termed anchors-that store observed cache deviations under varying prefixes. The anchor pool is maintained and updated online, allowing dynamic adaptation to distinct user requests and context structures. KVCOMM achieves over 70% reuse rate across diverse multi-agent workloads, including retrieval-augmented generation, math reasoning, and collaborative coding tasks, all without quality degradation. Particularly, when each fully-connected agent receives 1K input tokens with 512 prefix tokens and 512 output tokens under a five-agent setting, KVCOMM achieves up to 7.8x speedup compared to the standard prefill pipeline, reducing TTFT from ~430 ms to ~55 ms.
Authors: Justin Z. Tam, Pascal Grosset, Divya Banesh, Nesar Ramachandra, Terece L. Turton, James Ahrens
Abstract: Analyzing large-scale scientific datasets presents substantial challenges due to their sheer volume, structural complexity, and the need for specialized domain knowledge. Automation tools, such as PandasAI, typically require full data ingestion and lack context of the full data structure, making them impractical as intelligent data analysis assistants for datasets at the terabyte scale. To overcome these limitations, we propose InferA, a multi-agent system that leverages large language models to enable scalable and efficient scientific data analysis. At the core of the architecture is a supervisor agent that orchestrates a team of specialized agents responsible for distinct phases of the data retrieval and analysis. The system engages interactively with users to elicit their analytical intent and confirm query objectives, ensuring alignment between user goals and system actions. To demonstrate the framework's usability, we evaluate the system using ensemble runs from the HACC cosmology simulation which comprises several terabytes.
Authors: Mahsa Ghazvini Nejad, Hamed Jafarzadeh Asl, Amin Edraki, Mohammadreza Sadeghi, Masoud Asgharian, Yuanhao Yu, Vahid Partovi Nia
Abstract: Personalized Voice Activity Detection (PVAD) systems activate only in response to a specific target speaker by incorporating speaker embeddings from enrollment utterances. Unlike existing methods that require architectural changes, such as FiLM layers, our approach employs a hypernetwork to modify the weights of a few selected layers within a standard voice activity detection (VAD) model. This enables speaker conditioning without changing the VAD architecture, allowing the same VAD model to adapt to different speakers by updating only a small subset of the layers. We propose HyWA-PVAD, a hypernetwork weight adaptation method, and evaluate it against multiple baseline conditioning techniques. Our comparison shows consistent improvements in PVAD performance. HyWA also offers practical advantages for deployment by preserving the core VAD architecture. Our new approach improves the current conditioning techniques in two ways: i) increases the mean average precision, ii) simplifies deployment by reusing the same VAD architecture.
Authors: Minh Nguyen
Abstract: Retrieval-Augmented Generation (RAG) frameworks aim to enhance Code Language Models (CLMs) by including another module for retrieving relevant context to construct the input prompt. However, these retrieval modules commonly use semantic search, requiring substantial computational resources for training and hosting these embedded models, making them infeasible to integrate into lightweight applications such as in-IDE AI-based code completion. In this solution paper, we prove that using keyword-search is sufficient to retrieve relevant and useful code context inside large codebases, without the need for extensive GPU resources. The usefulness of code contexts found by our solution is demonstrated through their completion results on the Code Context Competition's benchmark, reaching 0.748 and 0.725 chRF scores on Kotlin and Python tracks, respectively.
Authors: Xiao He, Huangxuan Zhao, Guojia Wan, Wei Zhou, Yanxing Liu, Juhua Liu, Yongchao Xu, Yong Luo, Dacheng Tao, Bo Du
Abstract: Recent medical vision-language models have shown promise on tasks such as VQA, report generation, and anomaly detection. However, most are adapted to structured adult imaging and underperform in fetal ultrasound, which poses challenges of multi-view image reasoning, numerous diseases, and image diversity. To bridge this gap, we introduce FetalMind, a medical AI system tailored to fetal ultrasound for both report generation and diagnosis. Guided by clinical workflow, we propose Salient Epistemic Disentanglement (SED), which injects an expert-curated bipartite graph into the model to decouple view-disease associations and to steer preference selection along clinically faithful steps via reinforcement learning. This design mitigates variability across diseases and heterogeneity across views, reducing learning bottlenecks while aligning the model's inference with obstetric practice. To train FetalMind at scale, we curate FetalSigma-1M dataset, the first large-scale fetal ultrasound report corpus, comprising 20K reports from twelve medical centers, addressing the scarcity of domain data. Extensive experiments show that FetalMind outperforms open- and closed-source baselines across all gestational stages, achieving +14% average gains and +61.2% higher accuracy on critical conditions while remaining efficient, stable, and scalable. Project Page: https://hexiao0275.github.io/FetalMind.
Authors: Noor Islam S. Mohammad
Abstract: Standard benchmark datasets, such as MNIST, often fail to expose latent biases and multimodal feature complexities, limiting the trustworthiness of deep neural networks in high-stakes applications. We propose a novel multimodal Explainable AI (XAI) framework that unifies attention-augmented feature fusion, Grad-CAM++-based local explanations, and a Reveal-to-Revise feedback loop for bias detection and mitigation. Evaluated on multimodal extensions of MNIST, our approach achieves 93.2% classification accuracy, 91.6% F1-score, and 78.1% explanation fidelity (IoU-XAI), outperforming unimodal and non-explainable baselines. Ablation studies demonstrate that integrating interpretability with bias-aware learning enhances robustness and human alignment. Our work bridges the gap between performance, transparency, and fairness, highlighting a practical pathway for trustworthy AI in sensitive domains.
Authors: Binxin Gao, Jingjun Han
Abstract: Test-time scaling has enabled Large Language Models (LLMs) with remarkable reasoning capabilities, particularly in mathematical domains, through intermediate chain-of-thought (CoT) reasoning before generating final answers. However, the specific sources and mechanisms underlying these reasoning capabilities remain insufficiently understood. Optimization reasoning, i.e. finding extrema under constraints, represents a fundamental abstraction that underpins critical applications in planning, control, resource allocation, and prompt search. To systematically evaluate this capability, we introduce ExtremBench, a benchmark dataset for solving mathematical extremal problems, curated from inequality exercises used for Chinese Mathematical Olympiad and transformed into $93$ standardized extrema-finding problems. We conduct extensive evaluations across various state-of-the-art open-source model families, including the Qwen3, GPT-OSS, and DeepSeek. Our results reveal that LLMs' extremal-solving reasoning capabilities do not always align with those of current mathematical benchmarks such as AIME25 and MATH-500, with some models showing strong general mathematical reasoning but poor extremal-solving skills, and vice versa. This discrepancy highlights a critical gap in current evaluation practices and suggests that existing benchmarks may not comprehensively capture the full spectrum of mathematical reasoning abilities.
Authors: Pavan Kalyan, Shubhra Mishra, Satya Lokam, Navin Goyal
Abstract: We introduce a comprehensive continual learning dataset and benchmark (CurlL) grounded in human developmental trajectories from ages 5-10, enabling systematic and fine-grained assessment of models' ability to progressively acquire new skills. CurlL spans five developmental stages (0-4) covering ages 5-10, supported by a skill graph that breaks down broad skills into smaller abilities, concrete goals, and measurable indicators, while also capturing which abilities build on others. We generate a 23.4B-token synthetic dataset with controlled skill progression, vocabulary complexity, and format diversity, comprising paragraphs, comprehension-based QA (CQA), skill-testing QA (CSQA), and instruction-response (IR) pairs. Stage-wise token counts range from 2.12B to 6.78B tokens, supporting precise analysis of forgetting, forward transfer, and backward transfer. Using a 135M-parameter transformer trained under independent, joint, and sequential (continual) setups, we show trade-offs in skill retention and transfer efficiency. By mirroring human learning patterns and providing fine-grained control over skill dependencies, this work advances continual learning evaluations for language models.
Authors: Basad Barajeeh, Ala Yankouskaya, Sameha AlShakhsi, Chun Sing Maxwell Ho, Guandong Xu, Raian Ali
Abstract: As the use of large language models (LLMs) becomes increasingly global, understanding public attitudes toward these systems requires tools that are adapted to local contexts and languages. In the Arab world, LLM adoption has grown rapidly with both globally dominant platforms and regional ones like Fanar and Jais offering Arabic-specific solutions. This highlights the need for culturally and linguistically relevant scales to accurately measure attitudes toward LLMs in the region. Tools assessing attitudes toward artificial intelligence (AI) can provide a base for measuring attitudes specific to LLMs. The 5-item Attitudes Toward Artificial Intelligence (ATAI) scale, which measures two dimensions, the AI Fear and the AI Acceptance, has been recently adopted and adapted to develop new instruments in English using a sample from the UK: the Attitudes Toward General LLMs (AT-GLLM) and Attitudes Toward Primary LLM (AT-PLLM) scales. In this paper, we translate the two scales, AT-GLLM and AT-PLLM, and validate them using a sample of 249 Arabic-speaking adults. The results show that the scale, translated into Arabic, is a reliable and valid tool that can be used for the Arab population and language. Psychometric analyses confirmed a two-factor structure, strong measurement invariance across genders, and good internal reliability. The scales also demonstrated strong convergent and discriminant validity. Our scales will support research in a non-Western context, a much-needed effort to help draw a global picture of LLM perceptions, and will also facilitate localized research and policy-making in the Arab region.
Authors: Crystal Qian, Vivian Tsai, Michael Behr, Nada Hussein, L\'eo Laugier, Nithum Thain, Lucas Dixon
Abstract: Social and behavioral scientists increasingly aim to study how humans interact, collaborate, and make decisions alongside artificial intelligence. However, the experimental infrastructure for such work remains underdeveloped: (1) few platforms support real-time, multi-party studies at scale; (2) most deployments require bespoke engineering, limiting replicability and accessibility, and (3) existing tools do not treat AI agents as first-class participants. We present Deliberate Lab, an open-source platform for large-scale, real-time behavioral experiments that supports both human participants and large language model (LLM)-based agents. We report on a 12-month public deployment of the platform (N=88 experimenters, N=9195 experiment participants), analyzing usage patterns and workflows. Case studies and usage scenarios are aggregated from platform users, complemented by in-depth interviews with select experimenters. By lowering technical barriers and standardizing support for hybrid human-AI experimentation, Deliberate Lab expands the methodological repertoire for studying collective decision-making and human-centered AI.
Authors: Jiawen Li, Pascal Lefevre, Anwar Pp Abdul Majeed
Abstract: Based on Stochastic Gradient Descent (SGD), the paper introduces two optimizers, named Interpolational Accelerating Gradient Descent (IAGD) as well as Noise-Regularized Stochastic Gradient Descent (NRSGD). IAGD leverages second-order Newton Interpolation to expedite the convergence process during training, assuming relevancy in gradients between iterations. To avoid over-fitting, NRSGD incorporates a noise regularization technique that introduces controlled noise to the gradients during the optimization process. Comparative experiments of this research are conducted on the CIFAR-10, and CIFAR-100 datasets, benchmarking different CNNs(Convolutional Neural Networks) with IAGD and NRSGD against classical optimizers in Keras Package. Results demonstrate the potential of those two viable improvement methods in SGD, implicating the effectiveness of the advancements.
Authors: Zhengxu Tang, Zizheng Wang, Luning Wang, Zitao Shuai, Chenhao Zhang, Siyu Qian, Yirui Wu, Bohao Wang, Haosong Rao, Zhenyu Yang, Chenwei Wu
Abstract: Text-to-video (T2V) generation models have made significant progress in creating visually appealing videos. However, they struggle with generating coherent sequential narratives that require logical progression through multiple events. Existing T2V benchmarks primarily focus on visual quality metrics but fail to evaluate narrative coherence over extended sequences. To bridge this gap, we present SeqBench, a comprehensive benchmark for evaluating sequential narrative coherence in T2V generation. SeqBench includes a carefully designed dataset of 320 prompts spanning various narrative complexities, with 2,560 human-annotated videos generated from 8 state-of-the-art T2V models. Additionally, we design a Dynamic Temporal Graphs (DTG)-based automatic evaluation metric, which can efficiently capture long-range dependencies and temporal ordering while maintaining computational efficiency. Our DTG-based metric demonstrates a strong correlation with human annotations. Through systematic evaluation using SeqBench, we reveal critical limitations in current T2V models: failure to maintain consistent object states across multi-action sequences, physically implausible results in multi-object scenarios, and difficulties in preserving realistic timing and ordering relationships between sequential actions. SeqBench provides the first systematic framework for evaluating narrative coherence in T2V generation and offers concrete insights for improving sequential reasoning capabilities in future models. Please refer to https://videobench.github.io/SeqBench.github.io/ for more details.
Authors: Jungbin Cho, Minsu Kim, Jisoo Kim, Ce Zheng, Laszlo A. Jeni, Ming-Hsuan Yang, Youngjae Yu, Seonjoo Kim
Abstract: Human motion is inherently diverse and semantically rich, while also shaped by the surrounding scene. However, existing motion generation approaches address either motion semantics or scene-awareness in isolation, since constructing large-scale datasets with both rich text--motion coverage and precise scene interactions is extremely challenging. In this work, we introduce SceneAdapt, a framework that injects scene awareness into text-conditioned motion models by leveraging disjoint scene--motion and text--motion datasets through two adaptation stages: inbetweening and scene-aware inbetweening. The key idea is to use motion inbetweening, learnable without text, as a proxy task to bridge two distinct datasets and thereby inject scene-awareness to text-to-motion models. In the first stage, we introduce keyframing layers that modulate motion latents for inbetweening while preserving the latent manifold. In the second stage, we add a scene-conditioning layer that injects scene geometry by adaptively querying local context through cross-attention. Experimental results show that SceneAdapt effectively injects scene awareness into text-to-motion models, and we further analyze the mechanisms through which this awareness emerges. Code and models will be released.
Authors: Muhammad Faraz Ul Abrar, Nicol\`o Michelusi, Erik G. Larsson
Abstract: Classical optimization theory deals with fixed, time-invariant objective functions. However, time-varying optimization has emerged as an important subject for decision-making in dynamic environments. In this work, we study the problem of learning from streaming data through a time-varying optimization lens. Unlike prior works that focus on generic formulations, we introduce a structured, \emph{weight-based} formulation that explicitly captures the streaming-data origin of the time-varying objective, where at each time step, an agent aims to minimize a weighted average loss over all the past data samples. We focus on two specific weighting strategies: (1) uniform weights, which treat all samples equally, and (2) discounted weights, which geometrically decay the influence of older data. For both schemes, we derive tight bounds on the ``tracking error'' (TE), defined as the deviation between the model parameter and the time-varying optimum at a given time step, under gradient descent (GD) updates. We show that under uniform weighting, the TE vanishes asymptotically with a $\mathcal{O}(1/t)$ decay rate, whereas discounted weighting incurs a nonzero error floor controlled by the discount factor and the number of gradient updates performed at each time step. Our theoretical findings are validated through numerical simulations.
Authors: Ankit Goyal, Hugo Hadfield, Xuning Yang, Valts Blukis, Fabio Ramos
Abstract: Vision-Language-Action models (VLAs) hold immense promise for enabling generalist robot manipulation. However, the best way to build them remains an open question. Current approaches often add complexity, such as modifying the existing vocabulary of a Vision-Language Model (VLM) with action tokens or introducing special action heads. Curiously, the simplest strategy of representing actions directly as text has remained largely unexplored. This work introduces VLA-0 to investigate this idea. We find that VLA-0 is not only effective; it is surprisingly powerful. With the right design, VLA-0 outperforms more involved models. On LIBERO, a popular benchmark for evaluating VLAs, VLA-0 outperforms all existing methods trained on the same robotic data, including $\pi_0.5$-KI, OpenVLA-OFT and SmolVLA. Furthermore, without large-scale robotics-specific training, it outperforms methods trained on large-scale robotic data, like $\pi_0.5$-KI, $\pi_0$, GR00T-N1 and MolmoAct. These findings also translate to the real world, where VLA-0 outperforms SmolVLA, a VLA model pre-trained on large-scale real data. This paper summarizes our unexpected findings and spells out the specific techniques required to unlock the high performance of this simple yet potent VLA design. Visual results, code, and trained models are provided here: https://vla0.github.io/.
URLs: https://vla0.github.io/.
Authors: Adnan Jafar, Xun Jia
Abstract: Current radiation therapy treatment planning is limited by suboptimal plan quality, inefficiency, and high costs. This perspective paper explores the complexity of treatment planning and introduces Human-Centric Intelligent Treatment Planning (HCITP), an AI-driven framework under human oversight, which integrates clinical guidelines, automates plan generation, and enables direct interactions with operators. We expect that HCITP will enhance efficiency, potentially reducing planning time to minutes, and will deliver personalized, high-quality plans. Challenges and potential solutions are discussed.
Authors: Thomas W. Mitchel, Hyunwoo Ryu, Vincent Sitzmann
Abstract: In this paper, we identify that the key criterion for determining whether a model is truly capable of novel view synthesis (NVS) is transferability: Whether any pose representation extracted from one video sequence can be used to re-render the same camera trajectory in another. We analyze prior work on self-supervised NVS and find that their predicted poses do not transfer: The same set of poses lead to different camera trajectories in different 3D scenes. Here, we present XFactor, the first geometry-free self-supervised model capable of true NVS. XFactor combines pair-wise pose estimation with a simple augmentation scheme of the inputs and outputs that jointly enables disentangling camera pose from scene content and facilitates geometric reasoning. Remarkably, we show that XFactor achieves transferability with unconstrained latent pose variables, without any 3D inductive biases or concepts from multi-view geometry -- such as an explicit parameterization of poses as elements of SE(3). We introduce a new metric to quantify transferability, and through large-scale experiments, we demonstrate that XFactor significantly outperforms prior pose-free NVS transformers, and show that latent poses are highly correlated with real-world poses through probing experiments.
Authors: Konstantinos Barmpas, Na Lee, Alexandros Koliousis, Yannis Panagakis, Dimitrios A. Adamos, Nikolaos Laskaris, Stefanos Zafeiriou
Abstract: Electroencephalography (EEG) captures neural activity across multiple temporal and spectral scales, yielding signals that are rich but complex for representation learning. Recently, EEG foundation models trained to predict masked signal-tokens have shown promise for learning generalizable representations. However, their performance is hindered by their signal tokenization modules. Existing neural tokenizers fail to preserve high-frequency dynamics, limiting their ability to reconstruct EEG signals with high fidelity. We introduce NeuroRVQ, a scalable Large Brainwave Model (LBM) centered on a codebook-based tokenizer. Our tokenizer integrates: (i) multi-scale feature extraction modules that capture the full frequency neural spectrum; (ii) hierarchical residual vector quantization (RVQ) codebooks for high-resolution encoding; and, (iii) an EEG signal phase- and amplitude-aware loss function for efficient training. This design enables efficient EEG compression while supporting accurate reconstruction across all frequency bands, leading to robust generative masked modeling. Our empirical results demonstrate that NeuroRVQ achieves lower reconstruction error and outperforms existing LBMs on a variety of downstream tasks. More broadly, NeuroRVQ tokenizer establishes a strong prior for codebook-based general-purpose brainwave models, enabling advances in neural decoding, generative modeling and multimodal biosignal integration.
Authors: Yubo Zhang, Xiao-Yang Liu, Xiaodong Wang
Abstract: We develop an unsupervised deep learning framework for downlink beamforming in large-scale MU-MISO channels. The model is trained offline, allowing real-time inference through lightweight feedforward computations in dynamic communication environments. Following the learning-to-optimize (L2O) paradigm, a multi-layer Transformer iteratively refines both channel and beamformer features via residual connections. To enhance training, three strategies are introduced: (i) curriculum learning (CL) to improve early-stage convergence and avoid local optima, (ii) semi-amortized learning to refine each Transformer block with a few gradient ascent steps, and (iii) sliding-window training to stabilize optimization by training only a subset of Transformer blocks at a time. Extensive simulations show that the proposed scheme outperforms existing baselines at low-to-medium SNRs and closely approaches WMMSE performance at high SNRs, while achieving substantially faster inference than iterative and online learning approaches.
Authors: J. Gregory Pauloski, Kyle Chard, Ian T. Foster
Abstract: As data-driven methods, artificial intelligence (AI), and automated workflows accelerate scientific tasks, we see the rate of discovery increasingly limited by human decision-making tasks such as setting objectives, generating hypotheses, and designing experiments. We postulate that cooperative agents are needed to augment the role of humans and enable autonomous discovery. Realizing such agents will require progress in both AI and infrastructure.
Authors: Ningkang Peng, Yuzhe Mao, Yuhao Zhang, Linjin Qian, Qianfeng Yu, Yanhui Gu, Yi Chen, Li Kong
Abstract: Out-of-Distribution (OOD) detection is a cornerstone for the safe deployment of AI systems in the open world. However, existing methods treat OOD detection as a binary classification problem, a cognitive flattening that fails to distinguish between semantically close (Near-OOD) and distant (Far-OOD) unknown risks. This limitation poses a significant safety bottleneck in applications requiring fine-grained risk stratification. To address this, we propose a paradigm shift from a conventional probabilistic view to a principled information-theoretic framework. We formalize the core task as quantifying the Semantic Surprise of a new sample and introduce a novel ternary classification challenge: In-Distribution (ID) vs. Near-OOD vs. Far-OOD. The theoretical foundation of our work is the concept of Low-Entropy Semantic Manifolds, which are explicitly structured to reflect the data's intrinsic semantic hierarchy. To construct these manifolds, we design a Hierarchical Prototypical Network. We then introduce the Semantic Surprise Vector (SSV), a universal probe that decomposes a sample's total surprise into three complementary and interpretable dimensions: conformity, novelty, and ambiguity. To evaluate performance on this new task, we propose the Normalized Semantic Risk (nSR), a cost-sensitive metric. Experiments demonstrate that our framework not only establishes a new state-of-the-art (sota) on the challenging ternary task, but its robust representations also achieve top results on conventional binary benchmarks, reducing the False Positive Rate by over 60% on datasets like LSUN.
Authors: Mingda Li, Xinyu Li, Weinan Zhang, Longxuan Ma
Abstract: Uncertainty Quantification (UQ) is a promising approach to improve model reliability, yet quantifying the uncertainty of Large Language Models (LLMs) is non-trivial. In this work, we establish a connection between the uncertainty of LLMs and their invariance under semantic-preserving intervention from a causal perspective. Building on this foundation, we propose a novel grey-box uncertainty quantification method that measures the variation in model outputs before and after the semantic-preserving intervention. Through theoretical justification, we show that our method provides an effective estimate of epistemic uncertainty. Our extensive experiments, conducted across various LLMs and a variety of question-answering (QA) datasets, demonstrate that our method excels not only in terms of effectiveness but also in computational efficiency.
Authors: Ruoyu Sun, Da Song, Jiayang Song, Yuheng Huang, Lei Ma
Abstract: As Large Language Models (LLMs) continue to revolutionize Natural Language Processing (NLP) applications, critical concerns about their trustworthiness persist, particularly in safety and robustness. To address these challenges, we introduce TRUSTVIS, an automated evaluation framework that provides a comprehensive assessment of LLM trustworthiness. A key feature of our framework is its interactive user interface, designed to offer intuitive visualizations of trustworthiness metrics. By integrating well-known perturbation methods like AutoDAN and employing majority voting across various evaluation methods, TRUSTVIS not only provides reliable results but also makes complex evaluation processes accessible to users. Preliminary case studies on models like Vicuna-7b, Llama2-7b, and GPT-3.5 demonstrate the effectiveness of our framework in identifying safety and robustness vulnerabilities, while the interactive interface allows users to explore results in detail, empowering targeted model improvements. Video Link: https://youtu.be/k1TrBqNVg8g
Authors: Jingyu Song, Zhenxin Li, Shiyi Lan, Xinglong Sun, Nadine Chang, Maying Shen, Joshua Chen, Katherine A. Skinner, Jose M. Alvarez
Abstract: Benchmarking autonomous driving planners to align with human judgment remains a critical challenge, as state-of-the-art metrics like the Extended Predictive Driver Model Score (EPDMS) lack context awareness in nuanced scenarios. To address this, we introduce DriveCritic, a novel framework featuring two key contributions: the DriveCritic dataset, a curated collection of challenging scenarios where context is critical for correct judgment and annotated with pairwise human preferences, and the DriveCritic model, a Vision-Language Model (VLM) based evaluator. Fine-tuned using a two-stage supervised and reinforcement learning pipeline, the DriveCritic model learns to adjudicate between trajectory pairs by integrating visual and symbolic context. Experiments show DriveCritic significantly outperforms existing metrics and baselines in matching human preferences and demonstrates strong context awareness. Overall, our work provides a more reliable, human-aligned foundation to evaluating autonomous driving systems.
Authors: Surya Tejaswi Yerramsetty, Almas Fathimah
Abstract: Clinical trials are central to medical progress because they help improve understanding of human health and the healthcare system. They play a key role in discovering new ways to detect, prevent, or treat diseases, and it is essential that clinical trials include participants with appropriate and diverse medical backgrounds. In this paper, we propose a system that leverages Natural Language Processing (NLP) and Large Language Models (LLMs) to automate multi-label clinical text eligibility classification and summarization. The system combines feature extraction methods such as word embeddings (Word2Vec) and named entity recognition to identify relevant medical concepts, along with traditional vectorization techniques such as count vectorization and TF-IDF (Term Frequency-Inverse Document Frequency). We further explore weighted TF-IDF word embeddings that integrate both count-based and embedding-based strengths to capture term importance effectively. Multi-label classification using Random Forest and SVM models is applied to categorize documents based on eligibility criteria. Summarization techniques including TextRank, Luhn, and GPT-3 are evaluated to concisely summarize eligibility requirements. Evaluation with ROUGE scores demonstrates the effectiveness of the proposed methods. This system shows potential for automating clinical trial eligibility assessment using data-driven approaches, thereby improving research efficiency.
Authors: Anej Svete, Ashish Sabharwal
Abstract: Masked diffusion models (MDMs) for text offer a compelling alternative to traditional autoregressive language models. Parallel generation makes them efficient, but their computational capabilities and the limitations inherent to their parallelism remain largely unexplored. To this end, we characterize what types of reasoning problems MDMs can provably solve and how efficiently. We do this by connecting MDMs to the well-understood reasoning frameworks of chain of thought (CoT) and padded looped transformers (PLTs) in the finite-precision log-width setting: We show that MDMs and polynomially-padded PLTs are, in fact, equivalent in this setting, and that MDMs can solve all problems that CoT-augmented transformers can. Moreover, we showcase classes of problems (including regular languages) for which MDMs are inherently more efficient than CoT transformers, where parallel generation allows for substantially faster reasoning.
Authors: Junichiro Niimi
Abstract: Large language models (LLMs) have achieved remarkable results in wide range of domains. However, the accuracy and robustness of one-shot LLM predictions remain highly sensitive to the examples and the diversity among ensemble members. This study systematically investigates the effects of example representativeness (one-shot strategy) and output diversity (sampling temperature) on LLM ensemble performance. Two one-shot strategies are compared: centroid-based representative examples (proposed) and randomly sampled examples (baseline) and sampling temperature also is varied. The proposed approach with higher temperature setting significantly outperforms random selection by +7.6% (macro-F1) and -10.5% (RMSE). Furthermore, the proposed model exceeds 5-shot prompting by +21.1% (macro-F1) and -24.0% (RMSE). Our findings demonstrate that combining representative example selection with increased temperature provides the appropriate level of diversity to the ensemble. This work highlights the practical importance of both example selection and controlled diversity in designing effective one-shot LLM ensembles.
Authors: Subhendu Khatuya, Shashwat Naidu, Pawan Goyal, Niloy Ganguly
Abstract: Despite continuous advancements in the capabilities of large language models (LLMs), numerical reasoning remains a challenging area. Techniques like chain-of-thought prompting, tree-of-thought prompting, and program-of-thought prompting guide LLMs through intermediate reasoning steps. Although in-context learning with few-shot prompting has improved performance, LLMs still lag behind state-of-the-art models on financial numerical reasoning datasets such as FinQA and ConvFinQA. In this work, we introduce FINDER, a novel two-step framework, to enhance LLMs' capabilities in financial numerical reasoning. The first step utilizes a generative retriever to extract relevant facts from unstructured data, including both text and tables. This is followed by context-aware Program of Thought prompting with dynamic selection of in-context examples. Our model FINDER achieves a new state-of-the-art performance on both the FinQA and ConvFinQA datasets, surpassing previous benchmarks with execution accuracy improvements of 5.98% and 4.05%, respectively.
Authors: Haolin Pan, Jinyuan Dong, Hongbin Zhang, Hongyu Lin, Mingjie Xing, Yanjun Wu
Abstract: Learning effective numerical representations, or embeddings, of programs is a fundamental prerequisite for applying machine learning to automate and enhance compiler optimization. Prevailing paradigms, however, present a dilemma. Static representations, derived from source code or intermediate representation (IR), are efficient and deterministic but offer limited insight into how a program will behave or evolve under complex code transformations. Conversely, dynamic representations, which rely on runtime profiling, provide profound insights into performance bottlenecks but are often impractical for large-scale tasks due to prohibitive overhead and inherent non-determinism. This paper transcends this trade-off by proposing a novel quasi-dynamic framework for program representation. The core insight is to model a program's optimization sensitivity. We introduce the Program Behavior Spectrum, a new representation generated by probing a program's IR with a diverse set of optimization sequences and quantifying the resulting changes in its static features. To effectively encode this high-dimensional, continuous spectrum, we pioneer a compositional learning approach. Product Quantization is employed to discretize the continuous reaction vectors into structured, compositional sub-words. Subsequently, a multi-task Transformer model, termed PQ-BERT, is pre-trained to learn the deep contextual grammar of these behavioral codes. Comprehensive experiments on two representative compiler optimization tasks -- Best Pass Prediction and -Oz Benefit Prediction -- demonstrate that our method outperforms state-of-the-art static baselines. Our code is publicly available at https://github.com/Panhaolin2001/PREP/.
