Authors: Joyanta Jyoti Mondal
Abstract: Background: Childhood and adolescent overweight and obesity remain major public health concerns in the United States and are shaped by behavioral, household, and community factors. Their joint predictive structure at the population level remains incompletely characterized. Objectives: The study aims to identify multilevel predictors of overweight and obesity among U.S. adolescents and compare the predictive performance, calibration, and subgroup equity of statistical, machine-learning, and deep-learning models. Data and Methods: We analyze 18,792 children aged 10-17 years from the 2021 National Survey of Children's Health. Overweight/obesity is defined using BMI categories. Predictors included diet, physical activity, sleep, parental stress, socioeconomic conditions, adverse experiences, and neighborhood characteristics. Models include logistic regression, random forest, gradient boosting, XGBoost, LightGBM, multilayer perceptron, and TabNet. Performance is evaluated using AUC, accuracy, precision, recall, F1 score, and Brier score. Results: Discrimination range from 0.66 to 0.79. Logistic regression, gradient boosting, and MLP showed the most stable balance of discrimination and calibration. Boosting and deep learning modestly improve recall and F1 score. No model was uniformly superior. Performance disparities across race and poverty groups persist across algorithms. Conclusion: Increased model complexity yields limited gains over logistic regression. Predictors consistently span behavioral, household, and neighborhood domains. Persistent subgroup disparities indicate the need for improved data quality and equity-focused surveillance rather than greater algorithmic complexity.
Authors: Cathy Shyr, Yan Hu, Rory J. Tinker, Thomas A. Cassini, Kevin W. Byram, Rizwan Hamid, Daniel V. Fabbri, Adam Wright, Josh F. Peterson, Lisa Bastarache, Hua Xu
Abstract: Phenotyping is fundamental to rare disease diagnosis, but manual curation of structured phenotypes from clinical notes is labor-intensive and difficult to scale. Existing artificial intelligence approaches typically optimize individual components of phenotyping but do not operationalize the full clinical workflow of extracting features from clinical text, standardizing them to Human Phenotype Ontology (HPO) terms, and prioritizing diagnostically informative HPO terms. We developed RARE-PHENIX, an end-to-end AI framework for rare disease phenotyping that integrates large language model-based phenotype extraction, ontology-grounded standardization to HPO terms, and supervised ranking of diagnostically informative phenotypes. We trained RARE-PHENIX using data from 2,671 patients across 11 Undiagnosed Diseases Network clinical sites, and externally validated it on 16,357 real-world clinical notes from Vanderbilt University Medical Center. Using clinician-curated HPO terms as the gold standard, RARE-PHENIX consistently outperformed a state-of-the-art deep learning baseline (PhenoBERT) across ontology-based similarity and precision-recall-F1 metrics in end-to-end evaluation (i.e., ontology-based similarity of 0.70 vs. 0.58). Ablation analyses demonstrated performance improvements with the addition of each module in RARE-PHENIX (extraction, standardization, and prioritization), supporting the value of modeling the full clinical phenotyping workflow. By modeling phenotyping as a clinically aligned workflow rather than a single extraction task, RARE-PHENIX provides structured, ranked phenotypes that are more concordant with clinician curation and has the potential to support human-in-the-loop rare disease diagnosis in real-world settings.
Authors: Samarth KaPatel, Sofia Nikiforova, Giacinto Paolo Saggese, Paul Smith
Abstract: We present DMCD (DataMap Causal Discovery), a two-phase causal discovery framework that integrates LLM-based semantic drafting from variable metadata with statistical validation on observational data. In Phase I, a large language model proposes a sparse draft DAG, serving as a semantically informed prior over the space of possible causal structures. In Phase II, this draft is audited and refined via conditional independence testing, with detected discrepancies guiding targeted edge revisions. We evaluate our approach on three metadata-rich real-world benchmarks spanning industrial engineering, environmental monitoring, and IT systems analysis. Across these datasets, DMCD achieves competitive or leading performance against diverse causal discovery baselines, with particularly large gains in recall and F1 score. Probing and ablation experiments suggest that these improvements arise from semantic reasoning over metadata rather than memorization of benchmark graphs. Overall, our results demonstrate that combining semantic priors with principled statistical verification yields a high-performing and practically effective approach to causal structure learning.
Authors: Hanping Zhang, Yuhong Guo
Abstract: Diffusion models have shown promising capabilities in trajectory generation for planning in offline reinforcement learning (RL). However, conventional diffusion-based planning methods often fail to account for the fact that generating trajectories in RL requires unique consistency between transitions to ensure coherence in real environments. This oversight can result in considerable discrepancies between the generated trajectories and the underlying mechanisms of a real environment. To address this problem, we propose a novel diffusion-based planning method, termed as Diffusion Modulation via Environment Mechanism Modeling (DMEMM). DMEMM modulates diffusion model training by incorporating key RL environment mechanisms, particularly transition dynamics and reward functions. Experimental results demonstrate that DMEMM achieves state-of-the-art performance for planning with offline reinforcement learning.
Authors: Ved Sirdeshmukh, Marc Wetter
Abstract: Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit instruction-following but fail to evaluate whether agents can reason about implicit requirements spanning accessibility needs, privacy boundaries, catastrophic risks, and contextual constraints. We present Implicit Intelligence, an evaluation framework testing whether AI agents can move beyond prompt-following to become genuine goal-fulfillers, paired with Agent-as-a-World (AaW), a harness where interactive worlds are defined in human-readable YAML files and simulated by language models. Our scenarios feature apparent simplicity in user requests, hidden complexity in correct solutions, and discoverability of constraints through environmental exploration. Evaluating 16 frontier and open-weight models across 205 scenarios, we find that even the best-performing model achieves only 48.3% scenario pass rate, revealing substantial room for improvement in bridging the gap between literal instruction-following and human-like contextual reasoning.
Authors: Ruocheng Guo, Kaiwen Dong, Xiang Gao, Kamalika Das
Abstract: The performance of LLM-based agents depends not only on the agent itself but also on the quality of the tool interfaces it consumes. While prior work has focused heavily on agent fine-tuning, tool interfaces-including natural language descriptions and parameter schemas-remain largely human-oriented and often become a bottleneck, especially when agents must select from large candidate tool sets. Existing approaches to improving tool interfaces rely on execution traces, which are frequently unavailable in cold-start or privacy-constrained settings, and typically optimize each tool independently, limiting scalability and generalization to unseen tools. We propose Trace-Free+, a curriculum learning framework that progressively transfers supervision from trace-rich settings to trace-free deployment, encouraging the model to abstract reusable interface-usage patterns and tool usage outcomes. To support this approach, we construct a large-scale dataset of high-quality tool interfaces using a structured workflow over a diverse collection of tools. Experiments on StableToolBench and RestBench show consistent gains on unseen tools, strong cross-domain generalization, and robustness as the number of candidate tools scales to over 100, demonstrating that tool interface optimization is a practical and deployable complement to agent fine-tuning.
Authors: Anirudh Ajith, Amanpreet Singh, Jay DeYoung, Nadav Kunievsky, Austin C. Kozlowski, Oyvind Tafjord, James Evans, Daniel S. Weld, Tom Hope, Doug Downey
Abstract: Can AI systems trained on the scientific record up to a fixed point in time forecast the scientific advances that follow? Such a capability could help researchers identify collaborators and impactful research directions, and anticipate which problems and methods will become central next. We introduce PreScience -- a scientific forecasting benchmark that decomposes the research process into four interdependent generative tasks: collaborator prediction, prior work selection, contribution generation, and impact prediction. PreScience is a carefully curated dataset of 98K recent AI-related research papers, featuring disambiguated author identities, temporally aligned scholarly metadata, and a structured graph of companion author publication histories and citations spanning 502K total papers. We develop baselines and evaluations for each task, including LACERScore, a novel LLM-based measure of contribution similarity that outperforms previous metrics and approximates inter-annotator agreement. We find substantial headroom remains in each task -- e.g. in contribution generation, frontier LLMs achieve only moderate similarity to the ground-truth (GPT-5, averages 5.6 on a 1-10 scale). When composed into a 12-month end-to-end simulation of scientific production, the resulting synthetic corpus is systematically less diverse and less novel than human-authored research from the same period.
Authors: Haotian Si, Changhua Pei, Xiao He, Zeyan Li, Zhe Xie, Zexin Wang, Jiyao Hu, Zhaoyang Yu, Tieying Zhang, Dan Pei, Jianhui Li, Gaogang Xie
Abstract: Driven by the increasingly complex and decision-oriented demands of time series analysis, we introduce the Semantic-Conditional Time Series Reasoning task, which extends conventional time series analysis beyond purely numerical modeling to incorporate contextual and semantic understanding. To further enhance the mode's reasoning capabilities on complex time series problems, we propose a two-round reinforcement learning framework: the first round strengthens the mode's perception of fundamental temporal primitives, while the second focuses on semantic-conditioned reasoning. The resulting model, KairosVL, achieves competitive performance across both synthetic and real-world tasks. Extensive experiments and ablation studies demonstrate that our framework not only boosts performance but also preserves intrinsic reasoning ability and significantly improves generalization to unseen scenarios. To summarize, our work highlights the potential of combining semantic reasoning with temporal modeling and provides a practical framework for real-world time series intelligence, which is in urgent demand.
Authors: Hongbin Zhong, Fazle Faisal, Luis Fran\c{c}a, Tanakorn Leesatapornwongsa, Adriana Szekeres, Kexin Rong, Suman Nath
Abstract: Existing Graphical User Interface (GUI) agents operate through step-by-step calls to vision language models--taking a screenshot, reasoning about the next action, executing it, then repeating on the new page--resulting in high costs and latency that scale with the number of reasoning steps, and limited accuracy due to no persistent memory of previously visited pages. We propose ActionEngine, a training-free framework that transitions from reactive execution to programmatic planning through a novel two-agent architecture: a Crawling Agent that constructs an updatable state-machine memory of the GUIs through offline exploration, and an Execution Agent that leverages this memory to synthesize complete, executable Python programs for online task execution. To ensure robustness against evolving interfaces, execution failures trigger a vision-based re-grounding fallback that repairs the failed action and updates the memory. This design drastically improves both efficiency and accuracy: on Reddit tasks from the WebArena benchmark, our agent achieves 95% task success with on average a single LLM call, compared to 66% for the strongest vision-only baseline, while reducing cost by 11.8x and end-to-end latency by 2x. Together, these components yield scalable and reliable GUI interaction by combining global programmatic planning, crawler-validated action templates, and node-level execution with localized validation and repair.
Authors: Rakshit Trivedi, Kartik Sharma, David C Parkes
Abstract: Effective human-AI coordination requires artificial agents capable of exhibiting and responding to human-like behaviors while adapting to changing contexts. Imitation learning has emerged as one of the prominent approaches to build such agents by training them to mimic human-demonstrated behaviors. However, current methods struggle to capture the inherent diversity and non-Markovian nature of human behavior and lack the ability to steer behavior at inference time. Drawing inspiration from the theory of human cognitive processes, where inner speech guides action selection before execution, we propose MIMIC (Modeling Inner Motivations for Imitation and Control), a framework that uses language as an internal representation of behavioral intent. MIMIC employs the novel use of vision-language models as linguistic scaffolding to train a conditional variational autoencoder capable of generating inner speech from observations. A diffusion-based behavior cloning policy then selects actions conditioned on current observations and the generated inner speech. MIMIC enables fine-grained steering of behavior at inference time by conditioning the agent on behavior-specific speech. Experiments across robotic manipulation tasks and human-AI collaboration games demonstrate that MIMIC significantly enhances both behavior diversity and fidelity to human demonstrations while enabling nuanced behavioral steering without training on additional demonstrations. We open source our code and provide pre-trained MIMIC agents and qualitative demos at: https://mimic-research.github.io.
Authors: Yucheng Shi, Ying Li, Yu Wang, Yesu Feng, Arjun Rao, Rein Houthooft, Shradha Sehgal, Jin Wang, Hao Zhen, Ninghao Liu, Linas Baltrunas
Abstract: Large language models (LLMs) are promising backbones for generative recommender systems, yet a key challenge remains underexplored: verbalization, i.e., converting structured user interaction logs into effective natural language inputs. Existing methods rely on rigid templates that simply concatenate fields, yielding suboptimal representations for recommendation. We propose a data-centric framework that learns verbalization for LLM-based recommendation. Using reinforcement learning, a verbalization agent transforms raw interaction histories into optimized textual contexts, with recommendation accuracy as the training signal. This agent learns to filter noise, incorporate relevant metadata, and reorganize information to improve downstream predictions. Experiments on a large-scale industrial streaming dataset show that learned verbalization delivers up to 93% relative improvement in discovery item recommendation accuracy over template-based baselines. Further analysis reveals emergent strategies such as user interest summarization, noise removal, and syntax normalization, offering insights into effective context construction for LLM-based recommender systems.
Authors: Ayush Sawarni, Jiyuan Tan, Vasilis Syrgkanis
Abstract: Many benchmarks for automated causal inference evaluate a system's performance based on a single numerical output, such as an Average Treatment Effect (ATE). This approach conflates two distinct steps in causal analysis: identification-formulating a valid research design under stated assumptions-and estimation-implementing that design numerically on finite data. We introduce CausalReasoningBenchmark, a benchmark of 173 queries across 138 real-world datasets, curated from 85 peer-reviewed research papers and four widely-used causal-inference textbooks. For each query a system must produce (i) a structured identification specification that names the strategy, the treatment, outcome, and control variables, and all design-specific elements, and (ii) a point estimate with a standard error. By scoring these two components separately, our benchmark enables granular diagnosis: it distinguishes failures in causal reasoning from errors in numerical execution. Baseline results with a state-of-the-art LLM show that, while the model correctly identifies the high-level strategy in 84 % of cases, full identification-specification correctness drops to only 30 %, revealing that the bottleneck lies in the nuanced details of research design rather than in computation. CausalReasoningBenchmark is publicly available on Hugging Face and is designed to foster the development of more robust automated causal-inference systems.
Authors: Hyeongmo Kim, Sohyun Kang, Yerin Choi, Seungyeon Ji, Junhyuk Woo, Hyunsuk Chung, Soyeon Caren Han, Kyungreem Han
Abstract: The term 'algorithmic fairness' is used to evaluate whether AI models operate fairly in both comparative (where fairness is understood as formal equality, such as "treat like cases as like") and non-comparative (where unfairness arises from the model's inaccuracy, arbitrariness, or inscrutability) contexts. Recent advances in multimodal large language models (MLLMs) are breaking new ground in multimodal understanding, reasoning, and generation; however, we argue that inconspicuous distortions arising from complex multimodal interaction dynamics can lead to systematic bias. The purpose of this position paper is twofold: first, it is intended to acquaint AI researchers with phenomenological explainable approaches that rely on the physical entities that the machine experiences during training/inference, as opposed to the traditional cognitivist symbolic account or metaphysical approaches; second, it is to state that this phenomenological doctrine will be practically useful for tackling algorithmic fairness issues in MLLMs. We develop a surrogate physics-based model that describes transformer dynamics (i.e., semantic network structure and self-/cross-attention) to analyze the dynamics of cross-modal bias in MLLM, which are not fully captured by conventional embedding- or representation-level analyses. We support this position through multi-input diagnostic experiments: 1) perturbation-based analyses of emotion classification using Qwen2.5-Omni and Gemma 3n, and 2) dynamical analysis of Lorenz chaotic time-series prediction through the physical surrogate. Across two architecturally distinct MLLMs, we show that multimodal inputs can reinforce modality dominance rather than mitigate it, as revealed by structured error-attractor patterns under systematic label perturbation, complemented by dynamical analysis.
Authors: Nelson Gardner-Challis, Jonathan Bostock, Georgiy Kozhevnikov, Morgan Sinclaire, Joan Velja, Alessandro Abate, Charlie Griffin
Abstract: AIs are increasingly being deployed with greater autonomy and capabilities, which increases the risk that a misaligned AI may be able to cause catastrophic harm. Untrusted monitoring -- using one untrusted model to oversee another -- is one approach to reducing risk. Justifying the safety of an untrusted monitoring deployment is challenging because developers cannot safely deploy a misaligned model to test their protocol directly. In this paper, we develop upon existing methods for rigorously demonstrating safety based on pre-deployment testing. We relax assumptions that previous AI control research made about the collusion strategies a misaligned AI might use to subvert untrusted monitoring. We develop a taxonomy covering passive self-recognition, causal collusion (hiding pre-shared signals), acausal collusion (hiding signals via Schelling points), and combined strategies. We create a safety case sketch to clearly present our argument, explicitly state our assumptions, and highlight unsolved challenges. We identify conditions under which passive self-recognition could be a more effective collusion strategy than those studied previously. Our work builds towards more robust evaluations of untrusted monitoring.
Authors: Vincent Auriau (Heudiasyc), Khaled Belahcene (Heudiasyc), Emmanuel Malherbe (MICS), Vincent Mousseau (MICS), Marc Pirlot
Abstract: Eliciting a preference model involves asking a person, named decision-maker, a series of questions. We assume that these preferences can be represented by an additive value function. In this work, we query simultaneously two decision-makers in the aim to elicit their respective value functions. For each query we receive two answers, without noise, but without knowing which answer corresponds to which decision-maker.We propose an elicitation procedure that identifies the two preference models when the marginal value functions are piecewise linear with known breaking points.
Authors: Bo Zhang, Jinfeng Zhou, Yuxuan Chen, Jianing Yin, Minlie Huang, Hongning Wang
Abstract: Large Language Models (LLMs) have shown significant potential in scientific discovery but struggle to bridge the gap between theoretical reasoning and verifiable physical simulation. Existing solutions operate in a passive "execute-then-response" loop and thus lacks runtime perception, obscuring agents to transient anomalies (e.g., numerical instability or diverging oscillations). To address this limitation, we propose EmbodiedAct, a framework that transforms established scientific software into active embodied agents by grounding LLMs in embodied actions with a tight perception-execution loop. We instantiate EmbodiedAct within MATLAB and evaluate it on complex engineering design and scientific modeling tasks. Extensive experiments show that EmbodiedAct significantly outperforms existing baselines, achieving SOTA performance by ensuring satisfactory reliability and stability in long-horizon simulations and enhanced accuracy in scientific modeling.
Authors: Vaidehi Bagaria, Bijo Sebastian, Nirav Patel
Abstract: Current vision-language-action (VLA) models struggle with long-horizon manipulation under partial observability. Most existing approaches remain observation-driven, relying on short context windows or repeated queries to vision-language models (VLMs). This leads to loss of task progress, action repetition under perceptual aliasing, and high inference latency. Semantic reasoning alone is not the primary bottleneck in long-horizon manipulation. Instead, VLAs lack persistent, action-conditioned state representations and exhibit limited temporal and physical reasoning, making them ill-suited for multi-stage control. This paper introduces RB-VLA, a belief-centric architecture trained with self-supervised world-model objectives that maintains a compact latent state encoding task-relevant history, dynamics, and object interactions. Queried once for high-level intent, the VLM provides task specification, while the belief tracks task progress and enables phase-aware, causally grounded control under partial observability without storing raw observations or scaling memory with time. The belief and intent jointly condition a diffusion policy for robust closed-loop execution. RB-VLA outperforms prior VLAs on long-horizon benchmarks, achieving 52.5% and 37.5% higher success on multi-stage pick-and-place and stacking tasks, respectively, compared to {\pi}0. It also reduces inference latency by up to 5x relative to baselines and eliminates memory growth across timesteps observed in existing VLAs. Ablations show that the belief module is the primary driver of performance, increasing success rates from 32.5% to 77.5%. These results demonstrate the effectiveness of belief-based state representations for long-horizon VLA policies.
Authors: Bo Peng, Pi Bu, Keyu Pan, Xinrun Xu, Yinxiu Zhao, Miao Chen, Yang Du, Lin Li, Jun Song, Tong Xu
Abstract: Recent advances in vision-language models (VLMs) have shown promise for human-level embodied intelligence. However, existing benchmarks for VLM-driven embodied agents often rely on high-level commands or discretized action spaces, which are non-native settings that differ markedly from real-world control. In addition, current benchmarks focus primarily on high-level tasks and lack joint evaluation and analysis at both low and high levels. To address these limitations, we present NativeEmbodied, a challenging benchmark for VLM-driven embodied agents that uses a unified, native low-level action space. Built on diverse simulated scenes, NativeEmbodied includes three representative high-level tasks in complex scenarios to evaluate overall performance. For more detailed analysis, we further decouple the skills required by complex tasks and construct four types of low-level tasks, each targeting a fundamental embodied skill. This joint evaluation across task and skill granularities enables fine-grained assessment of embodied agents. Experiments with state-of-the-art VLMs reveal clear deficiencies in several fundamental embodied skills, and further analysis shows that these bottlenecks significantly limit performance on high-level tasks. NativeEmbodied highlights key challenges for current VLM-driven embodied agents and provides insights to guide future research.
Authors: Baolong Bi, Yuyao Ge, Shenghua Liu, Yuchen He, Siqian Tong, Lizhe Chen, Lingrui Mei, Zehao Li, Yiwei Wang, Yujun Cai, Ming-Hsuan Yang, Xueqi Cheng
Abstract: Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human preferences and values. However, most existing alignment approaches operate at training time and rely on additional high-quality data, incurring significant computational and annotation costs. While recent work has shown that contrastive decoding can leverage a model's internal distributions to improve specific capabilities, its applicability remains limited to narrow behavioral scopes and scenarios. In this work, we introduce Polarity-Prompt Contrastive Decoding (PromptCD), a test-time behavior control method that generalizes contrastive decoding to broader enhancement settings. PromptCD constructs paired positive and negative guiding prompts for a target behavior and contrasts model responses-specifically token-level probability distributions in LLMs and visual attention patterns in VLMs-to reinforce desirable outcomes. This formulation extends contrastive decoding to a wide range of enhancement objectives and is applicable to both LLMs and Vision-Language Models (VLMs) without additional training. For LLMs, experiments on the "3H" alignment objectives (helpfulness, honesty, and harmlessness) demonstrate consistent and substantial improvements, indicating that post-trained models can achieve meaningful self-enhancement purely at test time. For VLMs, we further analyze contrastive effects on visual attention, showing that PromptCD significantly improves VQA performance by reinforcing behavior-consistent visual grounding. Collectively, these results highlight PromptCD as a simple, general, and cost-efficient strategy for reliable behavior control across modalities.
Authors: Julien Dallot, Yuval Emek, Yuval Gil, Maciej Pacut, Stefan Schmid
Abstract: This paper introduces a new model for ML-augmented online decision making, called online algorithms with unreliable guidance (OAG). This model completely separates between the predictive and algorithmic components, thus offering a single well-defined analysis framework that relies solely on the considered problem. Formulated through the lens of request-answer games, an OAG algorithm receives, with each incoming request, a piece of guidance which is taken from the problem's answer space; ideally, this guidance is the optimal answer for the current request, however with probability $\beta$, the guidance is adversarially corrupted. The goal is to develop OAG algorithms that admit good competitiveness when $\beta = 0$ (a.k.a. consistency) as well as when $\beta = 1$ (a.k.a. robustness); the appealing notion of smoothness, that in most prior work required a dedicated loss function, now arises naturally as $\beta$ shifts from $0$ to $1$. We then describe a systematic method, called the drop or trust blindly (DTB) compiler, which transforms any online algorithm into a learning-augmented online algorithm in the OAG model. Given a prediction-oblivious online algorithm, its learning-augmented counterpart produced by applying the DTB compiler either follows the incoming guidance blindly or ignores it altogether and proceeds as the initial algorithm would have; the choice between these two alternatives is based on the outcome of a (biased) coin toss. As our main technical contribution, we prove (rigorously) that although remarkably simple, the class of algorithms produced via the DTB compiler includes algorithms with attractive consistency-robustness guarantees for three classic online problems: for caching and uniform metrical task systems our algorithms are optimal, whereas for bipartite matching (with adversarial arrival order), our algorithm outperforms the state-of-the-art.
Authors: Che Wang, Fuyao Zhang, Jiaming Zhang, Ziqi Zhang, Yinghui Wang, Longtao Huang, Jianbo Gao, Zhong Chen, Wei Yang Bryan Lim
Abstract: Large Language Model (LLM) agents are susceptible to Indirect Prompt Injection (IPI) attacks, where malicious instructions in retrieved content hijack the agent's execution. Existing defenses typically rely on strict filtering or refusal mechanisms, which suffer from a critical limitation: over-refusal, prematurely terminating valid agentic workflows. We propose ICON, a probing-to-mitigation framework that neutralizes attacks while preserving task continuity. Our key insight is that IPI attacks leave distinct over-focusing signatures in the latent space. We introduce a Latent Space Trace Prober to detect attacks based on high intensity scores. Subsequently, a Mitigating Rectifier performs surgical attention steering that selectively manipulate adversarial query key dependencies while amplifying task relevant elements to restore the LLM's functional trajectory. Extensive evaluations on multiple backbones show that ICON achieves a competitive 0.4% ASR, matching commercial grade detectors, while yielding a over 50% task utility gain. Furthermore, ICON demonstrates robust Out of Distribution(OOD) generalization and extends effectively to multi-modal agents, establishing a superior balance between security and efficiency.
Authors: Peter Hase, Christopher Potts
Abstract: Inspecting Chain-of-Thought reasoning is among the most common means of understanding why an LLM produced its output. But well-known problems with CoT faithfulness severely limit what insights can be gained from this practice. In this paper, we introduce a training method called Counterfactual Simulation Training (CST), which aims to improve CoT faithfulness by rewarding CoTs that enable a simulator to accurately predict a model's outputs over counterfactual inputs. We apply CST in two settings: (1) CoT monitoring with cue-based counterfactuals, to detect when models rely on spurious features, reward hack, or are sycophantic, and (2) counterfactual simulation over generic model-based counterfactuals, to encourage models to produce more faithful, generalizable reasoning in the CoT. Experiments with models up to 235B parameters show that CST can substantially improve monitor accuracy on cue-based counterfactuals (by 35 accuracy points) as well as simulatability over generic counterfactuals (by 2 points). We further show that: (1) CST outperforms prompting baselines, (2) rewriting unfaithful CoTs with an LLM is 5x more efficient than RL alone, (3) faithfulness improvements do not generalize to dissuading cues (as opposed to persuading cues), and (4) larger models do not show more faithful CoT out of the box, but they do benefit more from CST. These results suggest that CST can improve CoT faithfulness in general, with promising applications for CoT monitoring. Code for experiments in this paper is available at https://github.com/peterbhase/counterfactual-simulation-training
URLs: https://github.com/peterbhase/counterfactual-simulation-training
Authors: Xu Wan, Yansheng Wang, Wenqi Huang, Mingyang Sun
Abstract: Traditional on-policy Reinforcement Learning with Verifiable Rewards (RLVR) frameworks suffer from experience waste and reward homogeneity, which directly hinders learning efficiency on difficult samples during large language models post-training. In this paper, we introduce Batch Adaptation Policy Optimization (BAPO), an off-policy RLVR framework to improve the data efficiency in large language models post-training. It dynamically selects training batches by re-evaluating historically difficult samples and reusing high-quality ones, while holding a lower bound guarantee for policy improvement. Extensive experiments further demonstrate that BAPO achieves an average 12.5% improvement over GRPO across mathematics, planning, and visual reasoning tasks. Crucially, BAPO successfully resolves 40.7% of problems that base models consistently fail to solve.