Authors: Xi Chen, Yuchen Song, Satoshi Nakamura
Abstract: We propose a stress-aware speech-to-speech translation (S2ST) system that preserves word-level emphasis by leveraging LLMs for cross-lingual emphasis conversion. Our method translates source-language stress into target-language tags that guide a controllable TTS model. To overcome data scarcity, we developed a pipeline to automatically generate aligned training data and introduce the "LLM-as-Judge" for evaluation. Experiments show our approach substantially outperforms baselines in preserving emphasis while maintaining comparable translation quality, speaker intent, and naturalness. Our work highlights the importance of prosody in translation and provides an effective, data-efficient solution for preserving paralinguistic cues in S2ST.
Authors: Jing Yang, Qiyao Wei, Jiaxin Pei
Abstract: The rapid growth of AI conferences is straining an already fragile peer-review system, leading to heavy reviewer workloads, expertise mismatches, inconsistent evaluation standards, superficial or templated reviews, and limited accountability under compressed timelines. In response, conference organizers have introduced new policies and interventions to preserve review standards. Yet these ad-hoc changes often create further concerns and confusion about the review process, leaving how papers are ultimately accepted - and how practices evolve across years - largely opaque. We present Paper Copilot, a system that creates durable digital archives of peer reviews across a wide range of computer-science venues, an open dataset that enables researchers to study peer review at scale, and a large-scale empirical analysis of ICLR reviews spanning multiple years. By releasing both the infrastructure and the dataset, Paper Copilot supports reproducible research on the evolution of peer review. We hope these resources help the community track changes, diagnose failure modes, and inform evidence-based improvements toward a more robust, transparent, and reliable peer-review system.
Authors: Sai Suhruth Reddy Karri, Yashwanth Sai Nallapuneni, Laxmi Narasimha Reddy Mallireddy, Gopichand G
Abstract: Bias in AI systems, especially those relying on natural language data, raises ethical and practical concerns. Underrepresentation of certain groups often leads to uneven performance across demographics. Traditional fairness methods, such as pre-processing, in-processing, and post-processing, depend on protected-attribute labels, involve accuracy-fairness trade-offs, and may not generalize across datasets. To address these challenges, we propose LLM-Guided Synthetic Augmentation (LGSA), which uses large language models to generate counterfactual examples for underrepresented groups while preserving label integrity. We evaluated LGSA on a controlled dataset of short English sentences with gendered pronouns, professions, and binary classification labels. Structured prompts were used to produce gender-swapped paraphrases, followed by quality control including semantic similarity checks, attribute verification, toxicity screening, and human spot checks. The augmented dataset expanded training coverage and was used to train a classifier under consistent conditions. Results show that LGSA reduces performance disparities without compromising accuracy. The baseline model achieved 96.7 percent accuracy with a 7.2 percent gender bias gap. Simple swap augmentation reduced the gap to 0.7 percent but lowered accuracy to 95.6 percent. LGSA achieved 99.1 percent accuracy with a 1.9 percent bias gap, improving performance on female-labeled examples. These findings demonstrate that LGSA is an effective strategy for bias mitigation, enhancing subgroup balance while maintaining high task accuracy and label fidelity.
Authors: Amirhossein Mozafari, Kourosh Hashemi, Erfan Shafagh, Soroush Motamedi, Azar Taheri Tayebi, Mohammad A. Tayebi
Abstract: Healthcare fraud detection remains a critical challenge due to limited availability of labeled data, constantly evolving fraud tactics, and the high dimensionality of medical records. Traditional supervised methods are challenged by extreme label scarcity, while purely unsupervised approaches often fail to capture clinically meaningful anomalies. In this work, we introduce CleverCatch, a knowledge-guided weak supervision model designed to detect fraudulent prescription behaviors with improved accuracy and interpretability. Our approach integrates structured domain expertise into a neural architecture that aligns rules and data samples within a shared embedding space. By training encoders jointly on synthetic data representing both compliance and violation, CleverCatch learns soft rule embeddings that generalize to complex, real-world datasets. This hybrid design enables data-driven learning to be enhanced by domain-informed constraints, bridging the gap between expert heuristics and machine learning. Experiments on the large-scale real-world dataset demonstrate that CleverCatch outperforms four state-of-the-art anomaly detection baselines, yielding average improvements of 1.3\% in AUC and 3.4\% in recall. Our ablation study further highlights the complementary role of expert rules, confirming the adaptability of the framework. The results suggest that embedding expert rules into the learning process not only improves detection accuracy but also increases transparency, offering an interpretable approach for high-stakes domains such as healthcare fraud detection.
Authors: Lianlian Liu, YongKang He, Zhaojie Chu, Xiaofen Xing, Xiangmin Xu
Abstract: Generating stylized 3D human motion from speech signals presents substantial challenges, primarily due to the intricate and fine-grained relationships among speech signals, individual styles, and the corresponding body movements. Current style encoding approaches either oversimplify stylistic diversity or ignore regional motion style differences (e.g., upper vs. lower body), limiting motion realism. Additionally, motion style should dynamically adapt to changes in speech rhythm and emotion, but existing methods often overlook this. To address these issues, we propose MimicParts, a novel framework designed to enhance stylized motion generation based on part-aware style injection and part-aware denoising network. It divides the body into different regions to encode localized motion styles, enabling the model to capture fine-grained regional differences. Furthermore, our part-aware attention block allows rhythm and emotion cues to guide each body region precisely, ensuring that the generated motion aligns with variations in speech rhythm and emotional state. Experimental results show that our method outperforming existing methods showcasing naturalness and expressive 3D human motion sequences.
Authors: Inha Kang, Youngsun Lim, Seonho Lee, Jiho Choi, Junsuk Choe, Hyunjung Shim
Abstract: State-of-the-art vision-language models (VLMs) suffer from a critical failure in understanding negation, often referred to as affirmative bias. This limitation is particularly severe in described object detection (DOD) tasks. To address this, we propose two primary contributions: (1) a new dataset pipeline and (2) a novel, lightweight adaptation recipe. First, we introduce CoVAND, a dataset constructed with a systematic chain-of-thought (CoT) and VQA-based pipeline to generate high-quality, instance-grounded negation data. Second, we propose NegToMe, a novel text token merging module that directly tackles the architectural cause of affirmative bias. NegToMe fundamentally addresses the structural loss of negation cues in tokenization, grouping them with attributes into coherent semantic phrases. It maintains correct polarity at the input level, enabling robust negation understanding even with limited data. For instance, to prevent a model from treating the fragmented tokens "not" and "girl" as simply "girl", NegToMe binds them into a single token whose meaning is correctly distinguished from that of "girl" alone. This module is integrated with a parameter-efficient and strategic LoRA fine-tuning approach. Our method significantly improves performance on challenging negation benchmarks with a lowered false positive rate, boosting NMS-AP by up to +10.8 points on OVDEval and demonstrating generalization to SoTA VLMs. This work marks a crucial step forward in addressing negation understanding for real-world detection applications.
Authors: Xuanchen Wang, Heng Wang, Weidong Cai
Abstract: Music is both an auditory and an embodied phenomenon, closely linked to human motion and naturally expressed through dance. However, most existing audio representations neglect this embodied dimension, limiting their ability to capture rhythmic and structural cues that drive movement. We propose MotionBeat, a framework for motion-aligned music representation learning. MotionBeat is trained with two newly proposed objectives: the Embodied Contrastive Loss (ECL), an enhanced InfoNCE formulation with tempo-aware and beat-jitter negatives to achieve fine-grained rhythmic discrimination, and the Structural Rhythm Alignment Loss (SRAL), which ensures rhythm consistency by aligning music accents with corresponding motion events. Architecturally, MotionBeat introduces bar-equivariant phase rotations to capture cyclic rhythmic patterns and contact-guided attention to emphasize motion events synchronized with musical accents. Experiments show that MotionBeat outperforms state-of-the-art audio encoders in music-to-dance generation and transfers effectively to beat tracking, music tagging, genre and instrument classification, emotion recognition, and audio-visual retrieval. Our project demo page: https://motionbeat2025.github.io/.
Authors: Zhiyuan Zhao, Yubin Wen, Siyu Yang, Lichen Ning, Yuandong Liu, Junyu Gao
Abstract: Crowd counting is a task of estimating the number of the crowd through images, which is extremely valuable in the fields of intelligent security, urban planning, public safety management, and so on. However, the existing counting methods have some problems in practical application on embedded systems for these fields, such as excessive model parameters, abundant complex calculations, etc. The practical application of embedded systems requires the model to be real-time, which means that the model is fast enough. Considering the aforementioned problems, we design a super real-time model with a stem-encoder-decoder structure for crowd counting tasks, which achieves the fastest inference compared with state-of-the-arts. Firstly, large convolution kernels in the stem network are used to enlarge the receptive field, which effectively extracts detailed head information. Then, in the encoder part, we use conditional channel weighting and multi-branch local fusion block to merge multi-scale features with low computational consumption. This part is crucial to the super real-time performance of the model. Finally, the feature pyramid networks are added to the top of the encoder to alleviate its incomplete fusion problems. Experiments on three benchmarks show that our network is suitable for super real-time crowd counting on embedded systems, ensuring competitive accuracy. At the same time, the proposed network reasoning speed is the fastest. Specifically, the proposed network achieves 381.7 FPS on NVIDIA GTX 1080Ti and 71.9 FPS on NVIDIA Jetson TX1.
Authors: Bj\"orn Filter, Ralf M\"oller, \"Ozg\"ur L\"utf\"u \"Oz\c{c}ep
Abstract: Collaborative machine learning enables multiple data owners to jointly train models for improved predictive performance. However, ensuring incentive compatibility and fair contribution-based rewards remains a critical challenge. Prior work by Sim and colleagues (Rachel Hwee Ling Sim et al: Collaborative machine learning with incentive-aware model rewards. In: International conference on machine learning. PMLR. 2020, pp. 8927-8963) addressed this by allocating model rewards, which are non-monetary and freely replicable, based on the Shapley value of each party's data contribution, measured via information gain. In this paper, we introduce a ratio-based Shapley value that replaces the standard additive formulation with a relative contribution measure. While our overall reward framework, including the incentive definitions and model-reward setting, remains aligned with that of Sim and colleagues, the underlying value function is fundamentally different. Our alternative valuation induces a different distribution of model rewards and offers a new lens through which to analyze incentive properties. We formally define the ratio-based value and prove that it satisfies the same set of incentive conditions as the additive formulation, including adapted versions of fairness, individual rationality, and stability. Like the original approach, our method faces the same fundamental trade-offs between these incentives. Our contribution is a mathematically grounded alternative to the additive Shapley framework, potentially better suited to contexts where proportionality among contributors is more meaningful than additive differences.
Authors: Anna Hedstr\"om, Salim I. Amoukou, Tom Bewley, Saumitra Mishra, Manuela Veloso
Abstract: We introduce Mechanistic Error Reduction with Abstention (MERA), a principled framework for steering language models (LMs) to mitigate errors through selective, adaptive interventions. Unlike existing methods that rely on fixed, manually tuned steering strengths, often resulting in under or oversteering, MERA addresses these limitations by (i) optimising the intervention direction, and (ii) calibrating when, and how much to steer, thereby provably improving performance or abstaining when no confident correction is possible. Experiments across diverse datasets, and LM families demonstrate safe, effective, non-degrading error correction, and that MERA outperforms existing baselines. Moreover, MERA can be applied on top of existing steering techniques to further enhance their performance, establishing it as a general-purpose, and efficient approach to mechanistic activation steering.
Authors: Xuxin Cheng, Ke Zeng, Zhiquan Cao, Linyi Dai, Wenxuan Gao, Fei Han, Ai Jian, Feng Hong, Wenxing Hu, Zihe Huang, Dejian Kong, Jia Leng, Zhuoyuan Liao, Pei Liu, Jiaye Lin, Xing Ma, Jingqing Ruan, Jiaxing Song, Xiaoyu Tan, Ruixuan Xiao, Wenhui Yu, Wenyu Zhan, Haoxing Zhang, Chao Zhou, Hao Zhou, Shaodong Zheng, Ruinian Chen, Siyuan Chen, Ziyang Chen, Yiwen Dong, Yaoyou Fan, Yangyi Fang, Yang Gan, Shiguang Guo, Qi He, Chaowen Hu, Binghui Li, Dailin Li, Xiangyu Li, Yan Li, Chengjian Liu, Xiangfeng Liu, Jiahui Lv, Qiao Ma, Jiang Pan, Cong Qin, Chenxing Sun, Wen Sun, Zhonghui Wang, Abudukelimu Wuerkaixi, Xin Yang, Fangyi Yuan, Yawen Zhu, Tianyi Zhai, Jie Zhang, Runlai Zhang, Yao Xu, Yiran Zhao, Yifan Wang, Xunliang Cai, Yangen Hu, Cao Liu, Lu Pan, Xiaoli Wang, Bo Xiao, Wenyuan Yao, Qianlin Zhou, Benchang Zhu
Abstract: Enhancing customer experience is essential for business success, particularly as service demands grow in scale and complexity. Generative artificial intelligence and Large Language Models (LLMs) have empowered intelligent interaction systems to deliver efficient, personalized, and 24/7 support. In practice, intelligent interaction systems encounter several challenges: (1) Constructing high-quality data for cold-start training is difficult, hindering self-evolution and raising labor costs. (2) Multi-turn dialogue performance remains suboptimal due to inadequate intent understanding, rule compliance, and solution extraction. (3) Frequent evolution of business rules affects system operability and transferability, constraining low-cost expansion and adaptability. (4) Reliance on a single LLM is insufficient in complex scenarios, where the absence of multi-agent frameworks and effective collaboration undermines process completeness and service quality. (5) The open-domain nature of multi-turn dialogues, lacking unified golden answers, hampers quantitative evaluation and continuous optimization. To address these challenges, we introduce WOWService, an intelligent interaction system tailored for industrial applications. With the integration of LLMs and multi-agent architectures, WOWService enables autonomous task management and collaborative problem-solving. Specifically, WOWService focuses on core modules including data construction, general capability enhancement, business scenario adaptation, multi-agent coordination, and automated evaluation. Currently, WOWService is deployed on the Meituan App, achieving significant gains in key metrics, e.g., User Satisfaction Metric 1 (USM 1) -27.53% and User Satisfaction Metric 2 (USM 2) +25.51%, demonstrating its effectiveness in capturing user needs and advancing personalized service.
Authors: Pablo Miralles-Gonz\'alez, Javier Huertas-Tato, Alejandro Mart\'in, David Camacho
Abstract: Computational stylometry analyzes writing style through quantitative patterns in text, supporting applications from forensic tasks such as identity linking and plagiarism detection to literary attribution in the humanities. Supervised and contrastive approaches rely on data with spurious correlations and often confuse style with topic. Despite their natural use in AI-generated text detection, the CLM pre-training of modern LLMs has been scarcely leveraged for general authorship problems. We propose a novel unsupervised approach based on this extensive pre-training and the in-context learning capabilities of LLMs, employing the log-probabilities of an LLM to measure style transferability from one text to another. Our method significantly outperforms LLM prompting approaches of comparable scale and achieves higher accuracy than contrastively trained baselines when controlling for topical correlations. Moreover, performance scales fairly consistently with the size of the base model and, in the case of authorship verification, with an additional mechanism that increases test-time computation; enabling flexible trade-offs between computational cost and accuracy.
Authors: Eun Woo Im, Muhammad Kashif Ali, Vivek Gupta
Abstract: Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal capabilities, but they inherit the tendency to hallucinate from their underlying language models. While visual contrastive decoding has been proposed to mitigate this issue, existing methods often apply generic visual augmentations that disregard the specific context provided by the text query, limiting their effectiveness. This study introduces a novel training-free decoding strategy that addresses these limitations, featuring two key contributions. First, a self-augmentation prompting strategy that leverages the intrinsic knowledge of the model to dynamically align semantics between the query and the visual augmentation. Second, an adaptive thresholding algorithm that adaptively adjusts next token candidate size based on the output sparsity, utilizing full information from the logit distribution. Extensive experiments across four LVLMs and seven benchmarks demonstrate that the proposed decoding significantly enhances factual consistency compared to state-of-the-art decoding methods. This work highlights the importance of integrating query-dependent augmentation and entropy-aware decoding for improving effective generation of LVLMs.
Authors: Baogang Song, Dongdong Zhao, Jianwen Xiang, Qiben Xu, Zizhuo Yu
Abstract: Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack strategies still leave persistent traces that may be detected through static analysis. In this work, we introduce the first paradigm of revocable backdoor attacks, where the backdoor can be proactively and thoroughly removed after the attack objective is achieved. We formulate the trigger optimization in revocable backdoor attacks as a bilevel optimization problem: by simulating both backdoor injection and unlearning processes, the trigger generator is optimized to achieve a high attack success rate (ASR) while ensuring that the backdoor can be easily erased through unlearning. To mitigate the optimization conflict between injection and removal objectives, we employ a deterministic partition of poisoning and unlearning samples to reduce sampling-induced variance, and further apply the Projected Conflicting Gradient (PCGrad) technique to resolve the remaining gradient conflicts. Experiments on CIFAR-10 and ImageNet demonstrate that our method maintains ASR comparable to state-of-the-art backdoor attacks, while enabling effective removal of backdoor behavior after unlearning. This work opens a new direction for backdoor attack research and presents new challenges for the security of machine learning systems.
Authors: Nicolas Menet, Aleksandar Terzi\'c, Andreas Krause, Abbas Rahimi
Abstract: Bayesian optimization in large unstructured discrete spaces is often hindered by the computational cost of maximizing acquisition functions due to the absence of gradients. We propose a scalable alternative based on Thompson sampling that eliminates the need for acquisition function maximization by directly parameterizing the probability that a candidate yields the maximum reward. Our approach, Thompson Sampling via Fine-Tuning (ToSFiT) leverages the prior knowledge embedded in prompt-conditioned large language models, and incrementally adapts them toward the posterior. Theoretically, we derive a novel regret bound for a variational formulation of Thompson Sampling that matches the strong guarantees of its standard counterpart. Our analysis reveals the critical role of careful adaptation to the posterior probability of maximality--a principle that underpins our ToSFiT algorithm. Empirically, we validate our method on three diverse tasks: FAQ response refinement, thermally stable protein search, and quantum circuit design. We demonstrate that online fine-tuning significantly improves sample efficiency, with negligible impact on computational efficiency.
Authors: Shota Takayama, Katsuhide Fujita
Abstract: Multi-agent reinforcement learning focuses on training the behaviors of multiple learning agents that coexist in a shared environment. Recently, MARL models, such as the Multi-Agent Transformer (MAT) and ACtion dEpendent deep Q-learning (ACE), have significantly improved performance by leveraging sequential decision-making processes. Although these models can enhance performance, they do not explicitly consider the importance of the order in which agents make decisions. In this paper, we propose an Agent Order of Action Decisions-MAT (AOAD-MAT), a novel MAT model that considers the order in which agents make decisions. The proposed model explicitly incorporates the sequence of action decisions into the learning process, allowing the model to learn and predict the optimal order of agent actions. The AOAD-MAT model leverages a Transformer-based actor-critic architecture that dynamically adjusts the sequence of agent actions. To achieve this, we introduce a novel MARL architecture that cooperates with a subtask focused on predicting the next agent to act, integrated into a Proximal Policy Optimization based loss function to synergistically maximize the advantage of the sequential decision-making. The proposed method was validated through extensive experiments on the StarCraft Multi-Agent Challenge and Multi-Agent MuJoCo benchmarks. The experimental results show that the proposed AOAD-MAT model outperforms existing MAT and other baseline models, demonstrating the effectiveness of adjusting the AOAD order in MARL.
Authors: Karthik Avinash, Nikhil Pareek, Rishav Hada
Abstract: The increasing deployment of Large Language Models (LLMs) across enterprise and mission-critical domains has underscored the urgent need for robust guardrailing systems that ensure safety, reliability, and compliance. Existing solutions often struggle with real-time oversight, multi-modal data handling, and explainability -- limitations that hinder their adoption in regulated environments. Existing guardrails largely operate in isolation, focused on text alone making them inadequate for multi-modal, production-scale environments. We introduce Protect, natively multi-modal guardrailing model designed to operate seamlessly across text, image, and audio inputs, designed for enterprise-grade deployment. Protect integrates fine-tuned, category-specific adapters trained via Low-Rank Adaptation (LoRA) on an extensive, multi-modal dataset covering four safety dimensions: toxicity, sexism, data privacy, and prompt injection. Our teacher-assisted annotation pipeline leverages reasoning and explanation traces to generate high-fidelity, context-aware labels across modalities. Experimental results demonstrate state-of-the-art performance across all safety dimensions, surpassing existing open and proprietary models such as WildGuard, LlamaGuard-4, and GPT-4.1. Protect establishes a strong foundation for trustworthy, auditable, and production-ready safety systems capable of operating across text, image, and audio modalities.
Authors: Hamdan Al-Ali, Ali Reza Ghavamipour, Tommaso Caselli, Fatih Turkmen, Zeerak Talat, Hanan Aldarmaki
Abstract: Federated learning is a common method for privacy-preserving training of machine learning models. In this paper, we analyze the vulnerability of ASR models to attribute inference attacks in the federated setting. We test a non-parametric white-box attack method under a passive threat model on three ASR models: Wav2Vec2, HuBERT, and Whisper. The attack operates solely on weight differentials without access to raw speech from target speakers. We demonstrate attack feasibility on sensitive demographic and clinical attributes: gender, age, accent, emotion, and dysarthria. Our findings indicate that attributes that are underrepresented or absent in the pre-training data are more vulnerable to such inference attacks. In particular, information about accents can be reliably inferred from all models. Our findings expose previously undocumented vulnerabilities in federated ASR models and offer insights towards improved security.
Authors: Shingo Ayabe, Hiroshi Kera, Kazuhiko Kawamoto
Abstract: Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-space perturbations such as actuator faults. This study introduces an offline-to-online framework that trains policies on clean data and then performs adversarial fine-tuning, where perturbations are injected into executed actions to induce compensatory behavior and improve resilience. A performance-aware curriculum further adjusts the perturbation probability during training via an exponential-moving-average signal, balancing robustness and stability throughout the learning process. Experiments on continuous-control locomotion tasks demonstrate that the proposed method consistently improves robustness over offline-only baselines and converges faster than training from scratch. Matching the fine-tuning and evaluation conditions yields the strongest robustness to action-space perturbations, while the adaptive curriculum strategy mitigates the degradation of nominal performance observed with the linear curriculum strategy. Overall, the results show that adversarial fine-tuning enables adaptive and robust control under uncertain environments, bridging the gap between offline efficiency and online adaptability.
Authors: Yisen Wang, Yichuan Mo, Hongjun Wang, Junyi Li, Zhouchen Lin
Abstract: Despite the rapid progress of neural networks, they remain highly vulnerable to adversarial examples, for which adversarial training (AT) is currently the most effective defense. While AT has been extensively studied, its practical applications expose two major limitations: natural accuracy tends to degrade significantly compared with standard training, and robustness does not transfer well across attacks crafted under different norm constraints. Unlike prior works that attempt to address only one issue within a single network, we propose to partition the overall generalization goal into multiple sub-tasks, each assigned to a dedicated base learner. By specializing in its designated objective, each base learner quickly becomes an expert in its field. In the later stages of training, we interpolate their parameters to form a knowledgeable global learner, while periodically redistributing the global parameters back to the base learners to prevent their optimization trajectories from drifting too far from the shared target. We term this framework Generalist and introduce three variants tailored to different application scenarios. Both theoretical analysis and extensive experiments demonstrate that Generalist achieves lower generalization error and significantly alleviates the trade-off problems compared with baseline methods. Our results suggest that Generalist provides a promising step toward developing fully robust classifiers in the future.
Authors: MingZe Tang, Jubal Chandy Jacob
Abstract: Recent Vision-Language Models (VLMs) enable zero-shot classification by aligning images and text in a shared space, a promising approach for data-scarce conditions. However, the influence of prompt design on recognizing visually similar categories, such as human postures, is not well understood. This study investigates how prompt specificity affects the zero-shot classification of sitting, standing, and walking/running on a small, 285-image COCO-derived dataset. A suite of modern VLMs, including OpenCLIP, MetaCLIP 2, and SigLip, were evaluated using a three-tiered prompt design that systematically increases linguistic detail. Our findings reveal a compelling, counter-intuitive trend: for the highest-performing models (MetaCLIP 2 and OpenCLIP), the simplest, most basic prompts consistently achieve the best results. Adding descriptive detail significantly degrades performance for instance, MetaCLIP 2's multi-class accuracy drops from 68.8\% to 55.1\% a phenomenon we term "prompt overfitting". Conversely, the lower-performing SigLip model shows improved classification on ambiguous classes when given more descriptive, body-cue-based prompts.
Authors: Weishi Wang, Hengchang Hu, Zhijie Zhang, Zhaochen Li, Hongxin Shao, Daniel Dahlmeier
Abstract: Document AI (DAI) has emerged as a vital application area, and is significantly transformed by the advent of large language models (LLMs). While earlier approaches relied on encoder-decoder architectures, decoder-only LLMs have revolutionized DAI, bringing remarkable advancements in understanding and generation. This survey provides a comprehensive overview of DAI's evolution, highlighting current research attempts and future prospects of LLMs in this field. We explore key advancements and challenges in multimodal, multilingual, and retrieval-augmented DAI, while also suggesting future research directions, including agent-based approaches and document-specific foundation models. This paper aims to provide a structured analysis of the state-of-the-art in DAI and its implications for both academic and practical applications.
Authors: Nikita Kachaev, Daniil Zelezetsky, Egor Cherepanov, Alexey K. Kovelev, Aleksandr I. Panov
Abstract: Despite their effectiveness and popularity in offline or model-based reinforcement learning (RL), transformers remain underexplored in online model-free RL due to their sensitivity to training setups and model design decisions such as how to structure the policy and value networks, share components, or handle temporal information. In this paper, we show that transformers can be strong baselines for continuous control in online model-free RL. We investigate key design questions: how to condition inputs, share components between actor and critic, and slice sequential data for training. Our experiments reveal stable architectural and training strategies enabling competitive performance across fully and partially observable tasks, and in both vector- and image-based settings. These findings offer practical guidance for applying transformers in online RL.
Authors: Jiin Park, Misuk Kim
Abstract: Recent attempts to integrate large language models (LLMs) into recommender systems have gained momentum, but most remain limited to simple text generation or static prompt-based inference, failing to capture the complexity of user preferences and real-world interactions. This study proposes the Multi-Aspect Driven LLM Agent MADRec, an autonomous LLM-based recommender that constructs user and item profiles by unsupervised extraction of multi-aspect information from reviews and performs direct recommendation, sequential recommendation, and explanation generation. MADRec generates structured profiles via aspect-category-based summarization and applies Re-Ranking to construct high-density inputs. When the ground-truth item is missing from the output, the Self-Feedback mechanism dynamically adjusts the inference criteria. Experiments across multiple domains show that MADRec outperforms traditional and LLM-based baselines in both precision and explainability, with human evaluation further confirming the persuasiveness of the generated explanations.
Authors: Kei Itoh
Abstract: This study presents an inter-universal mathematical-logical framework constructed upon the minimal axiom Cogito, ergo sum (CES), integrating the Intermediate Meta-Universe (IMU) and the Hierarchical State Grid (HSG). The CES defines existence as a reflexive correspondence --'to be' and 'to be sayable'--and positions any formal system, including ZFC or HoTT, as an attachable extension atop this minimal structure. The IMU functions as a registry of axiomatic dependencies that connect heterogeneous theories, employing the Institution-theoretic framework to ensure coherent inter-theoretical linkages. The HSG concretizes these ideas through categorical construction, defined by three orthogonal axes: the state-depth axis, the mapping-hierarchy axis, and the temporal axis incorporating the principle of 'no future reference.' Through these, the identity of 'definition = state' is formally established as a categorical property. Extending this structure to biological systems, the neural system is implemented as a 0-3D complex of neuron-function fields on the HSG, while its categorical extensions via fiberization over the material base enable the parallel integration of multiple physiological universes-neural, endocrine, learning, genetic, and input/output systems-into a coherent adjoint ensemble. Within this framework, human behavior and cognition emerge as temporal compositions of inter-universal algorithms constrained by the material base. Finally, by contrasting human cognition, which relies on external CES, with machine existence, this study introduces the concept of internal CES, wherein a machine grounds its own logic upon the factuality of its operation. This internal self-axiomatization establishes a continuous bridge between philosophical ontology and engineering implementation, providing a new foundation for the autonomous and self-defining existence of artificial intelligence.
Authors: Jingkai Ying, Zhiyuan Qi, Yulong Feng, Zhijin Qin, Zhu Han, Rahim Tafazolli, Yonina C. Eldar
Abstract: Holographic video communication is considered a paradigm shift in visual communications, becoming increasingly popular for its ability to offer immersive experiences. This article provides an overview of holographic video communication and outlines the requirements of a holographic video communication system. Particularly, following a brief review of semantic com- munication, an architecture for a semantic-enabled holographic video communication system is presented. Key technologies, including semantic sampling, joint semantic-channel coding, and semantic-aware transmission, are designed based on the proposed architecture. Two related use cases are presented to demonstrate the performance gain of the proposed methods. Finally, potential research topics are discussed to pave the way for the realization of semantic-enabled holographic video communications.
Authors: Jiaxing Deng, Junbiao Pang, Zhicheng Wang, Haitao Yu
Abstract: Parking spots are essential components, providing vital mobile resources for residents in a city. Accurate Global Positioning System (GPS) points of parking spots are the core data for subsequent applications,e.g., parking management, parking policy, and urban development. However, high-rise buildings tend to cause GPS points to drift from the actual locations of parking spots; besides, the standard lower-cost GPS equipment itself has a certain location error. Therefore, it is a non-trivial task to correct a few wrong GPS points from a large number of parking spots in an unsupervised approach. In this paper, motivated by the physical constraints of parking spots (i.e., parking spots are parallel to the sides of roads), we propose an unsupervised low-rank method to effectively rectify errors in GPS points and further align them to the parking spots in a unified framework. The proposed unconventional rectification and alignment method is simple and yet effective for any type of GPS point errors. Extensive experiments demonstrate the superiority of the proposed method to solve a practical problem. The data set and the code are publicly accessible at:https://github.com/pangjunbiao/ITS-Parking-spots-Dataset.
URLs: https://github.com/pangjunbiao/ITS-Parking-spots-Dataset.
Authors: Nico Pelleriti, Christoph Spiegel, Shiwei Liu, David Mart\'inez-Rubio, Max Zimmer, Sebastian Pokutta
Abstract: Certifying nonnegativity of polynomials is a well-known NP-hard problem with direct applications spanning non-convex optimization, control, robotics, and beyond. A sufficient condition for nonnegativity is the Sum of Squares (SOS) property, i.e., it can be written as a sum of squares of other polynomials. In practice, however, certifying the SOS criterion remains computationally expensive and often involves solving a Semidefinite Program (SDP), whose dimensionality grows quadratically in the size of the monomial basis of the SOS expression; hence, various methods to reduce the size of the monomial basis have been proposed. In this work, we introduce the first learning-augmented algorithm to certify the SOS criterion. To this end, we train a Transformer model that predicts an almost-minimal monomial basis for a given polynomial, thereby drastically reducing the size of the corresponding SDP. Our overall methodology comprises three key components: efficient training dataset generation of over 100 million SOS polynomials, design and training of the corresponding Transformer architecture, and a systematic fallback mechanism to ensure correct termination, which we analyze theoretically. We validate our approach on over 200 benchmark datasets, achieving speedups of over $100\times$ compared to state-of-the-art solvers and enabling the solution of instances where competing approaches fail. Our findings provide novel insights towards transforming the practical scalability of SOS programming.
Authors: Tommaso Bonomo, Luca Gioffr\'e, Roberto Navigli
Abstract: Question Answering (QA) on narrative text poses a unique challenge to current systems, requiring a deep understanding of long, complex documents. However, the reliability of NarrativeQA, the most widely used benchmark in this domain, is hindered by noisy documents and flawed QA pairs. In this work, we introduce LiteraryQA, a high-quality subset of NarrativeQA focused on literary works. Using a human- and LLM-validated pipeline, we identify and correct low-quality QA samples while removing extraneous text from source documents. We then carry out a meta-evaluation of automatic metrics to clarify how systems should be evaluated on LiteraryQA. This analysis reveals that all n-gram-based metrics have a low system-level correlation to human judgment, while LLM-as-a-Judge evaluations, even with small open-weight models, can strongly agree with the ranking identified by humans. Finally, we benchmark a set of long-context LLMs on LiteraryQA. We release our code and data at https://github.com/SapienzaNLP/LiteraryQA.
Authors: Zexin Wang, Lin Shi, Haoyu Wu, Junru Luo, Xiangzeng Kong, Jun Qi
Abstract: Epilepsy is a prevalent neurological disorder marked by sudden, brief episodes of excessive neuronal activity caused by abnormal electrical discharges, which may lead to some mental disorders. Most existing deep learning methods for epilepsy detection rely solely on unimodal EEG signals, neglecting the potential benefits of multimodal information. To address this, we propose a novel multimodal model, DistilCLIP-EEG, based on the CLIP framework, which integrates both EEG signals and text descriptions to capture comprehensive features of epileptic seizures. The model involves an EEG encoder based on the Conformer architecture as a text encoder, the proposed Learnable BERT (BERT-LP) as prompt learning within the encoders. Both operate in a shared latent space for effective cross-modal representation learning. To enhance efficiency and adaptability, we introduce a knowledge distillation method where the trained DistilCLIP-EEG serves as a teacher to guide a more compact student model to reduce training complexity and time. On the TUSZ, AUBMC, and CHB-MIT datasets, both the teacher and student models achieved accuracy rates exceeding 97%. Across all datasets, the F1-scores were consistently above 0.94, demonstrating the robustness and reliability of the proposed framework. Moreover, the student model's parameter count and model size are approximately 58.1% of those of the teacher model, significantly reducing model complexity and storage requirements while maintaining high performance. These results highlight the potential of our proposed model for EEG-based epilepsy detection and establish a solid foundation for deploying lightweight models in resource-constrained settings.
Authors: Xiaozhe Li, TianYi Lyu, Siyi Yang, Yuxi Gong, Yizhao Yang, Jinxuan Huang, Ligao Zhang, Zhuoyi Huang, Qingwen Liu
Abstract: Understanding human intent is a complex, high-level task for large language models (LLMs), requiring analytical reasoning, contextual interpretation, dynamic information aggregation, and decision-making under uncertainty. Real-world public discussions, such as consumer product discussions, are rarely linear or involve a single user. Instead, they are characterized by interwoven and often conflicting perspectives, divergent concerns, goals, emotional tendencies, as well as implicit assumptions and background knowledge about usage scenarios. To accurately understand such explicit public intent, an LLM must go beyond parsing individual sentences; it must integrate multi-source signals, reason over inconsistencies, and adapt to evolving discourse, similar to how experts in fields like politics, economics, or finance approach complex, uncertain environments. Despite the importance of this capability, no large-scale benchmark currently exists for evaluating LLMs on real-world human intent understanding, primarily due to the challenges of collecting real-world public discussion data and constructing a robust evaluation pipeline. To bridge this gap, we introduce \bench, the first dynamic, live evaluation benchmark specifically designed for intent understanding, particularly in the consumer domain. \bench is the largest and most diverse benchmark of its kind, supporting real-time updates while preventing data contamination through an automated curation pipeline.
Authors: Shujun Xia, Haokun Lin, Yichen Wu, Yinan Zhou, Zixuan Li, Zhongwei Wan, Xingrun Xing, Yefeng Zheng, Xiang Li, Caifeng Shan, Zhenan Sun, Quanzheng Li
Abstract: LLMs hold great promise for healthcare applications, but the rapid evolution of medical knowledge and errors in training data often cause them to generate outdated or inaccurate information, limiting their applicability in high-stakes clinical practice. Model editing has emerged as a potential remedy without full retraining. While parameter-based editing often compromises locality and is thus ill-suited for the medical domain, retrieval-based editing offers a more viable alternative. However, it still faces two critical challenges: (1) representation overlap within the medical knowledge space often causes inaccurate retrieval and reduces editing accuracy; (2) existing methods are restricted to single-sample edits, while batch-editing remains largely unexplored despite its importance for real-world medical applications. To address these challenges, we first construct MedVersa, \hk{an enhanced benchmark with broader coverage of medical subjects, designed to evaluate both single and batch edits under strict locality constraints}. We then propose MedREK, a retrieval-based editing framework that integrates a shared query-key module for precise matching with an attention-based prompt encoder for informative guidance. Experimental results on various medical benchmarks demonstrate that our MedREK achieves superior performance across different core metrics and provides the first validated solution for batch-editing in medical LLMs. Our code and dataset are available at https://github.com/mylittleriver/MedREK.
Authors: Yulian Wu, Rushil Thareja, Praneeth Vepakomma, Francesco Orabona
Abstract: In this paper, we study the offline and online settings of reinforcement learning from human feedback (RLHF) with KL-regularization -- a widely used objective function in large language model alignment -- under the $\epsilon$ local differential privacy ($\epsilon$-LDP) model on the label of the human preference. In the offline setting, we design an algorithm based on the principle of pessimism and derive a new suboptimality gap of $\tilde{O}(1/[(e^\epsilon-1)^2 n])$ on the KL-regularized objective under single-policy concentrability. We also prove its optimality by providing a matching lower bound where $n$ is the sample size. In the online setting, we are the first one to theoretically investigate the problem of KL-regularized RLHF with LDP. We design an optimism-based algorithm and derive a logarithmic regret bound of $O(d_{\mathcal{F}}\log (N_{\mathcal{F}}\cdot T) /(e^\epsilon-1)^2 )$, where $T$ is the total time step, $N_{\mathcal{F}}$ is cardinality of the reward function space $\mathcal{F}$ and $d_{\mathcal{F}}$ is a variant of eluder dimension for RLHF. As a by-product of our analysis, our results also imply the first analysis for online KL-regularized RLHF without privacy. We implement our algorithm in the offline setting to verify our theoretical results and release our open source code at: https://github.com/rushil-thareja/PPKL-RLHF-Official.
Authors: Tiancheng Gu, Kaicheng Yang, Kaichen Zhang, Xiang An, Ziyong Feng, Yueyi Zhang, Weidong Cai, Jiankang Deng, Lidong Bing
Abstract: Universal multimodal embedding models are foundational to various tasks. Existing approaches typically employ in-batch negative mining by measuring the similarity of query-candidate pairs. However, these methods often struggle to capture subtle semantic differences among candidates and lack diversity in negative samples. Moreover, the embeddings exhibit limited discriminative ability in distinguishing false and hard negatives. In this paper, we leverage the advanced understanding capabilities of MLLMs to enhance representation learning and present a novel Universal Multimodal Embedding (UniME-V2) model. Our approach first constructs a potential hard negative set through global retrieval. We then introduce the MLLM-as-a-Judge mechanism, which utilizes MLLMs to assess the semantic alignment of query-candidate pairs and generate soft semantic matching scores. These scores serve as a foundation for hard negative mining, mitigating the impact of false negatives and enabling the identification of diverse, high-quality hard negatives. Furthermore, the semantic matching scores are used as soft labels to mitigate the rigid one-to-one mapping constraint. By aligning the similarity matrix with the soft semantic matching score matrix, the model learns semantic distinctions among candidates, significantly enhancing its discriminative capacity. To further improve performance, we propose UniME-V2-Reranker, a reranking model trained on our mined hard negatives through a joint pairwise and listwise optimization approach. We conduct comprehensive experiments on the MMEB benchmark and multiple retrieval tasks, demonstrating that our method achieves state-of-the-art performance on average across all tasks.
Authors: Timo Thun, Rory Conlin, Dario Panici, Daniel B\"ockenhoff
Abstract: Numerical computation of the ideal Magnetohydrodynamic (MHD) equilibrium magnetic field is at the base of stellarator optimisation and provides the starting point for solving more sophisticated Partial Differential Equations (PDEs) like transport or turbulence models. Conventional approaches solve for a single stationary point of the ideal MHD equations, which is fully defined by three invariants and the numerical scheme employed by the solver. We present the first numerical approach that can solve for a continuous distribution of equilibria with fixed boundary and rotational transform, varying only the pressure invariant. This approach minimises the force residual by optimising parameters of multilayer perceptrons (MLP) that map from a scalar pressure multiplier to the Fourier Zernike basis as implemented in the modern stellarator equilibrium solver DESC.
Authors: Donald Shenaj, Ondrej Bohdal, Taha Ceritli, Mete Ozay, Pietro Zanuttigh, Umberto Michieli
Abstract: On-device deployment of Large Language Models (LLMs) frequently leverages Low-Rank Adapters (LoRAs) to support diverse downstream tasks under tight resource constraints. To address the limited storage capacity of mobile devices, recent works have explored model merging techniques to fuse multiple LoRAs into a single one. In practice, however, LoRAs are often delivered incrementally, as users request support for new tasks (e.g., novel problem types or languages). This scenario introduces a new challenge: on-device online continual merging, where the objective is to incorporate new LoRAs while preserving the performance on previously supported tasks. In this paper, we propose a data-free and computationally efficient strategy for selecting and merging LoRAs when a new one becomes available, assuming the device can store only a limited number of adapters. Extensive experiments across real-world tasks demonstrate the superiority of our approach compared to alternative strategies while adhering to the storage budget and compute limitations of on-device settings.
Authors: Avihay Cohen
Abstract: Large Language Model (LLM) based agents integrated into web browsers (often called agentic AI browsers) offer powerful automation of web tasks. However, they are vulnerable to indirect prompt injection attacks, where malicious instructions hidden in a webpage deceive the agent into unwanted actions. These attacks can bypass traditional web security boundaries, as the AI agent operates with the user privileges across sites. In this paper, we present a novel fuzzing framework that runs entirely in the browser and is guided by an LLM to automatically discover such prompt injection vulnerabilities in real time.
Authors: David Freire-Obreg\'on, Jos\'e Salas-C\'aceres, Javier Lorenzo-Navarro, Oliverio J. Santana, Daniel Hern\'andez-Sosa, Modesto Castrill\'on-Santana
Abstract: Facial expression recognition (FER) must remain robust under both cultural variation and perceptually degraded visual conditions, yet most existing evaluations assume homogeneous data and high-quality imagery. We introduce an agent-based, streaming benchmark that reveals how cross-cultural composition and progressive blurring interact to shape face recognition robustness. Each agent operates in a frozen CLIP feature space with a lightweight residual adapter trained online at sigma=0 and fixed during testing. Agents move and interact on a 5x5 lattice, while the environment provides inputs with sigma-scheduled Gaussian blur. We examine monocultural populations (Western-only, Asian-only) and mixed environments with balanced (5/5) and imbalanced (8/2, 2/8) compositions, as well as different spatial contact structures. Results show clear asymmetric degradation curves between cultural groups: JAFFE (Asian) populations maintain higher performance at low blur but exhibit sharper drops at intermediate stages, whereas KDEF (Western) populations degrade more uniformly. Mixed populations exhibit intermediate patterns, with balanced mixtures mitigating early degradation, but imbalanced settings amplify majority-group weaknesses under high blur. These findings quantify how cultural composition and interaction structure influence the robustness of FER as perceptual conditions deteriorate.
Authors: Peng Di, Faqiang Chen, Xiao Bai, Hongjun Yang, Qingfeng Li, Ganglin Wei, Jian Mou, Feng Shi, Keting Chen, Peng Tang, Zhitao Shen, Zheng Li, Wenhui Shi, Junwei Guo, Hang Yu
Abstract: The escalating complexity of modern software imposes an unsustainable operational burden on Site Reliability Engineering (SRE) teams, demanding AI-driven automation that can emulate expert diagnostic reasoning. Existing solutions, from traditional AI methods to general-purpose multi-agent systems, fall short: they either lack deep causal reasoning or are not tailored for the specialized, investigative workflows unique to SRE. To address this gap, we present OpenDerisk, a specialized, open-source multi-agent framework architected for SRE. OpenDerisk integrates a diagnostic-native collaboration model, a pluggable reasoning engine, a knowledge engine, and a standardized protocol (MCP) to enable specialist agents to collectively solve complex, multi-domain problems. Our comprehensive evaluation demonstrates that OpenDerisk significantly outperforms state-of-the-art baselines in both accuracy and efficiency. This effectiveness is validated by its large-scale production deployment at Ant Group, where it serves over 3,000 daily users across diverse scenarios, confirming its industrial-grade scalability and practical impact. OpenDerisk is open source and available at https://github.com/derisk-ai/OpenDerisk/
Authors: Pasin Buakhaw, Kun Kerdthaisong, Phuree Phenhiran, Pitikorn Khlaisamniang, Supasate Vorathammathorn, Piyalitt Ittichaiwong, Nutchanon Yongsatianchot
Abstract: The emergence of large language models (LLMs) has opened new opportunities for cre- ating dynamic non-player characters (NPCs) in gaming environments, enabling both func- tional task execution and persona-consistent dialogue generation. In this paper, we (Tu_Character_lab) report our participation in the Commonsense Persona-Grounded Dialogue Challenge (CPDC) 2025 Round 2, which eval- uates agents across three tracks: task-oriented dialogue, context-aware dialogue, and their integration. Our approach combines two complementary strategies: (i) lightweight prompting techniques in the API track, including a Deflanderization prompting method to suppress excessive role-play and improve task fidelity, and (ii) fine-tuned large models in the GPU track, leveraging Qwen3-14B with supervisedfinetuning (SFT) and Low-Rank Adaptation(LoRA). Our best submissions ranked 2nd on Task 1, 2nd on Task 3 (API track), and 4th on Task 3 (GPU track).
Authors: Nicola Fabiano
Abstract: The European Union's Artificial Intelligence Act (Regulation (EU) 2024/1689) establishes the world's first comprehensive regulatory framework for AI systems through a sophisticated ecosystem of interconnected subjects defined in Article 3. This paper provides a structured examination of the six main categories of actors - providers, deployers, authorized representatives, importers, distributors, and product manufacturers - collectively referred to as "operators" within the regulation. Through examination of these Article 3 definitions and their elaboration across the regulation's 113 articles, 180 recitals, and 13 annexes, we map the complete governance structure and analyze how the AI Act regulates these subjects. Our analysis reveals critical transformation mechanisms whereby subjects can assume different roles under specific conditions, particularly through Article 25 provisions ensuring accountability follows control. We identify how obligations cascade through the supply chain via mandatory information flows and cooperation requirements, creating a distributed yet coordinated governance system. The findings demonstrate how the regulation balances innovation with the protection of fundamental rights through risk-based obligations that scale with the capabilities and deployment contexts of AI systems, providing essential guidance for stakeholders implementing the AI Act's requirements.
Authors: Yuxiang Huang, Chaojun Xiao, Xu Han, Zhiyuan Liu
Abstract: Trainable sparse attention has emerged as a promising solution to address the decoding efficiency bottleneck of LLMs in long-context processing, significantly saving memory accesses while minimally impacting task performance. However, existing sparse attention methods leave a crucial limitation unresolved: the size of the key-value (KV) cache remains unreduced, which constrains on-GPU batch sizes and throttles decoding throughput, especially in large-scale batched inference. In this paper, we show that trainable sparse attention naturally exhibits strong locality in token selection across adjacent decoding steps, thereby enabling KV cache offloading without altering the underlying attention computation. However, the inherent locality remains insufficient to achieve efficient offloading, as the transfer of selected KV pairs between the CPU and GPU continues to dominate the overall decoding cost. Building on this insight, we present NOSA, a trainable sparse attention framework designed to natively support KV cache offloading. NOSA introduces explicit locality constraints by decomposing token selection into query-aware and query-agnostic components, thereby reducing KV transfers while preserving the same attention computation as used during training. We pretrain a 1B-parameter model with NOSA and conduct extensive benchmarks, showing that it preserves near-lossless performance while achieving up to a 2.3x improvement in decoding throughput compared with the vanilla trainable sparse attention baseline (InfLLM-V2).
Authors: Pablo Barcel\'o, Fabian Jogl, Alexander Kozachinskiy, Matthias Lanzinger, Stefan Neumann, Crist\'obal Rojas
Abstract: We propose EB-1WL, an edge-based color-refinement test, and a corresponding GNN architecture, EB-GNN. Our architecture is inspired by a classic triangle counting algorithm by Chiba and Nishizeki, and explicitly uses triangles during message passing. We achieve the following results: (1)~EB-1WL is significantly more expressive than 1-WL. Further, we provide a complete logical characterization of EB-1WL based on first-order logic, and matching distinguishability results based on homomorphism counting. (2)~In an important distinction from previous proposals for more expressive GNN architectures, EB-1WL and EB-GNN require near-linear time and memory on practical graph learning tasks. (3)~Empirically, we show that EB-GNN is a highly-efficient general-purpose architecture: It substantially outperforms simple MPNNs, and remains competitive with task-specialized GNNs while being significantly more computationally efficient.
Authors: Yuexing Hao, Yue Huang, Haoran Zhang, Chenyang Zhao, Zhenwen Liang, Paul Pu Liang, Yue Zhao, Lichao Sun, Saleh Kalantari, Xiangliang Zhang, Marzyeh Ghassemi
Abstract: Cutting-edge research in Artificial Intelligence (AI) requires considerable resources, including Graphics Processing Units (GPUs), data, and human resources. In this paper, we evaluate of the relationship between these resources and the scientific advancement of foundation models (FM). We reviewed 6517 FM papers published between 2022 to 2024, and surveyed 229 first-authors to the impact of computing resources on scientific output. We find that increased computing is correlated with national funding allocations and citations, but our findings don't observe the strong correlations with research environment (academic or industrial), domain, or study methodology. We advise that individuals and institutions focus on creating shared and affordable computing opportunities to lower the entry barrier for under-resourced researchers. These steps can help expand participation in FM research, foster diversity of ideas and contributors, and sustain innovation and progress in AI. The data will be available at: https://mit-calc.csail.mit.edu/
Authors: Stefan Lenz, Lakisha Ortiz Rosario, Georg Vollmar, Arsenij Ustjanzew, Fatma Alickovic, Thomas Kindler, Torsten Panholzer
Abstract: Accurate coding of tumor diagnoses with ICD-10-GM and ICD-O-3 is essential for structured cancer documentation in Germany. Smaller open-weight LLMs are appealing for privacy-preserving automation but often struggle with coding accuracy in German-language contexts. This study investigates whether instruction-based fine-tuning on public datasets improves the coding accuracy of open-weight LLMs for German tumor diagnosis texts. The evaluation uses coded diagnoses from the local tumor documentation system as test data. In a systematic data quality assessment, the upper limit for ICD-10 coding performance was estimated at 60-79% for exact and 81-94% for partial (three-character codes only) derivation. As training data, over 500,000 question-answer pairs were created based on the ICD-10-GM, ICD-O-3, and OPS catalogues. Eight open-weight models from the Qwen, Llama, and Mistral families (7-70 B parameters) were fine-tuned. ICD-10-GM accuracy rose from 1.4-24% to 41-58%, and partial accuracy from 31-74% to 73-83%. The accuracy of ICD-O-3 topography coding also improved but started and remained considerably lower with an exact accuracy of 22-40% and a partial accuracy of 56-67% after fine-tuning. Malformed code outputs dropped to 0% for all models. Tumor-diagnosis recognition reached 99%. Accuracy correlated positively with model size, but gaps between small and large models narrowed after fine-tuning. The reasoning mode in Qwen3 generally yielded a lower performance than fine-tuning and was over 100 times slower. Our findings highlight the potential of leveraging public catalogues to build instruction datasets that improve LLMs in medical documentation tasks. The complete training dataset and the best-performing checkpoints of the fine-tuned models are available from https://huggingface.co/datasets/stefan-m-lenz/ICDOPS-QA-2024.
URLs: https://huggingface.co/datasets/stefan-m-lenz/ICDOPS-QA-2024.
Authors: Santiago Cuervo, Skyler Seto, Maureen de Seyssel, Richard He Bai, Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly, Zakaria Aldeneh
Abstract: Large Language Models (LLMs) can be adapted to extend their text capabilities to speech inputs. However, these speech-adapted LLMs consistently underperform their text-based counterparts--and even cascaded pipelines--on language understanding tasks. We term this shortfall the text-speech understanding gap: the performance drop observed when a speech-adapted LLM processes spoken inputs relative to when the original text-based LLM processes the equivalent text. Recent approaches to narrowing this gap either rely on large-scale speech synthesis of text corpora, which is costly and heavily dependent on synthetic data, or on large-scale proprietary speech datasets, which are not reproducible. As a result, there remains a need for more data-efficient alternatives for closing the text-speech understanding gap. In this work, we analyze the gap as driven by two factors: (i) forgetting of text capabilities during adaptation, and (ii) cross-modal misalignment between speech and text. Based on this analysis, we introduce SALAD--Sample-efficient Alignment with Learning through Active selection and cross-modal Distillation--which combines cross-modal distillation with targeted synthetic data to improve alignment while mitigating forgetting. Applied to 3B and 7B LLMs, SALAD achieves competitive performance with a strong open-weight model across broad-domain benchmarks in knowledge, language understanding, and reasoning, while training on over an order of magnitude less speech data from public corpora.
Authors: Marcel Meyer, Sascha Kaltenpoth, Kevin Zalipski, Oliver M\"uller
Abstract: Time Series Foundation Models (TSFMs) represent a new paradigm for time series forecasting, offering zero-shot forecasting capabilities without the need for domain-specific pre-training or fine-tuning. However, as with Large Language Models (LLMs), evaluating TSFMs is tricky, as with ever more extensive training sets, it becomes more and more challenging to ensure the integrity of benchmarking data. Our investigation of existing TSFM evaluation highlights multiple challenges, ranging from the representativeness of the benchmark datasets, over the lack of spatiotemporal evaluation, to risks of information leakage due to overlapping and obscure datasets, and the memorization of global patterns caused by external shocks like economic crises or pandemics. Our findings reveal widespread confusion regarding data partitions, risking inflated performance estimates and incorrect transfer of global knowledge to local time series. We argue for the development of robust evaluation methodologies to prevent pitfalls already observed in LLM and classical time series benchmarking, and call upon the research community to design new, principled approaches, such as evaluations on truly out-of-sample future data, to safeguard the integrity of TSFM assessment.
Authors: Hyunsu Kim, Jonggeon Park, Joan Bruna, Hongseok Yang, Juho Lee
Abstract: The advent of foundation models in AI has significantly advanced general-purpose learning, enabling remarkable capabilities in zero-shot inference and in-context learning. However, training such models on physics data, including solutions to partial differential equations (PDEs), poses a unique challenge due to varying dimensionalities across different systems. Traditional approaches either fix a maximum dimension or employ separate encoders for different dimensionalities, resulting in inefficiencies. To address this, we propose a dimension-agnostic neural network architecture, the Axial Neural Network (XNN), inspired by parameter-sharing structures such as Deep Sets and Graph Neural Networks. XNN generalizes across varying tensor dimensions while maintaining computational efficiency. We convert existing PDE foundation models into axial neural networks and evaluate their performance across three training scenarios: training from scratch, pretraining on multiple PDEs, and fine-tuning on a single PDE. Our experiments show that XNNs perform competitively with original models and exhibit superior generalization to unseen dimensions, highlighting the importance of multidimensional pretraining for foundation models.
Authors: Zian Li, Muhan Zhang
Abstract: Masked autoregressive models (MAR) have recently emerged as a powerful paradigm for image and video generation, combining the flexibility of masked modeling with the potential of continuous tokenizer. However, video MAR models suffer from two major limitations: the slow-start problem, caused by the lack of a structured global prior at early sampling stages, and error accumulation across the autoregression in both spatial and temporal dimensions. In this work, we propose CanvasMAR, a novel video MAR model that mitigates these issues by introducing a canvas mechanism--a blurred, global prediction of the next frame, used as the starting point for masked generation. The canvas provides global structure early in sampling, enabling faster and more coherent frame synthesis. Furthermore, we introduce compositional classifier-free guidance that jointly enlarges spatial (canvas) and temporal conditioning, and employ noise-based canvas augmentation to enhance robustness. Experiments on the BAIR and Kinetics-600 benchmarks demonstrate that CanvasMAR produces high-quality videos with fewer autoregressive steps. Our approach achieves remarkable performance among autoregressive models on Kinetics-600 dataset and rivals diffusion-based methods.
Authors: Minjung Shin, Hyunin Cho, Sooyeon Go, Jin-Hwa Kim, Youngjung Uh
Abstract: Multi-view generation with camera pose control and prompt-based customization are both essential elements for achieving controllable generative models. However, existing multi-view generation models do not support customization with geometric consistency, whereas customization models lack explicit viewpoint control, making them challenging to unify. Motivated by these gaps, we introduce a novel task, multi-view customization, which aims to jointly achieve multi-view camera pose control and customization. Due to the scarcity of training data in customization, existing multi-view generation models, which inherently rely on large-scale datasets, struggle to generalize to diverse prompts. To address this, we propose MVCustom, a novel diffusion-based framework explicitly designed to achieve both multi-view consistency and customization fidelity. In the training stage, MVCustom learns the subject's identity and geometry using a feature-field representation, incorporating the text-to-video diffusion backbone enhanced with dense spatio-temporal attention, which leverages temporal coherence for multi-view consistency. In the inference stage, we introduce two novel techniques: depth-aware feature rendering explicitly enforces geometric consistency, and consistent-aware latent completion ensures accurate perspective alignment of the customized subject and surrounding backgrounds. Extensive experiments demonstrate that MVCustom is the only framework that simultaneously achieves faithful multi-view generation and customization.
Authors: Johan Obando-Ceron, Walter Mayor, Samuel Lavoie, Scott Fujimoto, Aaron Courville, Pablo Samuel Castro
Abstract: Recent works have proposed accelerating the wall-clock training time of actor-critic methods via the use of large-scale environment parallelization; unfortunately, these can sometimes still require large number of environment interactions to achieve a desired level of performance. Noting that well-structured representations can improve the generalization and sample efficiency of deep reinforcement learning (RL) agents, we propose the use of simplicial embeddings: lightweight representation layers that constrain embeddings to simplicial structures. This geometric inductive bias results in sparse and discrete features that stabilize critic bootstrapping and strengthen policy gradients. When applied to FastTD3, FastSAC, and PPO, simplicial embeddings consistently improve sample efficiency and final performance across a variety of continuous- and discrete-control environments, without any loss in runtime speed.
Authors: Dan Jacobellis, Mateen Ulhaq, Fabien Racap\'e, Hyomin Choi, Neeraja J. Yadwadkar
Abstract: Remote inference allows lightweight devices to leverage powerful cloud models. However, communication network latency makes predictions stale and unsuitable for real-time tasks. To address this, we introduce Dedelayed, a delay-corrective method that mitigates arbitrary remote inference delays, allowing the local device to produce low-latency outputs in real time. Our method employs a lightweight local model that processes the current frame and fuses in features that a heavyweight remote model computes from past frames. On video from the BDD100K driving dataset, Dedelayed improves semantic segmentation accuracy over the stronger of the local-only and remote-only baselines across all realistic communication network delays beyond 33 ms. Without incurring additional delay, it improves accuracy by 6.4 mIoU compared to fully local inference and 9.8 mIoU compared to remote inference, for a round-trip delay of 100 ms. The advantage grows under longer delays and higher-motion scenes, as delay-mitigated split inference sustains accuracy more effectively, providing clear advantages for real-time tasks that must remain aligned with the current world state.