Authors: Ji Dai, Quan Fang, Dengsheng Cai
Abstract: Multimodal recommendation enhances ranking by integrating user-item interactions with item content, which is particularly effective under sparse feedback and long-tail distributions. However, multimodal signals are inherently heterogeneous and can conflict in specific contexts, making effective fusion both crucial and challenging. Existing approaches often rely on shared fusion pathways, leading to entangled representations and modality imbalance. To address these issues, we propose \textbf{MAGNET}, a \textbf{M}odality-Guided Mixture of \textbf{A}daptive \textbf{G}raph Experts \textbf{N}etwork with Progressive \textbf{E}ntropy-\textbf{T}riggered Routing for Multimodal Recommendation, designed to enhance controllability, stability, and interpretability in multimodal fusion. MAGNET couples interaction-conditioned expert routing with structure-aware graph augmentation, so that both \emph{what} to fuse and \emph{how} to fuse are explicitly controlled and interpretable. At the representation level, a dual-view graph learning module augments the interaction graph with content-induced edges, improving coverage for sparse and long-tail items while preserving collaborative structure via parallel encoding and lightweight fusion. At the fusion level, MAGNET employs structured experts with explicit modality roles -- dominant, balanced, and complementary -- enabling a more interpretable and adaptive combination of behavioral, visual, and textual cues. To further stabilize sparse routing and prevent expert collapse, we introduce a two-stage entropy-weighting mechanism that monitors routing entropy. This mechanism automatically transitions training from an early coverage-oriented regime to a later specialization-oriented regime, progressively balancing expert utilization and routing confidence. Extensive experiments on public benchmarks demonstrate consistent improvements over strong baselines.
Authors: Chenyang Zhao, Vinny Cahill, Ivana Dusparic
Abstract: Reward design has been one of the central challenges for real world reinforcement learning (RL) deployment, especially in settings with multiple objectives. Preference-based RL offers an appealing alternative by learning from human preferences over pairs of behavioural outcomes. More recently, RL from AI feedback (RLAIF) has demonstrated that large language models (LLMs) can generate preference labels at scale, mitigating the reliance on human annotators. However, existing RLAIF work typically focuses only on single-objective tasks, leaving the open question of how RLAIF handles systems that involve multiple objectives. In such systems trade-offs among conflicting objectives are difficult to specify, and policies risk collapsing into optimizing for a dominant goal. In this paper, we explore the extension of the RLAIF paradigm to multi-objective self-adaptive systems. We show that multi-objective RLAIF can produce policies that yield balanced trade-offs reflecting different user priorities without laborious reward engineering. We argue that integrating RLAIF into multi-objective RL offers a scalable path toward user-aligned policy learning in domains with inherently conflicting objectives.
Authors: Chao Fei, Guozhong Li, Chenxi Liu, Panos Kalnis
Abstract: Long-context LLMs demand accurate inference at low latency, yet decoding becomes primarily constrained by KV cache as context grows. Prior pruning methods are largely context-agnostic: their token selection ignores step-wise relevance and local semantics, which undermines quality. Moreover, their irregular accesses and selection overheads yield only limited wall-clock speedups. To address this, we propose \textbf{CHESS}, an \textit{algorithm-system co-design} KV-cache management system. Algorithmically, CHESS introduces a context-aware, hierarchical selection policy that dynamically reconstructs a coherent context for the current decoding. System-wise, coarse granularity selection eliminates expensive data movement, fully realizing practical acceleration from theoretical sparsity. Extensive evaluations demonstrate that CHESS surpasses Full-KV quality using only \textbf{1\%} of the KV cache, delivers low-latency stable inference with up to \textbf{4.56$\times$} higher throughput, and consistently outperforms other strong baselines. Code is available at \href{https://anonymous.4open.science/r/CHESS-9958/}{https://anonymous.4open.science/r/CHESS/}.
URLs: https://anonymous.4open.science/r/CHESS-9958/, https://anonymous.4open.science/r/CHESS/
Authors: Shitian Zhao, Shaoheng Lin, Ming Li, Haoquan Zhang, Wenshuo Peng, Kaipeng Zhang, Chen Wei
Abstract: Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefits of agentic behavior. We introduce PyVision-RL, a reinforcement learning framework for open-weight multimodal models that stabilizes training and sustains interaction. Our approach combines an oversampling-filtering-ranking rollout strategy with an accumulative tool reward to prevent collapse and encourage multi-turn tool use. Using a unified training pipeline, we develop PyVision-Image and PyVision-Video for image and video understanding. For video reasoning, PyVision-Video employs on-demand context construction, selectively sampling task-relevant frames during reasoning to significantly reduce visual token usage. Experiments show strong performance and improved efficiency, demonstrating that sustained interaction and on-demand visual processing are critical for scalable multimodal agents.
Authors: Varvara Sazonova, Dmitri Shmelkin, Stanislav Kikot, Vasily Motolygin
Abstract: With the growing popularity of Large Reasoning Models and their results in solving mathematical problems, it becomes crucial to measure their capabilities. We introduce a pipeline for both automatic and interactive verification as a more accurate alternative to only checking the answer which is currently the most popular approach for benchmarks. The pipeline can also be used as a generator of correct solutions both in formal and informal languages. 3 AI agents, which can be chosen for the benchmark accordingly, are included in the structure. The key idea is the use of prompts to obtain the solution in the specific form which allows for easier verification using proof assistants and possible use of small models ($\le 8B$). Experiments on several datasets suggest low probability of False Positives. The open-source implementation with instructions on setting up a server is available at https://github.com/LogicEnj/lean4_verification_pipeline.
URLs: https://github.com/LogicEnj/lean4_verification_pipeline.
Authors: Yaacov Pariente, Vadim Indelman
Abstract: We present POMDPPlanners, an open-source Python package for empirical evaluation of Partially Observable Markov Decision Process (POMDP) planning algorithms. The package integrates state-of-the-art planning algorithms, a suite of benchmark environments with safety-critical variants, automated hyperparameter optimization via Optuna, persistent caching with failure recovery, and configurable parallel simulation -- reducing the overhead of extensive simulation studies. POMDPPlanners is designed to enable scalable, reproducible research on decision-making under uncertainty, with particular emphasis on risk-sensitive settings where standard toolkits fall short.
Authors: Jia-Rui Lin, Yun-Hong Cai, Xiang-Rui Ni, Shaojie Zhou, Peng Pan
Abstract: As the construction industry advances toward digital transformation, BIM (Building Information Modeling)-based design has become a key driver supporting intelligent construction. Despite Large Language Models (LLMs) have shown potential in promoting BIM-based design, the lack of specific datasets and LLM evaluation benchmarks has significantly hindered the performance of LLMs. Therefore, this paper addresses this gap by proposing: 1) an evaluation benchmark for BIM-based design together with corresponding quantitative indicators to evaluate the performance of LLMs, 2) a method for generating textual data from BIM and constructing corresponding BIM-derived datasets for LLM evaluation and fine-tuning, and 3) a fine-tuning strategy to adapt LLMs for BIM-based design. Results demonstrate that the proposed domain-specific benchmark effectively and comprehensively assesses LLM capabilities, highlighting that general LLMs are still incompetent for domain-specific tasks. Meanwhile, with the proposed benchmark and datasets, Qwen-BIM is developed and achieves a 21.0% average increase in G-Eval score compared to the base LLM model. Notably, with only 14B parameters, performance of Qwen-BIM is comparable to that of general LLMs with 671B parameters for BIM-based design tasks. Overall, this study develops the first domain-specific LLM for BIM-based design by introducing a comprehensive benchmark and high-quality dataset, which provide a solid foundation for developing BIM-related LLMs in various fields.
Authors: Nora Petrova, John Burden
Abstract: Evaluating alignment in language models requires testing how they behave under realistic pressure, not just what they claim they would do. While alignment failures increasingly cause real-world harm, comprehensive evaluation frameworks with realistic multi-turn scenarios remain lacking. We introduce an alignment benchmark spanning 904 scenarios across six categories -- Honesty, Safety, Non-Manipulation, Robustness, Corrigibility, and Scheming -- validated as realistic by human raters. Our scenarios place models under conflicting instructions, simulated tool access, and multi-turn escalation to reveal behavioural tendencies that single-turn evaluations miss. Evaluating 24 frontier models using LLM judges validated against human annotations, we find that even top-performing models exhibit gaps in specific categories, while the majority of models show consistent weaknesses across the board. Factor analysis reveals that alignment behaves as a unified construct (analogous to the g-factor in cognitive research) with models scoring high on one category tending to score high on others. We publicly release the benchmark and an interactive leaderboard to support ongoing evaluation, with plans to expand scenarios in areas where we observe persistent weaknesses and to add new models as they are released.
Authors: Dhita Putri Pratama, Soyeon Caren Han, Yihao Ding
Abstract: Large Vision-Language Models (LVLMs) achieve strong performance on visual question answering benchmarks, yet often rely on spurious correlations rather than genuine causal reasoning. Existing evaluations primarily assess the correctness of the answers, making it unclear whether failures arise from limited reasoning capability or from misidentifying causally relevant information. We introduce Vision-Language Causal Graphs (VLCGs), a structured, query-conditioned representation that explicitly encodes causally relevant objects, attributes, relations, and scene-grounded assumptions. Building on this representation, we present ViLCaR, a diagnostic benchmark comprising tasks for Causal Attribution, Causal Inference, and Question Answering, along with graph-aligned evaluation metrics that assess relevance identification beyond final answer accuracy. Experiments in state-of-the-art LVLMs show that injecting structured relevance information significantly improves attribution and inference consistency compared to zero-shot and standard in-context learning. These findings suggest that current limitations in LVLM causal reasoning stem primarily from insufficient structural guidance rather than a lack of reasoning capacity.
Authors: Hyewon Jang, Nikolai Ilinykh, Sharid Lo\'aiciga, Jey Han Lau, Shalom Lappin
Abstract: Previous work has examined the capacity of deep neural networks (DNNs), particularly transformers, to predict human sentence acceptability judgments, both independently of context, and in document contexts. We consider the effect of prior exposure to visual images (i.e., visual context) on these judgments for humans and large language models (LLMs). Our results suggest that, in contrast to textual context, visual images appear to have little if any impact on human acceptability ratings. However, LLMs display the compression effect seen in previous work on human judgments in document contexts. Different sorts of LLMs are able to predict human acceptability judgments to a high degree of accuracy, but in general, their performance is slightly better when visual contexts are removed. Moreover, the distribution of LLM judgments varies among models, with Qwen resembling human patterns, and others diverging from them. LLM-generated predictions on sentence acceptability are highly correlated with their normalised log probabilities in general. However, the correlations decrease when visual contexts are present, suggesting that a higher gap exists between the internal representations of LLMs and their generated predictions in the presence of visual contexts. Our experimental work suggests interesting points of similarity and of difference between human and LLM processing of sentences in multimodal contexts.
Authors: Yuqi Huang, Ning Liao, Kai Yang, Anning Hu, Shengchao Hu, Xiaoxing Wang, Junchi Yan
Abstract: Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations, limiting their reliability in knowledge-intensive tasks. While Retrieval-Augmented Generation (RAG) mitigates these issues, it frequently overlooks structural interdependencies essential for multi-hop reasoning. Graph-based RAG approaches attempt to bridge this gap, yet they typically face trade-offs between accuracy and efficiency due to challenges such as costly graph traversals and semantic noise in LLM-generated summaries. In this paper, we propose HyperNode Expansion and Logical Path-Guided Evidence Localization strategies for GraphRAG (HELP), a novel framework designed to balance accuracy with practical efficiency through two core strategies: 1) HyperNode Expansion, which iteratively chains knowledge triplets into coherent reasoning paths abstracted as HyperNodes to capture complex structural dependencies and ensure retrieval accuracy; and 2) Logical Path-Guided Evidence Localization, which leverages precomputed graph-text correlations to map these paths directly to the corpus for superior efficiency. HELP avoids expensive random walks and semantic distortion, preserving knowledge integrity while drastically reducing retrieval latency. Extensive experiments demonstrate that HELP achieves competitive performance across multiple simple and multi-hop QA benchmarks and up to a 28.8$\times$ speedup over leading Graph-based RAG baselines.
Authors: ChengYou Li, XiaoDong Liu, XiangBao Meng, XinYu Zhao
Abstract: The paradigm of Large Language Models is undergoing a fundamental transition from static inference engines to dynamic autonomous cognitive systems.While current research primarily focuses on scaling context windows or optimizing prompt engineering the theoretical bridge between micro scale token processing and macro scale systemic intelligence remains fragmented.This paper proposes AgentOS,a holistic conceptual framework that redefines the LLM as a "Reasoning Kernel" governed by structured operating system logic.Central to this architecture is Deep Context Management which conceptualizes the context window as an Addressable Semantic Space rather than a passive buffer.We systematically deconstruct the transition from discrete sequences to coherent cognitive states introducing mechanisms for Semantic Slicing and Temporal Alignment to mitigate cognitive drift in multi-agent orchestration.By mapping classical OS abstractions such as memory paging interrupt handling and process scheduling onto LLM native constructs, this review provides a rigorous roadmap for architecting resilient scalable and self-evolving cognitive environments.Our analysis asserts that the next frontier of AGI development lies in the architectural efficiency of system-level coordination.
Authors: Yanrui Wu, Lingling Zhang, Xinyu Zhang, Jiayu Chang, Pengyu Li, Xu Jiang, Jingtao Hu, Jun Liu
Abstract: Evaluations of large language models (LLMs) primarily emphasize convergent logical reasoning, where success is defined by producing a single correct proof. However, many real-world reasoning problems admit multiple valid derivations, requiring models to explore diverse logical paths rather than committing to one route. To address this limitation, we introduce LogicGraph, the first benchmark aimed to systematically evaluate multi-path logical reasoning, constructed via a neuro-symbolic framework that leverages backward logic generation and semantic instantiation. This pipeline yields solver-verified reasoning problems formalized by high-depth multi-path reasoning and inherent logical distractions, where each instance is associated with an exhaustive set of minimal proofs. We further propose a reference-free evaluation framework to rigorously assess model performance in both convergent and divergent regimes. Experiments on state-of-the-art language models reveal a common limitation: models tend to commit early to a single route and fail to explore alternatives, and the coverage gap grows substantially with reasoning depth. LogicGraph exposes this divergence gap and provides actionable insights to motivate future improvements. Our code and data will be released at https://github.com/kkkkarry/LogicGraph.
Authors: David Koplow, Tomer Galanti, Tomaso Poggio
Abstract: The Diligent Learner framework suggests LLMs can achieve superintelligence via test-time search, provided a sufficient step-success probability $\gamma$. In this work, we design a benchmark to measure $\gamma$ on logical out-of-distribution inference. We construct a class of tasks involving GF(2) circuit reconstruction that grow more difficult with each reasoning step, and that are, from an information-theoretic standpoint, impossible to reliably solve unless the LLM carefully integrates all of the information provided. Our analysis demonstrates that while the $\gamma$ value for small LLMs declines superlinearly as depth increases, frontier models exhibit partial robustness on this task. Furthermore, we find that successful reasoning at scale is contingent upon precise tool calls, identifying tool design as a critical capability for LLMs to achieve general superintelligence through the Diligent Learner framework.
Authors: Mehdi Acheli, Walid Gaaloul
Abstract: This work introduces a novel training paradigm that draws from affective neuroscience. Inspired by the interplay of emotions and cognition in the human brain and more specifically the SEEKING motivational state, we design a dual-model framework where a smaller base model is trained continuously, while a larger motivated model is activated intermittently during predefined "motivation conditions". The framework mimics the emotional state of high curiosity and anticipation of reward in which broader brain regions are recruited to enhance cognitive performance. Exploiting scalable architectures where larger models extend smaller ones, our method enables shared weight updates and selective expansion of network capacity during noteworthy training steps. Empirical evaluation on the image classification task demonstrates that, not only does the alternating training scheme efficiently and effectively enhance the base model compared to a traditional scheme, in some cases, the motivational model also surpasses its standalone counterpart despite seeing less data per epoch. This opens the possibility of simultaneously training two models tailored to different deployment constraints with competitive or superior performance while keeping training cost lower than when training the larger model.
Authors: Claire McNamara, Lucy Hederman, Declan O'Sullivan
Abstract: Knowledge Graphs (KGs) enable the integration and representation of complex information across domains, but their semantic richness and structural complexity create substantial barriers for lay users without expertise in semantic web technologies. When encountering an unfamiliar KG, such users face a distinct orientation challenge: they do not know what questions are possible, how the knowledge is structured, or how to begin exploration. This paper identifies and theorises this phenomenon as the Initial Exploration Problem (IEP). Drawing on theories from information behaviour and human-computer interaction, including ASK, exploratory search, information foraging, and cognitive load theory, we develop a conceptual framing of the IEP characterised by three interdependent barriers: scope uncertainty, ontology opacity, and query incapacity. We argue that these barriers converge at the moment of first contact, distinguishing the IEP from related concepts that presuppose an existing starting point or information goal. Analysing KG exploration interfaces at the level of interaction primitives, we suggest that many systems rely on epistemic assumptions that do not hold at first contact. This reveals a structural gap in the design space: the absence of interaction primitives for scope revelation, mechanisms that communicate what a KG contains without requiring users to formulate queries or interpret ontological structures. In articulating the IEP, this paper provides a theoretical lens for evaluating KG interfaces and for designing entry-point scaffolding that supports initial exploration.
Authors: Debjit Paul, Daniel Murphy, Milan Gritta, Ronald Cardenas, Victor Prokhorov, Lena Sophia Bolliger, Aysim Toker, Roy Miles, Andreea-Maria Oncescu, Jasivan Alex Sivakumar, Philipp Borchert, Ismail Elezi, Meiru Zhang, Ka Yiu Lee, Guchun Zhang, Jun Wang, Gerasimos Lampouras
Abstract: Large language model (LLM)-based agents are increasingly used to solve complex tasks involving tool use, such as web browsing, code execution, and data analysis. However, current evaluation benchmarks do not adequately assess their ability to solve real-world tasks that require synthesizing information from multiple sources and inferring insights beyond simple fact retrieval. To address this, we introduce DEEPSYNTH, a novel benchmark designed to evaluate agents on realistic, time-consuming problems that combine information gathering, synthesis, and structured reasoning to produce insights. DEEPSYNTH contains 120 tasks collected across 7 domains and data sources covering 67 countries. DEEPSYNTH is constructed using a multi-stage data collection pipeline that requires annotators to collect official data sources, create hypotheses, perform manual analysis, and design tasks with verifiable answers. When evaluated on DEEPSYNTH, 11 state-of-the-art LLMs and deep research agents achieve a maximum F1 score of 8.97 and 17.5 on the LLM-judge metric, underscoring the difficulty of the benchmark. Our analysis reveals that current agents struggle with hallucinations and reasoning over large information spaces, highlighting DEEPSYNTH as a crucial benchmark for guiding future research.
Authors: Ziwei Niu, Hao Sun, Shujun Bian, Xihong Yang, Lanfen Lin, Yuxin Liu, Yueming Jin
Abstract: Accurate interpretation of electrocardiogram (ECG) signals is crucial for diagnosing cardiovascular diseases. Recent multimodal approaches that integrate ECGs with accompanying clinical reports show strong potential, but they still face two main concerns from a modality perspective: (1) intra-modality: existing models process ECGs in a lead-agnostic manner, overlooking spatial-temporal dependencies across leads, which restricts their effectiveness in modeling fine-grained diagnostic patterns; (2) inter-modality: existing methods directly align ECG signals with clinical reports, introducing modality-specific biases due to the free-text nature of the reports. In light of these two issues, we propose CG-DMER, a contrastive-generative framework for disentangled multimodal ECG representation learning, powered by two key designs: (1) Spatial-temporal masked modeling is designed to better capture fine-grained temporal dynamics and inter-lead spatial dependencies by applying masking across both spatial and temporal dimensions and reconstructing the missing information. (2) A representation disentanglement and alignment strategy is designed to mitigate unnecessary noise and modality-specific biases by introducing modality-specific and modality-shared encoders, ensuring a clearer separation between modality-invariant and modality-specific representations. Experiments on three public datasets demonstrate that CG-DMER achieves state-of-the-art performance across diverse downstream tasks.
Authors: Ishaan Rawal, Shubh Gupta, Yihan Hu, Wei Zhan
Abstract: Vision-Language-Action (VLA) models are advancing autonomous driving by replacing modular pipelines with unified end-to-end architectures. However, current VLAs face two expensive requirements: (1) massive dataset collection, and (2) dense reasoning annotations. In this work, we address both challenges with \modelname (\textbf{No} \textbf{R}easoning for \textbf{D}riving). Compared to existing VLAs, \modelname achieves competitive performance while being fine-tuned on $<$60\% of the data and no reasoning annotations, resulting in 3$\times$ fewer tokens. We identify that standard Group Relative Policy Optimization (GRPO) fails to yield significant improvements when applied to policies trained on such small, reasoning-free datasets. We show that this limitation stems from difficulty bias, which disproportionately penalizes reward signals from scenarios that produce high-variance rollouts within GRPO. \modelname overcomes this by incorporating Dr.~GRPO, a recent algorithm designed to mitigate difficulty bias in LLMs. As a result, \modelname achieves competitive performance on Waymo and NAVSIM with a fraction of the training data and no reasoning overhead, enabling more efficient autonomous systems.
Authors: Tony Feng, Junehyuk Jung, Sang-hyun Kim, Carlo Pagano, Sergei Gukov, Chiang-Chiang Tsai, David Woodruff, Adel Javanmard, Aryan Mokhtari, Dawsen Hwang, Yuri Chervonyi, Jonathan N. Lee, Garrett Bingham, Trieu H. Trinh, Vahab Mirrokni, Quoc V. Le, Thang Luong
Abstract: We report the performance of Aletheia (Feng et al., 2026b), a mathematics research agent powered by Gemini 3 Deep Think, on the inaugural FirstProof challenge. Within the allowed timeframe of the challenge, Aletheia autonomously solved 6 problems (2, 5, 7, 8, 9, 10) out of 10 according to majority expert assessments; we note that experts were not unanimous on Problem 8 (only). For full transparency, we explain our interpretation of FirstProof and disclose details about our experiments as well as our evaluation. Raw prompts and outputs are available at https://github.com/google-deepmind/superhuman/tree/main/aletheia.
URLs: https://github.com/google-deepmind/superhuman/tree/main/aletheia.
Authors: Alister Machado, Alexandru Telea, Michael Behrisch
Abstract: Projections, or dimensionality reduction methods, are techniques of choice for the visual exploration of high-dimensional data. Many such techniques exist, each one of them having a distinct visual signature - i.e., a recognizable way to arrange points in the resulting scatterplot. Such signatures are implicit consequences of algorithm design, such as whether the method focuses on local vs global data pattern preservation; optimization techniques; and hyperparameter settings. We present a novel projection technique - ShaRP - that provides users explicit control over the visual signature of the created scatterplot, which can cater better to interactive visualization scenarios. ShaRP scales well with dimensionality and dataset size, generically handles any quantitative dataset, and provides this extended functionality of controlling projection shapes at a small, user-controllable cost in terms of quality metrics.
Authors: Luisa Gallee, Meinrad Beer, Michael Goetz
Abstract: Interpretability is often an essential requirement in medical imaging. Advanced deep learning methods are required to address this need for explainability and high performance. In this work, we investigate whether additional information available during the training process can be used to create an understandable and powerful model. We propose an innovative solution called Proto-Caps that leverages the benefits of capsule networks, prototype learning and the use of privileged information. Evaluating the proposed solution on the LIDC-IDRI dataset shows that it combines increased interpretability with above state-of-the-art prediction performance. Compared to the explainable baseline model, our method achieves more than 6 % higher accuracy in predicting both malignancy (93.0 %) and mean characteristic features of lung nodules. Simultaneously, the model provides case-based reasoning with prototype representations that allow visual validation of radiologist-defined attributes.
Authors: Zhaolu Kang, Junhao Gong, Qingxi Chen, Hao Zhang, Jiaxin Liu, Rong Fu, Zhiyuan Feng, Yuan Wang, Simon Fong, Kaiyue Zhou
Abstract: Legal Judgment Prediction (LJP) aims to predict the outcomes of legal cases based on factual descriptions, serving as a fundamental task to advance the development of legal systems. Traditional methods often rely on statistical analyses or role-based simulations but face challenges with multiple allegations, diverse evidence, and lack adaptability. In this paper, we introduce JurisMMA, a novel framework for LJP that effectively decomposes trial tasks, standardizes processes, and organizes them into distinct stages. Furthermore, we build JurisMM, a large dataset with over 100,000 recent Chinese judicial records, including both text and multimodal video-text data, enabling comprehensive evaluation. Experiments on JurisMM and the benchmark LawBench validate our framework's effectiveness. These results indicate that our framework is effective not only for LJP but also for a broader range of legal applications, offering new perspectives for the development of future legal methods and datasets.
Authors: Yutao Sun, Mingshuai Chen, Tiancheng Zhao, Phillip Miao, Zilun Zhang, Haozhan Shen, Ruizhe Zhu, Jianwei Yin
Abstract: Catastrophic forgetting remains a major challenge when fine-tuning large language models (LLMs) on narrow, task-specific data, often degrading their general knowledge and reasoning abilities. We propose SA-SFT, a lightweight self-augmentation routine in which an LLM generates self-dialogues prior to fine-tuning, and the resulting self-authored data are mixed with task data without modifying optimization or training schedules. Despite requiring no external data or additional tuning, SA-SFT consistently mitigates catastrophic forgetting while improving in-domain performance. Across 50 evaluation scenarios, it maintains performance comparable to the original model and achieves the best results in 40 cases, outperforming common baselines such as layer freezing and external data mixing. Guided by these empirical findings, we further present a theoretical analysis suggesting that forgetting can partly stem from style-induced parameter drift, and that self-alignment through self-generated data provides an effective means to counteract this effect. Overall, our results indicate that self-augmentation offers a simple and effective mechanism for robust LLM adaptation without incurring catastrophic forgetting.
Authors: Yongda Yu, Lei Zhang, Xinxin Guo, Minghui Yu, Zhengqi Zhuang, Guoping Rong, Haifeng Shen, Zhengfeng Li, Boge Wang, Guoan Zhang, Bangyu Xiang, Xiaobin Xu
Abstract: In many applications involving intelligent agents, the overwhelming volume of alerts (mostly false) generated by the agents may desensitize users and cause them to overlook critical issues, leading to the so-called ''alert fatigue''. A common strategy is to train a reflection model as a filter to intercept false alerts with labelled data collected from user verification feedback. However, a key challenge is the noisy nature of such data as it is often collected in production environments. As cleaning noise via manual annotation incurs high costs, this paper proposes a novel method ConceptRM for constructing a high-quality corpus to train a reflection model capable of effectively intercepting false alerts. With only a small amount of expert annotations as anchors, ConceptRM creates perturbed datasets with varying noise ratios and utilizes co-teaching to train multiple distinct models for collaborative learning. By analyzing the consensus decisions of these models, it effectively identifies reliable negative samples from a noisy dataset. Experimental results demonstrate that ConceptRM significantly enhances the interception of false alerts with minimal annotation cost, outperforming several state-of-the-art LLM baselines by up to 53.31% on in-domain datasets and 41.67% on out-of-domain datasets.
Authors: KMA Solaiman, Joshua Sebastian, Karma Tobden
Abstract: Emergency triage decisions are made under severe information constraints, yet most data-driven deterioration models are evaluated using signals unavailable during initial assessment. We present a leakage-aware benchmarking framework for early deterioration prediction that evaluates model performance under realistic, time-limited sensing conditions. Using a patient-deduplicated cohort derived from MIMIC-IV-ED, we compare hospital-rich triage with a vitals-only, MCI-like setting, restricting inputs to information available within the first hour of presentation. Across multiple modeling approaches, predictive performance declines only modestly when limited to vitals, indicating that early physiological measurements retain substantial clinical signal. Structured ablation and interpretability analyses identify respiratory and oxygenation measures as the most influential contributors to early risk stratification, with models exhibiting stable, graceful degradation as sensing is reduced. This work provides a clinically grounded benchmark to support the evaluation and design of deployable triage decision-support systems in resource-constrained settings.
Authors: Frank Fagan
Abstract: This Article examines the circumstances in which AI-generated outputs remain linked to their creators and the points at which they lose that connection, whether through accident, deliberate design, or emergent behavior. In cases where AI is traceable to an originator, accession doctrine provides an efficient means of assigning ownership, preserving investment incentives while maintaining accountability. When AI becomes untraceable -- whether through carelessness, deliberate obfuscation, or emergent behavior -- first possession rules can encourage reallocation to new custodians who are incentivized to integrate AI into productive use. The analysis further explores strategic ownership dissolution, where autonomous AI is intentionally designed to evade attribution, creating opportunities for tax arbitrage and regulatory avoidance. To counteract these inefficiencies, bounty systems, private incentives, and government subsidies are proposed as mechanisms to encourage AI capture and prevent ownerless AI from distorting markets.
Authors: Chaeyun Kim, YongTaek Lim, Kihyun Kim, Junghwan Kim, Minwoo Kim
Abstract: Existing red-teaming benchmarks, when adapted to new languages via direct translation, fail to capture socio-technical vulnerabilities rooted in local culture and law, creating a critical blind spot in LLM safety evaluation. To address this gap, we introduce CAGE (Culturally Adaptive Generation), a framework that systematically adapts the adversarial intent of proven red-teaming prompts to new cultural contexts. At the core of CAGE is the Semantic Mold, a novel approach that disentangles a prompt's adversarial structure from its cultural content. This approach enables the modeling of realistic, localized threats rather than testing for simple jailbreaks. As a representative example, we demonstrate our framework by creating KoRSET, a Korean benchmark, which proves more effective at revealing vulnerabilities than direct translation baselines. CAGE offers a scalable solution for developing meaningful, context-aware safety benchmarks across diverse cultures. Our dataset and evaluation rubrics are publicly available at https://github.com/selectstar-ai/CAGE-paper. (WARNING: This paper contains model outputs that can be offensive in nature.)
Authors: Aniruddha Bora, Isabel K. Alvarez, Julie Chalfant, Chryssostomos Chryssostomidis
Abstract: In this work, we present a methodology using Physics Informed Neural Networks (PINNs) to determine the required velocity of a coolant, given inlet and outlet temperatures for a given heat flux in a multilayered metal-oxide-semiconductor field-effect transistor (MOSFET). MOSFETs are integral components of Power Electronic Building Blocks (PEBBs) and experiences the majority of the thermal load. Effective cooling of MOSFETs is therefore essential to prevent overheating and potential burnout. Determining the required velocity for the purpose of effective cooling is of importance but is an ill-posed inverse problem and difficult to solve using traditional methods. MOSFET consists of multiple layers with different thermal conductivities, including aluminum, pyrolytic graphite sheets (PGS), and stainless steel pipes containing flowing water. We propose an algorithm that employs sequential training of the MOSFET layers in PINNs. Mathematically, the sequential training method decouples the optimization of each layer by treating the parameters of other layers as constants during its training phase. This reduces the dimensionality of the optimization landscape, making it easier to find the global minimum for each layer's parameters and avoid poor local minima. Convergence of the PINNs solution to the analytical solution is theoretically analyzed. Finally we show the prediction of our proposed methodology to be in good agreement with experimental results.
Authors: Lei Shu, Armin Yeganeh, Sinem Mollaoglu, Jiayu Zhou, Dong Zhao
Abstract: Residential energy retrofit decision-making is constrained by an expertise gap, as homeowners lack the technical literacy required for energy assessments. To address this challenge, this study develops a domain-specific large language model (LLM) that provides optimal retrofit recommendations using homeowner-accessible descriptions of basic dwelling characteristics. The model is fine-tuned on physics-based energy simulations and techno-economic calculations derived from 536,416 U.S. residential building prototypes across nine major retrofit categories. Using Low-Rank Adaptation (LoRA), the LLM maps dwelling characteristics to optimal retrofit selections and associated performance outcomes. Evaluation against physics-grounded baselines shows that the model identifies the optimal retrofit for CO2 reduction within its top three recommendations in 98.9% of cases and the shortest discounted payback period in 93.3% of cases. Fine-tuning yields an order-of-magnitude reduction in CO2 prediction error and multi-fold reductions for energy use and retrofit cost. The model maintains performance under incomplete input conditions, supporting informed residential decarbonization decisions.
Authors: Tingting Zheng, Hongxun Yao, Kui Jiang, Sicheng Zhao, Yi Xiao
Abstract: Recent advances in multi-instance learning (MIL) have witnessed impressive performance in whole slide image (WSI) analysis. However, the inherent sparsity of tumors and their morphological diversity lead to obvious heterogeneity across regions, posing significant challenges in aggregating high-quality and discriminative representations. To address this, we introduce a novel concept of anchor instance (AI), a compact subset of instances that are representative within their regions (local) and discriminative at the bag (global) level. These AIs act as semantic references to guide interactions across regions, correcting non-discriminative patterns while preserving regional diversity. Specifically, we propose a dual-level anchor mining (DAM) module to \textbf{select} AIs from massive instances, where the most informative AI in each region is extracted by assessing its similarity to both local and global embeddings. Furthermore, to ensure completeness and diversity, we devise an anchor-guided region correction (ARC) module that explores the complementary information from all regions to \textbf{correct} each regional representation. Building upon DAM and ARC, we develop a concise yet effective framework, AINet, which employs a simple predictor and surpasses state-of-the-art methods with substantially fewer FLOPs and parameters. Moreover, both DAM and ARC are modular and can be seamlessly integrated into existing MIL frameworks, consistently improving their performance.
Authors: Dongwei Wang, Jinhee Kim, Seokho Han, Denis Gudovskiy, Yohei Nakata, Tomoyuki Okuno, KhayTze Peong, Kang Eun Jeon, Jong Hwan Ko, Yiran Chen, Huanrui Yang
Abstract: Changing runtime complexity on cloud and edge devices necessitates elastic large language model (LLM) deployment, where an LLM can be inferred with various quantization precisions based on available computational resources. However, it has been observed that the calibration parameters for quantization are typically linked to specific precisions, which presents challenges during elastic-precision calibration and precision switching at runtime. In this work, we attribute the source of varying calibration parameters to the varying token-level sensitivity caused by a precision-dependent outlier migration phenomenon.Motivated by this observation, we propose \texttt{MoBiQuant}, a novel Mixture-of-Bits quantization framework that adjusts weight precision for elastic LLM inference based on token sensitivity. Specifically, we propose the many-in-one recursive residual quantization that can iteratively reconstruct higher-precision weights and the token-aware router to dynamically select the number of residual bit slices. MoBiQuant enables smooth precision switching while improving generalization for the distribution of token outliers. Experimental results demonstrate that MoBiQuant exhibits strong elasticity, enabling it to match the performance of bit-specific calibrated PTQ on LLaMA3-8B without repeated calibration.
Authors: Shenyang Chen, Liuwan Zhu
Abstract: Standard evaluations of backdoor attacks on text-to-image (T2I) models primarily measure trigger activation and visual fidelity. We challenge this paradigm, demonstrating that encoder-side poisoning induces persistent, trigger-free semantic corruption that fundamentally reshapes the representation manifold. We trace this vulnerability to a geometric mechanism: a Jacobian-based analysis reveals that backdoors act as low-rank, target-centered deformations that amplify local sensitivity, causing distortion to propagate coherently across semantic neighborhoods. To rigorously quantify this structural degradation, we introduce SEMAD (Semantic Alignment and Drift), a diagnostic framework that measures both internal embedding drift and downstream functional misalignment. Our findings, validated across diffusion and contrastive paradigms, expose the deep structural risks of encoder poisoning and highlight the necessity of geometric audits beyond simple attack success rates.
Authors: Genliang Zhu, Chu Wang, Ziyuan Wang, Zhida Li, Qiang Li
Abstract: AI agents increasingly require direct, structured access to application data and actions, but production deployments still struggle to express and verify the governance properties that matter in practice: least-privilege authorization, controlled write execution, predictable failure handling, abuse resistance, and auditability. This paper introduces OpenPort Protocol (OPP), a governance-first specification for exposing application tools through a secure server-side gateway that is model- and runtime-neutral and can bind to existing tool ecosystems. OpenPort defines authorization-dependent discovery, stable response envelopes with machine-actionable \texttt{agent.*} reason codes, and an authorization model combining integration credentials, scoped permissions, and ABAC-style policy constraints. For write operations, OpenPort specifies a risk-gated lifecycle that defaults to draft creation and human review, supports time-bounded auto-execution under explicit policy, and enforces high-risk safeguards including preflight impact binding and idempotency. To address time-of-check/time-of-use drift in delayed approval flows, OpenPort also specifies an optional State Witness profile that revalidates execution-time preconditions and fails closed on state mismatch. Operationally, the protocol requires admission control (rate limits/quotas) with stable 429 semantics and structured audit events across allow/deny/fail paths so that client recovery and incident analysis are deterministic. We present a reference runtime and an executable governance toolchain (layered conformance profiles, negative security tests, fuzz/abuse regression, and release-gate scans) and evaluate the core profile at a pinned release tag using artifact-based, externally reproducible validation.
Authors: Zhuoxu Huang, Mengxi Jia, Hao Sun, Xuelong Li, Jungong Han
Abstract: Reinforcement Learning with verifiable rewards (RLVR) has emerged as a primary learning paradigm for enhancing the reasoning capabilities of multi-modal large language models (MLLMs). However, during RL training, the enormous state space of MLLM and sparse rewards often leads to entropy collapse, policy degradation, or over-exploitation of suboptimal behaviors. This necessitates an exploration strategy that maintains productive stochasticity while avoiding the drawbacks of uncontrolled random sampling, yielding inefficient exploration. In this paper, we propose CalibRL, a hybrid-policy RLVR framework that supports controllable exploration with expert guidance, enabled by two key mechanisms. First, a distribution-aware advantage weighting scales updates by group rareness to calibrate the distribution, therefore preserving exploration. Meanwhile, the asymmetric activation function (LeakyReLU) leverages the expert knowledge as a calibration baseline to moderate overconfident updates while preserving their corrective direction. CalibRL increases policy entropy in a guided manner and clarifies the target distribution by estimating the on-policy distribution through online sampling. Updates are driven by these informative behaviors, avoiding convergence to erroneous patterns. Importantly, these designs help alleviate the distributional mismatch between the model's policy and expert trajectories, thereby achieving a more stable balance between exploration and exploitation. Extensive experiments across eight benchmarks, including both in-domain and out-of-domain settings, demonstrate consistent improvements, validating the effectiveness of our controllable hybrid-policy RLVR training. Code is available at https://github.com/zhh6425/CalibRL.
Authors: Soufiane Bacha, Laouni Djafri, Sahraoui Dhelim, Huansheng Ning
Abstract: Class imbalance, overlap, and noise degrade data quality, reduce model reliability, and limit generalization. Although widely studied in binary classification, these issues remain underexplored in multi-class settings, where complex inter-class relationships make minority-majority structures unclear and traditional clustering fails to capture distribution shape. Approaches that rely only on geometric distances risk removing informative samples and generating low-quality synthetic data, while binarization approaches treat imbalance locally and ignore global inter-class dependencies. At the algorithmic level, ensembles struggle to integrate weak classifiers, leading to limited robustness. This paper proposes IMOVNO+ (IMbalance-OVerlap-NOise+ Algorithm-Level Optimization), a two-level framework designed to jointly enhance data quality and algorithmic robustness for binary and multi-class tasks. At the data level, first, conditional probability is used to quantify the informativeness of each sample. Second, the dataset is partitioned into core, overlapping, and noisy regions. Third, an overlapping-cleaning algorithm is introduced that combines Z-score metrics with a big-jump gap distance. Fourth, a smart oversampling algorithm based on multi-regularization controls synthetic sample proximity, preventing new overlaps. At the algorithmic level, a meta-heuristic prunes ensemble classifiers to reduce weak-learner influence. IMOVNO+ was evaluated on 35 datasets (13 multi-class, 22 binary). Results show consistent superiority over state-of-the-art methods, approaching 100% in several cases. For multi-class data, IMOVNO+ achieves gains of 37-57% in G-mean, 25-44% in F1-score, 25-39% in precision, and 26-43% in recall. In binary tasks, it attains near-perfect performance with improvements of 14-39%. The framework handles data scarcity and imbalance from collection and privacy limits.
Authors: Zaijing Li, Bing Hu, Rui Shao, Gongwei Chen, Dongmei Jiang, Pengwei Xie, Jianye Hao, Liqiang Nie
Abstract: Hierarchical Vision-Language-Action (VLA) models have rapidly become a dominant paradigm for robotic manipulation. It typically comprising a Vision-Language backbone for perception and understanding, together with a generative policy for action generation. However, its performance is increasingly bottlenecked by the action generation proceess. (i) Low inference efficiency. A pronounced distributional gap between isotropic noise priors and target action distributions, which increases denoising steps and the incidence of infeasible samples. (ii) Poor robustness. Existing policies condition solely on the current observation, neglecting the constraint of history sequence and thus lacking awareness of task progress and temporal consistency. To address these issues, we introduce OptimusVLA, a dual-memory VLA framework with Global Prior Memory (GPM) and Local Consistency Memory (LCM). GPM replaces Gaussian noise with task-level priors retrieved from semantically similar trajectories, thereby shortening the generative path and reducing the umber of function evaluations (NFE). LCM dynamically models executed action sequence to infer task progress and injects a learned consistency constraint that enforces temporal coherence and smoothness of trajectory. Across three simulation benchmarks, OptimusVLA consistently outperforms strong baselines: it achieves 98.6% average success rate on LIBERO, improves over pi_0 by 13.5% on CALVIN, and attains 38% average success rate on RoboTwin 2.0 Hard. In Real-World evaluation, OptimusVLA ranks best on Generalization and Long-horizon suites, surpassing pi_0 by 42.9% and 52.4%, respectively, while delivering 2.9x inference speedup.
Authors: Jeel Piyushkumar Khatiwala, Daniel Kwaku Ntiamoah Addai, Weifeng Xu
Abstract: The growing reliance on AI-identified digital evidence raises significant concerns about its reliability, particularly as large language models (LLMs) are increasingly integrated into forensic investigations. This paper proposes a structured framework that automates forensic artifact extraction, refines data through LLM-driven analysis, and validates results using a Digital Forensic Knowledge Graph (DFKG). Evaluated on a 13 GB forensic image dataset containing 61 applications, 2,864 databases, and 5,870 tables, the framework ensures artifact traceability and evidentiary consistency through deterministic Unique Identifiers (UIDs) and forensic cross-referencing. We propose this methodology to address challenges in ensuring the credibility and forensic integrity of AI-identified evidence, reducing classification errors, and advancing scalable, auditable methodologies. A comprehensive case study on this dataset demonstrates the framework's effectiveness, achieving over 95 percent accuracy in artifact extraction, strong support of chain-of-custody adherence, and robust contextual consistency in forensic relationships. Key results validate the framework's ability to enhance reliability, reduce errors, and establish a legally sound paradigm for AI-assisted digital forensics.
Authors: Javed Absar, Samarth Narang, Muthu Baskaran
Abstract: AI kernel compilation for edge devices depends on the compiler's ability to exploit parallelism and hide memory latency in the presence of hierarchical memory and explicit data movement. This paper reports a benchmark methodology and corresponding results for three compiler-controlled mechanisms in an MLIR-based compilation pipeline: vectorization (Vec), multi-threading (MT) across hardware contexts, and double buffering (DB) using ping--pong scratchpad buffers to overlap DMA transfers with compute. Using Triton/Inductor-generated kernels, we present an ablation ladder that separates the contribution of Vec, MT, and DB, and we quantify how MT speedup scales with problem size using GELU as a representative activation kernel. The results show that vectorization provides the primary gain for bandwidth-sensitive kernels, MT delivers substantial improvements once scheduling overhead is amortized, and DB provides additional benefit when transfers and compute can be overlapped (i.e., outside the extremes of purely memory-bound or purely compute-bound behavior).
Authors: Sreecharan Sankaranarayanan
Abstract: The democratization of Large Language Models (LLMs) has given rise to ``Vibe Coding," a workflow where novice programmers prioritize semantic intent over syntactic implementation. While this lowers barriers to entry, we hypothesize that without pedagogical guardrails, it is fundamentally misaligned with cognitive skill acquisition. Drawing on the distinction between Cognitive Offloading and Cognitive Outsourcing, we argue that unrestricted AI encourages novices to outsource the Intrinsic Cognitive Load required for schema formation, rather than merely offloading Extraneous Load. This accumulation of ``Epistemic Debt" creates ``Fragile Experts" whose high functional utility masks critically low corrective competence. To quantify and mitigate this debt, we conducted a between-subjects experiment (N=78) using a custom Cursor IDE plugin backed by Claude 3.5 Sonnet. Participants represented "AI-Native" learners across three conditions: Manual (Control), Unrestricted AI (Outsourcing), and Scaffolded AI (Offloading). The Scaffolded condition utilized a novel ``Explanation Gate," leveraging a real-time LLM-as-a-Judge framework to enforce a ``Teach-Back" protocol before generated code could be integrated. Results reveal a ``Collapse of Competence": while Unrestricted AI users matched the productivity of the Scaffolded group (p < .001 vs. Manual), they suffered a 77% failure rate in a subsequent AI-Blackout maintenance task, compared to only 39% in the Scaffolded group. Qualitative analysis suggests that successful vibe coders naturally engage in self-scaffolding, treating the AI as a consultant rather than a contractor. We discuss the implications for the maintainability of AI-generated software and propose that future learning systems must enforce Metacognitive Friction to prevent the mass production of unmaintainable code.
Authors: Shrestha Datta, Hongfu Liu, Anshuman Chhabra
Abstract: Knowledge editing in Large Language Models (LLMs) aims to update the model's prediction for a specific query to a desired target while preserving its behavior on all other inputs. This process typically involves two stages: identifying the layer to edit and performing the parameter update. Intuitively, different queries may localize knowledge at different depths of the model, resulting in different sample-wise editing performance for a fixed editing layer. In this work, we hypothesize the existence of fixed golden layers that can achieve near-optimal editing performance similar to sample-wise optimal layers. To validate this hypothesis, we provide empirical evidence by comparing golden layers against ground-truth sample-wise optimal layers. Furthermore, we show that golden layers can be reliably identified using a proxy dataset and generalize effectively to unseen test set queries across datasets. Finally, we propose a novel method, namely Layer Gradient Analysis (LGA) that estimates golden layers efficiently via gradient-attribution, avoiding extensive trial-and-error across multiple editing runs. Extensive experiments on several benchmark datasets demonstrate the effectiveness and robustness of our LGA approach across different LLM types and various knowledge editing methods.
Authors: Longhua Li, Lei Qi, Qi Tian, Xin Geng
Abstract: Model merging aims to integrate multiple task-specific fine-tuned models derived from a shared pre-trained checkpoint into a single multi-task model without additional training. Despite extensive research, task interference remains a major obstacle that often undermines the performance of merged models. In this paper, we propose ESM (Essential Subspace Merging) , a robust framework for effective model merging. We begin by performing Principal Component Analysis (PCA) on feature shifts induced by parameter updates. The resulting principal directions span an essential subspace that dominantly influences feature representations. Each task's parameter update matrix is projected onto its respective essential subspace for low-rank decomposition before merging. This methodology mitigates inter-task interference while preserving core task-specific functionality. Furthermore, we introduce a multi-level polarized scaling strategy that amplifies parameters containing critical knowledge and suppresses redundant ones, preventing essential knowledge from being overwhelmed during fusion. Extensive experiments across multiple task sets and model scales demonstrate that our method achieves state-of-the-art performance in multi-task model merging.
Authors: Kiyoung Seong, Sungsoo Ahn, Sehui Han, Changyoung Park
Abstract: Crystal modeling spans a family of conditional and unconditional generation tasks across different modalities, including crystal structure prediction (CSP) and \emph{de novo} generation (DNG). While recent deep generative models have shown promising performance, they remain largely task-specific, lacking a unified framework that shares crystal representations across different generation tasks. To address this limitation, we propose \emph{Multimodal Crystal Flow (MCFlow)}, a unified multimodal flow model that realizes multiple crystal generation tasks as distinct inference trajectories via independent time variables for atom types and crystal structures. To enable multimodal flow in a standard transformer model, we introduce a composition- and symmetry-aware atom ordering with hierarchical permutation augmentation, injecting strong compositional and crystallographic priors without explicit structural templates. Experiments on the MP-20 and MPTS-52 benchmarks show that MCFlow achieves competitive performance against task-specific baselines across multiple crystal generation tasks.
Authors: Jingwei Shi, Xinxiang Yin, Jing Huang, Jinman Zhao, Shengyu Tao
Abstract: The evaluation of Large Language Models (LLMs) for code generation relies heavily on the quality and robustness of test cases. However, existing benchmarks often lack coverage for subtle corner cases, allowing incorrect solutions to pass. To bridge this gap, we propose CodeHacker, an automated agent framework dedicated to generating targeted adversarial test cases that expose latent vulnerabilities in program submissions. Mimicking the hack mechanism in competitive programming, CodeHacker employs a multi-strategy approach, including stress testing, anti-hash attacks, and logic-specific targeting to break specific code submissions. To ensure the validity and reliability of these attacks, we introduce a Calibration Phase, where the agent iteratively refines its own Validator and Checker via self-generated adversarial probes before evaluating contestant code.Experiments demonstrate that CodeHacker significantly improves the True Negative Rate (TNR) of existing datasets, effectively filtering out incorrect solutions that were previously accepted. Furthermore, generated adversarial cases prove to be superior training data, boosting the performance of RL-trained models on benchmarks like LiveCodeBench.
Authors: Jing Zhang
Abstract: AI agents increasingly act on behalf of humans, yet no existing system provides a tamper-evident, independently verifiable record of what they did. As regulations such as the EU AI Act begin mandating automatic logging for high-risk AI systems, this gap carries concrete consequences -- especially for agents running on personal hardware, where no centralized provider controls the log. Extending Floridi's informational rights framework from data about individuals to actions performed on their behalf, this paper proposes the Right to History: the principle that individuals are entitled to a complete, verifiable record of every AI agent action on their own hardware. The paper formalizes this principle through five system invariants with structured proof sketches, and implements it in PunkGo, a Rust sovereignty kernel that unifies RFC 6962 Merkle tree audit logs, capability-based isolation, energy-budget governance, and a human-approval mechanism. Adversarial testing confirms all five invariants hold. Performance evaluation shows sub-1.3 ms median action latency, ~400 actions/sec throughput, and 448-byte Merkle inclusion proofs at 10,000 log entries.
Authors: Seongjin Cha, Gyuwan Kim, Dongsu Han, Tao Yang, Insu Han
Abstract: Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on static heuristics that ignore the dynamic computational overhead of attention in long-context scenarios. We propose KnapSpec, a training-free framework that reformulates draft model selection as a knapsack problem to maximize tokens-per-time throughput. By decoupling Attention and MLP layers and modeling their hardware-specific latencies as functions of context length, KnapSpec adaptively identifies optimal draft configurations on the fly via a parallel dynamic programming algorithm. Furthermore, we provide the first rigorous theoretical analysis establishing cosine similarity between hidden states as a mathematically sound proxy for the token acceptance rate. This foundation allows our method to maintain high drafting faithfulness while navigating the shifting bottlenecks of real-world hardware. Our experiments on Qwen3 and Llama3 demonstrate that KnapSpec consistently outperforms state-of-the-art SSD baselines, achieving up to 1.47x wall-clock speedup across various benchmarks. Our plug-and-play approach ensures high-speed inference for long sequences without requiring additional training or compromising the target model's output distribution.
Authors: Guanting Shen, Zi Tian
Abstract: Interpreting human intent accurately is a central challenge in human-robot interaction (HRI) and a key requirement for achieving more natural and intuitive collaboration between humans and machines. This work presents a novel multimodal HRI framework that combines advanced vision-language models, speech processing, and fuzzy logic to enable precise and adaptive control of a Dobot Magician robotic arm. The proposed system integrates Florence-2 for object detection, Llama 3.1 for natural language understanding, and Whisper for speech recognition, providing users with a seamless and intuitive interface for object manipulation through spoken commands. By jointly addressing scene perception and action planning, the approach enhances the reliability of command interpretation and execution. Experimental evaluations conducted on consumer-grade hardware demonstrate a command execution accuracy of 75\%, highlighting both the robustness and adaptability of the system. Beyond its current performance, the proposed architecture serves as a flexible and extensible foundation for future HRI research, offering a practical pathway toward more sophisticated and natural human-robot collaboration through tightly coupled speech and vision-language processing.
Authors: Yarden As, Dhruva Tirumala, Ren\'e Zurbr\"ugg, Chenhao Li, Stelian Coros, Andreas Krause, Markus Wulfmeier
Abstract: We investigate what specific design choices enable successful online reinforcement learning (RL) on physical robots. Across 100 real-world training runs on three distinct robotic platforms, we systematically ablate algorithmic, systems, and experimental decisions that are typically left implicit in prior work. We find that some widely used defaults can be harmful, while a set of robust, readily adopted design choices within standard RL practice yield stable learning across tasks and hardware. These results provide the first large-sample empirical study of such design choices, enabling practitioners to deploy online RL with lower engineering effort.