Authors: Run Luo, Xiaobo Xia, Lu Wang, Longze Chen, Renke Shan, Jing Luo, Min Yang, Tat-Seng Chua
Abstract: Next-generation multimodal foundation models capable of any-to-any cross-modal generation and multi-turn interaction will serve as core components of artificial general intelligence systems, playing a pivotal role in human-machine interaction. However, most existing multimodal models remain constrained by autoregressive architectures, whose inherent limitations prevent a balanced integration of understanding and generation capabilities. Although hybrid and decoupling strategies have been explored to address these tasks within unified frameworks separately, their redundant, non-integrated designs limit their applicability to broader scenarios, such as cross-modal retrieval.In this work, we introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms. By leveraging metric-induced probability paths and kinetic optimal velocities, NExT-OMNI natively supports any-to-any understanding and generation with enhanced response efficiency, while enabling broader application scenarios through concise unified representations rather than task-decoupled designs. Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks, while outperforming prior unified models in multi-turn multimodal interaction and cross-modal retrieval, highlighting its architectural advantages as a next-generation multimodal foundation model. To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
Authors: Aditya Tanikanti, Benoit C\^ot\'e, Yanfei Guo, Le Chen, Nickolaus Saint, Ryan Chard, Ken Raffenetti, Rajeev Thakur, Thomas Uram, Ian Foster, Michael E. Papka, Venkatram Vishwanath
Abstract: We present the Federated Inference Resource Scheduling Toolkit (FIRST), a framework enabling Inference-as-a-Service across distributed High-Performance Computing (HPC) clusters. FIRST provides cloud-like access to diverse AI models, like Large Language Models (LLMs), on existing HPC infrastructure. Leveraging Globus Auth and Globus Compute, the system allows researchers to run parallel inference workloads via an OpenAI-compliant API on private, secure environments. This cluster-agnostic API allows requests to be distributed across federated clusters, targeting numerous hosted models. FIRST supports multiple inference backends (e.g., vLLM), auto-scales resources, maintains "hot" nodes for low-latency execution, and offers both high-throughput batch and interactive modes. The framework addresses the growing demand for private, secure, and scalable AI inference in scientific workflows, allowing researchers to generate billions of tokens daily on-premises without relying on commercial cloud infrastructure.
Authors: Mustafa Munir, Alex Zhang, Radu Marculescu
Abstract: Vision graph neural networks (ViG) have demonstrated promise in vision tasks as a competitive alternative to conventional convolutional neural nets (CNN) and transformers (ViTs); however, common graph construction methods, such as k-nearest neighbor (KNN), can be expensive on larger images. While methods such as Sparse Vision Graph Attention (SVGA) have shown promise, SVGA's fixed step scale can lead to over-squashing and missing multiple connections to gain the same information that could be gained from a long-range link. Through this observation, we propose a new graph construction method, Logarithmic Scalable Graph Construction (LSGC) to enhance performance by limiting the number of long-range links. To this end, we propose LogViG, a novel hybrid CNN-GNN model that utilizes LSGC. Furthermore, inspired by the successes of multi-scale and high-resolution architectures, we introduce and apply a high-resolution branch and fuse features between our high-resolution and low-resolution branches for a multi-scale high-resolution Vision GNN network. Extensive experiments show that LogViG beats existing ViG, CNN, and ViT architectures in terms of accuracy, GMACs, and parameters on image classification and semantic segmentation tasks. Our smallest model, Ti-LogViG, achieves an average top-1 accuracy on ImageNet-1K of 79.9% with a standard deviation of 0.2%, 1.7% higher average accuracy than Vision GNN with a 24.3% reduction in parameters and 35.3% reduction in GMACs. Our work shows that leveraging long-range links in graph construction for ViGs through our proposed LSGC can exceed the performance of current state-of-the-art ViGs. Code is available at https://github.com/mmunir127/LogViG-Official.
Authors: Junhong Shen, Mu Cai, Bo Hu, Ameet Talwalkar, David A Ross, Cordelia Schmid, Alireza Fathi
Abstract: Multimodal Large Language Models (MLLMs) struggle with precise reasoning for structured visuals like charts and diagrams, as pixel-based perception lacks a mechanism for verification. To address this, we propose to leverage derendering -- the process of reverse-engineering visuals into executable code -- as a new modality for verifiable visual reasoning. Specifically, we propose RECODE, an agentic framework that first generates multiple candidate programs to reproduce the input image. It then uses a critic to select the most faithful reconstruction and iteratively refines the code. This process not only transforms an ambiguous perceptual task into a verifiable, symbolic problem, but also enables precise calculations and logical inferences later on. On various visual reasoning benchmarks such as CharXiv, ChartQA, and Geometry3K, RECODE significantly outperforms methods that do not leverage code or only use code for drawing auxiliary lines or cropping. Our work demonstrates that grounding visual perception in executable code provides a new path toward more accurate and verifiable multimodal reasoning.
Authors: Connor Lane, Daniel Z. Kaplan, Tanishq Mathew Abraham, Paul S. Scotti
Abstract: A key question for adapting modern deep learning architectures to functional MRI (fMRI) is how to represent the data for model input. To bridge the modality gap between fMRI and natural images, we transform the 4D volumetric fMRI data into videos of 2D fMRI activity flat maps. We train Vision Transformers on 2.3K hours of fMRI flat map videos from the Human Connectome Project using the spatiotemporal masked autoencoder (MAE) framework. We observe that masked fMRI modeling performance improves with dataset size according to a strict power scaling law. Downstream classification benchmarks show that our model learns rich representations supporting both fine-grained state decoding across subjects, as well as subject-specific trait decoding across changes in brain state. This work is part of an ongoing open science project to build foundation models for fMRI data. Our code and datasets are available at https://github.com/MedARC-AI/fmri-fm.
Authors: Xinyi Chen, Yilun Chen, Yanwei Fu, Ning Gao, Jiaya Jia, Weiyang Jin, Hao Li, Yao Mu, Jiangmiao Pang, Yu Qiao, Yang Tian, Bin Wang, Bolun Wang, Fangjing Wang, Hanqing Wang, Tai Wang, Ziqin Wang, Xueyuan Wei, Chao Wu, Shuai Yang, Jinhui Ye, Junqiu Yu, Jia Zeng, Jingjing Zhang, Jinyu Zhang, Shi Zhang, Feng Zheng, Bowen Zhou, Yangkun Zhu
Abstract: We introduce InternVLA-M1, a unified framework for spatial grounding and robot control that advances instruction-following robots toward scalable, general-purpose intelligence. Its core idea is spatially guided vision-language-action training, where spatial grounding serves as the critical link between instructions and robot actions. InternVLA-M1 employs a two-stage pipeline: (i) spatial grounding pre-training on over 2.3M spatial reasoning data to determine ``where to act'' by aligning instructions with visual, embodiment-agnostic positions, and (ii) spatially guided action post-training to decide ``how to act'' by generating embodiment-aware actions through plug-and-play spatial prompting. This spatially guided training recipe yields consistent gains: InternVLA-M1 outperforms its variant without spatial guidance by +14.6% on SimplerEnv Google Robot, +17% on WidowX, and +4.3% on LIBERO Franka, while demonstrating stronger spatial reasoning capability in box, point, and trace prediction. To further scale instruction following, we built a simulation engine to collect 244K generalizable pick-and-place episodes, enabling a 6.2% average improvement across 200 tasks and 3K+ objects. In real-world clustered pick-and-place, InternVLA-M1 improved by 7.3%, and with synthetic co-training, achieved +20.6% on unseen objects and novel configurations. Moreover, in long-horizon reasoning-intensive scenarios, it surpassed existing works by over 10%. These results highlight spatially guided training as a unifying principle for scalable and resilient generalist robots. Code and models are available at https://github.com/InternRobotics/InternVLA-M1.
Authors: Devvrit Khatri, Lovish Madaan, Rishabh Tiwari, Rachit Bansal, Sai Surya Duvvuri, Manzil Zaheer, Inderjit S. Dhillon, David Brandfonbrener, Rishabh Agarwal
Abstract: Reinforcement learning (RL) has become central to training large language models (LLMs), yet the field lacks predictive scaling methodologies comparable to those established for pre-training. Despite rapidly rising compute budgets, there is no principled understanding of how to evaluate algorithmic improvements for scaling RL compute. We present the first large-scale systematic study, amounting to more than 400,000 GPU-hours, that defines a principled framework for analyzing and predicting RL scaling in LLMs. We fit sigmoidal compute-performance curves for RL training and ablate a wide range of common design choices to analyze their effects on asymptotic performance and compute efficiency. We observe: (1) Not all recipes yield similar asymptotic performance, (2) Details such as loss aggregation, normalization, curriculum, and off-policy algorithm primarily modulate compute efficiency without materially shifting the asymptote, and (3) Stable, scalable recipes follow predictable scaling trajectories, enabling extrapolation from smaller-scale runs. Combining these insights, we propose a best-practice recipe, ScaleRL, and demonstrate its effectiveness by successfully scaling and predicting validation performance on a single RL run scaled up to 100,000 GPU-hours. Our work provides both a scientific framework for analyzing scaling in RL and a practical recipe that brings RL training closer to the predictability long achieved in pre-training.
Authors: Ziqing Lu, Lifeng Lai, Weiyu Xu
Abstract: Reinforcement learning (RL) for the Markov Decision Process (MDP) has emerged in many security-related applications, such as autonomous driving, financial decisions, and drone/robot algorithms. In order to improve the robustness/defense of RL systems against adversaries, studying various adversarial attacks on RL systems is very important. Most previous work considered deterministic adversarial attack strategies in MDP, which the recipient (victim) agent can defeat by reversing the deterministic attacks. In this paper, we propose a provably ``invincible'' or ``uncounterable'' type of adversarial attack on RL. The attackers apply a rate-distortion information-theoretic approach to randomly change agents' observations of the transition kernel (or other properties) so that the agent gains zero or very limited information about the ground-truth kernel (or other properties) during the training. We derive an information-theoretic lower bound on the recipient agent's reward regret and show the impact of rate-distortion attacks on state-of-the-art model-based and model-free algorithms. We also extend this notion of an information-theoretic approach to other types of adversarial attack, such as state observation attacks.
Authors: Yi Zhang, Bolin Ni, Xin-Sheng Chen, Heng-Rui Zhang, Yongming Rao, Houwen Peng, Qinglin Lu, Han Hu, Meng-Hao Guo, Shi-Min Hu
Abstract: Fully open multimodal large language models (MLLMs) currently lag behind proprietary counterparts, primarily due to a significant gap in data quality for supervised fine-tuning (SFT). Existing open-source datasets are often plagued by widespread noise and a critical deficit in complex reasoning data, such as Chain-of-Thought (CoT), which hinders the development of advanced model capabilities. Addressing these challenges, our work makes three primary contributions. First, we introduce Honey-Data-15M, a new SFT dataset comprising approximately 15 million QA pairs, processed through multiple cleaning techniques and enhanced with a novel dual-level (short and long) CoT enrichment strategy. Second, we introduce HoneyPipe, the data curation pipeline, and its underlying framework DataStudio, providing the community with a transparent and adaptable methodology for data curation that moves beyond static dataset releases. Finally, to validate our dataset and pipeline, we train Bee-8B, an 8B model on Honey-Data-15M. Experiments show that Bee-8B establishes a new state-of-the-art (SOTA) for fully open MLLMs, achieving performance that is competitive with, and in some cases surpasses, recent semi-open models such as InternVL3.5-8B. Our work delivers to the community a suite of foundational resources, including: the Honey-Data-15M corpus; the full-stack suite comprising HoneyPipe and DataStudio; training recipes; an evaluation harness; and the model weights. This effort demonstrates that a principled focus on data quality is a key pathway to developing fully open MLLMs that are highly competitive with their semi-open counterparts.
Authors: Xinchen Zhang, Xiaoying Zhang, Youbin Wu, Yanbin Cao, Renrui Zhang, Ruihang Chu, Ling Yang, Yujiu Yang
Abstract: We introduce Generative Universal Verifier, a novel concept and plugin designed for next-generation multimodal reasoning in vision-language models and unified multimodal models, providing the fundamental capability of reflection and refinement on visual outcomes during the reasoning and generation process. This work makes three main contributions: (1) We build ViVerBench, a comprehensive benchmark spanning 16 categories of critical tasks for evaluating visual outcomes in multimodal reasoning. Results show that existing VLMs consistently underperform across these tasks, underscoring a substantial gap from human-level capability in reliable visual verification. (2) We design two automated pipelines to construct large-scale visual verification data and train OmniVerifier-7B, the first omni-capable generative verifier trained for universal visual verification and achieves notable gains on ViVerBench(+8.3). Through training, we identify three atomic capabilities in visual verification and demonstrate how they generalize and interact synergistically. (3) We propose OmniVerifier-TTS, a sequential test-time scaling paradigm that leverages the universal verifier to bridge image generation and editing within unified models, enhancing the upper bound of generative ability through iterative fine-grained optimization. Beyond generation, we extend universal verifier to broader world-modeling interleaved reasoning scenarios. Empirically, OmniVerifier-TTS achieves improvements on T2I-ReasonBench(+3.7), and GenEval++(+4.3), outperforming existing parallel test-time scaling methods, such as Best-of-N. By endowing multimodal reasoning with reliable visual verification, OmniVerifier advances both reliable reflection during generation and scalable test-time refinement, marking a step toward more trustworthy and controllable next-generation reasoning systems.
Authors: Xiaocheng Li, Huaiyang Zhong, Margaret L. Brandeau
Abstract: The goal of a traditional Markov decision process (MDP) is to maximize expected cumulative reward over a defined horizon (possibly infinite). In many applications, however, a decision maker may be interested in optimizing a specific quantile of the cumulative reward instead of its expectation. In this paper we consider the problem of optimizing the quantiles of the cumulative rewards of a Markov decision process (MDP), which we refer to as a quantile Markov decision process (QMDP). We provide analytical results characterizing the optimal QMDP value function and present a dynamic programming-based algorithm to solve for the optimal policy. The algorithm also extends to the MDP problem with a conditional value-at-risk (CVaR) objective. We illustrate the practical relevance of our model by evaluating it on an HIV treatment initiation problem, where patients aim to balance the potential benefits and risks of the treatment.
Authors: Zhe Zheng, Jin Han, Ke-Yin Chen, Xin-Yu Cao, Xin-Zheng Lu, Jia-Rui Lin
Abstract: Translating clauses into executable code is a vital stage of automated rule checking (ARC) and is essential for effective building design compliance checking, particularly for rules with implicit properties or complex logic requiring domain knowledge. Thus, by systematically analyzing building clauses, 66 atomic functions are defined first to encapsulate common computational logics. Then, LLM-FuncMapper is proposed, a large language model (LLM)-based approach with rule-based adaptive prompts that match clauses to atomic functions. Finally, executable code is generated by composing functions through the LLMs. Experiments show LLM-FuncMapper outperforms fine-tuning methods by 19% in function matching while significantly reducing manual annotation efforts. Case study demonstrates that LLM-FuncMapper can automatically compose multiple atomic functions to generate executable code, boosting rule-checking efficiency. To our knowledge, this research represents the first application of LLMs for interpreting complex design clauses into executable code, which may shed light on further adoption of LLMs in the construction domain.
Authors: Taylor Webb, Shanka Subhra Mondal, Ida Momennejad
Abstract: Large language models (LLMs) demonstrate impressive performance on a wide variety of tasks, but they often struggle with tasks that require multi-step reasoning or goal-directed planning. Both cognitive neuroscience and reinforcement learning (RL) have proposed a number of interacting functional components that together implement search and evaluation in multi-step decision making. These components include conflict monitoring, state prediction, state evaluation, task decomposition, and orchestration. To improve planning with LLMs, we propose an agentic architecture, the Modular Agentic Planner (MAP), in which planning is accomplished via the recurrent interaction of the specialized modules mentioned above, each implemented using an LLM. MAP improves planning through the interaction of specialized modules that break down a larger problem into multiple brief automated calls to the LLM. We evaluate MAP on three challenging planning tasks -- graph traversal, Tower of Hanoi, and the PlanBench benchmark -- as well as an NLP task requiring multi-step reasoning (strategyQA). We find that MAP yields significant improvements over both standard LLM methods (zero-shot prompting, in-context learning) and competitive baselines (chain-of-thought, multi-agent debate, and tree-of-thought), can be effectively combined with smaller and more cost-efficient LLMs (Llama3-70B), and displays superior transfer across tasks. These results suggest the benefit of a modular and multi-agent approach to planning with LLMs.
Authors: Shubhra Mishra, Gabriel Poesia, Noah D. Goodman
Abstract: Large Language Models (LLMs) solely trained on next-token prediction learn to solve a wide range of problems involving mathematical reasoning. But how does this ability evolve during training? We show the first analysis of how mathematical reasoning abilities of several open-weight LLMs develop during pre-training and post-training. To this end, we construct MathCAMPS, a synthetic dataset of novel mathematical reasoning problems grounded in 44 fine-grained skills taken from the Common Core curriculum from K to 8th grades. In one experiment, we show that mathematical skills are learned during pre-training in an order that measurably correlates with the human-designed curriculum, even though training data are randomly ordered. We also show a detailed analysis of which mathematical abilities benefit from instruction tuning, a widely used post-training method and, in contrast, which skills suffer. Our work paves the way for an empirical understanding of LLM training dynamics in relation to reasoning.
Authors: Adilet Yerkin, Pakizar Shamoi, Elnara Kadyrgali
Abstract: In today's world, making decisions as a group is common, whether choosing a restaurant or deciding on a holiday destination. Group decision-making (GDM) systems play a crucial role by facilitating consensus among participants with diverse preferences. Discussions are one of the main tools people use to make decisions. When people discuss alternatives, they use natural language to express their opinions. Traditional GDM systems generally require participants to provide explicit opinion values to the system. However, in real-life scenarios, participants often express their opinions through some text (e.g., in comments, social media, messengers, etc.). This paper introduces a sentiment and emotion-aware multi-criteria fuzzy GDM system designed to enhance consensus-reaching effectiveness in group settings. This system incorporates natural language processing to analyze sentiments and emotions expressed in textual data, enabling an understanding of participant opinions besides the explicit numerical preference inputs. Once all the experts have provided their preferences for the alternatives, the individual preferences are aggregated into a single collective preference matrix. This matrix represents the collective expert opinion regarding the other options. Then, sentiments, emotions, and preference scores are inputted into a fuzzy inference system to get the overall score. The proposed system was used for a small decision-making process - choosing the hotel for a vacation by a group of friends. Our findings demonstrate that integrating sentiment and emotion analysis into GDM systems allows everyone's feelings and opinions to be considered during discussions and significantly improves consensus among participants.
Authors: Medant Sharan, Chandranath Adak
Abstract: This paper investigates the strategy game So Long Sucker (SLS) as a novel benchmark for multi-agent reinforcement learning (MARL). Unlike traditional board or video game testbeds, SLS is distinguished by its coalition formation, strategic deception, and dynamic elimination rules, making it a uniquely challenging environment for autonomous agents. We introduce the first publicly available computational framework for SLS, complete with a graphical user interface and benchmarking support for reinforcement learning algorithms. Using classical deep reinforcement learning methods (e.g., DQN, DDQN, and Dueling DQN), we train self-playing agents to learn the rules and basic strategies of SLS. Experimental results demonstrate that, although these agents achieve roughly half of the maximum attainable reward and consistently outperform random baselines, they require long training horizons (~2000 games) and still commit occasional illegal moves, highlighting both the promise and limitations of classical reinforcement learning. Our findings establish SLS as a negotiation-aware benchmark for MARL, opening avenues for future research that integrates game-theoretic reasoning, coalition-aware strategies, and advanced reinforcement learning architectures to better capture the social and adversarial dynamics of complex multi-agent games.
Authors: Jibang Wu, Chenghao Yang, Yi Wu, Simon Mahns, Chaoqi Wang, Hao Zhu, Fei Fang, Haifeng Xu
Abstract: This paper develops an agentic framework that employs large language models (LLMs) for grounded persuasive language generation in automated copywriting, with real estate marketing as a focal application. Our method is designed to align the generated content with user preferences while highlighting useful factual attributes. This agent consists of three key modules: (1) Grounding Module, mimicking expert human behavior to predict marketable features; (2) Personalization Module, aligning content with user preferences; (3) Marketing Module, ensuring factual accuracy and the inclusion of localized features. We conduct systematic human-subject experiments in the domain of real estate marketing, with a focus group of potential house buyers. The results demonstrate that marketing descriptions generated by our approach are preferred over those written by human experts by a clear margin while maintaining the same level of factual accuracy. Our findings suggest a promising agentic approach to automate large-scale targeted copywriting while ensuring factuality of content generation.
Authors: Yousef Emami, Hao Zhou, SeyedSina Nabavirazani, Luis Almeida
Abstract: Unmanned Aerial Vehicles (UAVs) are increasingly being utilized in various private and commercial applications, e.g., traffic control, parcel delivery, and Search and Rescue (SAR) missions. Machine Learning (ML) methods used in UAV-Assisted Sensor Networks (UASNETs) and, especially, in Deep Reinforcement Learning (DRL) face challenges such as complex and lengthy model training, gaps between simulation and reality, and low sampling efficiency, which conflict with the urgency of emergencies, such as SAR missions. In this paper, an In-Context Learning (ICL)-Data Collection Scheduling (ICLDC) system is proposed as an alternative to DRL in emergencies. The UAV collects sensory data and transmits it to a Large Language Model (LLM), which creates a task description in natural language. From this description, the UAV receives a data collection schedule that must be executed. A verifier ensures safe UAV operations by evaluating the schedules generated by the LLM and overriding unsafe schedules based on predefined rules. The system continuously adapts by incorporating feedback into the task descriptions and using this for future decisions. This method is tested against jailbreaking attacks, where the task description is manipulated to undermine network performance, highlighting the vulnerability of LLMs to such attacks. The proposed ICLDC significantly reduces cumulative packet loss compared to both the DQN and Maximum Channel Gain baselines. ICLDC presents a promising direction for intelligent scheduling and control in UASNETs.
Authors: Haoyu Yang, Kamyar Azizzadenesheli, Haoxing Ren
Abstract: Inverse design optimization aims to infer system parameters from observed solutions, posing critical challenges across domains such as semiconductor manufacturing, structural engineering, materials science, and fluid dynamics. The lack of explicit mathematical representations in many systems complicates this process and makes the first order optimization impossible. Mainstream approaches, including generative AI and Bayesian optimization, address these challenges but have limitations. Generative AI is computationally expensive, while Bayesian optimization, relying on surrogate models, suffers from scalability, sensitivity to priors, and noise issues, often leading to suboptimal solutions. This paper introduces Deep Physics Prior (DPP), a novel method enabling first-order gradient-based inverse optimization with surrogate machine learning models. By leveraging pretrained auxiliary Neural Operators, DPP enforces prior distribution constraints to ensure robust and meaningful solutions. This approach is particularly effective when prior data and observation distributions are unknown.
Authors: Jialong Zhou, Lichao Wang, Xiao Yang
Abstract: The emergence of large language models (LLMs) enables the development of intelligent agents capable of engaging in complex and multi-turn dialogues. However, multi-agent collaboration faces critical safety challenges, such as hallucination amplification and error injection and propagation. This paper presents GUARDIAN, a unified method for detecting and mitigating multiple safety concerns in GUARDing Intelligent Agent collaboratioNs. By modeling the multi-agent collaboration process as a discrete-time temporal attributed graph, GUARDIAN explicitly captures the propagation dynamics of hallucinations and errors. The unsupervised encoder-decoder architecture incorporating an incremental training paradigm learns to reconstruct node attributes and graph structures from latent embeddings, enabling the identification of anomalous nodes and edges with unparalleled precision. Moreover, we introduce a graph abstraction mechanism based on the Information Bottleneck Theory, which compresses temporal interaction graphs while preserving essential patterns. Extensive experiments demonstrate GUARDIAN's effectiveness in safeguarding LLM multi-agent collaborations against diverse safety vulnerabilities, achieving state-of-the-art accuracy with efficient resource utilization. The code is available at https://github.com/JialongZhou666/GUARDIAN
Authors: Xiangyu Zhao, Wanghan Xu, Bo Liu, Yuhao Zhou, Fenghua Ling, Ben Fei, Xiaoyu Yue, Lei Bai, Wenlong Zhang, Xiao-Ming Wu
Abstract: The rapid advancement of multimodal large language models (MLLMs) has unlocked new opportunities to tackle complex scientific challenges. Despite this progress, their application in addressing earth science problems, especially at the graduate level, remains underexplored. A significant barrier is the absence of benchmarks that capture the depth and contextual complexity of geoscientific reasoning. Current benchmarks often rely on synthetic datasets or simplistic figure-caption pairs, which do not adequately reflect the intricate reasoning and domain-specific insights required for real-world scientific applications. To address these gaps, we introduce MSEarth, a multimodal scientific benchmark curated from high-quality, open-access scientific publications. MSEarth encompasses the five major spheres of Earth science: atmosphere, cryosphere, hydrosphere, lithosphere, and biosphere, featuring over 289K figures with refined captions. These captions are crafted from the original figure captions and enriched with discussions and reasoning from the papers, ensuring the benchmark captures the nuanced reasoning and knowledge-intensive content essential for advanced scientific tasks. MSEarth supports a variety of tasks, including scientific figure captioning, multiple choice questions, and open-ended reasoning challenges. By bridging the gap in graduate-level benchmarks, MSEarth provides a scalable and high-fidelity resource to enhance the development and evaluation of MLLMs in scientific reasoning. The benchmark is publicly available to foster further research and innovation in this field.
Authors: Nicole Cho, Kirsty Fielding, William Watson, Sumitra Ganesh, Manuela Veloso
Abstract: Real-world financial documents report essential information about an entity's financial holdings that can span millions of different financial instrument types. Yet, these details are often buried in messy, multi-page, fragmented tables - for example, 99.4% of the tables in our dataset have no bounding boxes with the maximum number of rows amounting to 426 per table across 44 pages. To tackle these unique challenges from real-world tables, we present a continuously learning, agentic table extraction system, TASER (Table Agents for Schema-guided Extraction and Recommendation) that extracts highly unstructured, multi-page, heterogeneous tables into normalized, schema-conforming outputs. Our table agents execute on table detection, classification, extraction, and recommendations by leveraging an initial schema. Then, our Recommender Agent reviews the outputs, recommends schema revisions, and decides on the final recommendations, enabling TASER to outperform existing table detection models such as Table Transformer by 10.1%. Within this continuous learning process, we highlight that larger batch sizes result in a 104.3% increase in schema recommendations that are actionable and utilized, resulting in a 9.8% increase in extracted holdings - highlighting the importance of a continuous learning process. To train TASER, we have manually labeled 22,584 pages (28,150,449 tokens), 3,213 tables for $731,685,511,687 of holdings culminating in one of the first real financial table datasets. We release our dataset TASERTab to enable the research community to access real-world financial tables and outputs. Our results highlight the promise of agentic, schema-guided extraction systems for robust understanding of real-world financial tables.
Authors: Eduardo Illueca-Fernandez, Kaile Chen, Fernando Seoane, Farhad Abtahi
Abstract: Process mining has emerged as a powerful analytical technique for understanding complex healthcare workflows. However, its application faces significant barriers, including technical complexity, a lack of standardized approaches, and limited access to practical training resources. We introduce HealthProcessAI, a GenAI framework designed to simplify process mining applications in healthcare and epidemiology by providing a comprehensive wrapper around existing Python (PM4PY) and R (bupaR) libraries. To address unfamiliarity and improve accessibility, the framework integrates multiple Large Language Models (LLMs) for automated process map interpretation and report generation, helping translate technical analyses into outputs that diverse users can readily understand. We validated the framework using sepsis progression data as a proof-of-concept example and compared the outputs of five state-of-the-art LLM models through the OpenRouter platform. To test its functionality, the framework successfully processed sepsis data across four proof-of-concept scenarios, demonstrating robust technical performance and its capability to generate reports through automated LLM analysis. LLM evaluation using five independent LLMs as automated evaluators revealed distinct model strengths: Claude Sonnet-4 and Gemini 2.5-Pro achieved the highest consistency scores (3.79/4.0 and 3.65/4.0) when evaluated by automated LLM assessors. By integrating multiple Large Language Models (LLMs) for automated interpretation and report generation, the framework addresses widespread unfamiliarity with process mining outputs, making them more accessible to clinicians, data scientists, and researchers. This structured analytics and AI-driven interpretation combination represents a novel methodological advance in translating complex process mining results into potentially actionable insights for healthcare applications.
Authors: Jaewoo Ahn, Junseo Kim, Heeseung Yun, Jaehyeon Son, Dongmin Park, Jaewoong Cho, Gunhee Kim
Abstract: GUI agents powered by LLMs show promise in interacting with diverse digital environments. Among these, video games offer a valuable testbed due to their varied interfaces, with adventure games posing additional challenges through complex, narrative-driven interactions. Existing game benchmarks, however, lack diversity and rarely evaluate agents on completing entire storylines. To address this, we introduce FlashAdventure, a benchmark of 34 Flash-based adventure games designed to test full story arc completion and tackle the observation-behavior gap: the challenge of remembering and acting on earlier gameplay information. We also propose CUA-as-a-Judge, an automated gameplay evaluator, and COAST, an agentic framework leveraging long-term clue memory to better plan and solve sequential tasks. Experiments show current GUI agents struggle with full story arcs, while COAST improves milestone completion by bridging the observation-behavior gap. Nonetheless, a marked discrepancy between humans and best-performing agents warrants continued research efforts to narrow this divide.