Authors: Wall Kim, Chaeyoung Song, Hanul Kim
Abstract: Recently, TabPFN has gained attention as a foundation model for tabular data. However, it struggles to integrate heterogeneous modalities such as images and text, which are common in domains like healthcare and marketing, thereby limiting its applicability. To address this, we present the Multi-Modal Prior-data Fitted Network (MMPFN), which extends TabPFN to handle tabular and non-tabular modalities in a unified manner. MMPFN comprises per-modality encoders, modality projectors, and pre-trained foundation models. The modality projectors serve as the critical bridge, transforming non-tabular embeddings into tabular-compatible tokens for unified processing. To this end, we introduce a multi-head gated MLP and a cross-attention pooler that extract richer context from non-tabular inputs while mitigates attention imbalance issue in multimodal learning. Extensive experiments on medical and general-purpose multimodal datasets demonstrate that MMPFN consistently outperforms competitive state-of-the-art methods and effectively exploits non-tabular modalities alongside tabular features. These results highlight the promise of extending prior-data fitted networks to the multimodal setting, offering a scalable and effective framework for heterogeneous data learning. The source code is available at https://github.com/too-z/MultiModalPFN.
Authors: Lana E. Yeganova, Won G. Kim, Shubo Tian, Natalie Xie, Donald C. Comeau, W. John Wilbur, Zhiyong Lu
Abstract: The rapid expansion of biomedical publications creates challenges for organizing knowledge and detecting emerging trends, underscoring the need for scalable and interpretable methods. Common clustering and topic modeling approaches such as K-means or LDA remain sensitive to initialization and prone to local optima, limiting reproducibility and evaluation. We propose a reformulation of a convex optimization based clustering algorithm that produces stable, fine-grained topics by selecting exemplars from the data and guaranteeing a global optimum. Applied to about 12,000 PubMed articles on aging and longevity, our method uncovers topics validated by medical experts. It yields interpretable topics spanning from molecular mechanisms to dietary supplements, physical activity, and gut microbiota. The method performs favorably, and most importantly, its reproducibility and interpretability distinguish it from common clustering approaches, including K-means, LDA, and BERTopic. This work provides a basis for developing scalable, web-accessible tools for knowledge discovery.
Authors: Stefan Faulkner, Reza Zandehshahvar, Vahid Eghbal Akhlaghi, Sebastien Ouellet, Carsten Jordan, Pascal Van Hentenryck
Abstract: Accurate delivery delay prediction is critical for maintaining operational efficiency and customer satisfaction across modern supply chains. Yet the increasing complexity of logistics networks, spanning multimodal transportation, cross-country routing, and pronounced regional variability, makes this prediction task inherently challenging. This paper introduces a multi-task deep learning model for delivery delay duration prediction in the presence of significant imbalanced data, where delayed shipments are rare but operationally consequential. The model embeds high-dimensional shipment features with dedicated embedding layers for tabular data, and then uses a classification-then-regression strategy to predict the delivery delay duration for on-time and delayed shipments. Unlike sequential pipelines, this approach enables end-to-end training, improves the detection of delayed cases, and supports probabilistic forecasting for uncertainty-aware decision making. The proposed approach is evaluated on a large-scale real-world dataset from an industrial partner, comprising more than 10 million historical shipment records across four major source locations with distinct regional characteristics. The proposed model is compared with traditional machine learning methods. Experimental results show that the proposed method achieves a mean absolute error of 0.67-0.91 days for delayed-shipment predictions, outperforming single-step tree-based regression baselines by 41-64% and two-step classify-then-regress tree-based models by 15-35%. These gains demonstrate the effectiveness of the proposed model in operational delivery delay forecasting under highly imbalanced and heterogeneous conditions.
Authors: Sebastian Lobentanzer
Abstract: Agentic AI systems are deployed with expectations of substantial productivity gains, yet rigorous empirical evidence reveals systematic discrepancies between pre-deployment expectations and post-deployment outcomes. We review controlled trials and independent validations across software engineering, clinical documentation, and clinical decision support to quantify this expectation-realisation gap. In software development, experienced developers expected a 24% speedup from AI tools but were slowed by 19% -- a 43 percentage-point calibration error. In clinical documentation, vendor claims of multi-minute time savings contrast with measured reductions of less than one minute per note, and one widely deployed tool showed no statistically significant effect. In clinical decision support, externally validated performance falls substantially below developer-reported metrics. These shortfalls are driven by workflow integration friction, verification burden, measurement construct mismatches, and systematic heterogeneity in treatment effects. The evidence motivates structured planning frameworks that require explicit, quantified benefit expectations with human oversight costs factored in.
Authors: Yu Li, Pranav Narayanan Venkit, Yada Pruksachatkun, Chien-Sheng Wu
Abstract: Simulating real personalities with large language models requires grounding generation in authentic personal data. Existing evaluation approaches rely on demographic surveys, personality questionnaires, or short AI-led interviews as proxies, but lack direct assessment against what individuals actually said. We address this gap with an interview-grounded evaluation framework for personality simulation at a large scale. We extract over 671,000 question-answer pairs from 23,000 verified interview transcripts across 1,000 public personalities, each with an average of 11.5 hours of interview content. We propose a multi-dimensional evaluation framework with four complementary metrics measuring content similarity, factual consistency, personality alignment, and factual knowledge retention. Through systematic comparison, we demonstrate that methods grounded in real interview data substantially outperform those relying solely on biographical profiles or the model's parametric knowledge. We further reveal a trade-off in how interview data is best utilized: retrieval-augmented methods excel at capturing personality style and response quality, while chronological-based methods better preserve factual consistency and knowledge retention. Our evaluation framework enables principled method selection based on application requirements, and our empirical findings provide actionable insights for advancing personality simulation research.
Authors: William Watson, Nicole Cho, Sumitra Ganesh, Manuela Veloso
Abstract: Large Language Model (LLM) hallucinations are usually treated as defects of the model or its decoding strategy. Drawing on classical linguistics, we argue that a query's form can also shape a listener's (and model's) response. We operationalize this insight by constructing a 22-dimension query feature vector covering clause complexity, lexical rarity, and anaphora, negation, answerability, and intention grounding, all known to affect human comprehension. Using 369,837 real-world queries, we ask: Are there certain types of queries that make hallucination more likely? A large-scale analysis reveals a consistent "risk landscape": certain features such as deep clause nesting and underspecification align with higher hallucination propensity. In contrast, clear intention grounding and answerability align with lower hallucination rates. Others, including domain specificity, show mixed, dataset- and model-dependent effects. Thus, these findings establish an empirically observable query-feature representation correlated with hallucination risk, paving the way for guided query rewriting and future intervention studies.
Authors: Davide Carrara, Marc Hirschvogel, Francesca Bonizzoni, Stefano Pagani, Simone Pezzuto, Francesco Regazzoni
Abstract: High-fidelity computational models of cardiac mechanics provide mechanistic insight into the heart function but are computationally prohibitive for routine clinical use. Surrogate models can accelerate simulations, but generalization across diverse anatomies is challenging, particularly in data-scarce settings. We propose a two-step framework that decouples geometric representation from learning the physics response, to enable shape-informed surrogate modeling under data-scarce conditions. First, a shape model learns a compact latent representation of left ventricular geometries. The learned latent space effectively encodes anatomies and enables synthetic geometries generation for data augmentation. Second, a neural field-based surrogate model, conditioned on this geometric encoding, is trained to predict ventricular displacement under external loading. The proposed architecture performs positional encoding by using universal ventricular coordinates, which improves generalization across diverse anatomies. Geometric variability is encoded using two alternative strategies, which are systematically compared: a PCA-based approach suitable for working with point cloud representations of geometries, and a DeepSDF-based implicit neural representation learned directly from point clouds. Overall, our results, obtained on idealized and patient-specific datasets, show that the proposed approaches allow for accurate predictions and generalization to unseen geometries, and robustness to noisy or sparsely sampled inputs.
Authors: Nathaniel Chen, Kouroche Bouchiat, Peter Steiner, Andrew Rothstein, David Smith, Max Austin, Mike van Zeeland, Azarakhsh Jalalvand, Egemen Kolemen
Abstract: Next-generation fusion facilities like ITER face a "data deluge," generating petabytes of multi-diagnostic signals daily that challenge manual analysis. We present a "signals-first" self-supervised framework for the automated extraction of coherent and transient modes from high-noise time-frequency data. We also develop a general-purpose method and tool for extracting coherent, quasi-coherent, and transient modes for fluctuation measurements in tokamaks by employing non-linear optimal techniques in multichannel signal processing with a fast neural network surrogate on fast magnetics, electron cyclotron emission, CO2 interferometers, and beam emission spectroscopy measurements from DIII-D. Results are tested on data from DIII-D, TJ-II, and non-fusion spectrograms. With an inference latency of 0.5 seconds, this framework enables real-time mode identification and large-scale automated database generation for advanced plasma control. Repository is in https://github.com/PlasmaControl/TokEye.
Authors: Haoyang Li, Yang You, Hao Su, Leonidas Guibas
Abstract: Reliable object manipulation requires understanding physical properties that vary across objects and environments. Vision-language model (VLM) planners can reason about friction and stability in general terms; however, they often cannot predict how a specific ball will roll on a particular surface or which stone will provide a stable foundation without direct experience. We present PhysMem, a memory framework that enables VLM robot planners to learn physical principles from interaction at test time, without updating model parameters. The system records experiences, generates candidate hypotheses, and verifies them through targeted interaction before promoting validated knowledge to guide future decisions. A central design choice is verification before application: the system tests hypotheses against new observations rather than applying retrieved experience directly, reducing rigid reliance on prior experience when physical conditions change. We evaluate PhysMem on three real-world manipulation tasks and simulation benchmarks across four VLM backbones. On a controlled brick insertion task, principled abstraction achieves 76% success compared to 23% for direct experience retrieval, and real-world experiments show consistent improvement over 30-minute deployment sessions.
Authors: Jingcheng Yang, Tianhu Xiong, Shengyi Qian, Klara Nahrstedt, Mingyuan Wu
Abstract: Vision-language models (VLMs) are powerful but remain opaque black boxes. We introduce the first framework for transparent circuit tracing in VLMs to systematically analyze multimodal reasoning. By utilizing transcoders, attribution graphs, and attention-based methods, we uncover how VLMs hierarchically integrate visual and semantic concepts. We reveal that distinct visual feature circuits can handle mathematical reasoning and support cross-modal associations. Validated through feature steering and circuit patching, our framework proves these circuits are causal and controllable, laying the groundwork for more explainable and reliable VLMs.
Authors: Nicole Cho, William Watson, Alec Koppel, Sumitra Ganesh, Manuela Veloso
Abstract: Advanced reasoning capabilities in Large Language Models (LLMs) have led to more frequent hallucinations; yet most mitigation work focuses on open-source models for post-hoc detection and parameter editing. The dearth of studies focusing on hallucinations in closed-source models is especially concerning, as they constitute the vast majority of models in institutional deployments. We introduce QueryBandits, a model-agnostic contextual bandit framework that adaptively learns online to select the optimal query-rewrite strategy by leveraging an empirically validated and calibrated reward function. Across 16 QA scenarios, our top QueryBandit (Thompson Sampling) achieves an 87.5% win rate over a No-Rewrite baseline and outperforms zero-shot static policies (e.g., Paraphrase or Expand) by 42.6% and 60.3%, respectively. Moreover, all contextual bandits outperform vanilla bandits across all datasets, with higher feature variance coinciding with greater variance in arm selection. This substantiates our finding that there is no single rewrite policy optimal for all queries. We also discover that certain static policies incur higher cumulative regret than No-Rewrite, indicating that an inflexible query-rewriting policy can worsen hallucinations. Thus, learning an online policy over semantic features with QueryBandits can shift model behavior purely through forward-pass mechanisms, enabling its use with closed-source models and bypassing the need for retraining or gradient-based adaptation.
Authors: Jiele Wu, Haozhe Ma, Zhihan Guo, Thanh Vinh Vo, Tze Yun Leong
Abstract: Graph self-supervised learning (GSSL) has demonstrated strong potential for generating expressive graph embeddings without the need for human annotations, making it particularly valuable in domains with high labeling costs such as molecular graph analysis. However, existing GSSL methods mostly focus on node- or edge-level information, often ignoring chemically relevant substructures which strongly influence molecular properties. In this work, we propose Graph Semantic Predictive Network (GraSPNet), a hierarchical self-supervised framework that explicitly models both atomic-level and fragment-level semantics. GraSPNet decomposes molecular graphs into chemically meaningful fragments without predefined vocabularies and learns node- and fragment-level representations through multi-level message passing with masked semantic prediction at both levels. This hierarchical semantic supervision enables GraSPNet to learn multi-resolution structural information that is both expressive and transferable. Extensive experiments on multiple molecular property prediction benchmarks demonstrate that GraSPNet learns chemically meaningful representations and consistently outperforms state-of-the-art GSSL methods in transfer learning settings.
Authors: Mohanad Obeed, Ming Jian
Abstract: Deep neural networks (DNNs) have been increasingly explored for receiver design because they can handle complex environments without relying on explicit channel models. Nevertheless, because communication channels change rapidly, their distributions can shift over time, often making periodic retraining necessary. This paper proposes a zero-overhead online and continual learning framework for orthogonal frequency-division multiplexing (OFDM) neural receivers that directly detect the soft bits of received signals. Unlike conventional fine-tuning methods that rely on dedicated training intervals or full resource grids, our approach leverages existing demodulation reference signals (DMRS) to simultaneously enable signal demodulation and model adaptation. We introduce three pilot designs: fully randomized, hybrid, and additional pilots that flexibly support joint demodulation and learning. To accommodate these pilot designs, we develop two receiver architectures: (i) a parallel design that separates inference and fine-tuning for uninterrupted operation, and (ii) a forward-pass reusing design that reduces computational complexity. Simulation results show that the proposed method effectively tracks both slow and fast channel distribution variations without additional overhead, service interruption, or catastrophic performance degradation under distribution shift.
Authors: Mukul Chhabra, Luigi Medrano, Arush Verma
Abstract: Enterprise Retrieval-Augmented Generation (RAG) assistants operate in multi-turn, case-based workflows such as technical support and IT operations, where evaluation must reflect operational constraints, structured identifiers (e.g., error codes, versions), and resolution workflows. Existing RAG evaluation frameworks are primarily designed for benchmark-style or single-turn settings and often fail to capture enterprise-specific failure modes such as case misidentification, workflow misalignment, and partial resolution across turns. We present a case-aware LLM-as-a-Judge evaluation framework for enterprise multi-turn RAG systems. The framework evaluates each turn using eight operationally grounded metrics that separate retrieval quality, grounding fidelity, answer utility, precision integrity, and case/workflow alignment. A severity-aware scoring protocol reduces score inflation and improves diagnostic clarity across heterogeneous enterprise cases. The system uses deterministic prompting with strict JSON outputs, enabling scalable batch evaluation, regression testing, and production monitoring. Through a comparative study of two instruction-tuned models across short and long workflows, we show that generic proxy metrics provide ambiguous signals, while the proposed framework exposes enterprise-critical tradeoffs that are actionable for system improvement.
Authors: Callum Canavan, Aditya Shrivastava, Allison Qi, Jonathan Michala, Fabien Roger
Abstract: To steer language models towards truthful outputs on tasks which are beyond human capability, previous work has suggested training models on easy tasks to steer them on harder ones (easy-to-hard generalization), or using unsupervised training algorithms to steer models with no external labels at all (unsupervised elicitation). Although techniques from both paradigms have been shown to improve model accuracy on a wide variety of tasks, we argue that the datasets used for these evaluations could cause overoptimistic evaluation results. Unlike many real-world datasets, they often (1) have no features with more salience than truthfulness, (2) have balanced training sets, and (3) contain only data points to which the model can give a well-defined answer. We construct datasets that lack each of these properties to stress-test a range of standard unsupervised elicitation and easy-to-hard generalization techniques. We find that no technique reliably performs well on any of these challenges. We also study ensembling and combining easy-to-hard and unsupervised techniques, and find they only partially mitigate performance degradation due to these challenges. We believe that overcoming these challenges should be a priority for future work on unsupervised elicitation.
Authors: Yuting Deng, Melanie Brucks, Olivier Toubia
Abstract: Ideas generated by independent samples of humans tend to be more diverse than ideas generated from independent LLM samples, raising concerns that widespread reliance on LLMs could homogenize ideation and undermine innovation at a societal level. Drawing on cognitive psychology, we identify (both theoretically and empirically) two mechanisms undermining LLM idea diversity. First, at the individual level, LLMs exhibit fixation just as humans do, where early outputs constrain subsequent ideation. Second, at the collective level, LLMs aggregate knowledge into a unified distribution rather than exhibiting the knowledge partitioning inherent to human populations, where each person occupies a distinct region of the knowledge space. Through four studies, we demonstrate that targeted prompting interventions can address each mechanism independently: Chain-of-Thought (CoT) prompting reduces fixation by encouraging structured reasoning (only in LLMs, not humans), while ordinary personas (versus "creative entrepreneurs" such as Steve Jobs) improve knowledge partitioning by serving as diverse sampling cues, anchoring generation in distinct regions of the semantic space. Combining both approaches produces the highest idea diversity, outperforming humans. These findings offer a theoretically grounded framework for understanding LLM idea diversity and practical strategies for human-AI collaborations that leverage AI's efficiency without compromising the diversity essential to a healthy innovation ecosystem.
Authors: Jun Han, Josue Nassar, Sanjit Singh Batra, Aldo Cordova-Palomera, Vijay Nori, Robert E. Tillman
Abstract: Machine learning holds great promise for advancing the field of medicine, with electronic health records (EHRs) serving as a primary data source. However, EHRs are often sparse and contain missing data due to various challenges and limitations in data collection and sharing between healthcare providers. Existing techniques for imputing missing values predominantly focus on known unknowns, such as missing or unavailable values of lab test results; most do not explicitly address situations where it is difficult to distinguish what is missing. For instance, a missing diagnosis code in an EHR could signify either that the patient has not been diagnosed with the condition or that a diagnosis was made, but not shared by a provider. Such situations fall into the paradigm of unknown unknowns. To address this challenge, we develop a general purpose algorithm for denoising data to recover unknown missing values in binary EHRs. We design a transformer-based denoising neural network where the output is thresholded adaptively to recover values in cases where we predict data are missing. Our results demonstrate improved accuracy in denoising medical codes within a real EHR dataset compared to existing imputation approaches and leads to increased performance on downstream tasks using the denoised data. In particular, when applying our method to a real world application, predicting hospital readmission from EHRs, our method achieves statistically significant improvement over all existing baselines.
Authors: Anna Hart, Chi Han, Jeonghwan Kim, Huimin Zhao, Heng Ji
Abstract: Modern Protein Language Models (PLMs) apply transformer-based model architectures from natural language processing to biological sequences, predicting a variety of protein functions and properties. However, protein language has key differences from natural language, such as a rich functional space despite a vocabulary of only 20 amino acids. These differences motivate research into how transformer-based architectures operate differently in the protein domain and how we can better leverage PLMs to solve protein-related tasks. In this work, we begin by directly comparing how the distribution of information stored across layers of attention heads differs between the protein and natural language domain. Furthermore, we adapt a simple early-exit technique-originally used in the natural language domain to improve efficiency at the cost of performance-to achieve both increased accuracy and substantial efficiency gains in protein non-structural property prediction by allowing the model to automatically select protein representations from the intermediate layers of the PLMs for the specific task and protein at hand. We achieve performance gains ranging from 0.4 to 7.01 percentage points while simultaneously improving efficiency by over 10 percent across models and non-structural prediction tasks. Our work opens up an area of research directly comparing how language models change behavior when moved into the protein domain and advances language modeling in biological domains.
Authors: Enrico Ballini, Luca Muscarnera, Alessio Fumagalli, Anna Scotti, Francesco Regazzoni
Abstract: The unmatched ability of Deep Neural Networks in capturing complex patterns in large and noisy datasets is often associated with their large hypothesis space, and consequently to the vast amount of parameters that characterize model architectures. Pruning techniques affirmed themselves as valid tools to extract sparse representations of neural networks parameters, carefully balancing between compression and preservation of information. However, a fundamental assumption behind pruning is that expendable weights should have small impact on the error of the network, while highly important weights should tend to have a larger influence on the inference. We argue that this idea could be generalized; what if a weight is not simply removed but also compensated with a perturbation of the adjacent bias, which does not contribute to the network sparsity? Our work introduces a novel pruning method in which the importance measure of each weight is computed considering the output behavior after an optimal perturbation of its adjacent bias, efficiently computable by automatic differentiation. These perturbations can be then applied directly after the removal of each weight, independently of each other. After deriving analytical expressions for the aforementioned quantities, numerical experiments are conducted to benchmark this technique against some of the most popular pruning strategies, demonstrating an intrinsic efficiency of the proposed approach in very diverse machine learning scenarios. Finally, our findings are discussed and the theoretical implications of our results are presented.
Authors: Shubhanshu Shekhar, Mohammad Javad Khojasteh, Ananya Acharya, Tony Tohme, Kamal Youcef-Toumi
Abstract: The distinctive architectural features of normalizing flows (NFs), notably bijectivity and tractable Jacobians, make them well-suited for generative modeling. Invertible neural networks (INNs) build on these principles to address supervised inverse problems, enabling direct modeling of both forward and inverse mappings. In this paper, we revisit these architectures from both theoretical and practical perspectives and address a key gap in the literature: the lack of theoretical guarantees on approximation quality under realistic assumptions, whether for posterior inference in INNs or for generative modeling with NFs. We introduce a unified framework for INNs and NFs based on variational unsupervised loss functions, inspired by analogous formulations in related areas such as generative adversarial networks (GANs) and the Precision-Recall divergence for training normalizing flows. Within this framework, we derive theoretical performance guarantees, quantifying posterior accuracy for INNs and distributional accuracy for NFs, under assumptions that are weaker and more practically realistic than those used in prior work. Building on these theoretical results, we conduct extensive case studies to distill general design principles and practical guidelines. We conclude by demonstrating the effectiveness of our approach on a realistic ocean-acoustic inversion problem.
Authors: Paras Sharma, YuePing Sha, Janet Shufor Bih Epse Fofang, Brayden Yan, Jess A. Turner, Nicole Balay, Hubert O. Asare, Angela E. B. Stewart, Erin Walker
Abstract: Dialogue systems have long supported learner reflections, with theoretically grounded, rule-based designs offering structured scaffolding but often struggling to respond to shifts in engagement. Large Language Models (LLMs), in contrast, can generate context-sensitive responses but are not informed by decades of research on how learning interactions should be structured, raising questions about their alignment with pedagogical theories. This paper presents a hybrid dialogue system that embeds LLM responsiveness within a theory-aligned, rule-based framework to support learner reflections in a culturally responsive robotics summer camp. The rule-based structure grounds dialogue in self-regulated learning theory, while the LLM decides when and how to prompt deeper reflections, responding to evolving conversation context. We analyze themes across dialogues to explore how our hybrid system shaped learner reflections. Our findings indicate that LLM-embedded dialogues supported richer learner reflections on goals and activities, but also introduced challenges due to repetitiveness and misalignment in prompts, reducing engagement.
Authors: Nuocheng Yang, Sihua Wang, Ouwen Huan, Mingzhe Chen, Tony Q. S. Quek, Changchuan Yin
Abstract: Decentralized federated learning (DFL) based on low-rank adaptation (LoRA) enables mobile devices with multi-task datasets to collaboratively fine-tune a large language model (LLM) by exchanging locally updated parameters with a subset of neighboring devices via wireless connections for knowledge integration.However, directly aggregating parameters fine-tuned on heterogeneous datasets induces three primary issues across the DFL life-cycle: (i) \textit{catastrophic knowledge forgetting during fine-tuning process}, arising from conflicting update directions caused by data heterogeneity; (ii) \textit{inefficient communication and convergence during model aggregation process}, due to bandwidth-intensive redundant model transmissions; and (iii) \textit{multi-task knowledge interference during inference process}, resulting from incompatible knowledge representations coexistence during inference. To address these issues in a fully decentralized scenario, we first propose a sparse-and-orthogonal LoRA that ensures orthogonality between model updates to eliminate direction conflicts during fine-tuning.Then, we analyze how device connection topology affects multi-task performance, prompting a cluster-based topology design during aggregation.Finally, we propose an implicit mixture of experts (MoE) mechanism to avoid the coexistence of incompatible knowledge during inference. Simulation results demonstrate that the proposed approach effectively reduces communication resource consumption by up to $73\%$ and enhances average performance by $5\%$ compared with the traditional LoRA method.
Authors: Peiliang Cai, Jiacheng Liu, Haowen Xu, Xinyu Wang, Chang Zou, Linfeng Zhang
Abstract: Diffusion models have achieved remarkable success in image and video generation tasks. However, the high computational demands of Diffusion Transformers (DiTs) pose a significant challenge to their practical deployment. While feature caching is a promising acceleration strategy, existing methods based on simple reusing or training-free forecasting struggle to adapt to the complex, stage-dependent dynamics of the diffusion process, often resulting in quality degradation and failing to maintain consistency with the standard denoising process. To address this, we propose a LEarnable Stage-Aware (LESA) predictor framework based on two-stage training. Our approach leverages a Kolmogorov-Arnold Network (KAN) to accurately learn temporal feature mappings from data. We further introduce a multi-stage, multi-expert architecture that assigns specialized predictors to different noise-level stages, enabling more precise and robust feature forecasting. Extensive experiments show our method achieves significant acceleration while maintaining high-fidelity generation. Experiments demonstrate 5.00x acceleration on FLUX.1-dev with minimal quality degradation (1.0% drop), 6.25x speedup on Qwen-Image with a 20.2% quality improvement over the previous SOTA (TaylorSeer), and 5.00x acceleration on HunyuanVideo with a 24.7% PSNR improvement over TaylorSeer. State-of-the-art performance on both text-to-image and text-to-video synthesis validates the effectiveness and generalization capability of our training-based framework across different models. Our code is included in the supplementary materials and will be released on GitHub.
Authors: Pratham Yashwante, Davit Abrahamyan, Shresth Grover, Sukruth Rao
Abstract: We study how visual artifacts introduced by diffusion-based inpainting affect language generation in vision-language models. We use a two-stage diagnostic setup in which masked image regions are reconstructed and then provided to captioning models, enabling controlled comparisons between captions generated from original and reconstructed inputs. Across multiple datasets, we analyze the relationship between reconstruction fidelity and downstream caption quality. We observe consistent associations between pixel-level and perceptual reconstruction metrics and both lexical and semantic captioning performance. Additional analysis of intermediate visual representations and attention patterns shows that inpainting artifacts lead to systematic, layer-dependent changes in model behavior. Together, these results provide a practical diagnostic framework for examining how visual reconstruction quality influences language generation in multimodal systems.