Authors: Atma Anand
Abstract: Information-processing systems that coordinate multiple agents and objectives face fundamental thermodynamic constraints. We show that solutions with maximum utility to act as coordination focal points have a much higher selection pressure for being findable across agents rather than accuracy. We derive that the information-theoretic minimum description length of coordination protocols to precision $\varepsilon$ scales as $L(P)\geq NK\log_2 K+N^2d^2\log (1/\varepsilon)$ for $N$ agents with $d$ potentially conflicting objectives and internal model complexity $K$. This scaling forces progressive simplification, with coordination dynamics changing the environment itself and shifting optimization across hierarchical levels. Moving from established focal points requires re-coordination, creating persistent metastable states and hysteresis until significant environmental shifts trigger phase transitions through spontaneous symmetry breaking. We operationally define coordination temperature to predict critical phenomena and estimate coordination work costs, identifying measurable signatures across systems from neural networks to restaurant bills to bureaucracies. Extending the topological version of Arrow's theorem on the impossibility of consistent preference aggregation, we find it recursively binds whenever preferences are combined. This potentially explains the indefinite cycling in multi-objective gradient descent and alignment faking in Large Language Models trained with reinforcement learning with human feedback. We term this framework Thermodynamic Coordination Theory (TCT), which demonstrates that coordination requires radical information loss.
Authors: Jianshuo Dong, Sheng Guo, Hao Wang, Xun Chen, Zhuotao Liu, Tianwei Zhang, Ke Xu, Minlie Huang, Han Qiu
Abstract: Search agents connect LLMs to the Internet, enabling access to broader and more up-to-date information. However, unreliable search results may also pose safety threats to end users, establishing a new threat surface. In this work, we conduct two in-the-wild experiments to demonstrate both the prevalence of low-quality search results and their potential to misguide agent behaviors. To counter this threat, we introduce an automated red-teaming framework that is systematic, scalable, and cost-efficient, enabling lightweight and harmless safety assessments of search agents. Building on this framework, we construct the SafeSearch benchmark, which includes 300 test cases covering five categories of risks (e.g., misinformation and indirect prompt injection). Using this benchmark, we evaluate three representative search agent scaffolds, covering search workflow, tool-calling, and deep research, across 7 proprietary and 8 open-source backend LLMs. Our results reveal substantial vulnerabilities of LLM-based search agents: when exposed to unreliable websites, the highest ASR reached 90.5% for GPT-4.1-mini under a search workflow setting. Moreover, our analysis highlights the limited effectiveness of common defense practices, such as reminder prompting. This emphasizes the value of our framework in promoting transparency for safer agent development. Our codebase and test cases are publicly available: https://github.com/jianshuod/SafeSearch.
Authors: Zirui Tang, Weizheng Wang, Zihang Zhou, Yang Jiao, Bangrui Xu, Boyu Niu, Xuanhe Zhou, Guoliang Li, Yeye He, Wei Zhou, Yitong Song, Cheng Tan, Xue Yang, Bin Wang, Conghui He, Xiaoyang Wang, Fan Wu
Abstract: Large language model (LLM) and agent techniques for data analysis (a.k.a LLM/Agent-as-Data-Analyst) have demonstrated substantial impact in both academica and industry. In comparison with traditional rule or small-model based approaches, (agentic) LLMs enable complex data understanding, natural language interfaces, semantic analysis functions, and autonomous pipeline orchestration. The technical evolution further distills five key design goals for intelligent data analysis agents, namely semantic-aware design, modality-hybrid integration, autonomous pipelines, tool-augmented workflows, and support for open-world tasks. From a modality perspective, we review LLM-based techniques for (i) structured data (e.g., table question answering for relational data and NL2GQL for graph data), (ii) semi-structured data (e.g., markup languages understanding and semi-structured table modeling), (iii) unstructured data (e.g., chart understanding, document understanding, programming languages vulnerable detection), and (iv) heterogeneous data (e.g., data retrieval and modality alignment for data lakes). Finally, we outline the remaining challenges and propose several insights and practical directions for advancing LLM/Agent-powered data analysis.
Authors: Haiyang Li, Yaxiong Wang, Shengeng Tang, Lianwei Wu, Lechao Cheng, Zhun Zhong
Abstract: In recent years, detecting fake multimodal content on social media has drawn increasing attention. Two major forms of deception dominate: human-crafted misinformation (e.g., rumors and misleading posts) and AI-generated content produced by image synthesis models or vision-language models (VLMs). Although both share deceptive intent, they are typically studied in isolation. NLP research focuses on human-written misinformation, while the CV community targets AI-generated artifacts. As a result, existing models are often specialized for only one type of fake content. In real-world scenarios, however, the type of a multimodal post is usually unknown, limiting the effectiveness of such specialized systems. To bridge this gap, we construct the Omnibus Dataset for Multimodal News Deception (OmniFake), a comprehensive benchmark of 127K samples that integrates human-curated misinformation from existing resources with newly synthesized AI-generated examples. Based on this dataset, we propose Unified Multimodal Fake Content Detection (UMFDet), a framework designed to handle both forms of deception. UMFDet leverages a VLM backbone augmented with a Category-aware Mixture-of-Experts (MoE) Adapter to capture category-specific cues, and an attribution chain-of-thought mechanism that provides implicit reasoning guidance for locating salient deceptive signals. Extensive experiments demonstrate that UMFDet achieves robust and consistent performance across both misinformation types, outperforming specialized baselines and offering a practical solution for real-world multimodal deception detection.
Authors: Sipeng Zhang, Longfei Yun, Zilong Wang, Jingbo Shang, Letian Peng
Abstract: At the core of Deep Research is knowledge mining, the task of extracting structured information from massive unstructured text in response to user instructions. Large language models (LLMs) excel at interpreting such instructions but are prohibitively expensive to deploy at scale, while traditional pipelines of classifiers and extractors remain efficient yet brittle and unable to generalize to new tasks. We introduce Falconer, a collaborative framework that combines the agentic reasoning of LLMs with lightweight proxy models for scalable knowledge mining. In Falconer, LLMs act as planners, decomposing user instructions into executable pipelines, and as annotators, generating supervision to train small proxies. The framework unifies classification and extraction into two atomic operations, get label and get span, enabling a single instruction-following model to replace multiple task-specific components. To evaluate the consistency between proxy models incubated by Falconer and annotations provided by humans and large models, we construct new benchmarks covering both planning and end-to-end execution. Experiments show that Falconer closely matches state-of-the-art LLMs in instruction-following accuracy while reducing inference cost by up to 90% and accelerating large-scale knowledge mining by more than 20x, offering an efficient and scalable foundation for Deep Research.
Authors: Zerui Cheng, Stella Wohnig, Ruchika Gupta, Samiul Alam, Tassallah Abdullahi, Jo\~ao Alves Ribeiro, Christian Nielsen-Garcia, Saif Mir, Siran Li, Jason Orender, Seyed Ali Bahrainian, Daniel Kirste, Aaron Gokaslan, Miko{\l}aj Glinka, Carsten Eickhoff, Ruben Wolff
Abstract: The meteoric rise of AI, with its rapidly expanding market capitalization, presents both transformative opportunities and critical challenges. Chief among these is the urgent need for a new, unified paradigm for trustworthy evaluation, as current benchmarks increasingly reveal critical vulnerabilities. Issues like data contamination and selective reporting by model developers fuel hype, while inadequate data quality control can lead to biased evaluations that, even if unintentionally, may favor specific approaches. As a flood of participants enters the AI space, this "Wild West" of assessment makes distinguishing genuine progress from exaggerated claims exceptionally difficult. Such ambiguity blurs scientific signals and erodes public confidence, much as unchecked claims would destabilize financial markets reliant on credible oversight from agencies like Moody's. In high-stakes human examinations (e.g., SAT, GRE), substantial effort is devoted to ensuring fairness and credibility; why settle for less in evaluating AI, especially given its profound societal impact? This position paper argues that the current laissez-faire approach is unsustainable. We contend that true, sustainable AI advancement demands a paradigm shift: a unified, live, and quality-controlled benchmarking framework robust by construction, not by mere courtesy and goodwill. To this end, we dissect the systemic flaws undermining today's AI evaluation, distill the essential requirements for a new generation of assessments, and introduce PeerBench (with its prototype implementation at https://www.peerbench.ai/), a community-governed, proctored evaluation blueprint that embodies this paradigm through sealed execution, item banking with rolling renewal, and delayed transparency. Our goal is to pave the way for evaluations that can restore integrity and deliver genuinely trustworthy measures of AI progress.
Authors: Soohan Lim, Joonghyuk Hahn, Hyunwoo Park, Sang-Ki Ko, Yo-Sub Han
Abstract: Prevailing code generation benchmarks, such as HumanEval+ and MBPP+, primarily evaluate large language models (LLMs) with pass@k on functional correctness using well-formed inputs. However, they ignore a crucial aspect of real-world software: adherence to contracts-the preconditions and validity constraints that dictate how ill-formed inputs must be rejected. This critical oversight means that existing benchmarks fail to measure, and models consequently fail to generate, truly robust and reliable code snippets. We introduce PACT, a program assessment and contract-adherence evaluation framework, to bridge this gap. PACT is the first framework designed to systematically evaluate and enhance contract-adherence in LLM-generated code snippets alongside functional correctness. PACT's contributions are threefold: First, it provides a comprehensive test-suite corpus focused on contract violations, extending HumanEval+ and MBPP+. Second, it enables a systematic analysis of code generation under varied prompting conditions. This analysis demonstrates that augmenting prompts with contract-violating test cases significantly enhance a model's ability to respect contracts compared to using contract description alone. Finally, it introduces novel metrics to rigorously quantify contract adherence in both test generation and code generation. By revealing critical errors that conventional benchmarks overlook, PACT provides the rigorous and interpretable metrics to evaluate the robustness of LLM-generated code snippets in both functionality and contract-adherence. Our code and data are available at https://github.com/suhanmen/PACT.
Authors: Pedro Domingos
Abstract: Progress in AI is hindered by the lack of a programming language with all the requisite features. Libraries like PyTorch and TensorFlow provide automatic differentiation and efficient GPU implementation, but are additions to Python, which was never intended for AI. Their lack of support for automated reasoning and knowledge acquisition has led to a long and costly series of hacky attempts to tack them on. On the other hand, AI languages like LISP an Prolog lack scalability and support for learning. This paper proposes tensor logic, a language that solves these problems by unifying neural and symbolic AI at a fundamental level. The sole construct in tensor logic is the tensor equation, based on the observation that logical rules and Einstein summation are essentially the same operation, and all else can be reduced to them. I show how to elegantly implement key forms of neural, symbolic and statistical AI in tensor logic, including transformers, formal reasoning, kernel machines and graphical models. Most importantly, tensor logic makes new directions possible, such as sound reasoning in embedding space. This combines the scalability and learnability of neural networks with the reliability and transparency of symbolic reasoning, and is potentially a basis for the wider adoption of AI.
Authors: Jingcong Liang, Shijun Wan, Xuehai Wu, Yitong Li, Qianglong Chen, Duyu Tang, Siyuan Wang, Zhongyu Wei
Abstract: Large Reasoning Models (LRMs) have demonstrated impressive performance on complex tasks, including logical puzzle games that require deriving solutions satisfying all constraints. However, whether they can flexibly apply appropriate rules to varying conditions, particularly when faced with non-canonical game variants, remains an open question. Existing corpora focus on popular puzzles like 9x9 Sudoku, risking overfitting to canonical formats and memorization of solution patterns, which can mask deficiencies in understanding novel rules or adapting strategies to new variants. To address this, we introduce HardcoreLogic, a challenging benchmark of over 5,000 puzzles across 10 games, designed to test the robustness of LRMs on the "long-tail" of logical games. HardcoreLogic systematically transforms canonical puzzles through three dimensions: Increased Complexity (IC), Uncommon Elements (UE), and Unsolvable Puzzles (UP), reducing reliance on shortcut memorization. Evaluations on a diverse set of LRMs reveal significant performance drops, even for models achieving top scores on existing benchmarks, indicating heavy reliance on memorized stereotypes. While increased complexity is the dominant source of difficulty, models also struggle with subtle rule variations that do not necessarily increase puzzle difficulty. Our systematic error analysis on solvable and unsolvable puzzles further highlights gaps in genuine reasoning. Overall, HardcoreLogic exposes the limitations of current LRMs and establishes a benchmark for advancing high-level logical reasoning.
Authors: Dongsheng Ding, Kaiqing Zhang, Jiali Duan, Tamer Ba\c{s}ar, Mihailo R. Jovanovi\'c
Abstract: We study the sequential decision making problem of maximizing the expected total reward while satisfying a constraint on the expected total utility. We employ the natural policy gradient method to solve the discounted infinite-horizon optimal control problem for Constrained Markov Decision Processes (constrained MDPs). Specifically, we propose a new Natural Policy Gradient Primal-Dual (NPG-PD) method that updates the primal variable via natural policy gradient ascent and the dual variable via projected subgradient descent. Although the underlying maximization involves a nonconcave objective function and a nonconvex constraint set, under the softmax policy parametrization, we prove that our method achieves global convergence with sublinear rates regarding both the optimality gap and the constraint violation. Such convergence is independent of the size of the state-action space, i.e., it is~dimension-free. Furthermore, for log-linear and general smooth policy parametrizations, we establish sublinear convergence rates up to a function approximation error caused by restricted policy parametrization. We also provide convergence and finite-sample complexity guarantees for two sample-based NPG-PD algorithms. We use a set of computational experiments to showcase the effectiveness of our approach.
Authors: Haoyi Niu, Shubham Sharma, Yiwen Qiu, Ming Li, Guyue Zhou, Jianming Hu, Xianyuan Zhan
Abstract: Learning effective reinforcement learning (RL) policies to solve real-world complex tasks can be quite challenging without a high-fidelity simulation environment. In most cases, we are only given imperfect simulators with simplified dynamics, which inevitably lead to severe sim-to-real gaps in RL policy learning. The recently emerged field of offline RL provides another possibility to learn policies directly from pre-collected historical data. However, to achieve reasonable performance, existing offline RL algorithms need impractically large offline data with sufficient state-action space coverage for training. This brings up a new question: is it possible to combine learning from limited real data in offline RL and unrestricted exploration through imperfect simulators in online RL to address the drawbacks of both approaches? In this study, we propose the Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning (H2O) framework to provide an affirmative answer to this question. H2O introduces a dynamics-aware policy evaluation scheme, which adaptively penalizes the Q function learning on simulated state-action pairs with large dynamics gaps, while also simultaneously allowing learning from a fixed real-world dataset. Through extensive simulation and real-world tasks, as well as theoretical analysis, we demonstrate the superior performance of H2O against other cross-domain online and offline RL algorithms. H2O provides a brand new hybrid offline-and-online RL paradigm, which can potentially shed light on future RL algorithm design for solving practical real-world tasks.
Authors: Soroosh Shafiee, Liviu Aolaritei, Florian D\"orfler, Daniel Kuhn
Abstract: We study optimal transport-based distributionally robust optimization problems where a fictitious adversary, often envisioned as nature, can choose the distribution of the uncertain problem parameters by reshaping a prescribed reference distribution at a finite transportation cost. In this framework, we show that robustification is intimately related to various forms of variation and Lipschitz regularization even if the transportation cost function fails to be (some power of) a metric. We also derive conditions for the existence and the computability of a Nash equilibrium between the decision-maker and nature, and we demonstrate numerically that nature's Nash strategy can be viewed as a distribution that is supported on remarkably deceptive adversarial samples. Finally, we identify practically relevant classes of optimal transport-based distributionally robust optimization problems that can be addressed with efficient gradient descent algorithms even if the loss function or the transportation cost function are nonconvex (but not both at the same time).
Authors: Zichen Zhu, Yang Xu, Lu Chen, Jingkai Yang, Yichuan Ma, Yiming Sun, Hailin Wen, Jiaqi Liu, Jinyu Cai, Yingzi Ma, Situo Zhang, Zihan Zhao, Liangtai Sun, Kai Yu
Abstract: The rapid development of multimodal large language models (MLLMs) raises the question of how they compare to human performance. While existing datasets often feature synthetic or overly simplistic tasks, some models have already surpassed human expert baselines. In this paper, we present MULTI, a Chinese multimodal dataset derived from authentic examination questions. Comprising over 18,000 carefully selected and refined questions, MULTI evaluates models using real-world examination standards, encompassing image-text comprehension, complex reasoning, and knowledge recall. Additionally, We also introduce MULTI-Elite, a 500-question selected hard subset, and MULTI-Extend with more than 4,500 external knowledge context pieces for testing in-context learning capabilities. Our evaluation highlights substantial room for MLLM advancement, with Qwen2-VL-72B achieving a 76.9% accuracy on MULTI and 53.1% on MULTI-Elite leading 25 evaluated models, compared to human expert baselines of 86.1% and 73.1%. MULTI serves not only as a robust evaluation platform but also paves the way for the development of expert-level AI.
Authors: Chanwoo Park, Xiangyu Liu, Asuman Ozdaglar, Kaiqing Zhang
Abstract: Large language models (LLMs) have been increasingly employed for (interactive) decision-making, via the development of LLM-based autonomous agents. Despite their emerging successes, the performance of LLM agents in decision-making has not been fully investigated through quantitative metrics, especially in the multi-agent setting when they interact with each other, a typical scenario in real-world LLM-agent applications. To better understand the limits of LLM agents in these interactive environments, we propose to study their interactions in benchmark decision-making settings in online learning and game theory, through the performance metric of \emph{regret}. We first empirically study the {no-regret} behaviors of LLMs in canonical (non-stationary) online learning problems, as well as the emergence of equilibria when LLM agents interact through playing repeated games. We then provide some theoretical insights into the no-regret behaviors of LLM agents, under certain assumptions on the supervised pre-training and the rationality model of human decision-makers who generate the data. Notably, we also identify (simple) cases where advanced LLMs such as GPT-4 fail to be no-regret. To promote the no-regret behaviors, we propose a novel \emph{unsupervised} training loss of \emph{regret-loss}, which, in contrast to the supervised pre-training loss, does not require the labels of (optimal) actions. We then establish the statistical guarantee of generalization bound for regret-loss minimization, followed by the optimization guarantee that minimizing such a loss may automatically lead to known no-regret learning algorithms. Our further experiments demonstrate the effectiveness of our regret-loss, especially in addressing the above ``regrettable'' cases.
Authors: Zaitian Wang, Pengfei Wang, Kunpeng Liu, Pengyang Wang, Yanjie Fu, Chang-Tien Lu, Charu C. Aggarwal, Jian Pei, Yuanchun Zhou
Abstract: Data augmentation is a series of techniques that generate high-quality artificial data by manipulating existing data samples. By leveraging data augmentation techniques, AI models can achieve significantly improved applicability in tasks involving scarce or imbalanced datasets, thereby substantially enhancing AI models' generalization capabilities. Existing literature surveys only focus on a certain type of specific modality data and categorize these methods from modality-specific and operation-centric perspectives, which lacks a consistent summary of data augmentation methods across multiple modalities and limits the comprehension of how existing data samples serve the data augmentation process. To bridge this gap, this survey proposes a more enlightening taxonomy that encompasses data augmentation techniques for different common data modalities by investigating how to take advantage of the intrinsic relationship between and within instances. Additionally, it categorizes data augmentation methods across five data modalities through a unified inductive approach.
Authors: Leo Hoshikawa, Marcos V. Conde, Takeshi Ohashi, Atsushi Irie
Abstract: Implicit Neural Representations (INRs) and Neural Fields are a novel paradigm for signal representation, from images and audio to 3D scenes and videos. The fundamental idea is to represent a signal as a continuous and differentiable neural network. This new approach poses new theoretical questions and challenges. Considering a neural image as a 2D image represented as a neural network, we aim to explore novel neural image compression. In this work, we present a novel analysis on compressing neural fields, with focus on images and introduce Adaptive Neural Images (ANI), an efficient neural representation that enables adaptation to different inference or transmission requirements. Our proposed method allows us to reduce the bits-per-pixel (bpp) of the neural image by 8 times, without losing sensitive details or harming fidelity. Our work offers a new framework for developing compressed neural fields. We achieve a new state-of-the-art in terms of PSNR/bpp trade-off thanks to our successful implementation of 4-bit neural representations.
Authors: Zhuohang Jiang, Bingkui Tong, Xia Du, Ahmed Alhammadi, Jizhe Zhou
Abstract: The Privacy-sensitive Object Identification (POI) task allocates bounding boxes for privacy-sensitive objects in a scene. The key to POI is settling an object's privacy class (privacy-sensitive or non-privacy-sensitive). In contrast to conventional object classes which are determined by the visual appearance of an object, one object's privacy class is derived from the scene contexts and is subject to various implicit factors beyond its visual appearance. That is, visually similar objects may be totally opposite in their privacy classes. To explicitly derive the objects' privacy class from the scene contexts, in this paper, we interpret the POI task as a visual reasoning task aimed at the privacy of each object in the scene. Following this interpretation, we propose the PrivacyGuard framework for POI. PrivacyGuard contains three stages. i) Structuring: an unstructured image is first converted into a structured, heterogeneous scene graph that embeds rich scene contexts. ii) Data Augmentation: a contextual perturbation oversampling strategy is proposed to create slightly perturbed privacy-sensitive objects in a scene graph, thereby balancing the skewed distribution of privacy classes. iii) Hybrid Graph Generation & Reasoning: the balanced, heterogeneous scene graph is then transformed into a hybrid graph by endowing it with extra "node-node" and "edge-edge" homogeneous paths. These homogeneous paths allow direct message passing between nodes or edges, thereby accelerating reasoning and facilitating the capturing of subtle context changes. Based on this hybrid graph... **For the full abstract, see the original paper.**
Authors: Xuanjin Jin, Chendong Zeng, Shengfa Zhu, Chunxiao Liu, Panpan Cai
Abstract: Uncertainties in dynamic road environments pose significant challenges for behavior and trajectory planning in autonomous driving. This paper introduces Hi-Drive, a hierarchical planning algorithm addressing uncertainties at both behavior and trajectory levels using a hierarchical Partially Observable Markov Decision Process (POMDP) formulation. Hi-Drive employs driver models to represent uncertain behavioral intentions of other vehicles and uses their parameters to infer hidden driving styles. By treating driver models as high-level decision-making actions, our approach effectively manages the exponential complexity inherent in POMDPs. To further enhance safety and robustness, Hi-Drive integrates a trajectory optimization based on importance sampling, refining trajectories using a comprehensive analysis of critical agents. Evaluations on real-world urban driving datasets demonstrate that Hi-Drive significantly outperforms state-of-the-art planning-based and learning-based methods across diverse urban driving situations in real-world benchmarks.
Authors: Luckeciano C. Melo, Alessandro Abate, Yarin Gal
Abstract: Machine Learning models in real-world applications must continuously learn new tasks to adapt to shifts in the data-generating distribution. Yet, for Continual Learning (CL), models often struggle to balance learning new tasks (plasticity) with retaining previous knowledge (memory stability). Consequently, they are susceptible to Catastrophic Forgetting, which degrades performance and undermines the reliability of deployed systems. In the Bayesian CL literature, variational methods tackle this challenge by employing a learning objective that recursively updates the posterior distribution while constraining it to stay close to its previous estimate. Nonetheless, we argue that these methods may be ineffective due to compounding approximation errors over successive recursions. To mitigate this, we propose new learning objectives that integrate the regularization effects of multiple previous posterior estimations, preventing individual errors from dominating future posterior updates and compounding over time. We reveal insightful connections between these objectives and Temporal-Difference methods, a popular learning mechanism in Reinforcement Learning and Neuroscience. Experiments on challenging CL benchmarks show that our approach effectively mitigates Catastrophic Forgetting, outperforming strong Variational CL methods.
Authors: Or Ordentlich, Yury Polyanskiy
Abstract: Recent work in machine learning community proposed multiple methods for performing lossy compression (quantization) of large matrices. This quantization is important for accelerating matrix multiplication (main component of large language models), which is often bottlenecked by the speed of loading these matrices from memory. Unlike classical vector quantization and rate-distortion theory, the goal of these new compression algorithms is to be able to approximate not the matrices themselves, but their matrix product. Specifically, given a pair of real matrices $A,B$ an encoder (compressor) is applied to each of them independently producing descriptions with $R$ bits per entry. These representations subsequently are used by the decoder to estimate matrix product $A^\top B$. In this work, we provide a non-asymptotic lower bound on the mean squared error of this approximation (as a function of rate $R$) for the case of matrices $A,B$ with iid Gaussian entries. Algorithmically, we construct a universal quantizer based on nested lattices with an explicit guarantee of approximation error for any (non-random) pair of matrices $A$, $B$ in terms of only Frobenius norms $\|\bar{A}\|_F, \|\bar{B}\|_F$ and $\|\bar{A}^\top \bar{B}\|_F$, where $\bar{A},\bar{B}$ are versions of $A,B$ with zero-centered columns, respectively. For iid Gaussian matrices our quantizer achieves the lower bound and is, thus, asymptotically optimal. A practical low-complexity version of our quantizer achieves performance quite close to optimal. In addition, we derive rate-distortion function for matrix multiplication of iid Gaussian matrices, which exhibits an interesting phase-transition at $R\approx 0.906$ bit/entry, showing necessity of Johnson-Lindestrauss dimensionality reduction (sketching) in the low-rate regime.
Authors: Jingqi Zhou, Sheng Wang, Jingwei Dong, Kai Liu, Lei Li, Jiahui Gao, Jiyue Jiang, Lingpeng Kong, Chuan Wu
Abstract: Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation. To tackle this issue, we first identify the drawbacks of existing solutions (i.e., limited multi-modal reasoning capacities, and insufficient and irrelevant visual descriptions). We then decompose visual reasoning process into two stages: proactive visual perception (i.e., eyesight) and textual reasoning (i.e., wisdom), and introduce a novel visual reasoning framework named ProReason. This framework features decoupled vision-reasoning capabilities and multi-run proactive perception. Briefly, given a multi-modal question, ProReason iterates proactive information collection and reasoning until the answer can be concluded with necessary and sufficient visual descriptions. Notably, the disassociation of capabilities allows seamless integration of existing large language models (LLMs) to compensate for the reasoning deficits of LVLMs. Our extensive experiments demonstrate that ProReason outperforms existing multi-step reasoning frameworks on various benchmarks for both open-source and closed-source models, with the average performance gain reaching 13.2%. Besides, the integration of LLMs allows ProReason to produce high-quality visual reasoning data, which empowers ProReason-distilled models (i.e., ProReason-VL and ProReason-Q3) to achieve superior performance in downstream tasks. Our insights into existing solutions and the decoupled perspective for feasible integration of LLMs illuminate future research on visual reasoning techniques, especially LLM-assisted ones.
Authors: Jiawei Zhou, Amy Z. Chen, Darshi Shah, Laura M. Schwab Reese, Munmun De Choudhury
Abstract: Recent breakthroughs in large language models (LLMs) have generated both interest and concern about their potential adoption as information sources or communication tools across different domains. In public health, where stakes are high and impacts extend across diverse populations, adopting LLMs poses unique challenges that require thorough evaluation. However, structured approaches for assessing potential risks in public health remain under-explored. To address this gap, we conducted focus groups with public health professionals and individuals with lived experience to unpack their concerns, situated across three distinct and critical public health issues that demand high-quality information: infectious disease prevention (vaccines), chronic and well-being care (opioid use disorder), and community health and safety (intimate partner violence). We synthesize participants' perspectives into a risk taxonomy, identifying and contextualizing the potential harms LLMs may introduce when positioned alongside traditional health communication. This taxonomy highlights four dimensions of risk to individuals, human-centered care, information ecosystem, and technology accountability. For each dimension, we unpack specific risks and offer example reflection questions to help practitioners adopt a risk-reflexive approach. By summarizing distinctive LLM characteristics and linking them to identified risks, we discuss the need to revisit prior mental models of information behaviors and complement evaluations with external validity and domain expertise through lived experience and real-world practices. Together, this work contributes a shared vocabulary and reflection tool for people in both computing and public health to collaboratively anticipate, evaluate, and mitigate risks in deciding when to employ LLM capabilities (or not) and how to mitigate harm.
Authors: Chaeyun Jang, Deukhwan Cho, Seanie Lee, Hyungi Lee, Juho Lee
Abstract: Recently, Large Language Models (LLMs) have been increasingly used to support various decision-making tasks, assisting humans in making informed decisions. However, when LLMs confidently provide incorrect information, it can lead humans to make suboptimal decisions. To prevent LLMs from generating incorrect information on topics they are unsure of and to improve the accuracy of generated content, prior works have proposed Retrieval Augmented Generation (RAG), where external documents are referenced to generate responses. However, previous RAG methods focus only on retrieving documents most relevant to the input query, without specifically aiming to ensure that the human user's decisions are well-calibrated. To address this limitation, we propose a novel retrieval method called Calibrated Retrieval-Augmented Generation (CalibRAG), which ensures that decisions informed by RAG are well-calibrated. Then we empirically validate that CalibRAG improves calibration performance as well as accuracy, compared to other baselines across various datasets.
Authors: Alkis Kalavasis, Anay Mehrotra, Grigoris Velegkas
Abstract: Specifying all desirable properties of a language model is challenging, but certain requirements seem essential. Given samples from an unknown language, the trained model should produce valid strings not seen in training and be expressive enough to capture the language's full richness. Otherwise, outputting invalid strings constitutes "hallucination," and failing to capture the full range leads to "mode collapse." We ask if a language model can meet both requirements. We investigate this within a statistical language generation setting building on Gold and Angluin. Here, the model receives random samples from a distribution over an unknown language K, which belongs to a possibly infinite collection of languages. The goal is to generate unseen strings from K. We say the model generates from K with consistency and breadth if, as training size increases, its output converges to all unseen strings in K. Kleinberg and Mullainathan [KM24] asked if consistency and breadth in language generation are possible. We answer this negatively: for a large class of language models, including next-token prediction models, this is impossible for most collections of candidate languages. This contrasts with [KM24]'s result, showing consistent generation without breadth is possible for any countable collection of languages. Our finding highlights that generation with breadth fundamentally differs from generation without breadth. As a byproduct, we establish near-tight bounds on the number of samples needed for generation with or without breadth. Finally, our results offer hope: consistent generation with breadth is achievable for any countable collection of languages when negative examples (strings outside K) are available alongside positive ones. This suggests that post-training feedback, which encodes negative examples, can be crucial in reducing hallucinations while limiting mode collapse.