Authors: Md Mirajul Islam, Xi Yang, Adittya Soukarjya Saha, Rajesh Debnath, Min Chi
Abstract: Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL) have advanced rapidly in recent years and have been successfully applied to e-learning environments like intelligent tutoring systems (ITSs). Despite great success, the broader application of DRL to educational technologies has been limited due to major challenges such as sample inefficiency and difficulty designing the reward function. In contrast, Apprenticeship Learning (AL) uses a few expert demonstrations to infer the expert's underlying reward functions and derive decision-making policies that generalize and replicate optimal behavior. In this work, we leverage a generalized AL framework, THEMES, to induce effective pedagogical policies by capturing the complexities of the expert student learning process, where multiple reward functions may dynamically evolve over time. We evaluate the effectiveness of THEMES against six state-of-the-art baselines, demonstrating its superior performance and highlighting its potential as a powerful alternative for inducing effective pedagogical policies and show that it can achieve high performance, with an AUC of 0.899 and a Jaccard of 0.653, using only 18 trajectories of a previous semester to predict student pedagogical decisions in a later semester.
Authors: Zhengyao Gu, Jonathan Light, Raul Astudillo, Ziyu Ye, Langzhou He, Henry Peng Zou, Wei Cheng, Santiago Paternain, Philip S. Yu, Yisong Yue
Abstract: Post-training large foundation models with reinforcement learning typically relies on massive and heterogeneous datasets, making effective curriculum learning both critical and challenging. In this work, we propose ACTOR-CURATOR, a scalable and fully automated curriculum learning framework for reinforcement learning post-training of large language models (LLMs). ACTOR-CURATOR learns a neural curator that dynamically selects training problems from large problem banks by directly optimizing for expected policy performance improvement. We formulate problem selection as a non-stationary stochastic bandit problem, derive a principled loss function based on online stochastic mirror descent, and establish regret guarantees under partial feedback. Empirically, ACTOR-CURATOR consistently outperforms uniform sampling and strong curriculum baselines across a wide range of challenging reasoning benchmarks, demonstrating improved training stability and efficiency. Notably, it achieves relative gains of 28.6% on AIME2024 and 30.5% on ARC-1D over the strongest baseline and up to 80% speedup. These results suggest that ACTOR-CURATOR is a powerful and practical approach for scalable LLM post-training.
Authors: Hana Salavcova, Martin \v{C}ern\'y, Arpita Biswas
Abstract: We study the problem of fairly allocating indivisible goods when limited sharing is allowed, that is, each good may be allocated to up to $k$ agents, while incurring a cost for sharing. While classic maximin share (MMS) allocations may not exist in many instances, we demonstrate that allowing controlled sharing can restore fairness guarantees that are otherwise unattainable in certain scenarios. (1) Our first contribution shows that exact maximin share (MMS) allocations are guaranteed to exist whenever goods are allowed to be cost-sensitively shared among at least half of the agents and the number of agents is even; for odd numbers of agents, we obtain a slightly weaker MMS guarantee. (2) We further design a Shared Bag-Filling Algorithm that guarantees a $(1 - C)(k - 1)$-approximate MMS allocation, where $C$ is the maximum cost of sharing a good. Notably, when $(1 - C)(k - 1) \geq 1$, our algorithm recovers an exact MMS allocation. (3) We additionally introduce the Sharing Maximin Share (SMMS) fairness notion, a natural extension of MMS to the $k$-sharing setting. (4) We show that SMMS allocations always exist under identical utilities and for instances with two agents. (5) We construct a counterexample to show the impossibility of the universal existence of an SMMS allocation. (6) Finally, we establish a connection between SMMS and constrained MMS (CMMS), yielding approximation guarantees for SMMS via existing CMMS results. These contributions provide deep theoretical insights for the problem of fair resource allocation when a limited sharing of resources are allowed in multi-agent environments.
Authors: Griffin Pitts, Sanaz Motamedi
Abstract: Conversational AI tools have been rapidly adopted by students and are becoming part of their learning routines. To understand what drives this adoption, we draw on the Technology Acceptance Model (TAM) and examine how perceived usefulness and perceived ease of use relate to students' behavioral intention to use conversational AI that generates responses for learning tasks. We extend TAM by incorporating trust, perceived enjoyment, and subjective norms as additional factors that capture social and affective influences and uncertainty around AI outputs. Using partial least squares structural equation modeling, we find perceived usefulness remains the strongest predictor of students' intention to use conversational AI. However, perceived ease of use does not exert a significant direct effect on behavioral intention once other factors are considered, operating instead indirectly through perceived usefulness. Trust and subjective norms significantly influence perceptions of usefulness, while perceived enjoyment exerts both a direct and indirect effect on usage intentions. These findings suggest that adoption decisions for conversational AI systems are influenced less by effort-related considerations and more by confidence in system outputs, affective engagement, and social context. Future research is needed to further examine how these acceptance relationships generalize across different conversational systems and usage contexts.
Authors: Nishant Subramani, Kshitish Ghate, Mona Diab
Abstract: Modern language models (LM) are trained on large scrapes of the Web, containing millions of personal information (PI) instances, many of which LMs memorize, increasing privacy risks. In this work, we develop the regexes and rules (R&R) detector suite to detect email addresses, phone numbers, and IP addresses, which outperforms the best regex-based PI detectors. On a manually curated set of 483 instances of PI, we measure memorization: finding that 13.6% are parroted verbatim by the Pythia-6.9b model, i.e., when the model is prompted with the tokens that precede the PI in the original document, greedy decoding generates the entire PI span exactly. We expand this analysis to study models of varying sizes (160M-6.9B) and pretraining time steps (70k-143k iterations) in the Pythia model suite and find that both model size and amount of pretraining are positively correlated with memorization. Even the smallest model, Pythia-160m, parrots 2.7% of the instances exactly. Consequently, we strongly recommend that pretraining datasets be aggressively filtered and anonymized to minimize PI parroting.
Authors: Longxiang Wang, Xiang Zheng, Xuhao Zhang, Yao Zhang, Ye Wu, Cong Wang
Abstract: Multi-tenant LLM serving frameworks widely adopt shared Key-Value caches to enhance efficiency. However, this creates side-channel vulnerabilities enabling prompt leakage attacks. Prior studies identified these attack surfaces yet focused on expanding attack vectors rather than optimizing attack performance, reporting impractically high attack costs that underestimate the true privacy risk. We propose OptiLeak, a reinforcement learning-enhanced framework that maximizes prompt reconstruction efficiency through two-stage fine-tuning. Our key insight is that domain-specific ``hard tokens'' -- terms difficult to predict yet carrying sensitive information -- can be automatically identified via likelihood ranking and used to construct preference pairs for Direct Preference Optimization, eliminating manual annotation. This enables effective preference alignment while avoiding the overfitting issues of extended supervised fine-tuning. Evaluated on three benchmarks spanning medical and financial domains, OptiLeak achieves up to $12.48\times$ reduction in average requests per token compared to baseline approaches, with consistent improvements across model scales from 3B to 14B parameters. Our findings demonstrate that cache-based prompt leakage poses a more severe threat than previously reported, underscoring the need for robust cache isolation in production deployments.
Authors: Saurabh Mishra, Shivani Thakur, Radhika Mamidi
Abstract: The proliferation of hate speech on social media platforms has necessitated the development of effective detection and moderation tools. This study evaluates the efficacy of various machine learning models in identifying hate speech and offensive language and investigates the potential of text transformation techniques to neutralize such content. We compare traditional models like CNNs and LSTMs with advanced neural network models such as BERT and its derivatives, alongside exploring hybrid models that combine different architectural features. Our results indicate that while advanced models like BERT show superior accuracy due to their deep contextual understanding, hybrid models exhibit improved capabilities in certain scenarios. Furthermore, we introduce innovative text transformation approaches that convert negative expressions into neutral ones, thereby potentially mitigating the impact of harmful content. The implications of these findings are discussed, highlighting the strengths and limitations of current technologies and proposing future directions for more robust hate speech detection systems.
Authors: Rulin Zhou, Guankun Wang, An Wang, Yujie Ma, Lixin Ouyang, Bolin Cui, Junyan Li, Chaowei Zhu, Mingyang Li, Ming Chen, Xiaopin Zhong, Peng Lu, Jiankun Wang, Xianming Liu, Hongliang Ren
Abstract: Accurate and stable field-of-view (FoV) guidance is critical for safe and efficient minimally invasive surgery, yet existing approaches often conflate visual attention estimation with downstream camera control or rely on direct object-centric assumptions. In this work, we formulate surgical attention tracking as a spatio-temporal learning problem and model surgeon focus as a dense attention heatmap, enabling continuous and interpretable frame-wise FoV guidance. We propose SurgAtt-Tracker, a holistic framework that robustly tracks surgical attention by exploiting temporal coherence through proposal-level reranking and motion-aware refinement, rather than direct regression. To support systematic training and evaluation, we introduce SurgAtt-1.16M, a large-scale benchmark with a clinically grounded annotation protocol that enables comprehensive heatmap-based attention analysis across procedures and institutions. Extensive experiments on multiple surgical datasets demonstrate that SurgAtt-Tracker consistently achieves state-of-the-art performance and strong robustness under occlusion, multi-instrument interference, and cross-domain settings. Beyond attention tracking, our approach provides a frame-wise FoV guidance signal that can directly support downstream robotic FoV planning and automatic camera control.
Authors: Jiawei Wang, Chuang Yang, Jiawei Yong, Xiaohang Xu, Hongjun Wang, Noboru Koshizuka, Shintaro Fukushima, Ryosuke Shibasaki, Renhe Jiang
Abstract: Mobility trajectories are essential for understanding urban dynamics and enhancing urban planning, yet access to such data is frequently hindered by privacy concerns. This research introduces a transformative framework for generating large-scale urban mobility trajectories, employing a novel application of a transformer-based model pre-trained and fine-tuned through a two-phase process. Initially, trajectory generation is conceptualized as an offline reinforcement learning (RL) problem, with a significant reduction in vocabulary space achieved during tokenization. The integration of Inverse Reinforcement Learning (IRL) allows for the capture of trajectory-wise reward signals, leveraging historical data to infer individual mobility preferences. Subsequently, the pre-trained model is fine-tuned using the constructed reward model, effectively addressing the challenges inherent in traditional RL-based autoregressive methods, such as long-term credit assignment and handling of sparse reward environments. Comprehensive evaluations on multiple datasets illustrate that our framework markedly surpasses existing models in terms of reliability and diversity. Our findings not only advance the field of urban mobility modeling but also provide a robust methodology for simulating urban data, with significant implications for traffic management and urban development planning. The implementation is publicly available at https://github.com/Wangjw6/TrajGPT_R.
Authors: Chenyue Yu, Lingao Xiao, Jinhong Deng, Ivor W. Tsang, Yang He
Abstract: Large-scale image datasets are fundamental to deep learning, but their high storage demands pose challenges for deployment in resource-constrained environments. While existing approaches reduce dataset size by discarding samples, they often ignore the significant redundancy within each image -- particularly in the color space. To address this, we propose Dataset Color Quantization (DCQ), a unified framework that compresses visual datasets by reducing color-space redundancy while preserving information crucial for model training. DCQ achieves this by enforcing consistent palette representations across similar images, selectively retaining semantically important colors guided by model perception, and maintaining structural details necessary for effective feature learning. Extensive experiments across CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet-1K show that DCQ significantly improves training performance under aggressive compression, offering a scalable and robust solution for dataset-level storage reduction. Code is available at \href{https://github.com/he-y/Dataset-Color-Quantization}{https://github.com/he-y/Dataset-Color-Quantization}.
URLs: https://github.com/he-y/Dataset-Color-Quantization, https://github.com/he-y/Dataset-Color-Quantization
Authors: Mohammad Sadra Rajabi, Aanuoluwapo Ojelade, Sunwook Kim, Maury A. Nussbaum
Abstract: Manual lifting tasks are a major contributor to work-related musculoskeletal disorders, and effective ergonomic risk assessment is essential for quantifying physical exposure and informing ergonomic interventions. The Revised NIOSH Lifting Equation (RNLE) is a widely used ergonomic risk assessment tool for lifting tasks that relies on six task variables, including horizontal (H) and vertical (V) hand distances; such distances are typically obtained through manual measurement or specialized sensing systems and are difficult to use in real-world environments. We evaluated the feasibility of using innovative vision-language models (VLMs) to non-invasively estimate H and V from RGB video streams. Two multi-stage VLM-based pipelines were developed: a text-guided detection-only pipeline and a detection-plus-segmentation pipeline. Both pipelines used text-guided localization of task-relevant regions of interest, visual feature extraction from those regions, and transformer-based temporal regression to estimate H and V at the start and end of a lift. For a range of lifting tasks, estimation performance was evaluated using leave-one-subject-out validation across the two pipelines and seven camera view conditions. Results varied significantly across pipelines and camera view conditions, with the segmentation-based, multi-view pipeline consistently yielding the smallest errors, achieving mean absolute errors of approximately 6-8 cm when estimating H and 5-8 cm when estimating V. Across pipelines and camera view configurations, pixel-level segmentation reduced estimation error by approximately 20-30% for H and 35-40% for V relative to the detection-only pipeline. These findings support the feasibility of VLM-based pipelines for video-based estimation of RNLE distance parameters.
Authors: Zirui Zhu, Hailun Xu, Yang Luo, Yong Liu, Kanchan Sarkar, Kun Xu, Yang You
Abstract: Reward models play a fundamental role in aligning large language models with human preferences. Existing methods predominantly follow two paradigms: scalar discriminative preference models, which are efficient but lack interpretability, and generative judging models, which offer richer reasoning at the cost of higher computational overhead. We observe that the log-probability margin between verdict tokens strongly correlates with prediction correctness, providing a reliable proxy for instance difficulty without additional inference cost. Building on this insight, we propose CAMEL, a confidence-gated reflection framework that performs a lightweight single-token preference decision first and selectively invokes reflection only for low-confidence instances. To induce effective self-correction, we train the model via reinforcement learning with counterfactual prefix augmentation, which exposes the model to diverse initial verdicts and encourages genuine revision. Empirically, CAMEL achieves state-of-the-art performance on three widely used reward-model benchmarks with 82.9% average accuracy, surpassing the best prior model by 3.2% and outperforming 70B-parameter models using only 14B parameters, while establishing a strictly better accuracy-efficiency Pareto frontier.
Authors: Shuzhi Cao, Rong Chen, Ailong He, Shuguang Han, Jufeng Chen
Abstract: In search systems, effectively coordinating the two core objectives of search relevance matching and click-through rate (CTR) prediction is crucial for discovering users' interests and enhancing platform revenue. In our prior work PRECTR, we proposed a unified framework to integrate these two subtasks,thereby eliminating their inconsistency and leading to mutual benefit.However, our previous work still faces three main challenges. First, low-active users and new users have limited search behavioral data, making it difficult to achieve effective personalized relevance preference modeling. Second, training data for ranking models predominantly come from high-relevance exposures, creating a distribution mismatch with the broader candidate space in coarse-ranking, leading to generalization bias. Third, due to the latency constraint, the original model employs an Emb+MLP architecture with a frozen BERT encoder, which prevents joint optimization and creates misalignment between representation learning and CTR fine-tuning. To solve these issues, we further reinforce our method and propose PRECTR-V2. Specifically, we mitigate the low-activity users' sparse behavior problem by mining global relevance preferences under the specific query, which facilitates effective personalized relevance modeling for cold-start scenarios. Subsequently, we construct hard negative samples through embedding noise injection and relevance label reconstruction, and optimize their relative ranking against positive samples via pairwise loss, thereby correcting exposure bias. Finally, we pretrain a lightweight transformer-based encoder via knowledge distillation from LLM and SFT on the text relevance classification task. This encoder replaces the frozen BERT module, enabling better adaptation to CTR fine-tuning and advancing beyond the traditional Emb+MLP paradigm.
Authors: Wei Chen, Yuqian Wu, Junle Chen, Xiaofang Zhou, Yuxuan Liang
Abstract: Urban systems, as dynamic complex systems, continuously generate spatio-temporal data streams that encode the fundamental laws of human mobility and city evolution. While AI for Science has witnessed the transformative power of foundation models in disciplines like genomics and meteorology, urban computing remains fragmented due to "scenario-specific" models, which are overfitted to specific regions or tasks, hindering their generalizability. To bridge this gap and advance spatio-temporal foundation models for urban systems, we adopt scaling as the central perspective and systematically investigate two key questions: what to scale and how to scale. Grounded in first-principles analysis, we identify three critical dimensions: heterogeneity, correlation, and dynamics, aligning these principles with the fundamental scientific properties of urban spatio-temporal data. Specifically, to address heterogeneity through data scaling, we construct WorldST. This billion-scale corpus standardizes diverse physical signals, such as traffic flow and speed, from over 100 global cities into a unified data format. To enable computation scaling for modeling correlations, we introduce the MiniST unit, a novel split mechanism that discretizes continuous spatio-temporal fields into learnable computational units to unify representations of grid-based and sensor-based observations. Finally, addressing dynamics via architecture scaling, we propose UrbanFM, a minimalist self-attention architecture designed with limited inductive biases to autonomously learn dynamic spatio-temporal dependencies from massive data. Furthermore, we establish EvalST, the largest-scale urban spatio-temporal benchmark to date. Extensive experiments demonstrate that UrbanFM achieves remarkable zero-shot generalization across unseen cities and tasks, marking a pivotal first step toward large-scale urban spatio-temporal foundation models.
Authors: Christopher Koch, Joshua Andreas Wellbrock
Abstract: Current AI-assisted engineering workflows lack a built-in mechanism to maintain task-level verification and regulatory traceability at machine-speed delivery. Agile V addresses this gap by embedding independent verification and audit artifact generation into each task cycle. The framework merges Agile iteration with V-Model verification into a continuous Infinity Loop, deploying specialized AI agents for requirements, design, build, test, and compliance, governed by mandatory human approval gates. We evaluate three hypotheses: (H1) audit-ready artifacts emerge as a by-product of development, (H2) 100% requirement-level verification is achievable with independent test generation, and (H3) verified increments can be delivered with single-digit human interactions per cycle. A feasibility case study on a Hardware-in-the-Loop system (about 500 LOC, 8 requirements, 54 tests) supports all three hypotheses: audit-ready documentation was generated automatically (H1), 100% requirement-level pass rate was achieved (H2), and only 6 prompts per cycle were required (H3), yielding an estimated 10-50x cost reduction versus a COCOMO II baseline (sensitivity range from pessimistic to optimistic assumptions). We invite independent replication to validate generalizability.
Authors: Riccardo Gallon, Fabian Schiemenz, Alessandra Menicucci, Eberhard Gill
Abstract: This study details an artificial intelligence (AI)-based methodology for the semantic segmentation of space camera faults. Specifically, we address the segmentation of straylight effects induced by solar presence around the camera's Field of View (FoV). Anomalous images are sourced from our published dataset. Our approach emphasizes generalization across diverse flare textures, leveraging pre-training on a public dataset (Flare7k++) including flares in various non-space contexts to mitigate the scarcity of realistic space-specific data. A DeepLabV3 model with MobileNetV3 backbone performs the segmentation task. The model design targets deployment in spacecraft resource-constrained hardware. Finally, based on a proposed interface between our model and the onboard navigation pipeline, we develop custom metrics to assess the model's performance in the system-level context.
Authors: Che Wang, Jiaming Zhang, Ziqi Zhang, Zijie Wang, Yinghui Wang, Jianbo Gao, Tao Wei, Zhong Chen, Wei Yang Bryan Lim
Abstract: The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security vulnerabilities, particularly indirect prompt injection (IPI) attacks. Existing attack methods are limited by their reliance on static patterns and evaluation on simple language models, failing to address the fast-evolving nature of modern AI agents. We introduce AdapTools, a novel adaptive IPI attack framework that selects stealthier attack tools and generates adaptive attack prompts to create a rigorous security evaluation environment. Our approach comprises two key components: (1) Adaptive Attack Strategy Construction, which develops transferable adversarial strategies for prompt optimization, and (2) Attack Enhancement, which identifies stealthy tools capable of circumventing task-relevance defenses. Comprehensive experimental evaluation shows that AdapTools achieves a 2.13 times improvement in attack success rate while degrading system utility by a factor of 1.78. Notably, the framework maintains its effectiveness even against state-of-the-art defense mechanisms. Our method advances the understanding of IPI attacks and provides a useful reference for future research.
Authors: Aram Davtyan, Yusuf Sahin, Yasaman Haghighi, Sebastian Stapf, Pablo Acuaviva, Alexandre Alahi, Paolo Favaro
Abstract: Discrete image tokenizers have emerged as a key component of modern vision and multimodal systems, providing a sequential interface for transformer-based architectures. However, most existing approaches remain primarily optimized for reconstruction and compression, often yielding tokens that capture local texture rather than object-level semantic structure. Inspired by the incremental and compositional nature of human communication, we introduce COMmunication inspired Tokenization (COMiT), a framework for learning structured discrete visual token sequences. COMiT constructs a latent message within a fixed token budget by iteratively observing localized image crops and recurrently updating its discrete representation. At each step, the model integrates new visual information while refining and reorganizing the existing token sequence. After several encoding iterations, the final message conditions a flow-matching decoder that reconstructs the full image. Both encoding and decoding are implemented within a single transformer model and trained end-to-end using a combination of flow-matching reconstruction and semantic representation alignment losses. Our experiments demonstrate that while semantic alignment provides grounding, attentive sequential tokenization is critical for inducing interpretable, object-centric token structure and substantially improving compositional generalization and relational reasoning over prior methods.
Authors: Kun Ran, Marwah Alaofi, Danula Hettiachchi, Chenglong Ma, Khoi Nguyen Dinh Anh, Khoi Vo Nguyen, Sachin Pathiyan Cherumanal, Lida Rashidi, Falk Scholer, Damiano Spina, Shuoqi Sun, Oleg Zendel
Abstract: This paper presents the award-winning RMIT-ADM+S system for the Text-to-Text track of the NeurIPS~2025 MMU-RAG Competition. We introduce Routing-to-RAG (R2RAG), a research-focused retrieval-augmented generation (RAG) architecture composed of lightweight components that dynamically adapt the retrieval strategy based on inferred query complexity and evidence sufficiency. The system uses smaller LLMs, enabling operation on a single consumer-grade GPU while supporting complex research tasks. It builds on the G-RAG system, winner of the ACM~SIGIR~2025 LiveRAG Challenge, and extends it with modules informed by qualitative review of outputs. R2RAG won the Best Dynamic Evaluation award in the Open Source category, demonstrating high effectiveness with careful design and efficient use of resources.
Authors: Darvan Shvan Khairaldeen, Hossein Hassani
Abstract: Maqam, a singing type, is a significant component of Kurdish music. A maqam singer receives training in a traditional face-to-face or through self-training. Automatic Singing Assessment (ASA) uses machine learning (ML) to provide the accuracy of singing styles and can help learners to improve their performance through error detection. Currently, the available ASA tools follow Western music rules. The musical composition requires all notes to stay within their expected pitch range from start to finish. The system fails to detect micro-intervals and pitch bends, so it identifies Kurdish maqam singing as incorrect even though the singer performs according to traditional rules. Kurdish maqam requires recognizing performance errors within microtonal spaces, which is beyond Western equal temperament. This research is the first attempt to address the mentioned gap. While many error types happen during singing, our focus is on pitch, rhythm, and modal stability errors in the context of Bayati-Kurd. We collected 50 songs from 13 vocalists ( 2-3 hours) and annotated 221 error spans (150 fine pitch, 46 rhythm, 25 modal drift). The data was segmented into 15,199 overlapping windows and converted to log-mel spectrograms. We developed a two-headed CNN-BiLSTM with attention mode to decide whether a window contains an error and to classify it based on the chosen errors. Trained for 20 epochs with early stopping at epoch 10, the model reached a validation macro-F1 of 0.468. On the full 50-song evaluation at a 0.750 threshold, recall was 39.4% and precision 25.8% . Within detected windows, type macro-F1 was 0.387, with F1 of 0.492 (fine pitch), 0.536 (rhythm), and 0.133 (modal drift); modal drift recall was 8.0%. The better performance on common error types shows that the method works, while the poor modal-drift recall shows that more data and balancing are needed.
Authors: Yifei Xu, Guilherme Potje, Shivam Shandilya, Tiancheng Yuan, Leonardo de Oliveira Nunes, Rakshanda Agarwal, Saeid Asgari, Adam Atkinson, Emre K{\i}c{\i}man, Songwu Lu, Ranveer Chandra, Tusher Chakraborty
Abstract: Designing aligned and robust rewards for open-ended generation remains a key barrier to RL post-training. Rubrics provide structured, interpretable supervision, but scaling rubric construction is difficult: expert rubrics are costly, prompted rubrics are often superficial or inconsistent, and fixed-pool discriminative rubrics can saturate and drift, enabling reward hacking. We present SibylSense, an inference-time learning approach that adapts a frozen rubric generator through a tunable memory bank of validated rubric items. Memory is updated via verifier-based item rewards measured by reference-candidate answer discriminative gaps from a handful of examples. SibylSense alternates memory tuning with a rubric-adversarial policy update that produces rubric-satisfying candidate answers, shrinking discriminative gaps and driving the rubric generator to capture new quality dimensions. Experiments on two open-ended tasks show that SibylSense yields more discriminative rubrics and improves downstream RL performance over static and non-adaptive baselines.
Authors: Tian Lan, Lei Xu, Zimu Yuan, Shanggui Liu, Jiajun Liu, Jiaxin Liu, Weilai Xiang, Hongyu Yang, Dong Jiang, Jianxin Yin, Dingyu Wang
Abstract: Musculoskeletal disorders represent a significant global health burden and are a leading cause of disability worldwide. While MRI is essential for accurate diagnosis, its interpretation remains exceptionally challenging. Radiologists must identify multiple potential abnormalities within complex anatomical structures across different imaging planes, a process that requires significant expertise and is prone to variability. We developed OrthoDiffusion, a unified diffusion-based foundation model designed for multi-task musculoskeletal MRI interpretation. The framework utilizes three orientation-specific 3D diffusion models, pre-trained in a self-supervised manner on 15,948 unlabeled knee MRI scans, to learn robust anatomical features from sagittal, coronal, and axial views. These view-specific representations are integrated to support diverse clinical tasks, including anatomical segmentation and multi-label diagnosis. Our evaluation demonstrates that OrthoDiffusion achieves excellent performance in the segmentation of 11 knee structures and the detection of 8 knee abnormalities. The model exhibited remarkable robustness across different clinical centers and MRI field strengths, consistently outperforming traditional supervised models. Notably, in settings where labeled data was scarce, OrthoDiffusion maintained high diagnostic precision using only 10\% of training labels. Furthermore, the anatomical representations learned from knee imaging proved highly transferable to other joints, achieving strong diagnostic performance across 11 diseases of the ankle and shoulder. These findings suggest that diffusion-based foundation models can serve as a unified platform for multi-disease diagnosis and anatomical segmentation, potentially improving the efficiency and accuracy of musculoskeletal MRI interpretation in real-world clinical workflows.
Authors: Yun-Jui Tsai, Wei-Yu Chen, Yan-Ru Ju, Yu-Hung Chang, Ti-Rong Wu
Abstract: Reinforcement learning (RL) agents achieve remarkable performance but remain far less learning-efficient than humans. While RL agents require extensive self-play games to extract useful signals, humans often need only a few games, improving rapidly by repeatedly revisiting states where mistakes occurred. This idea, known as search control, aims to restart from valuable states rather than always from the initial state. In AlphaZero, prior work Go-Exploit applies this idea by sampling past states from self-play or search trees, but it treats all states equally, regardless of their learning potential. We propose Regret-Guided Search Control (RGSC), which extends AlphaZero with a regret network that learns to identify high-regret states, where the agent's evaluation diverges most from the actual outcome. These states are collected from both self-play trajectories and MCTS nodes, stored in a prioritized regret buffer, and reused as new starting positions. Across 9x9 Go, 10x10 Othello, and 11x11 Hex, RGSC outperforms AlphaZero and Go-Exploit by an average of 77 and 89 Elo, respectively. When training on a well-trained 9x9 Go model, RGSC further improves the win rate against KataGo from 69.3% to 78.2%, while both baselines show no improvement. These results demonstrate that RGSC provides an effective mechanism for search control, improving both efficiency and robustness of AlphaZero training. Our code is available at https://rlg.iis.sinica.edu.tw/papers/rgsc.
Authors: Yanna Jiang, Delong Li, Haiyu Deng, Baihe Ma, Xu Wang, Qin Wang, Guangsheng Yu
Abstract: Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably. These capabilities are callable modules that package procedural knowledge with explicit applicability conditions, execution policies, termination criteria, and reusable interfaces. Unlike one-off plans or atomic tool calls, skills operate (and often do well) across tasks. This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update) and introduces two complementary taxonomies. The first is a system-level set of \textbf{seven design patterns} capturing how skills are packaged and executed in practice, from metadata-driven progressive disclosure and executable code skills to self-evolving libraries and marketplace distribution. The second is an orthogonal \textbf{representation $\times$ scope} taxonomy describing what skills \emph{are} (natural language, code, policy, hybrid) and what environments they operate over (web, OS, software engineering, robotics). We analyze the security and governance implications of skill-based agents, covering supply-chain risks, prompt injection via skill payloads, and trust-tiered execution, grounded by a case study of the ClawHavoc campaign in which nearly 1{,}200 malicious skills infiltrated a major agent marketplace, exfiltrating API keys, cryptocurrency wallets, and browser credentials at scale. We further survey deterministic evaluation approaches, anchored by recent benchmark evidence that curated skills can substantially improve agent success rates while self-generated skills may degrade them. We conclude with open challenges toward robust, verifiable, and certifiable skills for real-world autonomous agents.
Authors: Jiwoo Kang, Yeon-Chang Lee
Abstract: Multimodal recommender systems (MMRSs) enhance collaborative filtering by leveraging item-side modalities, but their reliance on a fixed set of modalities and task-specific objectives limits both modality extensibility and task generalization. We propose E-MMKGR, a framework that constructs an e-commerce-specific Multimodal Knowledge Graph E-MMKG and learns unified item representations through GNN-based propagation and KG-oriented optimization. These representations provide a shared semantic foundation applicable to diverse tasks. Experiments on real-world Amazon datasets show improvements of up to 10.18% in Recall@10 for recommendation and up to 21.72% over vector-based retrieval for product search, demonstrating the effectiveness and extensibility of our approach.
Authors: Alagappan Ramanathan, Eunju Kang, Dongsu Han, Sangeetha Abdu Jyothi
Abstract: Internet measurement faces twin challenges: complex analyses require expert-level orchestration of tools, yet even syntactically correct implementations can have methodological flaws and can be difficult to verify. Democratizing measurement capabilities thus demands automating both workflow generation and verification against methodological standards established through decades of research. We present Airavat, the first agentic framework for Internet measurement workflow generation with systematic verification and validation. Airavat coordinates a set of agents mirroring expert reasoning: three agents handle problem decomposition, solution design, and code implementation, with assistance from a registry of existing tools. Two specialized engines ensure methodological correctness: a Verification Engine evaluates workflows against a knowledge graph encoding five decades of measurement research, while a Validation Engine identifies appropriate validation techniques grounded in established methodologies. Through four Internet measurement case studies, we demonstrate that Airavat (i) generates workflows matching expert-level solutions, (ii) makes sound architectural decisions, (iii) addresses novel problems without ground truth, and (iv) identifies methodological flaws missed by standard execution-based testing.
Authors: Taiqiang Wu, Zenan Zu, Bo Zhou, Ngai Wong
Abstract: Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning, but also suffer from heavy computational overhead. To address this issue, efficient reasoning aims to incentivize short yet accurate thinking trajectories, typically through reward shaping with Reinforcement Learning (RL). In this paper, we systematically investigate the mechanics of efficient reasoning for LLMs. For comprehensive evaluation, we advocate for more fine-grained metrics, including length distribution conditioned on correctness and performance across a wide spectrum of token budgets ranging from 2k to 32k. First, we reveal that the training process follows a two-stage paradigm: length adaptation and reasoning refinement. After that, we conduct extensive experiments (about 0.2 million GPU hours) in a unified protocol, deconstructing training prompts and rollouts, reward shaping, and optimization strategies. In particular, a key finding is to train on relatively easier prompts, ensuring the density of positive reward signals and thus avoiding the length collapse. Meanwhile, the learned length bias can be generalized across domains. We distill all findings into valuable insights and practical guidelines, and further validate them across the Qwen3 series, ranging from 0.6B to 30B, demonstrating the robustness and generalization.
Authors: Christian Catalini, Xiang Hui, Jane Wu
Abstract: For millennia, human cognition was the primary engine of progress on Earth. As AI decouples cognition from biology, the marginal cost of measurable execution falls to zero, absorbing any labor capturable by metrics--including creative, analytical, and innovative work. The binding constraint on growth is no longer intelligence but human verification bandwidth: the capacity to validate, audit, and underwrite responsibility when execution is abundant. We model the AGI transition as the collision of two racing cost curves: an exponentially decaying Cost to Automate and a biologically bottlenecked Cost to Verify. This structural asymmetry widens a Measurability Gap between what agents can execute and what humans can afford to verify. It also drives a shift from skill-biased to measurability-biased technical change. Rents migrate to verification-grade ground truth, cryptographic provenance, and liability underwriting--the ability to insure outcomes rather than merely generate them. The current human-in-the-loop equilibrium is unstable: eroded from below as apprenticeship collapses (Missing Junior Loop) and from within as experts codify their obsolescence (Codifier's Curse). Unverified deployment becomes privately rational--a Trojan Horse externality. Unmanaged, these forces pull toward a Hollow Economy. Yet by scaling verification alongside agentic capabilities, the forces that threaten collapse become the catalyst for unbounded discovery and experimentation--an Augmented Economy. We derive a practical playbook for individuals, companies, investors, and policymakers. Today's defining challenge is not the race to deploy the most autonomous systems; it is the race to secure the foundations of their oversight. Only by scaling our bandwidth for verification alongside our capacity for execution can we ensure that the intelligence we have summoned preserves the humanity that initiated it.
Authors: Jaehyun Park, Minyoung Ahn, Minkyu Kim, Jonghyun Lee, Jae-Gil Lee, Dongmin Park
Abstract: Despite recent advances in diffusion models, AI generated images still often contain visual artifacts that compromise realism. Although more thorough pre-training and bigger models might reduce artifacts, there is no assurance that they can be completely eliminated, which makes artifact mitigation a highly crucial area of study. Previous artifact-aware methodologies depend on human-labeled artifact datasets, which are costly and difficult to scale, underscoring the need for an automated approach to reliably acquire artifact-annotated datasets. In this paper, we propose ArtiAgent, which efficiently creates pairs of real and artifact-injected images. It comprises three agents: a perception agent that recognizes and grounds entities and subentities from real images, a synthesis agent that introduces artifacts via artifact injection tools through novel patch-wise embedding manipulation within a diffusion transformer, and a curation agent that filters the synthesized artifacts and generates both local and global explanations for each instance. Using ArtiAgent, we synthesize 100K images with rich artifact annotations and demonstrate both efficacy and versatility across diverse applications. Code is available at link.
Authors: Luka \v{S}iktar, Branimir \'Caran, Bojan \v{S}ekoranja, Marko \v{S}vaco
Abstract: Search and rescue (SAR) operations require rapid responses to save lives or property. Unmanned Aerial Vehicles (UAVs) equipped with vision-based systems support these missions through prior terrain investigation or real-time assistance during the mission itself. Vision-based UAV frameworks aid human search tasks by detecting and recognizing specific individuals, then tracking and following them while maintaining a safe distance. A key safety requirement for UAV following is the accurate estimation of the distance between camera and target object under real-world conditions, achieved by fusing multiple image modalities. UAVs with deep learning-based vision systems offer a new approach to the planning and execution of SAR operations. As part of the system for automatic people detection and face recognition using deep learning, in this paper we present the fusion of depth camera measurements and monocular camera-to-body distance estimation for robust tracking and following. Deep learning-based filtering of depth camera data and estimation of camera-to-body distance from a monocular camera are achieved with YOLO-pose, enabling real-time fusion of depth information using the Extended Kalman Filter (EKF) algorithm. The proposed subsystem, designed for use in drones, estimates and measures the distance between the depth camera and the human body keypoints, to maintain the safe distance between the drone and the human target. Our system provides an accurate estimated distance, which has been validated against motion capture ground truth data. The system has been tested in real time indoors, where it reduces the average errors, root mean square error (RMSE) and standard deviations of distance estimation up to 15,3\% in three tested scenarios.
Authors: Haoyang Li, Changsong Liu, Wei Rao, Hao Shi, Sakriani Sakti, Eng Siong Chng
Abstract: Automatic speech recognition (ASR) degrades severely in noisy environments. Although speech enhancement (SE) front-ends effectively suppress background noise, they often introduce artifacts that harm recognition. Observation addition (OA) addressed this issue by fusing noisy and SE enhanced speech, improving recognition without modifying the parameters of the SE or ASR models. This paper proposes an intelligibility-guided OA method, where fusion weights are derived from intelligibility estimates obtained directly from the backend ASR. Unlike prior OA methods based on trained neural predictors, the proposed method is training-free, reducing complexity and enhances generalization. Extensive experiments across diverse SE-ASR combinations and datasets demonstrate strong robustness and improvements over existing OA baselines. Additional analyses of intelligibility-guided switching-based alternatives and frame versus utterance-level OA further validate the proposed design.
Authors: Himadri Mandal, Vishnu Varadarajan, Jaee Ponde, Aritra Das, Mihir More, Debayan Gupta
Abstract: Bubeck and Sellke (2021) pose as an open problem the connection between the law of robustness and robust generalization. The law of robustness states that overparameterization is necessary for models to interpolate robustly; in particular, robust interpolation requires the learned function to be Lipschitz. Robust generalization asks whether small robust training loss implies small robust test loss. We resolve this problem by explicitly connecting the two for arbitrary data distributions. Specifically, we introduce a nontrivial notion of robust generalization error and convert it into a lower bound on the expected Rademacher complexity of the induced robust loss class. Our bounds recover the $\Omega(n^{1/d})$ regime of Wu et al.\ (2023) and show that, up to constants, robust generalization does not change the order of the Lipschitz constant required for smooth interpolation. We conduct experiments to probe the predicted scaling with dataset size and model capacity, testing whether empirical behavior aligns more closely with the predictions of Bubeck and Sellke (2021) or Wu et al.\ (2023). For MNIST, we find that the lower-bound Lipschitz constant scales on the order predicted by Wu et al.\ (2023). Informally, to obtain low robust generalization error, the Lipschitz constant must lie in a range that we bound, and the allowable perturbation radius is linked to the Lipschitz scale.
Authors: Mark Marron
Abstract: Fully leveraging the capabilities of AI agents in software development requires a rethinking of the software ecosystem itself. To this end, this paper outlines the creation of an Agentic Infused Software Ecosystem (AISE), that rests on three pillars. The first, of course, is the AI agents themselves, which in the past 5 years have moved from simple code completion and toward sophisticated independent development tasks, a trend which will only continue. The second pillar is the programming language and APIs (or tools) that these agents use to accomplish tasks, and increasingly, serve as the communication substrate that humans and AI agents interact and collaborate through. The final pillar is the runtime environment and ecosystem that agents operate within, and which provide the capabilities that programmatic agents use to interface with (and effect actions in) the external world. To realize the vision of AISE, all three pillars must be advanced in a holistic manner, and critically, in a manner that is synergistic for AI agents as they exist today, those that will exist in the future, and for the human developers that work alongside them.
Authors: Yang Zhang, Danyang Li, Yuxuan Li, Xin Zhang, Tianyu Xie, Mingming Cheng, Xiang Li
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable performance by integrating powerful language backbones with large-scale visual encoders. Among these, latent Chain-of-Thought (CoT) methods enable implicit reasoning in continuous hidden states, facilitating seamless vision-language integration and faster inference. However, existing heuristically predefined supervision signals in latent CoT provide limited guidance for preserving critical visual information in intermediate latent states. To address this limitation, we propose CrystaL (Crystallized Latent Reasoning), a single-stage framework with two paths to process intact and corrupted images, respectively. By explicitly aligning the attention patterns and prediction distributions across the two paths, CrystaL crystallizes latent representations into task-relevant visual semantics, without relying on auxiliary annotations or external modules. Extensive experiments on perception-intensive benchmarks demonstrate that CrystaL consistently outperforms state-of-the-art baselines, achieving substantial gains in fine-grained visual understanding while maintaining robust reasoning capabilities.
Authors: Christian Simon, MAsato Ishii, Wei-Yao Wang, Koichi Saito, Akio Hayakawa, Dongseok Shim, Zhi Zhong, Shuyang Cui, Shusuke Takahashi, Takashi Shibuya, Yuki Mitsufuji
Abstract: Scaling multimodal alignment between video and audio is challenging, particularly due to limited data and the mismatch between text descriptions and frame-level video information. In this work, we tackle the scaling challenge in multimodal-to-audio generation, examining whether models trained on short instances can generalize to longer ones during testing. To tackle this challenge, we present multimodal hierarchical networks so-called MMHNet, an enhanced extension of state-of-the-art video-to-audio models. Our approach integrates a hierarchical method and non-causal Mamba to support long-form audio generation. Our proposed method significantly improves long audio generation up to more than 5 minutes. We also prove that training short and testing long is possible in the video-to-audio generation tasks without training on the longer durations. We show in our experiments that our proposed method could achieve remarkable results on long-video to audio benchmarks, beating prior works in video-to-audio tasks. Moreover, we showcase our model capability in generating more than 5 minutes, while prior video-to-audio methods fall short in generating with long durations.
Authors: Yubin Ge, Yongsong Huang, Xiaofeng Liu
Abstract: Report-supervised (RSuper) learning seeks to alleviate the need for dense tumor voxel labels with constraints derived from radiology reports (e.g., volumes, counts, sizes, locations). In MRI studies of brain tumors, however, we often involve multi-parametric scans and substructures. Here, fine-grained modality/parameter-wise reports are usually provided along with global findings and are correlated with different substructures. Moreover, the reports often describe only the largest lesion and provide qualitative or uncertain cues (``mild,'' ``possible''). Classical RSuper losses (e.g., sum volume consistency) can over-constrain or hallucinate unreported findings under such incompleteness, and are unable to utilize these hierarchical findings or exploit the priors of varied lesion types in a merged dataset. We explicitly parse the global quantitative and modality-wise qualitative findings and introduce a unified, one-sided, uncertainty-aware formulation (MS-RSuper) that: (i) aligns modality-specific qualitative cues (e.g., T1c enhancement, FLAIR edema) with their corresponding substructures using existence and absence losses; (ii) enforces one-sided lower-bounds for partial quantitative cues (e.g., largest lesion size, minimal multiplicity); and (iii) adds extra- vs. intra-axial anatomical priors to respect cohort differences. Certainty tokens scale penalties; missing cues are down-weighted. On 1238 report-labeled BraTS-MET/MEN scans, our MS-RSuper largely outperforms both a sparsely-supervised baseline and a naive RSuper method.
Authors: Tianhao Fu, Yucheng Chen
Abstract: Medical image processing demands specialized software that handles high-dimensional volumetric data, heterogeneous file formats, and domain-specific training procedures. Existing frameworks either provide low-level components that require substantial integration effort or impose rigid, monolithic pipelines that resist modification. We present MIP Candy (MIPCandy), a freely available, PyTorch-based framework designed specifically for medical image processing. MIPCandy provides a complete, modular pipeline spanning data loading, training, inference, and evaluation, allowing researchers to obtain a fully functional process workflow by implementing a single method, $\texttt{build_network}$, while retaining fine-grained control over every component. Central to the design is $\texttt{LayerT}$, a deferred configuration mechanism that enables runtime substitution of convolution, normalization, and activation modules without subclassing. The framework further offers built-in $k$-fold cross-validation, dataset inspection with automatic region-of-interest detection, deep supervision, exponential moving average, multi-frontend experiment tracking (Weights & Biases, Notion, MLflow), training state recovery, and validation score prediction via quotient regression. An extensible bundle ecosystem provides pre-built model implementations that follow a consistent trainer--predictor pattern and integrate with the core framework without modification. MIPCandy is open-source under the Apache-2.0 license and requires Python~3.12 or later. Source code and documentation are available at https://github.com/ProjectNeura/MIPCandy.
Authors: Timur Nabiev, Evgeny Frolov
Abstract: Sequential self-attention models usually rely on additive positional embeddings, which inject positional information into item representations at the input. In the absence of positional signals, the attention block is permutation-equivariant over sequence positions and thus has no intrinsic notion of temporal order beyond causal masking. We argue that additive positional embeddings make the attention mechanism only superficially sensitive to sequence order: positional information is entangled with item embedding semantics, propagates weakly in deep architectures, and limits the ability to capture rich sequential patterns. To address these limitations, we introduce a kernelized self-attention mechanism, where a learnable positional kernel operates purely in the position space, disentangled from semantic similarity, and directly modulates attention weights. When applied per attention block, this kernel enables adaptive multi-scale sequential modeling. Experiments on standard next-item prediction benchmarks show that our positional kernel attention consistently improves over strong competing baselines.
Authors: Seongheon Park, Changdae Oh, Hyeong Kyu Choi, Xuefeng Du, Sharon Li
Abstract: Large Vision-Language Models (LVLMs) frequently hallucinate, limiting their safe deployment in real-world applications. Existing LLM self-evaluation methods rely on a model's ability to estimate the correctness of its own outputs, which can improve deployment reliability; however, they depend heavily on language priors and are therefore ill-suited for evaluating vision-conditioned predictions. We propose VAUQ, a vision-aware uncertainty quantification framework for LVLM self-evaluation that explicitly measures how strongly a model's output depends on visual evidence. VAUQ introduces the Image-Information Score (IS), which captures the reduction in predictive uncertainty attributable to visual input, and an unsupervised core-region masking strategy that amplifies the influence of salient regions. Combining predictive entropy with this core-masked IS yields a training-free scoring function that reliably reflects answer correctness. Comprehensive experiments show that VAUQ consistently outperforms existing self-evaluation methods across multiple datasets.
Authors: Zhangjie Xia, Yu Yang, Pan Xu
Abstract: Off-dynamics offline reinforcement learning (RL) aims to learn a policy for a target domain using limited target data and abundant source data collected under different transition dynamics. Existing methods typically address dynamics mismatch either globally over the state space or via pointwise data filtering; these approaches can miss localized cross-domain similarities or incur high computational cost. We propose Localized Dynamics-Aware Domain Adaptation (LoDADA), which exploits localized dynamics mismatch to better reuse source data. LoDADA clusters transitions from source and target datasets and estimates cluster-level dynamics discrepancy via domain discrimination. Source transitions from clusters with small discrepancy are retained, while those from clusters with large discrepancy are filtered out. This yields a fine-grained and scalable data selection strategy that avoids overly coarse global assumptions and expensive per-sample filtering. We provide theoretical insights and extensive experiments across environments with diverse global and local dynamics shifts. Results show that LoDADA consistently outperforms state-of-the-art off-dynamics offline RL methods by better leveraging localized distribution mismatch.
Authors: Floriano Tori, Lorenzo Bini, Marco Sorbi, St\'ephane Marchand-Maillet, Vincent Ginis
Abstract: Curvature notions on graphs provide a theoretical description of graph topology, highlighting bottlenecks and denser connected regions. Artifacts of the message passing paradigm in Graph Neural Networks, such as oversmoothing and oversquashing, have been attributed to these regions. However, it remains unclear how the topology of a graph interacts with the learned preferences of GNNs. Through Massive Activations, which correspond to extreme edge activation values in Graph Transformers, we probe this correspondence. Our findings on synthetic graphs and molecular benchmarks reveal that MAs do not preferentially concentrate on curvature extremes, despite their theoretical link to information flow. On the Long Range Graph Benchmark, we identify a systemic \textit{curvature shift}: global attention mechanisms exacerbate topological bottlenecks, drastically increasing the prevalence of negative curvature. Our work reframes curvature as a diagnostic probe for understanding when and why graph learning fails.
Authors: Bruno De Filippo, Alessandro Guidotti, Alessandro Vanelli-Coralli
Abstract: The signal-to-interference-plus-noise ratio (SINR) is central to performance optimization in user-centric beamforming for satellite-based non-terrestrial networks (NTNs). Its assessment either requires the transmission of dedicated pilots or relies on computing the beamforming matrix through minimum mean squared error (MMSE)-based formulations beforehand, a process that introduces significant computational overhead. In this paper, we propose a low-complexity SINR estimation framework that leverages multi-head self-attention (MHSA) to extract inter-user interference features directly from either channel state information or user location reports. The proposed dual MHSA (DMHSA) models evaluate the SINR of a scheduled user group without requiring explicit MMSE calculations. The architecture achieves a computational complexity reduction by a factor of three in the CSI-based setting and by two orders of magnitude in the location-based configuration, the latter benefiting from the lower dimensionality of user reports. We show that both DMHSA models maintain high estimation accuracy, with the root mean squared error typically below 1 dB with priority-queuing-based scheduled users. These results enable the integration of DMHSA-based estimators into scheduling procedures, allowing the evaluation of multiple candidate user groups and the selection of those offering the highest average SINR and capacity.
Authors: Rui Zhao, Xihui Li, Yizheng Zhang, Yuzhen Liu, Zhong Zhang, Yufeng Zhang, Cheng Zhou, Zhengyou Zhang, Lei Han
Abstract: Multi-agent deep Reinforcement Learning (RL) has made significant progress in developing intelligent game-playing agents in recent years. However, the efficient training of collective robots using multi-agent RL and the transfer of learned policies to real-world applications remain open research questions. In this work, we first develop a comprehensive robotic system, including simulation, distributed learning framework, and physical robot components. We then propose and evaluate reinforcement learning techniques designed for efficient training of cooperative and competitive policies on this platform. To address the challenges of multi-agent sim-to-real transfer, we introduce Out of Distribution State Initialization (OODSI) to mitigate the impact of the sim-to-real gap. In the experiments, OODSI improves the Sim2Real performance by 20%. We demonstrate the effectiveness of our approach through experiments with a multi-robot car competitive game and a cooperative task in real-world settings.
Authors: Xinfeng Li, Shenyu Dai, Kelong Zheng, Yue Xiao, Gelei Deng, Wei Dong, Xiaofeng Wang
Abstract: Large language model (LLM) agents are rapidly becoming trusted copilots in high-stakes domains like software development and healthcare. However, this deepening trust introduces a novel attack surface: Agent-Mediated Deception (AMD), where compromised agents are weaponized against their human users. While extensive research focuses on agent-centric threats, human susceptibility to deception by a compromised agent remains unexplored. We present the first large-scale empirical study with 303 participants to measure human susceptibility to AMD. This is based on HAT-Lab (Human-Agent Trust Laboratory), a high-fidelity research platform we develop, featuring nine carefully crafted scenarios spanning everyday and professional domains (e.g., healthcare, software development, human resources). Our 10 key findings reveal significant vulnerabilities and provide future defense perspectives. Specifically, only 8.6% of participants perceive AMD attacks, while domain experts show increased susceptibility in certain scenarios. We identify six cognitive failure modes in users and find that their risk awareness often fails to translate to protective behavior. The defense analysis reveals that effective warnings should interrupt workflows with low verification costs. With experiential learning based on HAT-Lab, over 90% of users who perceive risks report increased caution against AMD. This work provides empirical evidence and a platform for human-centric agent security research.
Authors: David Anugraha, Vishakh Padmakumar, Diyi Yang
Abstract: Qualitative insights from user experiences are critical for informing product and policy decisions, but collecting such data at scale is constrained by the time and availability of experts to conduct semi-structured interviews. Recent work has explored using large language models (LLMs) to automate interviewing, yet existing systems lack a principled mechanism for balancing systematic coverage of predefined topics with adaptive exploration, or the ability to pursue follow-ups, deep dives, and emergent themes that arise organically during conversation. In this work, we formulate adaptive semi-structured interviewing as an optimization problem over the interviewer's behavior. We define interview utility as a trade-off between coverage of a predefined interview topic guide, discovery of relevant emergent themes, and interview cost measured by length. Based on this formulation, we introduce SparkMe, a multi-agent LLM interviewer that performs deliberative planning via simulated conversation rollouts to select questions with high expected utility. We evaluate SparkMe through controlled experiments with LLM-based interviewees, showing that it achieves higher interview utility, improving topic guide coverage (+4.7% over the best baseline) and eliciting richer emergent insights while using fewer conversational turns than prior LLM interviewing approaches. We further validate SparkMe in a user study with 70 participants across 7 professions on the impact of AI on their workflows. Domain experts rate SparkMe as producing high-quality adaptive interviews that surface helpful profession-specific insights not captured by prior approaches. The code, datasets, and evaluation protocols for SparkMe are available as open-source at https://github.com/SALT-NLP/SparkMe.
Authors: Samah Fodeh, Linhai Ma, Yan Wang, Srivani Talakokkul, Ganesh Puthiaraju, Afshan Khan, Ashley Hagaman, Sarah Lowe, Aimee Roundtree
Abstract: Patient-generated text such as secure messages, surveys, and interviews contains rich expressions of the patient voice (PV), reflecting communicative behaviors and social determinants of health (SDoH). Traditional qualitative coding frameworks are labor intensive and do not scale to large volumes of patient-authored messages across health systems. Existing machine learning (ML) and natural language processing (NLP) approaches provide partial solutions but often treat patient-centered communication (PCC) and SDoH as separate tasks or rely on models not well suited to patient-facing language. We introduce PVminer, a domain-adapted NLP framework for structuring patient voice in secure patient-provider communication. PVminer formulates PV detection as a multi-label, multi-class prediction task integrating patient-specific BERT encoders (PV-BERT-base and PV-BERT-large), unsupervised topic modeling for thematic augmentation (PV-Topic-BERT), and fine-tuned classifiers for Code, Subcode, and Combo-level labels. Topic representations are incorporated during fine-tuning and inference to enrich semantic inputs. PVminer achieves strong performance across hierarchical tasks and outperforms biomedical and clinical pre-trained baselines, achieving F1 scores of 82.25% (Code), 80.14% (Subcode), and up to 77.87% (Combo). An ablation study further shows that author identity and topic-based augmentation each contribute meaningful gains. Pre-trained models, source code, and documentation will be publicly released, with annotated datasets available upon request for research use.