Authors: Anxhelo Diko, Antonino Furnari, Luigi Cinque, Giovanni Maria Farinella
Abstract: Unsupervised domain adaptation remains a critical challenge in enabling the knowledge transfer of models across unseen domains. Existing methods struggle to balance the need for domain-invariant representations with preserving domain-specific features, which is often due to alignment approaches that impose the projection of samples with similar semantics close in the latent space despite their drastic domain differences. We introduce a novel approach that shifts the focus from aligning representations in absolute coordinates to aligning the relative positioning of equivalent concepts in latent spaces. Our method defines a domain-agnostic structure upon the semantic/geometric relationships between class labels in language space and guides adaptation, ensuring that the organization of samples in visual space reflects reference inter-class relationships while preserving domain-specific characteristics. We empirically demonstrate our method's superiority in domain adaptation tasks across four diverse image and video datasets. Remarkably, we surpass previous works in 18 different adaptation scenarios across four diverse image and video datasets with average accuracy improvements of +3.32% on DomainNet, +5.75% in GeoPlaces, +4.77% on GeoImnet, and +1.94% mean class accuracy improvement on EgoExo4D.
Authors: Xingjian Zhou, Keyi Shen, Andy Xu, Hongji Xu, Cho-Jui Hsieh, Huan Zhang, Zhouxing Shi
Abstract: Neural network (NN) verification aims to formally verify properties of NNs, which is crucial for ensuring the behavior of NN-based models in safety-critical applications. In recent years, the community has developed many NN verifiers and benchmarks to evaluate them. However, existing benchmarks typically lack ground-truth for hard instances where no current verifier can verify the property and no counterexample can be found. This makes it difficult to validate the soundness of a verifier, when it claims verification on such challenging instances that no other verifier can handle. In this work, we develop a new benchmark for NN verification, named "SoundnessBench", specifically for testing the soundness of NN verifiers. SoundnessBench consists of instances with deliberately inserted counterexamples that are hidden from adversarial attacks commonly used to find counterexamples. Thereby, it can identify false verification claims when hidden counterexamples are known to exist. We design a training method to produce NNs with hidden counterexamples and systematically construct our SoundnessBench with instances across various model architectures, activation functions, and input data. We demonstrate that our training effectively produces hidden counterexamples and our SoundnessBench successfully identifies bugs in state-of-the-art NN verifiers. Our code is available at https://github.com/MVP-Harry/SoundnessBench and our benchmark is available at https://huggingface.co/datasets/SoundnessBench/SoundnessBench.
URLs: https://github.com/MVP-Harry/SoundnessBench, https://huggingface.co/datasets/SoundnessBench/SoundnessBench.
Authors: Zijian Zhao, Fanyi Meng, Zhonghao Lyu, Hang Li, Xiaoyang Li, Guangxu Zhu
Abstract: Channel state information (CSI) is a fundamental component in both wireless communication and sensing systems, enabling critical functions such as radio resource optimization and environmental perception. In wireless sensing, data scarcity and packet loss hinder efficient model training, while in wireless communication, high-dimensional CSI matrices and short coherent times caused by high mobility present challenges in CSI estimation.To address these issues, we propose a unified framework named CSI-BERT2 for CSI prediction and classification tasks, built on CSI-BERT, which adapts BERT to capture the complex relationships among CSI sequences through a bidirectional self-attention mechanism. We introduce a two-stage training method that first uses a mask language model (MLM) to enable the model to learn general feature extraction from scarce datasets in an unsupervised manner, followed by fine-tuning for specific downstream tasks. Specifically, we extend MLM into a mask prediction model (MPM), which efficiently addresses the CSI prediction task. To further enhance the representation capacity of CSI data, we modify the structure of the original CSI-BERT. We introduce an adaptive re-weighting layer (ARL) to enhance subcarrier representation and a multi-layer perceptron (MLP)-based temporal embedding module to mitigate temporal information loss problem inherent in the original Transformer.Extensive experiments on both real-world collected and simulated datasets demonstrate that CSI-BERT2 achieves state-of-the-art performance across all tasks. Our results further show that CSI-BERT2 generalizes effectively across varying sampling rates and robustly handles discontinuous CSI sequences caused by packet loss-challenges that conventional methods fail to address. The dataset and code are publicly available at https://github.com/RS2002/CSI-BERT2 .
Authors: Kanishk Gandhi, Michael Y. Li, Lyle Goodyear, Agam Bhatia, Louise Li, Aditi Bhaskar, Mohammed Zaman, Noah D. Goodman
Abstract: Understanding the world and explaining it with scientific theories is a central aspiration of artificial intelligence research. Proposing theories, designing experiments to test them, and then revising them based on data are fundamental to scientific discovery. Despite the significant promise of LLM-based scientific agents, no benchmarks systematically test LLM's ability to propose scientific models, collect experimental data, and revise them in light of new data. We introduce BoxingGym, a benchmark with 10 environments for systematically evaluating both experimental design (e.g. collecting data to test a scientific theory) and model discovery (e.g. proposing and revising scientific theories). To enable tractable and quantitative evaluation, we implement each environment as a generative probabilistic model with which a scientific agent can run interactive experiments. These probabilistic models are drawn from various real-world scientific domains ranging from psychology to ecology. To quantitatively evaluate a scientific agent's ability to collect informative experimental data, we compute the expected information gain (EIG), an information-theoretic quantity which measures how much an experiment reduces uncertainty about the parameters of a generative model. A good scientific theory is a concise and predictive explanation. Therefore, to quantitatively evaluate model discovery, we ask a scientific agent to explain their model and then assess whether this explanation enables another scientific agent to make reliable predictions about this environment. In addition to this explanation-based evaluation, we compute standard model evaluation metrics such as prediction errors. We find that current LLMs, such as GPT-4o, struggle with both experimental design and model discovery. We find that augmenting the LLM-based agent with an explicit statistical model does not reliably improve these results.
Authors: Jing Yang
Abstract: The rapid growth of submissions to top-tier Artificial Intelligence (AI) and Machine Learning (ML) conferences has prompted many venues to transition from closed to open review platforms. Some have fully embraced open peer reviews, allowing public visibility throughout the process, while others adopt hybrid approaches, such as releasing reviews only after final decisions or keeping reviews private despite using open peer review systems. In this work, we analyze the strengths and limitations of these models, highlighting the growing community interest in transparent peer review. To support this discussion, we examine insights from Paper Copilot, a website launched two years ago to aggregate and analyze AI / ML conference data while engaging a global audience. The site has attracted over 200,000 early-career researchers, particularly those aged 18-34 from 177 countries, many of whom are actively engaged in the peer review process. Drawing on our findings, this position paper advocates for a more transparent, open, and well-regulated peer review aiming to foster greater community involvement and propel advancements in the field.
Authors: Jinwei Hu, Zhenglin Huang, Xiangyu Yin, Wenjie Ruan, Guangliang Cheng, Yi Dong, Xiaowei Huang
Abstract: Large language models have been widely applied, but can inadvertently encode sensitive or harmful information, raising significant safety concerns. Machine unlearning has emerged to alleviate this concern; however, existing training-time unlearning approaches, relying on coarse-grained loss combinations, have limitations in precisely separating knowledge and balancing removal effectiveness with model utility. In contrast, we propose Fine-grained Activation manipuLation by Contrastive Orthogonal uNalignment (FALCON), a novel representation-guided unlearning approach that leverages information-theoretic guidance for efficient parameter selection, employs contrastive mechanisms to enhance representation separation, and projects conflict gradients onto orthogonal subspaces to resolve conflicts between forgetting and retention objectives. Extensive experiments demonstrate that FALCON achieves superior unlearning effectiveness while maintaining model utility, exhibiting robust resistance against knowledge recovery attempts.
Authors: Jinhe Bi, Yifan Wang, Danqi Yan, Aniri, Wenke Huang, Zengjie Jin, Xiaowen Ma, Artur Hecker, Mang Ye, Xun Xiao, Hinrich Schuetze, Volker Tresp, Yunpu Ma
Abstract: Visual instruction tuning adapts pre-trained Multimodal Large Language Models (MLLMs) to follow human instructions for real-world applications. However, the rapid growth of these datasets introduces significant redundancy, leading to increased computational costs. Existing methods for selecting instruction data aim to prune this redundancy, but predominantly rely on computationally demanding techniques such as proxy-based inference or training-based metrics. Consequently, the substantial computational costs incurred by these selection processes often exacerbate the very efficiency bottlenecks they are intended to resolve, posing a significant challenge to the scalable and effective tuning of MLLMs. To address this challenge, we first identify a critical, yet previously overlooked, factor: the anisotropy inherent in visual feature distributions. We find that this anisotropy induces a \textit{Global Semantic Drift}, and overlooking this phenomenon is a key factor limiting the efficiency of current data selection methods. Motivated by this insight, we devise \textbf{PRISM}, the first training-free framework for efficient visual instruction selection. PRISM surgically removes the corrupting influence of global background features by modeling the intrinsic visual semantics via implicit re-centering. Empirically, PRISM reduces the end-to-end time for data selection and model tuning to just 30\% of conventional pipelines. More remarkably, it achieves this efficiency while simultaneously enhancing performance, surpassing models fine-tuned on the full dataset across eight multimodal and three language understanding benchmarks, culminating in a 101.7\% relative improvement over the baseline. The code is available for access via \href{https://github.com/bibisbar/PRISM}{this repository}.
Authors: Yiming Wang, Pei Zhang, Siyuan Huang, Baosong Yang, Zhuosheng Zhang, Fei Huang, Rui Wang
Abstract: Test-time scaling enhances large language model performance by allocating additional compute resources during inference. Best-of-N (BoN) sampling serves as a common sampling-based scaling technique, broadening the search space in parallel to find better solutions from the model distribution. However, its cost-performance trade-off is still underexplored. Two main challenges limit the efficiency of BoN sampling: (1) Generating N full samples consumes substantial GPU memory, reducing inference capacity under limited resources. (2) Reward models add extra memory and latency overhead, and training strong reward models introduces potential training data costs. Although some studies have explored efficiency improvements, none have addressed both challenges at once. To address this gap, we propose Self-Truncation Best-of-N (ST-BoN), a decoding method that avoids fully generating all N samples and eliminates the need for reward models. It leverages early sampling consistency in the model's internal states to identify the most promising path and truncate suboptimal ones. In terms of cost, ST-BoN reduces dynamic GPU memory usage by over 80% and inference latency by 50%. In terms of cost-performance trade-off, ST-BoN achieves the same performance as Full-BoN while saving computational cost by 70%-80%, and under the same cost, it can improve accuracy by 3-4 points.
Authors: Xue Jiang, Xiulian Peng, Yuan Zhang, Yan Lu
Abstract: Current large speech language models are mainly based on semantic tokens from discretization of self-supervised learned representations and acoustic tokens from a neural codec, following a semantic-modeling and acoustic-synthesis paradigm. However, semantic tokens discard paralinguistic attributes of speakers that is important for natural spoken communication, while prompt-based acoustic synthesis from semantic tokens has limits in recovering paralinguistic details and suffers from robustness issues, especially when there are domain gaps between the prompt and the target. This paper unifies two types of tokens and proposes the UniCodec, a universal speech token learning that encapsulates all semantics of speech, including linguistic and paralinguistic information, into a compact and semantically-disentangled unified token. Such a unified token can not only benefit speech language models in understanding with paralinguistic hints but also help speech generation with high-quality output. A low-bitrate neural codec is leveraged to learn such disentangled discrete representations at global and local scales, with knowledge distilled from self-supervised learned features. Extensive evaluations on multilingual datasets demonstrate its effectiveness in generating natural, expressive and long-term consistent output quality with paralinguistic attributes well preserved in several speech processing tasks.
Authors: Angelo Di Porzio, Marco Coraggio
Abstract: The deployment of autonomous virtual avatars (in extended reality) and robots in human group activities -- such as rehabilitation therapy, sports, and manufacturing -- is expected to increase as these technologies become more pervasive. Designing cognitive architectures and control strategies to drive these agents requires realistic models of human motion. Furthermore, recent research has shown that each person exhibits a unique velocity signature, highlighting how individual motor behaviors are both rich in variability and internally consistent. However, existing models only provide simplified descriptions of human motor behavior, hindering the development of effective cognitive architectures. In this work, we first show that motion amplitude provides a valid and complementary characterization of individual motor signatures. Then, we propose a fully data-driven approach, based on long short-term memory neural networks, to generate original motion that captures the unique features of specific individuals. We validate the architecture using real human data from participants performing spontaneous oscillatory motion. Extensive analyses show that state-of-the-art Kuramoto-like models fail to replicate individual motor signatures, whereas our model accurately reproduces the velocity distribution and amplitude envelopes of the individual it was trained on, while remaining distinct from others.
Authors: Jirui Qi, Raquel Fern\'andez, Arianna Bisazza
Abstract: Retrieval-augmented generation (RAG) with large language models (LLMs) has demonstrated strong performance in multilingual question-answering (QA) tasks by leveraging relevant passages retrieved from corpora. In multilingual RAG (mRAG), the retrieved passages can be written in languages other than that of the query entered by the user, making it challenging for LLMs to effectively utilize the provided information. Recent research suggests that retrieving passages from multilingual corpora can improve RAG performance, particularly for low-resource languages. However, the extent to which LLMs can leverage different kinds of multilingual contexts to generate accurate answers, *independently from retrieval quality*, remains understudied. In this paper, we conduct an extensive assessment of LLMs' ability to (i) make consistent use of a relevant passage regardless of its language, (ii) respond in the expected language, and (iii) focus on the relevant passage even when multiple `distracting' passages in different languages are provided in the context. Our experiments with four LLMs across three QA datasets covering a total of 48 languages reveal a surprising ability of LLMs to extract the relevant information from passages in a different language than the query, but a much weaker ability to formulate a full answer in the correct language. Our analysis, based on both accuracy and feature attribution techniques, further shows that distracting passages negatively impact answer quality regardless of their language. However, distractors in the query language exert a slightly stronger influence. Taken together, our findings deepen the understanding of how LLMs utilize context in mRAG systems, providing directions for future improvements.
Authors: Enming Zhang, Zhengyu Li, Yanru Wu, Jingge Wang, Yang Tan, Guan Wang, Yang Li, Xiaoping Zhang
Abstract: Recent advances in Vision Transformers (ViTs) have significantly advanced semantic segmentation performance. However, their adaptation to new target domains remains challenged by distribution shifts, which often disrupt global attention mechanisms. While existing global and patch-level adaptation methods offer some improvements, they overlook the spatially varying transferability inherent in different image regions. To address this, we propose the Transferable Mask Transformer (TMT), a region-adaptive framework designed to enhance cross-domain representation learning through transferability guidance. First, we dynamically partition the image into coherent regions, grouped by structural and semantic similarity, and estimates their domain transferability at a localized level. Then, we incorporate region-level transferability maps directly into the self-attention mechanism of ViTs, allowing the model to adaptively focus attention on areas with lower transferability and higher semantic uncertainty. Extensive experiments across 20 diverse cross-domain settings demonstrate that TMT not only mitigates the performance degradation typically associated with domain shift but also consistently outperforms existing approaches.
Authors: Belinda Trotta, Robert Johnson, Catherine de Burgh-Day, Debra Hudson, Esteban Abellan, James Canvin, Andrew Kelly, Daniel Mentiplay, Benjamin Owen, Jennifer Whelan
Abstract: Artificial Intelligence (AI) weather models are now reaching operational-grade performance for some variables, but like traditional Numerical Weather Prediction (NWP) models, they exhibit systematic biases and reliability issues. We test the application of the Bureau of Meteorology's existing statistical post-processing system, IMPROVER, to ECMWF's deterministic Artificial Intelligence Forecasting System (AIFS), and compare results against post-processed outputs from the ECMWF HRES and ENS models. Without any modification to processing workflows, post-processing yields comparable accuracy improvements for AIFS as for traditional NWP forecasts, in both expected value and probabilistic outputs. We show that blending AIFS with NWP models improves overall forecast skill, even when AIFS alone is not the most accurate component. These findings show that statistical post-processing methods developed for NWP are directly applicable to AI models, enabling national meteorological centres to incorporate AI forecasts into existing workflows in a low-risk, incremental fashion.
Authors: Subin Kim, Hoonrae Kim, Jihyun Lee, Yejin Jeon, Gary Geunbae Lee
Abstract: Recent studies have explored the use of large language models (LLMs) in psychotherapy; however, text-based cognitive behavioral therapy (CBT) models often struggle with client resistance, which can weaken therapeutic alliance. To address this, we propose a multimodal approach that incorporates nonverbal cues, which allows the AI therapist to better align its responses with the client's negative emotional state. Specifically, we introduce a new synthetic dataset, Mirror (Multimodal Interactive Rolling with Resistance), which is a novel synthetic dataset that pairs each client's statements with corresponding facial images. Using this dataset, we train baseline vision language models (VLMs) so that they can analyze facial cues, infer emotions, and generate empathetic responses to effectively manage client resistance. These models are then evaluated in terms of both their counseling skills as a therapist, and the strength of therapeutic alliance in the presence of client resistance. Our results demonstrate that Mirror significantly enhances the AI therapist's ability to handle resistance, which outperforms existing text-based CBT approaches. Human expert evaluations further confirm the effectiveness of our approach in managing client resistance and fostering therapeutic alliance.
Authors: Chaitali Bhattacharyya, Hyunsei Lee, Junyoung Lee, Shinhyoung Jang, Il hong Suh, Yeseong Kim
Abstract: Training large language models (LLMs) from scratch requires significant computational resources, driving interest in developing smaller, domain-specific LLMs that maintain both efficiency and strong task performance. Medium-sized models such as LLaMA, llama} have served as starting points for domain-specific adaptation, but they often suffer from accuracy degradation when tested on specialized datasets. We introduce FineScope, a framework for deriving compact, domain-optimized LLMs from larger pretrained models. FineScope leverages the Sparse Autoencoder (SAE) framework, inspired by its ability to produce interpretable feature representations, to extract domain-specific subsets from large datasets. We apply structured pruning with domain-specific constraints, ensuring that the resulting pruned models retain essential knowledge for the target domain. To further enhance performance, these pruned models undergo self-data distillation, leveraging SAE-curated datasets to restore key domain-specific information lost during pruning. Extensive experiments and ablation studies demonstrate that FineScope achieves highly competitive performance, outperforming several large-scale state-of-the-art LLMs in domain-specific tasks. Additionally, our results show that FineScope enables pruned models to regain a substantial portion of their original performance when fine-tuned with SAE-curated datasets. Furthermore, applying these datasets to fine-tune pretrained LLMs without pruning also improves their domain-specific accuracy, highlighting the robustness of our approach.
Authors: John L. Zhou, Jonathan C. Kao
Abstract: Offline goal-conditioned reinforcement learning (GCRL) is a promising approach for pretraining generalist policies on large datasets of reward-free trajectories, akin to the self-supervised objectives used to train foundation models for computer vision and natural language processing. However, scaling GCRL to longer horizons remains challenging due to the combination of sparse rewards and discounting, which obscures the comparative advantages of primitive actions with respect to distant goals. Hierarchical RL methods achieve strong empirical results on long-horizon goal-reaching tasks, but their reliance on modular, timescale-specific policies and subgoal generation introduces significant additional complexity and hinders scaling to high-dimensional goal spaces. In this work, we introduce an algorithm to train a flat (non-hierarchical) goal-conditioned policy by bootstrapping on subgoal-conditioned policies with advantage-weighted importance sampling. Our approach eliminates the need for a generative model over the (sub)goal space, which we find is key for scaling to high-dimensional control in large state spaces. We further show that existing hierarchical and bootstrapping-based approaches correspond to specific design choices within our derivation. Across a comprehensive suite of state- and pixel-based locomotion and manipulation benchmarks, our method matches or surpasses state-of-the-art offline GCRL algorithms and scales to complex, long-horizon tasks where prior approaches fail. Project page: https://johnlyzhou.github.io/saw/
Authors: Fanrui Zhang, Dian Li, Qiang Zhang, Jun Chen, Gang Liu, Junxiong Lin, Jiahong Yan, Jiawei Liu, Zheng-Jun Zha
Abstract: The rapid spread of multimodal misinformation on social media has raised growing concerns, while research on video misinformation detection remains limited due to the lack of large-scale, diverse datasets. Existing methods often overfit to rigid templates and lack deep reasoning over deceptive content. To address these challenges, we introduce FakeVV, a large-scale benchmark comprising over 100,000 video-text pairs with fine-grained, interpretable annotations. In addition, we further propose Fact-R1, a novel framework that integrates deep reasoning with collaborative rule-based reinforcement learning. Fact-R1 is trained through a three-stage process: (1) misinformation long-Chain-of-Thought (CoT) instruction tuning, (2) preference alignment via Direct Preference Optimization (DPO), and (3) Group Relative Policy Optimization (GRPO) using a novel verifiable reward function. This enables Fact-R1 to exhibit emergent reasoning behaviors comparable to those observed in advanced text-based reinforcement learning systems, but in the more complex multimodal misinformation setting. Our work establishes a new paradigm for misinformation detection, bridging large-scale video understanding, reasoning-guided alignment, and interpretable verification.
Authors: Runyang You, Yongqi Li, Xinyu Lin, Xin Zhang, Wenjie Wang, Wenjie Li, Liqiang Nie
Abstract: Large recommender models have extended LLMs as powerful recommenders via encoding or item generation, and recent breakthroughs in LLM reasoning synchronously motivate the exploration of reasoning in recommendation. In this work, we propose R$^2$ec, a unified large recommender model with intrinsic reasoning capability. R$^2$ec introduces a dual-head architecture that supports both reasoning chain generation and efficient item prediction in a single model, significantly reducing inference latency. To overcome the lack of annotated reasoning data, we design RecPO, a reinforcement learning framework that optimizes reasoning and recommendation jointly with a novel fused reward mechanism. Extensive experiments on three datasets demonstrate that R$^2$ec outperforms traditional, LLM-based, and reasoning-augmented recommender baselines, while further analyses validate its competitive efficiency among conventional LLM-based recommender baselines and strong adaptability to diverse recommendation scenarios. Code and checkpoints available at https://github.com/YRYangang/RRec.
Authors: Changyi Li, Jiayi Wang, Xudong Pan, Geng Hong, Min Yang
Abstract: Large Reasoning Models (LRMs) leverage transparent reasoning traces, known as Chain-of-Thoughts (CoTs), to break down complex problems into intermediate steps and derive final answers. However, these reasoning traces introduce unique safety challenges: harmful content can be embedded in intermediate steps even when final answers appear benign. Existing moderation tools, designed to handle generated answers, struggle to effectively detect hidden risks within CoTs. To address these challenges, we introduce ReasoningShield, a lightweight yet robust framework for moderating CoTs in LRMs. Our key contributions include: (1) formalizing the task of CoT moderation with a multi-level taxonomy of 10 risk categories across 3 safety levels, (2) creating the first CoT moderation benchmark which contains 9.2K pairs of queries and reasoning traces, including a 7K-sample training set annotated via a human-AI framework and a rigorously curated 2.2K human-annotated test set, and (3) developing a two-stage training strategy that combines stepwise risk analysis and contrastive learning to enhance robustness. Experiments show that ReasoningShield achieves state-of-the-art performance, outperforming task-specific tools like LlamaGuard-4 by 35.6% and general-purpose commercial models like GPT-4o by 15.8% on benchmarks, while also generalizing effectively across diverse reasoning paradigms, tasks, and unseen scenarios. All resources are released at https://github.com/CosmosYi/ReasoningShield.
Authors: Yukin Zhang, Qi Dong
Abstract: Large Language Models (LLMs) exhibit remarkable emergent abilities but remain poorly understood at a mechanistic level. This paper introduces the Multi-Scale Probabilistic Generation Theory (MSPGT), a theoretical framework that models LLMs as Hierarchical Variational Information Bottleneck (H-VIB) systems. MSPGT posits that standard language modeling objectives implicitly optimize multi-scale information compression, leading to the spontaneous formation of three internal processing scales-Global, Intermediate, and Local. We formalize this principle, derive falsifiable predictions about boundary positions and architectural dependencies, and validate them through cross-model experiments combining multi-signal fusion and causal interventions. Results across Llama and Qwen families reveal consistent multi-scale organization but strong architecture-specific variations, partially supporting and refining the theory. MSPGT thus advances interpretability from descriptive observation toward predictive, information-theoretic understanding of how hierarchical structure emerges within large neural language models.
Authors: Hanyin Wang, Zhenbang Wu, Gururaj Kolar, Hariprasad Korsapati, Brian Bartlett, Bryan Hull, Jimeng Sun
Abstract: Diagnosis-Related Group (DRG) codes are essential for hospital reimbursement and operations but require labor-intensive assignment. Large Language Models (LLMs) struggle with DRG coding due to the out-of-distribution (OOD) nature of the task: pretraining corpora rarely contain private clinical or billing data. We introduce DRG-Sapphire, which uses large-scale reinforcement learning (RL) for automated DRG coding from clinical notes. Built on Qwen2.5-7B and trained with Group Relative Policy Optimization (GRPO) using rule-based rewards, DRG-Sapphire introduces a series of RL enhancements to address domain-specific challenges not seen in previous mathematical tasks. Our model achieves state-of-the-art accuracy on the MIMIC-IV benchmark and generates physician-validated reasoning for DRG assignments, significantly enhancing explainability. Our study further sheds light on broader challenges of applying RL to knowledge-intensive, OOD tasks. We observe that RL performance scales approximately linearly with the logarithm of the number of supervised fine-tuning (SFT) examples, suggesting that RL effectiveness is fundamentally constrained by the domain knowledge encoded in the base model. For OOD tasks like DRG coding, strong RL performance requires sufficient knowledge infusion prior to RL. Consequently, scaling SFT may be more effective and computationally efficient than scaling RL alone for such tasks.
Authors: Paul Krzakala, Gabriel Melo, Charlotte Laclau, Florence d'Alch\'e-Buc, R\'emi Flamary
Abstract: Although graph-based learning has attracted a lot of attention, graph representation learning is still a challenging task whose resolution may impact key application fields such as chemistry or biology. To this end, we introduce GRALE, a novel graph autoencoder that encodes and decodes graphs of varying sizes into a shared embedding space. GRALE is trained using an Optimal Transport-inspired loss that compares the original and reconstructed graphs and leverages a differentiable node matching module, which is trained jointly with the encoder and decoder. The proposed attention-based architecture relies on Evoformer, the core component of AlphaFold, which we extend to support both graph encoding and decoding. We show, in numerical experiments on simulated and molecular data, that GRALE enables a highly general form of pre-training, applicable to a wide range of downstream tasks, from classification and regression to more complex tasks such as graph interpolation, editing, matching, and prediction.
Authors: Hao Yin, Lijun Gu, Paritosh Parmar, Lin Xu, Tianxiao Guo, Weiwei Fu, Yang Zhang, Tianyou Zheng
Abstract: With the increasing awareness of health and the growing desire for aesthetic physique, fitness has become a prevailing trend. However, the potential risks associated with fitness training, especially with weight-loaded fitness actions, cannot be overlooked. Action Quality Assessment (AQA), a technology that quantifies the quality of human action and provides feedback, holds the potential to assist fitness enthusiasts of varying skill levels in achieving better training outcomes. Nevertheless, current AQA methodologies and datasets are limited to single-view competitive sports scenarios and RGB modality and lack professional assessment and guidance of fitness actions. To address this gap, we propose the FLEX dataset, the first multi-modal, multi-action, large-scale dataset that incorporates surface electromyography (sEMG) signals into AQA. FLEX utilizes high-precision MoCap to collect 20 different weight-loaded actions performed by 38 subjects across 3 different skill levels for 10 repetitions each, containing 5 different views of the RGB video, 3D pose, sEMG, and physiological information. Additionally, FLEX incorporates knowledge graphs into AQA, constructing annotation rules in the form of penalty functions that map weight-loaded actions, action keysteps, error types, and feedback. We conducted various baseline methodologies on FLEX, demonstrating that multimodal data, multiview data, and fine-grained annotations significantly enhance model performance. FLEX not only advances AQA methodologies and datasets towards multi-modal and multi-action scenarios but also fosters the integration of artificial intelligence within the fitness domain. Dataset and code are available at https://haoyin116.github.io/FLEX_Dataset.
Authors: Luis Pinto
Abstract: Pretrained molecular encoders have become indispensable in computational chemistry for tasks such as property prediction and molecular generation. However, the standard practice of relying solely on final-layer embeddings for downstream tasks may discard valuable information. In this work, we first analyze the information flow in five diverse molecular encoders and find that intermediate layers retain more general-purpose features, whereas the final-layer specializes and compresses information. We then perform an empirical layer-wise evaluation across 22 property prediction tasks. We find that using frozen embeddings from optimal intermediate layers improves downstream performance by an average of 5.4%, up to 28.6%, compared to the final-layer. Furthermore, finetuning encoders truncated at intermediate depths achieves even greater average improvements of 8.5%, with increases as high as 40.8%, obtaining new state-of-the-art results on several benchmarks. These findings highlight the importance of exploring the full representational depth of molecular encoders to achieve substantial performance improvements and computational efficiency. The code will be made publicly available.
Authors: Jan Corazza, Hadi Partovi Aria, Hyohun Kim, Daniel Neider, Zhe Xu
Abstract: Reinforcement learning (RL) algorithms can find an optimal policy for a single agent to accomplish a particular task. However, many real-world problems require multiple agents to collaborate in order to achieve a common goal. For example, a robot executing a task in a warehouse may require the assistance of a drone to retrieve items from high shelves. In Decentralized Multi-Agent RL (DMARL), agents learn independently and then combine their policies at execution time, but often must satisfy constraints on compatibility of local policies to ensure that they can achieve the global task when combined. In this paper, we study how providing high-level symbolic knowledge to agents can help address unique challenges of this setting, such as privacy constraints, communication limitations, and performance concerns. In particular, we extend the formal tools used to check the compatibility of local policies with the team task, making decentralized training with theoretical guarantees usable in more scenarios. Furthermore, we empirically demonstrate that symbolic knowledge about the temporal evolution of events in the environment can significantly expedite the learning process in DMARL.
Authors: Daniel Lawson, Adriana Hugessen, Charlotte Cloutier, Glen Berseth, Khimya Khetarpal
Abstract: While goal-conditioned behavior cloning (GCBC) methods can perform well on in-distribution training tasks, they do not necessarily generalize zero-shot to tasks that require conditioning on novel state-goal pairs, i.e. combinatorial generalization. In part, this limitation can be attributed to a lack of temporal consistency in the state representation learned by BC; if temporally correlated states are properly encoded to similar latent representations, then the out-of-distribution gap for novel state-goal pairs would be reduced. We formalize this notion by demonstrating how encouraging long-range temporal consistency via successor representations (SR) can facilitate generalization. We then propose a simple yet effective representation learning objective, $\text{BYOL-}\gamma$ for GCBC, which theoretically approximates the successor representation in the finite MDP case through self-predictive representations, and achieves competitive empirical performance across a suite of challenging tasks requiring combinatorial generalization.
Authors: Ching Chang, Jeehyun Hwang, Yidan Shi, Haixin Wang, Wen-Chih Peng, Tien-Fu Chen, Wei Wang
Abstract: Time series data in real-world applications such as healthcare, climate modeling, and finance are often irregular, multimodal, and messy, with varying sampling rates, asynchronous modalities, and pervasive missingness. However, existing benchmarks typically assume clean, regularly sampled, unimodal data, creating a significant gap between research and real-world deployment. We introduce Time-IMM, a dataset specifically designed to capture cause-driven irregularity in multimodal multivariate time series. Time-IMM represents nine distinct types of time series irregularity, categorized into trigger-based, constraint-based, and artifact-based mechanisms. Complementing the dataset, we introduce IMM-TSF, a benchmark library for forecasting on irregular multimodal time series, enabling asynchronous integration and realistic evaluation. IMM-TSF includes specialized fusion modules, including a timestamp-to-text fusion module and a multimodality fusion module, which support both recency-aware averaging and attention-based integration strategies. Empirical results demonstrate that explicitly modeling multimodality on irregular time series data leads to substantial gains in forecasting performance. Time-IMM and IMM-TSF provide a foundation for advancing time series analysis under real-world conditions. The dataset is publicly available at https://github.com/blacksnail789521/Time-IMM, and the benchmark library can be accessed at https://github.com/blacksnail789521/IMM-TSF. Project page: https://blacksnail789521.github.io/time-imm-project-page/
URLs: https://github.com/blacksnail789521/Time-IMM,, https://github.com/blacksnail789521/IMM-TSF., https://blacksnail789521.github.io/time-imm-project-page/
Authors: Tony Alex, Wish Suharitdamrong, Sara Atito, Armin Mustafa, Philip J. B. Jackson, Imran Razzak, Muhammad Awais
Abstract: Integration of audio perception into large language models (LLMs) is an emerging research area for enabling machine listening applications, yet efficient transfer of rich audio semantics from audio encoders to LLMs remains underexplored. The most widely used integration paradigm projects the audio encoder output tokens into the LLM input space (e.g., via an MLP or a Q-Former), then prepends or inserts them to the text tokens. We refer to this generic scheme as Prepend to the LLM's input token space (PLITS) integration. We propose an efficient alternative, Lightweight Audio LLM Integration (LAL). LAL introduces audio representations solely via the attention mechanism within different layers of the LLM, bypassing its feedforward module. LAL encodes rich audio semantics at an appropriate level of abstraction for integration into different blocks of LLMs. Our design significantly reduces computational overhead compared to existing integration approaches. Observing with Whisper that the speech encoder benefits from PLITS integration, we propose an audio encoder aware approach for efficiently Probing Audio encoders via LLM (PAL), which employs PLITS integration for Whisper and LAL for general audio encoders. Under an identical training curriculum, LAL consistently maintains performance or outperforms existing integration approaches across multiple base LLMs and tasks. For general audio tasks, LAL improvement is up to 30% over a strong PLITS baseline while reducing memory usage by up to 64.1% and increasing throughput by up to 247.5%. Furthermore, for general audio-music-speech LLM, PAL performs on par with a fully PLITS integration-based system but with substantially improved computational and memory efficiency. Project page: https://ta012.github.io/PAL/
Authors: Antara Raaghavi Bhattacharya, Isabel Papadimitriou, Kathryn Davidson, David Alvarez-Melis
Abstract: Across languages, numeral systems vary widely in how they construct and combine numbers. While humans consistently learn to navigate this diversity, large language models (LLMs) struggle with linguistic-mathematical puzzles involving cross-linguistic numeral systems, which humans can learn to solve successfully. We investigate why this task is difficult for LLMs through a series of experiments that untangle the linguistic and mathematical aspects of numbers in language. Our experiments establish that models cannot consistently solve such problems unless the mathematical operations in the problems are explicitly marked using known symbols ($+$, $\times$, etc., as in "twenty + three"). In further ablation studies, we probe how individual parameters of numeral construction and combination affect performance. While humans use their linguistic understanding of numbers to make inferences about the implicit compositional structure of numerals, LLMs seem to lack this notion of implicit numeral structure. We conclude that the ability to flexibly infer compositional rules from implicit patterns in human-scale data remains an open challenge for current reasoning models.
Authors: Qianqian Liao, Wuque Cai, Hongze Sun, Dongze Liu, Duo Chen, Dezhong Yao, Daqing Guo
Abstract: Recent developed graph-based methods for diagnosing brain disorders using functional connectivity highly rely on predefined brain atlases, but overlook the rich information embedded within atlases and the confounding effects of site and phenotype variability. To address these challenges, we propose a two-stage Brain-to-Population Graph Learning (B2P-GL) framework that integrates the semantic similarity of brain regions and condition-based population graph modeling. In the first stage, termed brain representation learning, we leverage brain atlas knowledge from GPT-4 to enrich the graph representation and refine the brain graph through an adaptive node reassignment graph attention network. In the second stage, termed population disorder diagnosis, phenotypic data is incorporated into population graph construction and feature fusion to mitigate confounding effects and enhance diagnosis performance. Experiments on the ABIDE I, ADHD-200, and Rest-meta-MDD datasets show that B2P-GL outperforms state-of-the-art methods in prediction accuracy while enhancing interpretability. Overall, our proposed framework offers a reliable and personalized approach to brain disorder diagnosis, advancing clinical applicability.
Authors: Chenghao Yang, Ari Holtzman
Abstract: Despite their impressive capabilities, aligned large language models (LLMs) often generate outputs that lack diversity. What drives this consistency in the generation? We investigate this phenomenon through the lens of probability concentration in the model's output distribution. To quantify this concentration, we introduce the *Branching Factor* (BF)--a token-invariant measure of the effective number of plausible next steps during generation. Our empirical analysis reveals two key findings: (1) BF often decreases as generation progresses, suggesting that LLMs become more predictable as they generate. (2) alignment tuning substantially sharpens the model's output distribution from the outset, reducing BF by nearly an order of magnitude (e.g., from 12 to 1.2) relative to base models. This stark reduction helps explain why aligned models often appear less sensitive to decoding strategies. Building on this insight, we find this consistency has surprising implications for complex reasoning. Aligned Chain-of-Thought (CoT) models (e.g., DeepSeek-distilled models), for instance, leverage this effect; by generating longer reasoning chains, they push generation into later, more deterministic (lower BF) stages, resulting in more stable outputs. We hypothesize that alignment tuning does not fundamentally change a model's behavior, but instead steers it toward stylistic tokens (e.g., ``Sure'') that unlock low-entropy trajectories already present in the base model. This view is supported by nudging experiments, which show prompting base models with such tokens can similarly reduce BF. Together, our findings establish BF as a powerful diagnostic for understanding and controlling LLM outputs - clarifying how alignment reduces variability, how CoT promotes stable generations, and how base models can be steered away from diversity.
Authors: Zeju Qiu, Weiyang Liu, Adrian Weller, Bernhard Sch\"olkopf
Abstract: Orthogonal finetuning (OFT) offers highly parameter-efficient adaptation while preventing catastrophic forgetting, but its high runtime and memory demands limit practical deployment. We identify the core computational bottleneck in OFT as its weight-centric implementation, which relies on costly matrix-matrix multiplications with cubic complexity. To overcome this, we propose OFTv2, an input-centric reformulation that instead uses matrix-vector multiplications (i.e., matrix-free computation), reducing the computational cost to quadratic. We further introduce the Cayley-Neumann parameterization, an efficient orthogonal parameterization that approximates the matrix inversion in the Cayley transform via a truncated Neumann series. These modifications allow OFTv2 to achieve up to 10x faster training and 3x lower GPU memory usage without compromising performance. In addition, we extend OFTv2 to support finetuning quantized foundation models and show that it outperforms the popular QLoRA in training stability, efficiency, and memory usage.
Authors: Artur Zolkowski, Kei Nishimura-Gasparian, Robert McCarthy, Roland S. Zimmermann, David Lindner
Abstract: Monitoring Large Language Model (LLM) outputs is crucial for mitigating risks from misuse and misalignment. However, LLMs could evade monitoring through steganography: Encoding hidden information within seemingly benign generations. In this paper, we evaluate the steganography capabilities in frontier LLMs to better understand the risk they pose. We focus on two types of steganography: passing encoded messages and performing encoded reasoning. We find that current models are unable to encode short messages in their outputs without a monitor noticing under standard affordances. They can succeed, however, if given additional affordances like using an unmonitored scratchpad and coordinating on what encoding scheme to use. We additionally find early signs that models can perform basic encoded reasoning in a simple state-tracking problem. This includes some ability to reason with their own and pre-defined schemes, including encoding schemes such as Hexadecimal. Despite this, they can rarely hide reasoning subtly within a cover task to fool a monitor. Overall, our results indicate that current LLMs exhibit nascent steganographic capabilities. While these capabilities are likely insufficient to bypass well-designed monitors at present, this could change in the future.
Authors: A. Bochkov
Abstract: Understanding the locus of semantic representation in large language models (LLMs) is crucial for interpretability and architectural innovation. The dominant paradigm posits that trainable input embeddings serve as foundational "meaning vectors." This paper challenges that view. We construct Transformer models where the embedding layer is entirely frozen, with vectors derived not from data, but from the visual structure of Unicode glyphs. These non-semantic, precomputed visual embeddings are fixed throughout training. Our method is compatible with any tokenizer, including a novel Unicode-centric tokenizer we introduce to ensure universal text coverage. Despite the absence of trainable, semantically initialized embeddings, our models converge, generate coherent text, and, critically, outperform architecturally identical models with trainable embeddings on the MMLU reasoning benchmark. We attribute this to "representational interference" in conventional models, where the embedding layer is burdened with learning both structural and semantic features. Our results indicate that high-level semantics are not inherent to input embeddings but are an emergent property of the Transformer's compositional architecture and data scale. This reframes the role of embeddings from meaning containers to structural primitives. We release all code and models to foster further research.
Authors: Chuzhan Hao, Wenfeng Feng, Yuewei Zhang, Hao Wang
Abstract: Multi-step agentic retrieval systems based on large language models (LLMs) have demonstrated remarkable performance in complex information search tasks. However, these systems still face significant challenges in practical applications, particularly in generating factually inconsistent intermediate queries and inefficient search trajectories, which can lead to reasoning deviations or redundant computations. To address these issues, we propose DynaSearcher, an innovative search agent enhanced by dynamic knowledge graphs and multi-reward reinforcement learning (RL). Specifically, our system leverages knowledge graphs as external structured knowledge to guide the search process by explicitly modeling entity relationships, thereby ensuring factual consistency in intermediate queries and mitigating biases from irrelevant information. Furthermore, we employ a multi-reward RL framework for fine-grained control over training objectives such as retrieval accuracy, efficiency, and response quality. This framework promotes the generation of high-quality intermediate queries and comprehensive final answers, while discouraging unnecessary exploration and minimizing information omissions or redundancy. Experimental results demonstrate that our approach achieves state-of-the-art answer accuracy on six multi-hop question answering datasets, matching frontier LLMs while using only small-scale models and limited computational resources. Furthermore, our approach demonstrates strong generalization and robustness across diverse retrieval environments and larger-scale models, highlighting its broad applicability.
Authors: Hoyoung Lee, Junhyuk Seo, Suhwan Park, Junhyeong Lee, Wonbin Ahn, Chanyeol Choi, Alejandro Lopez-Lira, Yongjae Lee
Abstract: In finance, Large Language Models (LLMs) face frequent knowledge conflicts arising from discrepancies between their pre-trained parametric knowledge and real-time market data. These conflicts are especially problematic in real-world investment services, where a model's inherent biases can misalign with institutional objectives, leading to unreliable recommendations. Despite this risk, the intrinsic investment biases of LLMs remain underexplored. We propose an experimental framework to investigate emergent behaviors in such conflict scenarios, offering a quantitative analysis of bias in LLM-based investment analysis. Using hypothetical scenarios with balanced and imbalanced arguments, we extract the latent biases of models and measure their persistence. Our analysis, centered on sector, size, and momentum, reveals distinct, model-specific biases. Across most models, a tendency to prefer technology stocks, large-cap stocks, and contrarian strategies is observed. These foundational biases often escalate into confirmation bias, causing models to cling to initial judgments even when faced with increasing counter-evidence. A public leaderboard benchmarking bias across a broader set of models is available at https://linqalpha.com/leaderboard
Authors: Aditi Singh, Abul Ehtesham, Mahesh Lambe, Jared James Grogan, Abhishek Singh, Saket Kumar, Luca Muscariello, Vijoy Pandey, Guillaume Sauvage De Saint Marc, Pradyumna Chari, Ramesh Raskar
Abstract: Autonomous AI agents now operate across cloud, enterprise, and decentralized domains, creating demand for registry infrastructures that enable trustworthy discovery, capability negotiation, and identity assurance. We analyze five prominent approaches: (1) MCP Registry (centralized publication of mcp.json descriptors), (2) A2A Agent Cards (decentralized self-describing JSON capability manifests), (3) AGNTCY Agent Directory Service (IPFS Kademlia DHT content routing extended for semantic taxonomy-based content discovery, OCI artifact storage, and Sigstore-backed integrity), (4) Microsoft Entra Agent ID (enterprise SaaS directory with policy and zero-trust integration), and (5) NANDA Index AgentFacts (cryptographically verifiable, privacy-preserving fact model with credentialed assertions). Using four evaluation dimensions: security, authentication, scalability, and maintainability, we surface architectural trade-offs between centralized control, enterprise governance, and distributed resilience. We conclude with design recommendations for an emerging Internet of AI Agents requiring verifiable identity, adaptive discovery flows, and interoperable capability semantics.
Authors: Meng Gai, Guoping Wang, Sheng Li
Abstract: Real-time rendering with global illumination is crucial to afford the user realistic experience in virtual environments. We present a learning-based estimator to predict diffuse indirect illumination in screen space, which then is combined with direct illumination to synthesize globally-illuminated high dynamic range (HDR) results. Our approach tackles the challenges of capturing long-range/long-distance indirect illumination when employing neural networks and is generalized to handle complex lighting and scenarios. From the neural network thinking of the solver to the rendering equation, we present a novel network architecture to predict indirect illumination. Our network is equipped with a modified attention mechanism that aggregates global information guided by spacial geometry features, as well as a monochromatic design that encodes each color channel individually. We conducted extensive evaluations, and the experimental results demonstrate our superiority over previous learning-based techniques. Our approach excels at handling complex lighting such as varying-colored lighting and environment lighting. It can successfully capture distant indirect illumination and simulates the interreflections between textured surfaces well (i.e., color bleeding effects); it can also effectively handle new scenes that are not present in the training dataset.
Authors: Adolfo Gonz\'alez, V\'ictor Parada
Abstract: Demand forecasting in competitive and uncertain business environments requires models that can integrate multiple evaluation perspectives, rather than being restricted to hyperparameter optimization through a single metric. This traditional approach tends to prioritize one error indicator, which can bias results when metrics provide contradictory signals. In this context, the Hierarchical Evaluation Function (HEF) is proposed as a multi-metric framework for hyperparameter optimization that integrates explanatory power (R2), sensitivity to extreme errors (RMSE), and average accuracy (MAE). The performance of HEF was assessed using four widely recognized benchmark datasets in the forecasting domain: the Walmart, M3, M4, and M5 datasets. Prediction models were optimized through Grid Search, Particle Swarm Optimization (PSO), and Optuna, and statistical analyses based on difference-of-proportions tests confirmed that HEF delivers superior results compared to a unimetric reference function, regardless of the optimizer employed, with particular relevance for heterogeneous monthly time series (M3) and highly granular daily demand scenarios (M5). The findings demonstrate that HEF improves stability, generalization, and robustness at a low computational cost, consolidating its role as a reliable evaluation framework that enhances model selection, enables more accurate demand forecasts, and supports decision-making in dynamic and competitive business environments.
Authors: Zhongzhou Chen
Abstract: We present a method for generating large numbers of isomorphic physics problems using generative AI services such as ChatGPT, through prompt chaining and tool use. This approach enables precise control over structural variations-such as numeric values and spatial relations-while supporting diverse contextual variations in the problem body. By utilizing the Python code interpreter, the method supports automatic solution validation and simple diagram generation, addressing key limitations in existing LLM-based methods. We generated two example isomorphic problem banks and compared the outcome against two simpler prompt-based approaches. Results show that prompt-chaining produces significantly higher quality and more consistent outputs than simpler, non-chaining prompts. We also show that GenAI services can be used to validate the quality of the generated isomorphic problems. This work demonstrates a promising method for efficient and scalable problem creation accessible to the average instructor, which opens new possibilities for personalized adaptive testing and automated content development.
Authors: Haokun Lin, Haobo Xu, Yichen Wu, Ziyu Guo, Renrui Zhang, Zhichao Lu, Ying Wei, Qingfu Zhang, Zhenan Sun
Abstract: Recent advances in diffusion large language models (dLLMs) have introduced a promising alternative to autoregressive (AR) LLMs for natural language generation tasks, leveraging full attention and denoising-based decoding strategies. However, the deployment of these models on edge devices remains challenging due to their massive parameter scale and high resource demands. While post-training quantization (PTQ) has emerged as a widely adopted technique for compressing AR LLMs, its applicability to dLLMs remains largely unexplored. In this work, we present the first systematic study on quantizing diffusion-based language models. We begin by identifying the presence of activation outliers, characterized by abnormally large activation values that dominate the dynamic range. These outliers pose a key challenge to low-bit quantization, as they make it difficult to preserve precision for the majority of values. More importantly, we implement state-of-the-art PTQ methods and conduct a comprehensive evaluation across multiple task types and model variants. Our analysis is structured along four key dimensions: bit-width, quantization method, task category, and model type. Through this multi-perspective evaluation, we offer practical insights into the quantization behavior of dLLMs under different configurations. We hope our findings provide a foundation for future research in efficient dLLM deployment. Our code is publicly available at https://github.com/FelixMessi/QDLM.
Authors: Seongheon Park, Sharon Li
Abstract: Object hallucination in large vision-language models presents a significant challenge to their safe deployment in real-world applications. Recent works have proposed object-level hallucination scores to estimate the likelihood of object hallucination; however, these methods typically adopt either a global or local perspective in isolation, which may limit detection reliability. In this paper, we introduce GLSim, a novel training-free object hallucination detection framework that leverages complementary global and local embedding similarity signals between image and text modalities, enabling more accurate and reliable hallucination detection in diverse scenarios. We comprehensively benchmark existing object hallucination detection methods and demonstrate that GLSim achieves superior detection performance, outperforming competitive baselines by a significant margin.
Authors: Delin Qu, Haoming Song, Qizhi Chen, Zhaoqing Chen, Xianqiang Gao, Xinyi Ye, Qi Lv, Modi Shi, Guanghui Ren, Cheng Ruan, Maoqing Yao, Haoran Yang, Jiacheng Bao, Bin Zhao, Dong Wang
Abstract: The human ability to seamlessly perform multimodal reasoning and physical interaction in the open world is a core goal for general-purpose embodied intelligent systems. Recent vision-language-action (VLA) models, which are co-trained on large-scale robot and visual-text data, have demonstrated notable progress in general robot control. However, they still fail to achieve human-level flexibility in interleaved reasoning and interaction. In this work, introduce EO-Robotics, consists of EO-1 model and EO-Data1.5M dataset. EO-1 is a unified embodied foundation model that achieves superior performance in multimodal embodied reasoning and robot control through interleaved vision-text-action pre-training. The development of EO-1 is based on two key pillars: (i) a unified architecture that processes multimodal inputs indiscriminately (image, text, video, and action), and (ii) a massive, high-quality multimodal embodied reasoning dataset, EO-Data1.5M, which contains over 1.5 million samples with emphasis on interleaved vision-text-action comprehension. EO-1 is trained through synergies between auto-regressive decoding and flow matching denoising on EO-Data1.5M, enabling seamless robot action generation and multimodal embodied reasoning. Extensive experiments demonstrate the effectiveness of interleaved vision-text-action learning for open-world understanding and generalization, validated through a variety of long-horizon, dexterous manipulation tasks across multiple embodiments. This paper details the architecture of EO-1, the data construction strategy of EO-Data1.5M, and the training methodology, offering valuable insights for developing advanced embodied foundation models.
Authors: Maggie Chen, Hala Lambdouar, Luca Marini, Laura Mart\'inez-Ferrer, Chris Bridges, Giacomo Acciarini
Abstract: Methane is a potent greenhouse gas and a major driver of climate change, making its timely detection critical for effective mitigation. Machine learning (ML) deployed onboard satellites can enable rapid detection while reducing downlink costs, supporting faster response systems. Conventional methane detection methods often rely on image processing techniques, such as orthorectification to correct geometric distortions and matched filters to enhance plume signals. We introduce a novel approach that bypasses these preprocessing steps by using \textit{unorthorectified} data (UnorthoDOS). We find that ML models trained on this dataset achieve performance comparable to those trained on orthorectified data. Moreover, we also train models on an orthorectified dataset, showing that they can outperform the matched filter baseline (mag1c). We release model checkpoints and two ML-ready datasets comprising orthorectified and unorthorectified hyperspectral images from the Earth Surface Mineral Dust Source Investigation (EMIT) sensor at https://huggingface.co/datasets/SpaceML/UnorthoDOS , along with code at https://github.com/spaceml-org/plume-hunter.
URLs: https://huggingface.co/datasets/SpaceML/UnorthoDOS, https://github.com/spaceml-org/plume-hunter.
Authors: Jie Zhang, Ting Xu, Gelei Deng, Runyi Hu, Han Qiu, Tianwei Zhang, Qing Guo, Ivor Tsang
Abstract: Writing is a universal cultural technology that reuses vision for symbolic communication. Humans display striking resilience: we readily recognize words even when characters are fragmented, fused, or partially occluded. This paper investigates whether advanced vision language models (VLMs) share this resilience. We construct two psychophysics inspired benchmarks across distinct writing systems, Chinese logographs and English alphabetic words, by splicing, recombining, and overlaying glyphs to yield ''visible but unreadable'' stimuli for models while remaining legible to humans. Despite strong performance on clean text, contemporary VLMs show a severe drop under these perturbations, frequently producing unrelated or incoherent outputs. The pattern suggests a structural limitation: models heavily leverage generic visual invariances but under rely on compositional priors needed for robust literacy. We release stimuli generation code, prompts, and evaluation protocols to facilitate transparent replication and follow up work. Our findings motivate architectures and training strategies that encode symbol segmentation, composition, and binding across scripts, and they delineate concrete challenges for deploying multimodal systems in education, accessibility, cultural heritage, and security.
Authors: Yihao Guo, Haocheng Bian, Liutong Zhou, Ze Wang, Zhaoyi Zhang, Francois Kawala, Milan Dean, Ian Fischer, Yuantao Peng, Noyan Tokgozoglu, Ivan Barrientos, Riyaaz Shaik, Rachel Li, Chandru Venkataraman, Reza Shifteh Far, Moses Pawar, Venkat Sundaranatha, Michael Xu, Frank Chu
Abstract: With the deployment of Large Language Models (LLMs) in interactive applications, online malicious intent detection has become increasingly critical. However, existing approaches fall short of handling diverse and complex user queries in real time. To address these challenges, we introduce ADRAG (Adversarial Distilled Retrieval-Augmented Guard), a two-stage framework for robust and efficient online malicious intent detection. In the training stage, a high-capacity teacher model is trained on adversarially perturbed, retrieval-augmented inputs to learn robust decision boundaries over diverse and complex user queries. In the inference stage, a distillation scheduler transfers the teacher's knowledge into a compact student model, with a continually updated knowledge base collected online. At deployment, the compact student model leverages top-K similar safety exemplars retrieved from the online-updated knowledge base to enable both online and real-time malicious query detection. Evaluations across ten safety benchmarks demonstrate that ADRAG, with a 149M-parameter model, achieves 98.5% of WildGuard-7B's performance, surpasses GPT-4 by 3.3% and Llama-Guard-3-8B by 9.5% on out-of-distribution detection, while simultaneously delivering up to 5.6x lower latency at 300 queries per second (QPS) in real-time applications.
Authors: Yiyi Liu, Chunyang Liu, Bohan Wang, Weiqin Jiao, Bojian Wu, Lubin Fan, Yuwei Chen, Fashuai Li, Biao Xiong
Abstract: We present CAGE (Continuity-Aware edGE) network, a robust framework for reconstructing vector floorplans directly from point-cloud density maps. Traditional corner-based polygon representations are highly sensitive to noise and incomplete observations, often resulting in fragmented or implausible layouts.Recent line grouping methods leverage structural cues to improve robustness but still struggle to recover fine geometric details. To address these limitations,we propose a native edge-centric formulation, modeling each wall segment as a directed, geometrically continuous edge. This representation enables inference of coherent floorplan structures, ensuring watertight, topologically valid room boundaries while improving robustness and reducing artifacts. Towards this design, we develop a dual-query transformer decoder that integrates perturbed and latent queries within a denoising framework, which not only stabilizes optimization but also accelerates convergence. Extensive experiments on Structured3D and SceneCAD show that CAGE achieves state-of-the-art performance, with F1 scores of 99.1% (rooms), 91.7% (corners), and 89.3% (angles). The method also demonstrates strong cross-dataset generalization, underscoring the efficacy of our architectural innovations. Code and pretrained models are available on our project page: https://github.com/ee-Liu/CAGE.git.
Authors: Fengyuan Liu, Rui Zhao, Shuo Chen, Guohao Li, Philip Torr, Lei Han, Jindong Gu
Abstract: Individual Large Language Models (LLMs) have demonstrated significant capabilities across various domains, such as healthcare and law. Recent studies also show that coordinated multi-agent systems exhibit enhanced decision-making and reasoning abilities through collaboration. However, due to the vulnerabilities of individual LLMs and the difficulty of accessing all agents in a multi-agent system, a key question arises: If attackers only know one agent, could they still generate adversarial samples capable of misleading the collective decision? To explore this question, we formulate it as a game with incomplete information, where attackers know only one target agent and lack knowledge of the other agents in the system. With this formulation, we propose M-Spoiler, a framework that simulates agent interactions within a multi-agent system to generate adversarial samples. These samples are then used to manipulate the target agent in the target system, misleading the system's collaborative decision-making process. More specifically, M-Spoiler introduces a stubborn agent that actively aids in optimizing adversarial samples by simulating potential stubborn responses from agents in the target system. This enhances the effectiveness of the generated adversarial samples in misleading the system. Through extensive experiments across various tasks, our findings confirm the risks posed by the knowledge of an individual agent in multi-agent systems and demonstrate the effectiveness of our framework. We also explore several defense mechanisms, showing that our proposed attack framework remains more potent than baselines, underscoring the need for further research into defensive strategies.
Authors: Jiazheng Kang, Le Huang, Cheng Hou, Zhe Zhao, Zhenxiang Yan, Ting Bai
Abstract: In real-world industrial settings, large language models (LLMs) must learn continually to keep pace with diverse and evolving tasks, requiring self-evolution to refine knowledge under dynamic data distributions. However, existing continual learning (CL) approaches, such as replay and parameter isolation, often suffer from catastrophic forgetting: training on new tasks degrades performance on earlier ones by overfitting to the new distribution and weakening generalization.We propose MoE-CL, a parameter-efficient adversarial mixture-of-experts framework for industrial-scale, self-evolving continual instruction tuning of LLMs. MoE-CL uses a dual-expert design: (1) a dedicated LoRA expert per task to preserve task-specific knowledge via parameter independence, mitigating forgetting; and (2) a shared LoRA expert to enable cross-task transfer. To prevent transferring task-irrelevant noise through the shared pathway, we integrate a task-aware discriminator within a GAN. The discriminator encourages the shared expert to pass only task-aligned information during sequential training. Through adversarial learning, the shared expert acquires generalized representations that mimic the discriminator, while dedicated experts retain task-specific details, balancing knowledge retention and cross-task generalization and thereby supporting self-evolution.Extensive experiments on the public MTL5 benchmark and an industrial Tencent3 benchmark validate the effectiveness of MoE-CL for continual instruction tuning. In real-world A/B testing for content compliance review on the Tencent Video platform, MoE-CL reduced manual review costs by 15.3%. These results demonstrate that MoE-CL is practical for large-scale industrial deployment where continual adaptation and stable transfer are critical.