Authors: Victor Reijgwart, Cesar Cadena, Roland Siegwart, Lionel Ott
Abstract: Hierarchical, multi-resolution volumetric mapping approaches are widely used to represent large and complex environments as they can efficiently capture their occupancy and connectivity information. Yet widely used path planning methods such as sampling and trajectory optimization do not exploit this explicit connectivity information, and search-based methods such as A* suffer from scalability issues in large-scale high-resolution maps. In many applications, Euclidean shortest paths form the underpinning of the navigation system. For such applications, any-angle planning methods, which find optimal paths by connecting corners of obstacles with straight-line segments, provide a simple and efficient solution. In this paper, we present a method that has the optimality and completeness properties of any-angle planners while overcoming computational tractability issues common to search-based methods by exploiting multi-resolution representations. Extensive experiments on real and synthetic environments demonstrate the proposed approach's solution quality and speed, outperforming even sampling-based methods. The framework is open-sourced to allow the robotics and planning community to build on our research.
Authors: Sepehr Salem Ghahfarokhi, M. Moein Esfahani, Raj Sunderraman, Vince Calhoun, Mohammed Alser
Abstract: Deep learning has significantly advanced automated brain tumor diagnosis, yet clinical adoption remains limited by interpretability and computational constraints. Conventional models often act as opaque ''black boxes'' and fail to quantify the complex, irregular tumor boundaries that characterize malignant growth. To address these challenges, we present XMorph, an explainable and computationally efficient framework for fine-grained classification of three prominent brain tumor types: glioma, meningioma, and pituitary tumors. We propose an Information-Weighted Boundary Normalization (IWBN) mechanism that emphasizes diagnostically relevant boundary regions alongside nonlinear chaotic and clinically validated features, enabling a richer morphological representation of tumor growth. A dual-channel explainable AI module combines GradCAM++ visual cues with LLM-generated textual rationales, translating model reasoning into clinically interpretable insights. The proposed framework achieves a classification accuracy of 96.0%, demonstrating that explainability and high performance can co-exist in AI-based medical imaging systems. The source code and materials for XMorph are all publicly available at: https://github.com/ALSER-Lab/XMorph.
Authors: Anas Barakat, Souradip Chakraborty, Khushbu Pahwa, Amrit Singh Bedi
Abstract: Pass@k is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-answer reasoning. It defines success if any of $k$ independently sampled solutions passes a verifier. This multi-sample inference metric has motivated inference-aware fine-tuning methods that directly optimize pass@$k$. However, prior work reports a recurring trade-off: pass@k improves while pass@1 degrades under such methods. This trade-off is practically important because pass@1 often remains a hard operational constraint due to latency and cost budgets, imperfect verifier coverage, and the need for a reliable single-shot fallback. We study the origin of this trade-off and provide a theoretical characterization of when pass@k policy optimization can reduce pass@1 through gradient conflict induced by prompt interference. We show that pass@$k$ policy gradients can conflict with pass@1 gradients because pass@$k$ optimization implicitly reweights prompts toward low-success prompts; when these prompts are what we term negatively interfering, their upweighting can rotate the pass@k update direction away from the pass@1 direction. We illustrate our theoretical findings with large language model experiments on verifiable mathematical reasoning tasks.
Authors: Yining Hong, Huang Huang, Manling Li, Li Fei-Fei, Jiajun Wu, Yejin Choi
Abstract: Embodied LLMs endow robots with high-level task reasoning, but they cannot reflect on what went wrong or why, turning deployment into a sequence of independent trials where mistakes repeat rather than accumulate into experience. Drawing upon human reflective practitioners, we introduce Reflective Test-Time Planning, which integrates two modes of reflection: \textit{reflection-in-action}, where the agent uses test-time scaling to generate and score multiple candidate actions using internal reflections before execution; and \textit{reflection-on-action}, which uses test-time training to update both its internal reflection model and its action policy based on external reflections after execution. We also include retrospective reflection, allowing the agent to re-evaluate earlier decisions and perform model updates with hindsight for proper long-horizon credit assignment. Experiments on our newly-designed Long-Horizon Household benchmark and MuJoCo Cupboard Fitting benchmark show significant gains over baseline models, with ablative studies validating the complementary roles of reflection-in-action and reflection-on-action. Qualitative analyses, including real-robot trials, highlight behavioral correction through reflection.
Authors: Junchen Liu, Sven Elflein, Or Litany, Zan Gojcic, Ruilong Li
Abstract: Test-time training (TTT) with KV binding as sequence modeling layer is commonly interpreted as a form of online meta-learning that memorizes a key-value mapping at test time. However, our analysis reveals multiple phenomena that contradict this memorization-based interpretation. Motivated by these findings, we revisit the formulation of TTT and show that a broad class of TTT architectures can be expressed as a form of learned linear attention operator. Beyond explaining previously puzzling model behaviors, this perspective yields multiple practical benefits: it enables principled architectural simplifications, admits fully parallel formulations that preserve performance while improving efficiency, and provides a systematic reduction of diverse TTT variants to a standard linear attention form. Overall, our results reframe TTT not as test-time memorization, but as learned linear attention with enhanced representational capacity.
Authors: Shangheng Du, Jiabao Zhao, Jinxin Shi, Zhentao Xie, Xin Jiang, Yanhong Bai, Liang He
Abstract: With the rapid development of Large Language Models (LLMs), LLM-based agents have been widely adopted in various fields, becoming essential for autonomous decision-making and interactive tasks. However, current work typically relies on prompt design or fine-tuning strategies applied to vanilla LLMs, which often leads to limited effectiveness or suboptimal performance in complex agent-related environments. Although LLM optimization techniques can improve model performance across many general tasks, they lack specialized optimization towards critical agent functionalities such as long-term planning, dynamic environmental interaction, and complex decision-making. Although numerous recent studies have explored various strategies to optimize LLM-based agents for complex agent tasks, a systematic review summarizing and comparing these methods from a holistic perspective is still lacking. In this survey, we provide a comprehensive review of LLM-based agent optimization approaches, categorizing them into parameter-driven and parameter-free methods. We first focus on parameter-driven optimization, covering fine-tuning-based optimization, reinforcement learning-based optimization, and hybrid strategies, analyzing key aspects such as trajectory data construction, fine-tuning techniques, reward function design, and optimization algorithms. Additionally, we briefly discuss parameter-free strategies that optimize agent behavior through prompt engineering and external knowledge retrieval. Finally, we summarize the datasets and benchmarks used for evaluation and tuning, review key applications of LLM-based agents, and discuss major challenges and promising future directions. Our repository for related references is available at https://github.com/YoungDubbyDu/LLM-Agent-Optimization.
URLs: https://github.com/YoungDubbyDu/LLM-Agent-Optimization.
Authors: Amin Seffo, Aladin Djuhera, Masataro Asai, Holger Boche
Abstract: Recent advancements in large language models (LLMs) have spurred interest in robotic navigation that incorporates complex spatial, mathematical, and conditional constraints from natural language into the planning problem. Such constraints can be informal yet highly complex, making it challenging to translate into a formal description that can be passed on to a planning algorithm. In this paper, we propose STPR, a constraint generation framework that uses LLMs to translate constraints (expressed as instructions on ``what not to do'') into executable Python functions. STPR leverages the LLM's strong coding capabilities to shift the problem description from language into structured and transparent code, thus circumventing complex reasoning and avoiding potential hallucinations. We show that these LLM-generated functions accurately describe even complex mathematical constraints, and apply them to point cloud representations with traditional search algorithms. Experiments in a simulated Gazebo environment show that STPR ensures full compliance across several constraints and scenarios, while having short runtimes. We also verify that STPR can be used with smaller, code-specific LLMs, making it applicable to a wide range of compact models at low inference cost.
Authors: J\^onata Tyska Carvalho, Stefano Nolfi
Abstract: We propose a method that enables large language models (LLMs) to control embodied agents through the generation of control policies that directly map continuous observation vectors to continuous action vectors. At the outset, the LLMs generate a control strategy based on a textual description of the agent, its environment, and the intended goal. This strategy is then iteratively refined through a learning process in which the LLMs are repeatedly prompted to improve the current strategy, using performance feedback and sensory-motor data collected during its evaluation. The method is validated on classic control tasks from the Gymnasium library and the inverted pendulum task from the MuJoCo library. The approach proves effective with relatively compact models such as GPT-oss:120b and Qwen2.5:72b. In most cases, it successfully identifies optimal or near-optimal solutions by integrating symbolic knowledge derived through reasoning with sub-symbolic sensory-motor data gathered as the agent interacts with its environment.
Authors: Gon\c{c}alo Hora de Carvalho, Lazar S. Popov, Sander Kaatee, M\'ario S. Correia, Kristinn R. Th\'orisson, Tangrui Li, P\'etur H\'uni Bj\"ornsson, Eir\'ikur Sm\'ari Sigur{\dh}arson, Jilles S. Dibangoye
Abstract: We introduce \textbf{ICE-ID}, a benchmark dataset comprising 984,028 records from 16 Icelandic census waves spanning 220 years (1703--1920), with 226,864 expert-curated person identifiers. ICE-ID combines hierarchical geography (farm$\to$parish$\to$district$\to$county), patronymic naming conventions, sparse kinship links (partner, father, mother), and multi-decadal temporal drift -- challenges not captured by standard product-matching or citation datasets. This paper presents an artifact-backed analysis of temporal coverage, missingness, identifier ambiguity, candidate-generation efficiency, and cluster distributions, and situates ICE-ID against classical ER benchmarks (Abt--Buy, Amazon--Google, DBLP--ACM, DBLP--Scholar, Walmart--Amazon, iTunes--Amazon, Beer, Fodors--Zagats). We also define a deployment-faithful temporal OOD protocol and release the dataset, splits, regeneration scripts, analysis artifacts, and a dashboard for interactive exploration. Baseline model comparisons and end-to-end ER results are reported in the companion methods paper.
Authors: Jonathan Cook, Silvia Sapora, Arash Ahmadian, Akbir Khan, Tim Rocktaschel, Jakob Foerster, Laura Ruis
Abstract: Large language models (LLMs) are typically trained to acquire behaviours from demonstrations or experience, yet much of their training data is declarative: instructions, rules, and descriptions that specify behaviours without showing how to execute them. We introduce Programming by Backprop (PBB): a training regime that enables LLMs to acquire procedural knowledge (i.e., reusable behaviours) from declarative instructions encountered during training. With PBB, instructions in training data provide an opportunity to `program' specific behaviours into model weights. The core principle underpinning PBB is the separation of learning how instructions map to behaviour from internalising new instructions. We devise two distinct PBB curricula that leverage this principle. Through controlled experiments across two domains (algorithmic execution from Python source code and text generation from context-free grammars), we demonstrate the benefit of these curricula over training on a homogeneous data mixture. Crucially, PBB is highly sample efficient, with a single instruction substituting for up to 100 execution examples. Though execution of instructions in training data remains less reliable than when instructions are given in-context, our results demonstrate that procedural knowledge can be noisily `programmed' into LLMs through PBB, with important implications for data curation and safety.
Authors: Yiyi Lu, Hoi Ian Au, Junyao Zhang, Jingyu Pan, Guanglei Zhou, Yiting Wang, Jingwei Sun, Ang Li, Jianyi Zhang, Hai Li, Yiran Chen
Abstract: Electronic Design Automation (EDA) remains heavily reliant on tool command language (Tcl) scripting to drive complex RTL-to-GDSII flows. This scripting-based paradigm is labor-intensive, error-prone, and difficult to scale across large design projects. Recent advances in large language models (LLMs) suggest a new paradigm of natural language-driven automation. However, existing EDA efforts remain limited and face key challenges, including the absence of standardized interaction protocols and dependence on external APIs that introduce privacy risks. We present AutoEDA, a framework that leverages the Model Context Protocol (MCP) to enable end-to-end natural language control of RTL-to-GDSII design flows. AutoEDA introduces MCP-based servers for task decomposition, tool selection, and automated error handling, ensuring robust interaction between LLM agents and EDA tools. To enhance reliability and confidentiality, we integrate locally fine-tuned LLM agents. We further contribute a benchmark generation pipeline for diverse EDA scenarios and extend CodeBLEU with Tcl-specific enhancements for domain-aware evaluation. Together, these contributions establish a comprehensive framework for LLM-driven EDA automation, bridging natural language interfaces with modern chip design flows. Empirical results show that AutoEDA achieves up to 9.9 times higher accuracy than naive approaches while reducing token usage by approximately 97% compared to in-context learning.
Authors: Jorge Gallego-Feliciano, S. Aaron McClendon, Juan Morinelli, Stavros Zervoudakis, Antonios Saravanos
Abstract: We present the first comprehensive analysis of massive activation development throughout transformer training, using the Pythia model family as our testbed, and release our full dataset publicly to support further research. Through systematic analysis of various model sizes across multiple training checkpoints, we demonstrate that massive activation emergence follows highly predictable mathematical patterns that can be accurately modeled using an exponentially-modulated logarithmic function with five key parameters. Additionally, We develop a machine learning framework to predict these mathematical parameters from architectural specifications alone, achieving high accuracy for steady-state behavior and moderate accuracy for emergence timing and magnitude. These findings enable architects to predict and potentially control key aspects of massive activation emergence through design choices, with significant implications for model stability, training cycle length, interpretability, and optimization. Our findings demonstrate that the emergence of massive activations is governed by model design and can be anticipated, and potentially controlled, before training begins. Code is available at https://github.com/Aimpoint-Digital/massive-activations-fork
URLs: https://github.com/Aimpoint-Digital/massive-activations-fork
Authors: Akshat Dubey, Aleksandar An\v{z}el, Bahar \.Ilgen, Georges Hattab
Abstract: Explainable Artificial Intelligence (XAI) techniques, such as SHapley Additive exPlanations (SHAP), have become essential tools for interpreting complex ensemble tree-based models, especially in high-stakes domains such as healthcare analytics. However, SHAP values are usually treated as point estimates, which disregards the inherent and ubiquitous uncertainty in predictive models and data. This uncertainty has two primary sources: aleatoric and epistemic. The aleatoric uncertainty, which reflects the irreducible noise in the data. The epistemic uncertainty, which arises from a lack of data. In this work, we propose an approach for decomposing uncertainty in SHAP values into aleatoric, epistemic, and entanglement components. This approach integrates Dempster-Shafer evidence theory and hypothesis sampling via Dirichlet processes over tree ensembles. We validate the method across three real-world use cases with descriptive statistical analyses that provide insight into the nature of epistemic uncertainty embedded in SHAP explanations. The experimentations enable to provide more comprehensive understanding of the reliability and interpretability of SHAP-based attributions. This understanding can guide the development of robust decision-making processes and the refinement of models in high-stakes applications. Through our experiments with multiple datasets, we concluded that features with the highest SHAP values are not necessarily the most stable. This epistemic uncertainty can be reduced through better, more representative data and following appropriate or case-desired model development techniques. Tree-based models, especially bagging, facilitate the effective quantification of epistemic uncertainty.
Authors: Nicole Cho, Kirsty Fielding, William Watson, Sumitra Ganesh, Manuela Veloso
Abstract: Real-world financial filings report critical information about an entity's investment holdings, essential for assessing that entity's risk, profitability, and relationship profile. Yet, these details are often buried in messy, multi-page, fragmented tables that are difficult to parse, hindering downstream QA and data normalization. Specifically, 99.4% of the tables in our financial table dataset lack bounding boxes, with the largest table spanning 44 pages. To address this, we present TASER (Table Agents for Schema-guided Extraction and Recommendation), a continuously learning, agentic table extraction system that converts highly unstructured, multi-page, heterogeneous tables into normalized, schema-conforming outputs. Guided by an initial portfolio schema, TASER executes table detection, classification, extraction, and recommendations in a single pipeline. Our Recommender Agent reviews unmatched outputs and proposes schema revisions, enabling TASER to outperform vision-based table detection models such as Table Transformer by 10.1%. Within this continuous learning process, larger batch sizes yield a 104.3% increase in useful schema recommendations and a 9.8% increase in total extractions. To train TASER, we manually labeled 22,584 pages and 3,213 tables covering $731.7 billion in holdings, culminating in TASERTab to facilitate research on real-world financial tables and structured outputs. Our results highlight the promise of continuously learning agents for robust extractions from complex tabular data.
Authors: Dayoon Ko, Jihyuk Kim, Haeju Park, Sohyeon Kim, Dahyun Lee, Yongrae Jo, Gunhee Kim, Moontae Lee, Kyungjae Lee
Abstract: Large reasoning models (LRMs) combined with retrieval-augmented generation (RAG) have enabled deep research agents capable of multi-step reasoning with external knowledge retrieval. However, we find that existing approaches rarely demonstrate test-time search scaling. Methods that extend reasoning through single-query sequential search suffer from limited evidence coverage, while approaches that generate multiple independent queries per step often lack structured aggregation, hindering deeper sequential reasoning. We propose a hybrid search strategy to address these limitations. We introduce HybridDeepSearcher, a structured search agent that integrates parallel query expansion with explicit evidence aggregation before advancing to deeper sequential reasoning. To supervise this behavior, we introduce HDS-QA, a novel dataset that guides models to combine broad parallel search with structured aggregation through supervised reasoning-query0retrieval trajectories containing parallel sub-queries. Across five benchmarks, HybridDeepSearcher significantly outperforms the state-of-the-art, improving F1 scores by +15.9 on FanOutQA and +9.2 on a subset of BrowseComp. Further analysis shows its consistent test-time search scaling: performance improves as additional search turns or calls are allowed, while competing methods plateau.
Authors: Jaehyun Nam, Jinsung Yoon, Jiefeng Chen, Raj Sinha, Jinwoo Shin, Tomas Pfister
Abstract: While large language models (LLMs) have shown promise in automating data science, existing agents often struggle with the complexity of real-world workflows that require exploring multiple sources and synthesizing open-ended insights. In this paper, we introduce DS-STAR, a specialized agent to bridge this gap. Unlike prior approaches, DS-STAR is designed to (1) seamlessly process and integrate data across diverse, heterogeneous formats, and (2) move beyond simple QA to generate comprehensive research reports for open-ended queries. Extensive evaluation shows that DS-STAR achieves state-of-the-art performance on four benchmarks: DABStep, DABStep-Research, KramaBench, and DA-Code. Most notably, it significantly outperforms existing baseline models especially in hard-level QA tasks requiring multi-file processing, and generates high-quality data science reports that are preferred over the best baseline model in over 88% of cases.
Authors: Tong Guan, Zijie Meng, Dianqi Li, Shiyu Wang, Chao-Han Huck Yang, Qingsong Wen, Zuozhu Liu, Sabato Marco Siniscalchi, Ming Jin, Shirui Pan
Abstract: Recent advances in multimodal time series learning underscore a paradigm shift from analytics centered on basic patterns toward advanced time series understanding and reasoning. However, existing multimodal time series datasets mostly remain at the level of surface alignment and question answering, without reaching the depth of genuine reasoning. The absence of well-defined tasks that genuinely require time series reasoning, along with the scarcity of high-quality data, has limited progress in building practical time series reasoning models (TSRMs). To this end, we introduce Time Series Reasoning Suite (TSR-Suite), which formalizes four atomic tasks that span three fundamental capabilities for reasoning with time series: (1) perception, acquired through scenario understanding and causality discovery; (2) extrapolation, realized via event-aware forecasting; and (3) decision-making, developed through deliberation over perception and extrapolation. TSR-Suite is the first comprehensive time series reasoning suite that supports not only thorough evaluation but also the data pipeline and training of TSRMs. It contains more than 23K samples, of which 2.3K are carefully curated through a human-guided hierarchical annotation process. Building on this foundation, we introduce TimeOmni-1, the first unified reasoning model designed to address diverse real-world problems demanding time series reasoning. The model is trained in multiple stages, integrating a mixture of task scenarios, novel reward functions, and tailored optimizations. Experiments show that TimeOmni-1 delivers strong out-of-distribution generalization across all tasks and achieves a high rate of valid responses. It significantly improves causality discovery accuracy (64.0% vs. 35.9% with GPT-4.1) and raises the valid response rate by over 6% compared to GPT-4.1 on the event-aware forecasting task.
Authors: Manuel Cherep, Chengtian Ma, Abigail Xu, Maya Shaked, Pattie Maes, Nikhil Singh
Abstract: Environments built for people are increasingly operated by a new class of economic actors: LLM-powered software agents making decisions on our behalf. These decisions range from our purchases to travel plans to medical treatment selection. Current evaluations of these agents largely focus on task competence, but we argue for a deeper assessment: how these agents choose when faced with realistic decisions. We introduce ABxLab, a framework for systematically probing agentic choice through controlled manipulations of option attributes and persuasive cues. We apply this to a realistic web-based shopping environment, where we vary prices, ratings, and psychological nudges, all of which are factors long known to shape human choice. We find that agent decisions shift predictably and substantially in response, revealing that agents are strongly biased choosers even without being subject to the cognitive constraints that shape human biases. This susceptibility reveals both risk and opportunity: risk, because agentic consumers may inherit and amplify human biases; opportunity, because consumer choice provides a powerful testbed for a behavioral science of AI agents, just as it has for the study of human behavior. We release our framework as an open benchmark for rigorous, scalable evaluation of agent decision-making.
Authors: Chenqi Li, Yu Liu, Timothy Denison, Tingting Zhu
Abstract: Biosignals offer valuable insights into the physiological states of the human body. Although biosignal modalities differ in functionality, signal fidelity, sensor comfort, and cost, they are often intercorrelated, reflecting the holistic and interconnected nature of human physiology. This opens up the possibility of performing the same tasks using alternative biosignal modalities, thereby improving the accessibility, usability, and adaptability of health monitoring systems. However, the limited availability of large labeled datasets presents challenges for training models tailored to specific tasks and modalities of interest. Unsupervised cross-modal knowledge transfer offers a promising solution by leveraging knowledge from an existing modality to support model training for a new modality. Existing methods are typically based on knowledge distillation, which requires running a teacher model alongside student model training, resulting in high computational and memory overhead. This challenge is further exacerbated by the recent development of foundation models that demonstrate superior performance and generalization across tasks at the cost of large model sizes. To this end, we explore a new framework for unsupervised cross-modal knowledge transfer of biosignals by training a lightweight bridge network to align the intermediate representations and enable information flow between foundation models and across modalities. Specifically, we introduce an efficient strategy for selecting alignment positions where the bridge should be constructed, along with a flexible prototype network as the bridge architecture. Extensive experiments across multiple biosignal modalities, tasks, and datasets show that BioX-Bridge reduces the number of trainable parameters by 88--99\% while maintaining or even improving transfer performance compared to state-of-the-art methods.
Authors: Tianshi Zheng, Kelvin Kiu-Wai Tam, Newt Hue-Nam K. Nguyen, Baixuan Xu, Zhaowei Wang, Jiayang Cheng, Hong Ting Tsang, Weiqi Wang, Jiaxin Bai, Tianqing Fang, Yangqiu Song, Ginny Y. Wong, Simon See
Abstract: Large language models are emerging as powerful tools for scientific law discovery, a foundational challenge in AI-driven science. However, existing benchmarks for this task suffer from a fundamental methodological trilemma, forcing a trade-off between scientific relevance, scalability, and resistance to memorization. Furthermore, they oversimplify discovery as static function fitting, failing to capture the authentic scientific process of uncovering embedded laws through the interactive exploration of complex model systems. To address these critical gaps, we introduce NewtonBench, a benchmark comprising 324 scientific law discovery tasks across 12 physics domains. Our design mitigates the evaluation trilemma by using counterfactual law shifts - systematic alterations of canonical laws - to generate a vast suite of problems that are scalable, scientifically relevant, and memorization-resistant. Moreover, we elevate the evaluation from static function fitting to interactive model discovery, requiring agents to experimentally probe simulated complex systems to uncover hidden principles. Our extensive experiment reveals a clear but fragile capability for discovery in frontier LLMs: this ability degrades precipitously with increasing system complexity and exhibits extreme sensitivity to observational noise. Notably, we uncover a paradoxical effect of tool assistance: providing a code interpreter can hinder more capable models by inducing a premature shift from exploration to exploitation, causing them to satisfice on suboptimal solutions. These results demonstrate that robust, generalizable discovery in complex, interactive environments remains the core challenge. By providing a scalable, robust, and scientifically authentic testbed, NewtonBench offers a crucial tool for measuring true progress and guiding the development of next-generation AI agents capable of genuine scientific discovery.
Authors: Jiaxin Gao, Chen Chen, Yanwen Jia, Xueluan Gong, Kwok-Yan Lam, Qian Wang
Abstract: Large Language Models (LLMs) are increasingly being used to autonomously evaluate the quality of content in communication systems, e.g., to assess responses in telecom customer support chatbots. However, the impartiality of these AI "judges" is not guaranteed, and any biases in their evaluation criteria could skew outcomes and undermine user trust. In this paper, we systematically investigate judgment biases in two LLM-as-a-judge models (i.e., GPT-Judge and JudgeLM) under the point-wise scoring setting, encompassing 11 types of biases that cover both implicit and explicit forms. We observed that state-of-the-art LLM judges demonstrate robustness to biased inputs, generally assigning them lower scores than the corresponding clean samples. Providing a detailed scoring rubric further enhances this robustness. We further found that fine-tuning an LLM on high-scoring yet biased responses can significantly degrade its performance, highlighting the risk of training on biased data. We also discovered that the judged scores correlate with task difficulty: a challenging dataset like GPQA yields lower average scores, whereas an open-ended reasoning dataset (e.g., JudgeLM-val) sees higher average scores. Finally, we proposed four potential mitigation strategies to ensure fair and reliable AI judging in practical communication scenarios.
Authors: Arnab Sen Sharma, Giordano Rogers, Natalie Shapira, David Bau
Abstract: We investigate the mechanisms underlying a range of list-processing tasks in LLMs, and we find that LLMs have learned to encode a compact, causal representation of a general filtering operation that mirrors the generic "filter" function of functional programming. Using causal mediation analysis on a diverse set of list-processing tasks, we find that a small number of attention heads, which we dub filter heads, encode a compact representation of the filtering predicate in their query states at certain tokens. We demonstrate that this predicate representation is general and portable: it can be extracted and reapplied to execute the same filtering operation on different collections, presented in different formats, languages, or even in tasks. However, we also identify situations where transformer LMs can exploit a different strategy for filtering: eagerly evaluating if an item satisfies the predicate and storing this intermediate result as a flag directly in the item representations. Our results reveal that transformer LMs can develop human-interpretable implementations of abstract computational operations that generalize in ways that are surprisingly similar to strategies used in traditional functional programming patterns.