Authors: Zejun Liu, Yunshan Chen, Chengxi Xie, Yugui Xie, Huan Liu
Abstract: EEG-based multimodal emotion recognition(EMER) has gained significant attention and witnessed notable advancements, the inherent complexity of human neural systems has motivated substantial efforts toward multimodal approaches. However, this field currently suffers from three critical limitations: (i) the absence of open-source implementations. (ii) the lack of standardized and transparent benchmarks for fair performance analysis. (iii) in-depth discussion regarding main challenges and promising research directions is a notable scarcity. To address these challenges, we introduce LibEMER, a unified evaluation framework that provides fully reproducible PyTorch implementations of curated deep learning methods alongside standardized protocols for data preprocessing, model realization, and experimental setups. This framework enables unbiased performance assessment on three widely-used public datasets across two learning tasks. The open-source library is publicly accessible at: https://anonymous.4open.science/r/2025ULUIUBUEUMUEUR485384
URLs: https://anonymous.4open.science/r/2025ULUIUBUEUMUEUR485384
Authors: Birk Torpmann-Hagen, Michael A. Riegler, P{\aa}l Halvorsen, Dag Johansen
Abstract: Deep neural networks are being utilized in a growing number of applications, both in production systems and for personal use. Network checkpoints are as a consequence often shared and distributed on various platforms to ease the development process. This work considers the threat of neural network stegomalware, where malware is embedded in neural network checkpoints at a negligible cost to network accuracy. This constitutes a significant security concern, but is nevertheless largely neglected by the deep learning practitioners and security specialists alike. We propose the first effective countermeasure to these attacks. In particular, we show that state-of-the-art neural network stegomalware can be efficiently and effectively neutralized through shuffling the column order of the weight- and bias-matrices, or equivalently the channel-order of convolutional layers. We show that this effectively corrupts payloads that have been embedded by state-of-the-art methods in neural network steganography at no cost to network accuracy, outperforming competing methods by a significant margin. We then discuss possible means by which to bypass this defense, additional defense methods, and advocate for continued research into the security of machine learning systems.
Authors: Zilun Zhang, Zian Guan, Tiancheng Zhao, Haozhan Shen, Tianyu Li, Yuxiang Cai, Zhonggen Su, Zhaojun Liu, Jianwei Yin, Xiang Li
Abstract: Referring expression understanding in remote sensing poses unique challenges, as it requires reasoning over complex object-context relationships. While supervised fine-tuning (SFT) on multimodal large language models achieves strong performance with massive labeled datasets, they struggle in data-scarce scenarios, leading to poor generalization. To address this limitation, we propose Geo-R1, a reasoning-centric reinforcement fine-tuning (RFT) paradigm for few-shot geospatial referring. Geo-R1 enforces the model to first generate explicit, interpretable reasoning chains that decompose referring expressions, and then leverage these rationales to localize target objects. This "reason first, then act" process enables the model to make more effective use of limited annotations, enhances generalization, and provides interpretability. We validate Geo-R1 on three carefully designed few-shot geospatial referring benchmarks, where our model consistently and substantially outperforms SFT baselines. It also demonstrates strong cross-dataset generalization, highlighting its robustness. Code and data will be released at: https://github.com/Geo-R1/geo-r1.
Authors: Pavan Karjol, Vivek V Kashyap, Rohan Kashyap, Prathosh A P
Abstract: In this study, we introduce a method for learning group (known or unknown) equivariant functions by learning the associated quadratic form $x^T A x$ corresponding to the group from the data. Certain groups, known as orthogonal groups, preserve a specific quadratic form, and we leverage this property to uncover the underlying symmetry group under the assumption that it is orthogonal. By utilizing the corresponding unique symmetric matrix and its inherent diagonal form, we incorporate suitable inductive biases into the neural network architecture, leading to models that are both simplified and efficient. Our approach results in an invariant model that preserves norms, while the equivariant model is represented as a product of a norm-invariant model and a scale-invariant model, where the ``product'' refers to the group action. Moreover, we extend our framework to a more general setting where the function acts on tuples of input vectors via a diagonal (or product) group action. In this extension, the equivariant function is decomposed into an angular component extracted solely from the normalized first vector and a scale-invariant component that depends on the full Gram matrix of the tuple. This decomposition captures the inter-dependencies between multiple inputs while preserving the underlying group symmetry. We assess the effectiveness of our framework across multiple tasks, including polynomial regression, top quark tagging, and moment of inertia matrix prediction. Comparative analysis with baseline methods demonstrates that our model consistently excels in both discovering the underlying symmetry and efficiently learning the corresponding equivariant function.
Authors: Xiangxin Zhou, Zichen Liu, Haonan Wang, Chao Du, Min Lin, Chongxuan Li, Liang Wang, Tianyu Pang
Abstract: We introduce a variational reasoning framework for language models that treats thinking traces as latent variables and optimizes them through variational inference. Starting from the evidence lower bound (ELBO), we extend it to a multi-trace objective for tighter bounds and propose a forward-KL formulation that stabilizes the training of the variational posterior. We further show that rejection sampling finetuning and binary-reward RL, including GRPO, can be interpreted as local forward-KL objectives, where an implicit weighting by model accuracy naturally arises from the derivation and reveals a previously unnoticed bias toward easier questions. We empirically validate our method on the Qwen 2.5 and Qwen 3 model families across a wide range of reasoning tasks. Overall, our work provides a principled probabilistic perspective that unifies variational inference with RL-style methods and yields stable objectives for improving the reasoning ability of language models. Our code is available at https://github.com/sail-sg/variational-reasoning.
Authors: Qinxun Bai, Yuxuan Han, Wei Xu, Zhengyuan Zhou
Abstract: Off-policy reinforcement learning (RL) with function approximation offers an effective way to improve sample efficiency by reusing past experience. Within this setting, the actor-critic (AC) framework has achieved strong empirical success. However, both the critic and actor learning is challenging for the off-policy AC methods: first of all, in addition to the classic "deadly triad" instability of off-policy evaluation, it also suffers from a "moving target" problem, where the policy being evaluated changes continually; secondly, actor learning becomes less efficient due to the difficulty of estimating the exact off-policy policy gradient. The first challenge essentially reduces the problem to repeatedly performing off-policy evaluation for changing policies. For the second challenge, the off-policy policy gradient theorem requires a complex and often impractical algorithm to estimate an additional emphasis critic, which is typically neglected in practice, thereby reducing to the on-policy policy gradient as an approximation. In this work, we introduce a novel concept of functional critic modeling, which leads to a new AC framework that addresses both challenges for actor-critic learning under the deadly triad setting. We provide a theoretical analysis in the linear function setting, establishing the provable convergence of our framework, which, to the best of our knowledge, is the first convergent off-policy target-based AC algorithm. From a practical perspective, we further propose a carefully designed neural network architecture for the functional critic modeling and demonstrate its effectiveness through preliminary experiments on widely used RL tasks from the DeepMind Control Benchmark.
Authors: Zhe Liu, Yuyan Ni, Zhichen Pu, Qiming Sun, Siyuan Liu, Wen Yan
Abstract: Recently, sophisticated deep learning-based approaches have been developed for generating efficient initial guesses to accelerate the convergence of density functional theory (DFT) calculations. While the actual initial guesses are often density matrices (DM), quantities that can convert into density matrices also qualify as alternative forms of initial guesses. Hence, existing works mostly rely on the prediction of the Hamiltonian matrix for obtaining high-quality initial guesses. However, the Hamiltonian matrix is both numerically difficult to predict and intrinsically non-transferable, hindering the application of such models in real scenarios. In light of this, we propose a method that constructs DFT initial guesses by predicting the electron density in a compact auxiliary basis representation using E(3)-equivariant neural networks. Trained on small molecules with up to 20 atoms, our model is able to achieve an average 33.3% self-consistent field (SCF) step reduction on systems up to 60 atoms, substantially outperforming Hamiltonian-centric and DM-centric models. Critically, this acceleration remains nearly constant with increasing system sizes and exhibits strong transferring behaviors across orbital basis sets and exchange-correlation (XC) functionals. To the best of our knowledge, this work represents the first and robust candidate for a universally transferable DFT acceleration method. We are also releasing the SCFbench dataset and its accompanying code to facilitate future research in this promising direction.
Authors: Ahmed A. Elhag, Arun Raja, Alex Morehead, Samuel M. Blau, Garrett M. Morris, Michael M. Bronstein
Abstract: Accurate and scalable machine-learned inter-atomic potentials (MLIPs) are essential for molecular simulations ranging from drug discovery to new material design. Current state-of-the-art models enforce roto-translational symmetries through equivariant neural network architectures, a hard-wired inductive bias that can often lead to reduced flexibility, computational efficiency, and scalability. In this work, we introduce TransIP: Transformer-based Inter-Atomic Potentials, a novel training paradigm for interatomic potentials achieving symmetry compliance without explicit architectural constraints. Our approach guides a generic non-equivariant Transformer-based model to learn SO(3)-equivariance by optimizing its representations in the embedding space. Trained on the recent Open Molecules (OMol25) collection, a large and diverse molecular dataset built specifically for MLIPs and covering different types of molecules (including small organics, biomolecular fragments, and electrolyte-like species), TransIP effectively learns symmetry in its latent space, providing low equivariance error. Further, compared to a data augmentation baseline, TransIP achieves 40% to 60% improvement in performance across varying OMol25 dataset sizes. More broadly, our work shows that learned equivariance can be a powerful and efficient alternative to augmentation-based MLIP models.
Authors: Jianing Guo, Zhenhong Wu, Chang Tu, Yiyao Ma, Xiangqi Kong, Zhiqian Liu, Jiaming Ji, Shuning Zhang, Yuanpei Chen, Kai Chen, Xianglong Liu, Qi Dou, Yaodong Yang, Huijie Zhao, Weifeng Lv, Simin Li
Abstract: In Vision-Language-Action (VLA) models, robustness to real-world perturbations is critical for deployment. Existing methods target simple visual disturbances, overlooking the broader multi-modal perturbations that arise in actions, instructions, environments, and observations. Here, we first evaluate the robustness of mainstream VLAs under 17 perturbations across four modalities. We find (1) actions as the most fragile modality, (2) Existing visual-robust VLA do not gain robustness in other modality, and (3) pi0 demonstrates superior robustness with a diffusion-based action head. To build multi-modal robust VLAs, we propose RobustVLA against perturbations in VLA inputs and outputs. For output robustness, we perform offline robust optimization against worst-case action noise that maximizes mismatch in flow matching objective. This can be seen as adversarial training, label smoothing, and outlier penalization. For input robustness, we enforce consistent actions across input variations that preserve task semantics. To account for multiple perturbations, we formulate robustness as a multi-armed bandit problem and apply an upper confidence bound algorithm to automatically identify the most harmful noise. Experiments on LIBERO demonstrate our RobustVLA delivers absolute gains over baselines of 12.6% on the pi0 backbone and 10.4% on the OpenVLA backbone across all 17 perturbations, achieving 50.6x faster inference than existing visual-robust VLAs, and a 10.4% gain under mixed perturbations. Our RobustVLA is particularly effective on real-world FR5 robot with limited demonstrations, showing absolute gains by 65.6% under perturbations of four modalities.
Authors: Jiaye Tan, Haonan Luo, Linfeng Song, Shuaiqi Chen, Yishan Lyu, Zian Zhong, Roujia Wang, Daniel Jiang, Haoran Zhang, Jiaming Bai, Haoran Cheng, Q. Vera Liao, Hao-Wen Dong
Abstract: Low-latency symbolic music generation is essential for real-time improvisation and human-AI co-creation. Existing transformer-based models, however, face a trade-off between inference speed and musical quality. Traditional acceleration techniques such as embedding pooling significantly degrade quality, while recently proposed Byte Pair Encoding (BPE) methods - though effective on single-track piano data - suffer large performance drops in multi-track settings, as revealed by our analysis. We propose Attribute-Specialized Key-Value Head Sharing (AS-KVHS), adapted to music's structured symbolic representation, achieving about 30% inference speedup with only a negligible (about 0.4%) quality drop in objective evaluations and slight improvements in subjective listening tests. Our main contributions are (1) the first systematic study of BPE's generalizability in multi-track symbolic music, and (2) the introduction of AS-KVHS for low-latency symbolic music generation. Beyond these, we also release SAGE-Music, an open-source benchmark that matches or surpasses state-of-the-art models in generation quality.
Authors: Jiashun Liu, Johan Obando-Ceron, Han Lu, Yancheng He, Weixun Wang, Wenbo Su, Bo Zheng, Pablo Samuel Castro, Aaron Courville, Ling Pan
Abstract: Most recent RL for LLMs (RL4LLM) methods avoid explicit critics, replacing them with average advantage baselines. This shift is largely pragmatic: conventional value functions are computationally expensive to train at LLM scale and often fail under sparse rewards and long reasoning horizons. We revisit this bottleneck from an architectural perspective and introduce Asymmetric Proximal Policy Optimization (AsyPPO), a simple and scalable framework that restores the critics role while remaining efficient in large-model settings. AsyPPO employs a set of lightweight mini-critics, each trained on disjoint prompt shards. This design encourages diversity while preserving calibration, reducing value-estimation bias. Beyond robust estimation, AsyPPO leverages inter-critic uncertainty to refine the policy update: (i) masking advantages in states where critics agree and gradients add little learning signal, and (ii) filtering high-divergence states from entropy regularization, suppressing spurious exploration. After training on open-source data with only 5,000 samples, AsyPPO consistently improves learning stability and performance across multiple benchmarks over strong baselines, such as GRPO, achieving performance gains of more than six percent on Qwen3-4b-Base and about three percent on Qwen3-8b-Base and Qwen3-14b-Base over classic PPO, without additional tricks. These results highlight the importance of architectural innovations for scalable, efficient algorithms.
Authors: Hengxiang Zhang, Hyeong Kyu Choi, Sharon Li, Hongxin Wei
Abstract: Reasoning distillation has emerged as an efficient and powerful paradigm for enhancing the reasoning capabilities of large language models. However, reasoning distillation may inadvertently cause benchmark contamination, where evaluation data included in distillation datasets can inflate performance metrics of distilled models. In this work, we formally define the task of distillation data detection, which is uniquely challenging due to the partial availability of distillation data. Then, we propose a novel and effective method Token Probability Deviation (TBD), which leverages the probability patterns of the generated output tokens. Our method is motivated by the analysis that distilled models tend to generate near-deterministic tokens for seen questions, while producing more low-probability tokens for unseen questions. Our key idea behind TBD is to quantify how far the generated tokens' probabilities deviate from a high reference probability. In effect, our method achieves competitive detection performance by producing lower scores for seen questions than for unseen questions. Extensive experiments demonstrate the effectiveness of our method, achieving an AUC of 0.918 and a TPR@1% FPR of 0.470 on the S1 dataset.
Authors: Peter Van Katwyk, Karianne J. Bergen
Abstract: Uncertainty quantification is critical for ensuring robustness in high-stakes machine learning applications. We introduce HybridFlow, a modular hybrid architecture that unifies the modeling of aleatoric and epistemic uncertainty by combining a Conditional Masked Autoregressive normalizing flow for estimating aleatoric uncertainty with a flexible probabilistic predictor for epistemic uncertainty. The framework supports integration with any probabilistic model class, allowing users to easily adapt HybridFlow to existing architectures without sacrificing predictive performance. HybridFlow improves upon previous uncertainty quantification frameworks across a range of regression tasks, such as depth estimation, a collection of regression benchmarks, and a scientific case study of ice sheet emulation. We also provide empirical results of the quantified uncertainty, showing that the uncertainty quantified by HybridFlow is calibrated and better aligns with model error than existing methods for quantifying aleatoric and epistemic uncertainty. HybridFlow addresses a key challenge in Bayesian deep learning, unifying aleatoric and epistemic uncertainty modeling in a single robust framework.
Authors: Peigui Qi, Kunsheng Tang, Wenbo Zhou, Weiming Zhang, Nenghai Yu, Tianwei Zhang, Qing Guo, Jie Zhang
Abstract: Text-to-image models have shown remarkable capabilities in generating high-quality images from natural language descriptions. However, these models are highly vulnerable to adversarial prompts, which can bypass safety measures and produce harmful content. Despite various defensive strategies, achieving robustness against attacks while maintaining practical utility in real-world applications remains a significant challenge. To address this issue, we first conduct an empirical study of the text encoder in the Stable Diffusion (SD) model, which is a widely used and representative text-to-image model. Our findings reveal that the [EOS] token acts as a semantic aggregator, exhibiting distinct distributional patterns between benign and adversarial prompts in its embedding space. Building on this insight, we introduce SafeGuider, a two-step framework designed for robust safety control without compromising generation quality. SafeGuider combines an embedding-level recognition model with a safety-aware feature erasure beam search algorithm. This integration enables the framework to maintain high-quality image generation for benign prompts while ensuring robust defense against both in-domain and out-of-domain attacks. SafeGuider demonstrates exceptional effectiveness in minimizing attack success rates, achieving a maximum rate of only 5.48\% across various attack scenarios. Moreover, instead of refusing to generate or producing black images for unsafe prompts, SafeGuider generates safe and meaningful images, enhancing its practical utility. In addition, SafeGuider is not limited to the SD model and can be effectively applied to other text-to-image models, such as the Flux model, demonstrating its versatility and adaptability across different architectures. We hope that SafeGuider can shed some light on the practical deployment of secure text-to-image systems.
Authors: Sumeet Ramesh Motwani, Alesia Ivanova, Ziyang Cai, Philip Torr, Riashat Islam, Shital Shah, Christian Schroeder de Witt, Charles London
Abstract: Large language models excel at short-horizon reasoning tasks, but performance drops as reasoning horizon lengths increase. Existing approaches to combat this rely on inference-time scaffolding or costly step-level supervision, neither of which scales easily. In this work, we introduce a scalable method to bootstrap long-horizon reasoning capabilities using only existing, abundant short-horizon data. Our approach synthetically composes simple problems into complex, multi-step dependency chains of arbitrary length. We train models on this data using outcome-only rewards under a curriculum that automatically increases in complexity, allowing RL training to be scaled much further without saturating. Empirically, our method generalizes remarkably well: curriculum training on composed 6th-grade level math problems (GSM8K) boosts accuracy on longer, competition-level benchmarks (GSM-Symbolic, MATH-500, AIME) by up to 2.06x. It also transfers significantly to diverse out-of-distribution ReasoningGym domains and long-context benchmarks, indicating broader generalization. Importantly, our long-horizon improvements are significantly higher than baselines even at high pass@k, showing that models can learn new reasoning paths under RL. Theoretically, we show that curriculum RL with outcome rewards achieves an exponential improvement in sample complexity over full-horizon training, providing training signal comparable to dense supervision. h1 therefore introduces an efficient path towards scaling RL for long-horizon problems using only existing data.
Authors: Tajamul Ashraf, Umair Nawaz, Abdelrahman M. Shaker, Rao Anwer, Philip Torr, Fahad Shahbaz Khan, Salman Khan
Abstract: Vision language models (VLMs) are increasingly deployed as controllers with access to external tools for complex reasoning and decision-making, yet their effectiveness remains limited by the scarcity of high-quality multimodal trajectories and the cost of manual annotation. We address this challenge with a vision-centric agent tuning framework that automatically synthesizes multimodal trajectories, generates step-wise preference pairs, and trains a VLM controller for robust tool-use reasoning. Our pipeline first constructs M-TRACE, a large-scale dataset of 28.5K multimodal tasks with 177K verified trajectories, enabling imitation-based trajectory tuning. Building on this, we develop MATRIX Agent, a controller finetuned on M-TRACE for step-wise tool reasoning. To achieve finer alignment, we further introduce Pref-X, a set of 11K automatically generated preference pairs, and optimize MATRIX on it via step-wise preference learning. Across three benchmarks, Agent-X, GTA, and GAIA, MATRIX consistently surpasses both open- and closed-source VLMs, demonstrating scalable and effective multimodal tool use. Our data and code is avaliable at https://github.com/mbzuai-oryx/MATRIX.
Authors: Spandan Garg, Benjamin Steenhoek, Yufan Huang
Abstract: Current benchmarks for evaluating software engineering agents, such as SWE-Bench Verified, are predominantly derived from GitHub issues and fail to accurately reflect how developers interact with chat-based coding assistants in integrated development environments (IDEs). We posit that this mismatch leads to a systematic overestimation of agent's capabilities in real-world scenarios, especially bug fixing. We introduce a novel benchmarking framework that transforms existing formal benchmarks into realistic user queries through systematic analysis of developer interaction patterns with chat-based agents. Our methodology is flexible and can be easily extended to existing benchmarks. In this paper, we apply our testing framework to SWE-Bench Verified, the TypeScript subset of Multi-SWE-Bench and a private benchmark, SWE-Bench C# and transform formal GitHub issue descriptions into realistic user-style queries based on telemetry analysis of a popular chat-based agent interactions. Our findings reveal that existing benchmarks significantly overestimate agent capabilities for some models by >50% over baseline performance for public benchmarks and ~10-16% for our internal benchmark. This work establishes a new paradigm for evaluating interactive chat-based software engineering agents through benchmark mutation techniques.
Authors: Ranjan Sapkota, Manoj Karkee
Abstract: This paper presents a comprehensive overview of the Ultralytics YOLO(You Only Look Once) family of object detectors, focusing the architectural evolution, benchmarking, deployment perspectives, and future challenges. The review begins with the most recent release, YOLO26 (or YOLOv26), which introduces key innovations including Distribution Focal Loss (DFL) removal, native NMS-free inference, Progressive Loss Balancing (ProgLoss), Small-Target-Aware Label Assignment (STAL), and the MuSGD optimizer for stable training. The progression is then traced through YOLO11, with its hybrid task assignment and efficiency-focused modules; YOLOv8, which advanced with a decoupled detection head and anchor-free predictions; and YOLOv5, which established the modular PyTorch foundation that enabled modern YOLO development. Benchmarking on the MS COCO dataset provides a detailed quantitative comparison of YOLOv5, YOLOv8, YOLO11, and YOLO26 (YOLOv26), alongside cross-comparisons with YOLOv12, YOLOv13, RT-DETR, and DEIM(DETR with Improved Matching). Metrics including precision, recall, F1 score, mean Average Precision, and inference speed are analyzed to highlight trade-offs between accuracy and efficiency. Deployment and application perspectives are further discussed, covering export formats, quantization strategies, and real-world use in robotics, agriculture, surveillance, and manufacturing. Finally, the paper identifies challenges and future directions, including dense-scene limitations, hybrid CNN-Transformer integration, open-vocabulary detection, and edge-aware training approaches. (Object Detection, YOLOv26, YOLO)
Authors: Xiaonan Si, Meilin Zhu, Simeng Qin, Lijia Yu, Lijun Zhang, Shuaitong Liu, Xinfeng Li, Ranjie Duan, Yang Liu, Xiaojun Jia
Abstract: Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but are vulnerable to corpus poisoning and contamination attacks, which can compromise output integrity. Existing defenses often apply aggressive filtering, leading to unnecessary loss of valuable information and reduced reliability in generation. To address this problem, we propose a two-stage semantic filtering and conflict-free framework for trustworthy RAG. In the first stage, we perform a joint filter with semantic and cluster-based filtering which is guided by the Entity-intent-relation extractor (EIRE). EIRE extracts entities, latent objectives, and entity relations from both the user query and filtered documents, scores their semantic relevance, and selectively adds valuable documents into the clean retrieval database. In the second stage, we proposed an EIRE-guided conflict-aware filtering module, which analyzes semantic consistency between the query, candidate answers, and retrieved knowledge before final answer generation, filtering out internal and external contradictions that could mislead the model. Through this two-stage process, SeCon-RAG effectively preserves useful knowledge while mitigating conflict contamination, achieving significant improvements in both generation robustness and output trustworthiness. Extensive experiments across various LLMs and datasets demonstrate that the proposed SeCon-RAG markedly outperforms state-of-the-art defense methods.
Authors: Yanjiang Guo, Lucy Xiaoyang Shi, Jianyu Chen, Chelsea Finn
Abstract: Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number of real-world rollouts, while systematic improvement demands additional corrective data with expert labels. Both of these processes are slow, costly, and difficult to scale. World models offer a promising, scalable alternative by enabling policies to rollout within imagination space. However, a key challenge is building a controllable world model that can handle multi-step interactions with generalist robot policies. This requires a world model compatible with modern generalist policies by supporting multi-view prediction, fine-grained action control, and consistent long-horizon interactions, which is not achieved by previous works. In this paper, we make a step forward by introducing a controllable multi-view world model that can be used to evaluate and improve the instruction-following ability of generalist robot policies. Our model maintains long-horizon consistency with a pose-conditioned memory retrieval mechanism and achieves precise action control through frame-level action conditioning. Trained on the DROID dataset (95k trajectories, 564 scenes), our model generates spatially and temporally consistent trajectories under novel scenarios and new camera placements for over 20 seconds. We show that our method can accurately rank policy performance without real-world robot rollouts. Moreover, by synthesizing successful trajectories in imagination and using them for supervised fine-tuning, our approach can improve policy success by 44.7\%.
Authors: Giulio Ruffini
Abstract: The regulator theorem states that, under certain conditions, any optimal controller must embody a model of the system it regulates, grounding the idea that controllers embed, explicitly or implicitly, internal models of the controlled. This principle underpins neuroscience and predictive brain theories like the Free-Energy Principle or Kolmogorov/Algorithmic Agent theory. However, the theorem is only proven in limited settings. Here, we treat the deterministic, closed, coupled world-regulator system $(W,R)$ as a single self-delimiting program $p$ via a constant-size wrapper that produces the world output string~$x$ fed to the regulator. We analyze regulation from the viewpoint of the algorithmic complexity of the output, $K(x)$. We define $R$ to be a \emph{good algorithmic regulator} if it \emph{reduces} the algorithmic complexity of the readout relative to a null (unregulated) baseline $\varnothing$, i.e., \[ \Delta = K\big(O_{W,\varnothing}\big) - K\big(O_{W,R}\big) > 0. \] We then prove that the larger $\Delta$ is, the more world-regulator pairs with high mutual algorithmic information are favored. More precisely, a complexity gap $\Delta > 0$ yields \[ \Pr\big((W,R)\mid x\big) \le C\,2^{\,M(W{:}R)}\,2^{-\Delta}, \] making low $M(W{:}R)$ exponentially unlikely as $\Delta$ grows. This is an AIT version of the idea that ``the regulator contains a model of the world.'' The framework is distribution-free, applies to individual sequences, and complements the Internal Model Principle. Beyond this necessity claim, the same coding-theorem calculus singles out a \emph{canonical scalar objective} and implicates a \emph{planner}. On the realized episode, a regulator behaves \emph{as if} it minimized the conditional description length of the readout.
Authors: Michal Sadowski, Tadija Radusinovi\'c, Maria Wyrzykowska, Lukasz Sztukiewicz, Jan Rzymkowski, Pawe{\l} W{\l}odarczyk-Pruszy\'nski, Miko{\l}aj Sacha, Piotr Kozakowski, Ruard van Workum, Stanislaw Kamil Jastrzebski
Abstract: Retrosynthesis is one of the domains transformed by the rise of generative models, and it is one where the problem of nonsensical or erroneous outputs (hallucinations) is particularly insidious: reliable assessment of synthetic plans is time-consuming, with automatic methods lacking. In this work, we present RetroTrim, a retrosynthesis system that successfully avoids nonsensical plans on a set of challenging drug-like targets. Compared to common baselines in the field, our system is not only the sole method that succeeds in filtering out hallucinated reactions, but it also results in the highest number of high-quality paths overall. The key insight behind RetroTrim is the combination of diverse reaction scoring strategies, based on machine learning models and existing chemical databases. We show that our scoring strategies capture different classes of hallucinations by analyzing them on a dataset of labeled retrosynthetic intermediates. This approach formed the basis of our winning solution to the Standard Industries \$1 million Retrosynthesis Challenge. To measure the performance of retrosynthesis systems, we propose a novel evaluation protocol for reactions and synthetic paths based on a structured review by expert chemists. Using this protocol, we compare systems on a set of 32 novel targets, curated to reflect recent trends in drug structures. While the insights behind our methodology are broadly applicable to retrosynthesis, our focus is on targets in the drug-like domain. By releasing our benchmark targets and the details of our evaluation protocol, we hope to inspire further research into reliable retrosynthesis.
Authors: Arip Asadulaev, Semyon Semenov, Abduragim Shtanchaev, Eric Moulines, Fakhri Karray, Martin Takac
Abstract: Modern continuous-time generative models often induce V-shaped transport: each sample travels independently along nearly straight trajectories from prior to data, overlooking shared structure. We introduce Y-shaped generative flows, which move probability mass together along shared pathways before branching to target-specific endpoints. Our formulation is based on novel velocity-powered objective with a sublinear exponent (between zero and one). this concave dependence rewards joint and fast mass movement. Practically, we instantiate the idea in a scalable neural ODE training objective. On synthetic, image, and biology datasets, Y-flows recover hierarchy-aware structure, improve distributional metrics over strong flow-based baselines, and reach targets with fewer integration steps.
Authors: Kevin Krings, Nino S. Bohn, Thomas Ludwig
Abstract: Recent advancements in generative artificial intelligence (GenAI), particularly large language models, have introduced new possibilities for software development practices. In our paper we investigate the emerging Vibe Coding (VC) paradigm that emphasizes intuitive, affect-driven, and improvisational interactions between developers and AI systems. Building upon the discourse of End-User Development (EUD), we explore how VC diverges from conventional programming approaches such as those supported by tools like GitHub Copilot. Through five semi-structured interview sessions with ten experienced software practitioners, we identify five thematic dimensions: creativity, sustainability, the future of programming, collaboration, and criticism. Our analysis conceptualizes VC within the metaphor of co-drifting, contrasting it with the prevalent co-piloting perspective of AI-assisted development. We argue that VC reconfigures the developers role, blurring boundaries between professional and non-developers. While VC enables novel forms of expression and rapid prototyping, it also introduces challenges regarding reproducibility, scalability, and inclusivity. We propose that VC represents a meaningful shift in programming culture, warranting further investigation within human-computer interaction (HCI) and software engineering research.