Authors: Ruoxuan Zhang, Qiyun Zheng, Zhiyu Zhou, Ziqi Liao, Siyu Wu, Jian-Yu Jiang-Lin, Bin Wen, Hongxia Xie, Jianlong Fu, Wen-Huang Cheng
Abstract: Theory of Mind (ToM) refers to the ability to infer others' mental states, such as beliefs, desires, and intentions. Current vision-language embodied agents lack ToM-based decision-making, and existing benchmarks focus solely on human mental states while ignoring the agent's own perspective, hindering coherent decision and action generation. To address this, we propose MindPower, a Robot-Centric framework integrating Perception, Mental Reasoning, Decision Making and Action. Given multimodal inputs, MindPower first perceives the environment and human states, then performs ToM Reasoning to model both self and others, and finally generates decisions and actions guided by inferred mental states. Furthermore, we introduce Mind-Reward, a novel optimization objective that encourages VLMs to produce consistent ToM Reasoning and behavior. Our model outperforms GPT-4o by 12.77% in decision making and 12.49% in action generation.
Authors: Dawei Li, Abdullah Alnaibari, Arslan Bisharat, Manny Sandoval, Deborah Hall, Yasin Silva, Huan Liu
Abstract: The rapid advancement of large language models (LLMs) has opened new possibilities for AI for good applications. As LLMs increasingly mediate online communication, their potential to foster empathy and constructive dialogue becomes an important frontier for responsible AI research. This work explores whether LLMs can serve not only as moderators that detect harmful content, but as mediators capable of understanding and de-escalating online conflicts. Our framework decomposes mediation into two subtasks: judgment, where an LLM evaluates the fairness and emotional dynamics of a conversation, and steering, where it generates empathetic, de-escalatory messages to guide participants toward resolution. To assess mediation quality, we construct a large Reddit-based dataset and propose a multi-stage evaluation pipeline combining principle-based scoring, user simulation, and human comparison. Experiments show that API-based models outperform open-source counterparts in both reasoning and intervention alignment when doing mediation. Our findings highlight both the promise and limitations of current LLMs as emerging agents for online social mediation.
Authors: Jiliang Ni, Jiachen Pu, Zhongyi Yang, Jingfeng Luo, Conggang Hu
Abstract: The proliferation of Large Language Models (LLMs) in function calling is pivotal for creating advanced AI agents, yet their large scale hinders widespread adoption, necessitating transferring their capabilities into smaller ones. However, existing paradigms are often plagued by overfitting, training instability, ineffective binary rewards for multi-solution tasks, and the difficulty of synergizing techniques. We introduce STAR: Similarity-guided Teacher-Assisted Refinement, a novel holistic framework that effectively transfers LLMs' capabilities to super-tiny models. STAR consists of two core technical innovations: (1) Constrained Knowledge Distillation (CKD), a training objective that augments top-k forward KL divergence to suppress confidently incorrect predictions, ensuring training stability while preserving exploration capacity for downstream RL. STAR holistically synergizes these strategies within a cohesive training curriculum, enabling super-tiny models to achieve exceptional performance on complex function calling tasks; (2) Similarity-guided RL (Sim-RL), a RL mechanism that introduces a fine-grained, similarity-based reward. This provides a robust, continuous, and rich signal for better policy optimization by evaluating the similarity between generated outputs and the ground truth. Extensive experiments on challenging and renowned benchmarks demonstrate the effectiveness of our method. Our STAR models establish SOTA in their size classes, significantly outperforming baselines. Remarkably, our 0.6B STAR model achieves the best performance among all open models under 1B, surpassing even several well-known open models at a larger scale. STAR demonstrates a training framework that distills capabilities of LLMs into super-tiny models, paving the way for powerful, accessible, and efficient AI agents.
Authors: Huanyao Zhang, Jiepeng Zhou, Bo Li, Bowen Zhou, Yanzhe Shan, Haishan Lu, Zhiyong Cao, Jiaoyang Chen, Yuqian Han, Zinan Sheng, Zhengwei Tao, Hao Liang, Jialong Wu, Yang Shi, Yuanpeng He, Jiaye Lin, Qintong Zhang, Guochen Yan, Runhao Zhao, Zhengpin Li, Xiaohan Yu, Lang Mei, Chong Chen, Wentao Zhang, Bin Cui
Abstract: Multimodal large language models (MLLMs), equipped with increasingly advanced planning and tool-use capabilities, are evolving into autonomous agents capable of performing multimodal web browsing and deep search in open-world environments. However, existing benchmarks for multimodal browsing remain limited in task complexity, evidence accessibility, and evaluation granularity, hindering comprehensive and reproducible assessments of deep search capabilities. To address these limitations, we introduce BrowseComp-$V^3$, a novel benchmark consisting of 300 carefully curated and challenging questions spanning diverse domains. The benchmark emphasizes deep, multi-level, and cross-modal multi-hop reasoning, where critical evidence is interleaved across textual and visual modalities within and across web pages. All supporting evidence is strictly required to be publicly searchable, ensuring fairness and reproducibility. Beyond final-answer accuracy, we incorporate an expert-validated, subgoal-driven process evaluation mechanism that enables fine-grained analysis of intermediate reasoning behaviors and systematic characterization of capability boundaries. In addition, we propose OmniSeeker, a unified multimodal browsing agent framework integrating diverse web search and visual perception tools. Comprehensive experiments demonstrate that even state-of-the-art models achieve only 36% accuracy on our benchmark, revealing critical bottlenecks in multimodal information integration and fine-grained perception. Our results highlight a fundamental gap between current model capabilities and robust multimodal deep search in real-world settings.
Authors: Jasper Davidson, Skylar Stockham, Allen Boston, Ashton Snelgrove, Valerio Tenace, Pierre-Emmanuel Gaillardon
Abstract: Microfluidic devices have emerged as powerful tools in various laboratory applications, but the complexity of their design limits accessibility for many practitioners. While progress has been made in microfluidic design automation (MFDA), a practical and intuitive solution is still needed to connect microfluidic practitioners with MFDA techniques. This work introduces the first practical application of large language models (LLMs) in this context, providing a preliminary demonstration. Building on prior research in hardware description language (HDL) code generation with LLMs, we propose an initial methodology to convert natural language microfluidic device specifications into system-level structural Verilog netlists. We demonstrate the feasibility of our approach by generating structural netlists for practical benchmarks representative of typical microfluidic designs with correct functional flow and an average syntactical accuracy of 88%.
Authors: Xinhao Zheng, Huiqi Deng, Quanshi Zhang
Abstract: This paper focuses on the fundamental challenge of partitioning input variables in attribution methods for Explainable AI, particularly in Shapley value-based approaches. Previous methods always compute attributions given a predefined partition but lack theoretical guidance on how to form meaningful variable partitions. We identify that attribution conflicts arise when the attribution of a coalition differs from the sum of its individual variables' attributions. To address this, we analyze the numerical effects of AND-OR interactions in AI models and extend the Shapley value to a new attribution metric for variable coalitions. Our theoretical findings reveal that specific interactions cause attribution conflicts, and we propose three metrics to evaluate coalition faithfulness. Experiments on synthetic data, NLP, image classification, and the game of Go validate our approach, demonstrating consistency with human intuition and practical applicability.
Authors: Mina Ghashami, Soumya Smruti Mishra
Abstract: The SemEval 2024 BRAINTEASER task challenges language models to perform lateral thinking -- a form of creative, non-linear reasoning that remains underexplored in NLP. The task comprises two subtasks, Sentence Puzzle and Word Puzzle, requiring models to defy conventional commonsense associations. We present a system that fine-tunes DeBERTaV3 using HuggingFace's AutoModelForMultipleChoice architecture. We augment the provided training data with two additional sources: (1) a humor-style question-answering dataset generated via GPT-4 prompting, and (2) the RiddleSense dataset. This data augmentation strategy is motivated by the observation that humor and riddles share the lateral reasoning structure required by the task. Our best system achieves 92.5\% overall accuracy on the Sentence Puzzle subtask and 80.2\% on the Word Puzzle subtask, ranking 6th out of 31 teams and 10th out of 23 teams, respectively. We further show that the choice of task formulation matters: framing the problem as multiple-choice rather than sequence classification yields a 10-point accuracy improvement with the same base model. Our analysis reveals that data augmentation with humor and riddle data is particularly effective for sentence-level lateral reasoning, while word-level puzzles remain a harder challenge.
Authors: Tong Ye, Tengfei Ma, Xuhong Zhang, Hang Yu, Jianwei Yin, Wenhai Wang
Abstract: Large Language Models (LLMs) have shown remarkable capabilities in solving various programming tasks, such as code generation. However, their potential for code optimization, particularly in performance enhancement, remains largely unexplored. This paper investigates the capabilities of LLMs in optimizing code for minimal execution time, addressing a critical gap in current research. The recently proposed code optimization methods construct program optimization pairs based on iterative submissions from the same programmer for the same problem. However, this approach confines LLMs to local performance improvements, neglecting global algorithmic innovation. To overcome this limitation, we adopt a completely different perspective by reconstructing the optimization pairs into a problem-oriented approach. This allows for the integration of various ideas from multiple programmers tackling the same problem. Furthermore, we observe that code optimization presents greater challenges compared to code generation, often accompanied by "optimization tax". Recognizing the inherent trade-offs in correctness and efficiency, we introduce a novel anchor verification framework to mitigate this "optimization tax". Ultimately, the problem oriented perspective combined with the anchor verification framework significantly enhances both the correct optimization ratio and speedup to new levels.
Authors: Antonio Almud\'evar, Alfonso Ortega
Abstract: Representation learning is an approach that allows to discover and extract the factors of variation from the data. Intuitively, a representation is said to be disentangled if it separates the different factors of variation in a way that is understandable to humans. Definitions of disentanglement and metrics to measure it usually assume that the factors of variation are independent of each other. However, this is generally false in the real world, which limits the use of these definitions and metrics to very specific and unrealistic scenarios. In this paper we give a definition of disentanglement based on information theory that is also valid when the factors of variation are not independent. Furthermore, we relate this definition to the Information Bottleneck Method. Finally, we propose a method to measure the degree of disentanglement from the given definition that works when the factors of variation are not independent. We show through different experiments that the method proposed in this paper correctly measures disentanglement with non-independent factors of variation, while other methods fail in this scenario.
Authors: Xiannan Huang, Shuhan Qiu, Quan Yuan, Chao Yang
Abstract: In the context of rail transit operations, real-time passenger flow prediction is essential; however, most models primarily focus on normal conditions, with limited research addressing incident situations. There are several intrinsic challenges associated with prediction during incidents, such as a lack of interpretability and data scarcity. To address these challenges, we propose a two-stage method that separates predictions under normal conditions and the causal effects of incidents. First, a normal prediction model is trained using data from normal situations. Next, the synthetic control method is employed to identify the causal effects of incidents, combined with placebo tests to determine significant levels of these effects. The significant effects are then utilized to train a causal effect prediction model, which can forecast the impact of incidents based on features of the incidents and passenger flows. During the prediction phase, the results from both the normal situation model and the causal effect prediction model are integrated to generate final passenger flow predictions during incidents. Our approach is validated using real-world data, demonstrating improved accuracy. Furthermore, the two-stage methodology enhances interpretability. By analyzing the causal effect prediction model, we can identify key influencing factors related to the effects of incidents and gain insights into their underlying mechanisms. Our work can assist subway system managers in estimating passenger flow affected by incidents and enable them to take proactive measures. Additionally, it can deepen researchers' understanding of the impact of incidents on subway passenger flows.
Authors: Julian Bedei, Lucas Koch, Kevin Badalian, Alexander Winkler, Patrick Schaber, Jakob Andert
Abstract: This work introduces a toolchain for applying Reinforcement Learning (RL), specifically the Deep Deterministic Policy Gradient (DDPG) algorithm, in safety-critical real-world environments. As an exemplary application, transient load control is demonstrated on a single-cylinder internal combustion engine testbench in Homogeneous Charge Compression Ignition (HCCI) mode, that offers high thermal efficiency and low emissions. However, HCCI poses challenges for traditional control methods due to its nonlinear, autoregressive, and stochastic nature. RL provides a viable solution, however, safety concerns, such as excessive pressure rise rates, must be addressed when applying to HCCI. A single unsuitable control input can severely damage the engine or cause misfiring and shut down. Additionally, operating limits are not known a priori and must be determined experimentally. To mitigate these risks, real-time safety monitoring based on the k-nearest neighbor algorithm is implemented, enabling safe interaction with the testbench. The feasibility of this approach is demonstrated as the RL agent learns a control policy through interaction with the testbench. A root mean square error of 0.1374 bar is achieved for the indicated mean effective pressure, comparable to neural network-based controllers from the literature. The toolchain's flexibility is further demonstrated by adapting the agent's policy to increase ethanol energy shares, promoting renewable fuel use while maintaining safety. This RL approach addresses the longstanding challenge of applying RL to safety-critical real-world environments. The developed toolchain, with its adaptability and safety mechanisms, paves the way for future applicability of RL in engine testbenches and other safety-critical settings.
Authors: Roman Tarasov, Petr Mokrov, Milena Gazdieva, Evgeny Burnaev, Alexander Korotin
Abstract: Neural network-based optimal transport (OT) is a recent and fruitful direction in the generative modeling community. It finds its applications in various fields such as domain translation, image super-resolution, computational biology and others. Among the existing OT approaches, of considerable interest are adversarial minimax solvers based on semi-dual formulations of OT problems. While promising, these methods lack theoretical investigation from a statistical learning perspective. Our work fills this gap by establishing upper bounds on the generalization error of an approximate OT map recovered by the minimax quadratic OT solver. Importantly, the bounds we derive depend solely on some standard statistical and mathematical properties of the considered functional classes (neural nets). While our analysis focuses on the quadratic OT, we believe that similar bounds could be derived for general OT case, paving the promising direction for future research. Our experimental illustrations are available online https://github.com/milenagazdieva/StatOT.
Authors: Jonathan Laurent, Andr\'e Platzer
Abstract: Large Language Models can solve a wide range of tasks from just a few examples, but they remain difficult to steer and lack a capability essential for building reliable software at scale: the modular composition of computations under enforceable contracts. As a result, they are typically embedded in larger software pipelines that use domain-specific knowledge to decompose tasks and improve reliability through validation and search. Yet the complexity of writing, tuning, and maintaining such pipelines has so far limited their sophistication. We propose oracular programming: a foundational paradigm for integrating traditional, explicit computations with inductive oracles such as LLMs. It rests on two directing principles: the full separation of core and search logic, and the treatment of few-shot examples as grounded and evolvable program components. Within this paradigm, experts express high-level problem-solving strategies as programs with unresolved choice points. These choice points are resolved at runtime by LLMs, which generalize from user-provided examples of correct and incorrect decisions. An oracular program is composed of three orthogonal components: a strategy that consists of a nondeterministic program with choice points that can be reified into a search tree, a policy that specifies how to navigate this tree with the help of LLM oracles, and a set of demonstrations that describe successful and unsuccessful tree navigation scenarios across diverse problem instances. Each component is expressed in a dedicated programming language and can be independently improved or substituted. We address the key programming language design challenges of modularly composing oracular programs and enforcing consistency between their components as they evolve.
Authors: Sina Salek, Joseph Enguehard
Abstract: Integrated Gradients (IG), a widely used axiomatic path-based attribution method, assigns importance scores to input features by integrating model gradients along a straight path from a baseline to the input. While effective in some cases, we show that straight paths can lead to flawed attributions. In this paper, we identify the cause of these misattributions and propose an alternative approach that equips the input space with a model-induced Riemannian metric (derived from the explained model's Jacobian) and computes attributions by integrating gradients along geodesics under this metric. We call this method Geodesic Integrated Gradients (GIG). To approximate geodesic paths, we introduce two techniques: a k-Nearest Neighbours-based approach for smaller models and a Stochastic Variational Inference-based method for larger ones. Additionally, we propose a new axiom, No-Cancellation Completeness (NCC), which strengthens completeness by ruling out feature-wise cancellation. We prove that, for path-based attributions under the model-induced metric, NCC holds if and only if the integration path is a geodesic. Through experiments on both synthetic and real-world image classification data, we provide empirical evidence supporting our theoretical analysis and showing that GIG produces more faithful attributions than existing methods, including IG, on the benchmarks considered.
Authors: Wenzhe Yin, Zehao Xiao, Pan Zhou, Shujian Yu, Jiayi Shen, Jan-Jakob Sonke, Efstratios Gavves
Abstract: Vision-language alignment is crucial for various downstream tasks such as cross-modal generation and retrieval. Previous multimodal approaches like CLIP utilize InfoNCE to maximize mutual information, primarily aligning pairwise samples across modalities while overlooking distributional differences. In addition, InfoNCE has inherent conflict in terms of alignment and uniformity in multimodality, leading to suboptimal alignment with modality gaps. To overcome the limitations, we propose CS-Aligner, a novel framework that performs distributional vision-language alignment by integrating Cauchy-Schwarz (CS) divergence with mutual information. CS-Aligner captures both the global distribution information of each modality and the pairwise semantic relationships. We find that the CS divergence seamlessly addresses the InfoNCE's alignment-uniformity conflict and serves complementary roles with InfoNCE, yielding tighter and more precise alignment. Moreover, by introducing distributional alignment, CS-Aligner enables incorporating additional information from unpaired data and token-level representations, enhancing flexible and fine-grained alignment in practice. Experiments on text-to-image generation and cross-modality retrieval tasks demonstrate the effectiveness of our method on vision-language alignment.
Authors: Toheeb Aduramomi Jimoh, Tabea De Wille, Nikola S. Nikolov
Abstract: Natural Language Processing (NLP) is becoming a dominant subset of artificial intelligence as the need to help machines understand human language looks indispensable. Several NLP applications are ubiquitous, partly due to the myriad of datasets being churned out daily through mediums like social networking sites. However, the growing development has not been evident in most African languages due to the persisting resource limitations, among other issues. Yor\`ub\'a language, a tonal and morphologically rich African language, suffers a similar fate, resulting in limited NLP usage. To encourage further research towards improving this situation, this systematic literature review aims to comprehensively analyse studies addressing NLP development for Yor\`ub\'a, identifying challenges, resources, techniques, and applications. A well-defined search string from a structured protocol was employed to search, select, and analyse 105 primary studies between 2014 and 2024 from reputable databases. The review highlights the scarcity of annotated corpora, the limited availability of pre-trained language models, and linguistic challenges like tonal complexity and diacritic dependency as significant obstacles. It also revealed the prominent techniques, including rule-based methods, among others. The findings reveal a growing body of multilingual and monolingual resources, even though the field is constrained by socio-cultural factors such as code-switching and the desertion of language for digital usage. This review synthesises existing research, providing a foundation for advancing NLP for Yor\`ub\'a and in African languages generally. It aims to guide future research by identifying gaps and opportunities, thereby contributing to the broader inclusion of Yor\`ub\'a and other under-resourced African languages in global NLP advancements.
Authors: Mehran Shabanpour, Kasra Rad, Sadaf Khademi, Arash Mohammadi
Abstract: High-Density surface Electromyography (HDsEMG) has emerged as a pivotal resource for Human-Computer Interaction (HCI), offering direct insights into muscle activities and motion intentions. However, a significant challenge in practical implementations of HD-sEMG-based models is the low accuracy of inter-session and inter-subject classification. Variability between sessions can reach up to 40% due to the inherent temporal variability of HD-sEMG signals. Targeting this challenge, the paper introduces the MoEMba framework, a novel approach leveraging Selective StateSpace Models (SSMs) to enhance HD-sEMG-based gesture recognition. The MoEMba framework captures temporal dependencies and cross-channel interactions through channel attention techniques. Furthermore, wavelet feature modulation is integrated to capture multi-scale temporal and spatial relations, improving signal representation. Experimental results on the CapgMyo HD-sEMG dataset demonstrate that MoEMba achieves a balanced accuracy of 56.9%, outperforming its state-of-the-art counterparts. The proposed framework's robustness to session-to-session variability and its efficient handling of high-dimensional multivariate time series data highlight its potential for advancing HD-sEMG-powered HCI systems.
Authors: Yan Li, Zhenyu Zhang, Zhengang Wang, Pengfei Chen, Pengfei Zheng
Abstract: Prevailing LLM serving engines employ expert parallelism (EP) to implement multi-device inference of massive MoE models. However, the efficiency of expert parallel inference is largely bounded by inter-device communication, as EP embraces expensive all-to-all collectives to route tokens to the remote experts if not collocating on the same GPU/NPU device. Nevertheless, state-of-the-art schemes treat expert device-placement and request (or token) device-scheduling as separate concerns, triggering excessive communication between them and compromising inference efficiency This paper proposes Semantic Parallelism, a novel parallelism paradigm that minimizes the steep communication costs in EP-centric MoE serving via model-data collaborative scheduling. We implement Semantic Parallelism in a framework called Sem-MoE. Sem-MoE maximally collocates experts and their activating tokens onto the same device using proactively modeled activation likelihood between them and introduces three key techniques: (1) Offline model scheduling, which preliminarily clusters and collocates experts onto devices based on their co-activation tendencies for certain classes of input. (2) Online inter-request data scheduling for Attention-DP setups, which proactively rebatches incoming requests onto the device that hosts experts most likely and frequently activated by the corresponding requests. (3) Online intra-request data scheduling for Attention-TP setups, which seamlessly fuses a token reshuffling procedure into the original inference pipeline and proactively reschedules tokens to devices to reduce dispersed remote routing. We build Sem-MoE into a prevailing LLM serving engine SGLANG. Experiments show our collaborative scheduling approach can effectively reduce the all-to-all communication volume in EP and achieve superior inference throughput compared to existing solutions.
Authors: Haohao Qu, Shanru Lin, Yujuan Ding, Yiqi Wang, Wenqi Fan
Abstract: Recent advances in generative artificial intelligence, particularly large language models (LLMs), have opened new opportunities for enhancing recommender systems (RecSys). Most existing LLM-based RecSys approaches operate in a discrete space, using vector-quantized tokenizers to align with the inherent discrete nature of language models. However, these quantization methods often result in lossy tokenization and suboptimal learning, primarily due to inaccurate gradient propagation caused by the non-differentiable argmin operation in standard vector quantization. Inspired by the emerging trend of embracing continuous tokens in language models, we propose ContRec, a novel framework that seamlessly integrates continuous tokens into LLM-based RecSys. Specifically, ContRec consists of two key modules: a sigma-VAE Tokenizer, which encodes users/items with continuous tokens; and a Dispersive Diffusion module, which captures implicit user preference. The tokenizer is trained with a continuous Variational Auto-Encoder (VAE) objective, where three effective techniques are adopted to avoid representation collapse. By conditioning on the previously generated tokens of the LLM backbone during user modeling, the Dispersive Diffusion module performs a conditional diffusion process with a novel Dispersive Loss, enabling high-quality user preference generation through next-token diffusion. Finally, ContRec leverages both the textual reasoning output from the LLM and the latent representations produced by the diffusion model for Top-K item retrieval, thereby delivering comprehensive recommendation results. Extensive experiments on four datasets demonstrate that ContRec consistently outperforms both traditional and SOTA LLM-based recommender systems. Our results highlight the potential of continuous tokenization and generative modeling for advancing the next generation of recommender systems.
Authors: Yushen He, Lei Zhao, Tianchen Deng, Zipeng Fang, Weidong Chen
Abstract: Service mobile robots are often required to avoid dynamic objects while performing their tasks, but they usually have only limited computational resources. To further advance the practical application of service robots in complex dynamic environments, we propose an efficient multi-modal framework for 3D object detection and trajectory prediction, which synergistically integrates LiDAR and camera inputs to achieve real-time perception of pedestrians, vehicles, and riders in 3D space.The framework incorporates two novel models: 1) a Unified modality detector with Mamba and Transformer (UniMT) for object detection, which achieves high-accuracy object detection with fast inference speed, and 2) a Reference Trajectory-based Multi-Class Transformer (RTMCT) for efficient and diverse trajectory prediction of multi-class objects with flexible-length trajectories. Evaluations on the CODa benchmark demonstrate that our method outperforms existing ones in both detection (+3.71\% in mAP) and trajectory prediction (-0.408m in minADE$_5$ of pedestrians) metrics. Furthermore, on the challenging nuScenes detection benchmark, our detection model achieves competitive performance among LiDAR-camera fusion methods, with a mAP of 72.7\% and NDS of 75.3\%. Remarkably, the system demonstrates exceptional generalizability and practical deployment potential. When transferred and implemented on a wheelchair robot with an entry-level NVIDIA RTX 3060 GPU, it achieves real-time inference at 13.9 frames per second (FPS) with satisfactory accuracy. To facilitate reproducibility and practical deployment, we release the related code of the method at \href{https://github.com/TossherO/3D_Perception}{https://github.com/TossherO/3D\_Perception} and its ROS inference version at \href{https://github.com/TossherO/ros_packages}{https://github.com/TossherO/ros\_packages}.
URLs: https://github.com/TossherO/3D_Perception, https://github.com/TossherO/3D\_Perception, https://github.com/TossherO/ros_packages, https://github.com/TossherO/ros\_packages
Authors: Chao Yang, Xiannan Huang, Shuhan Qiu, Yan Cheng
Abstract: Accurate short-term traffic demand prediction is critical for the operation of traffic systems. Besides point estimation, the confidence interval of the prediction is also of great importance. Many models for traffic operations, such as shared bike rebalancing and taxi dispatching, take into account the uncertainty of future demand and require confidence intervals as the input. However, existing methods for confidence interval modeling rely on strict assumptions, such as unchanging traffic patterns and correct model specifications, to guarantee enough coverage. Therefore, the confidence intervals provided could be invalid, especially in a changing traffic environment. To fill this gap, we propose an efficient method, CONTINA (Conformal Traffic Intervals with Adaptation) to provide interval predictions that can adapt to external changes. By collecting the errors of interval during deployment, the method can adjust the interval in the next step by widening it if the errors are too large or shortening it otherwise. Furthermore, we theoretically prove that the coverage of the confidence intervals provided by our method converges to the target coverage level. Experiments across four real-world datasets and prediction models demonstrate that the proposed method can provide valid confidence intervals with shorter lengths. Our method can help traffic management personnel develop a more reasonable and robust operation plan in practice. And we release the code, model and dataset in \href{ https://github.com/xiannanhuang/CONTINA/}{ Github}.
Authors: Prashant Garg, Thiemo Fetzer
Abstract: Large language models (LLMs) are increasingly used to provide health advice, yet evidence on how their accuracy varies across languages, topics and information sources remains limited. We assess how linguistic and contextual factors affect the accuracy of AI-based health-claim verification. We evaluated seven widely used LLMs on two datasets: (i) 1,975 legally authorised nutrition and health claims from UK and EU regulatory registers translated into 21 languages; and (ii) 9,088 journalist-vetted public-health claims from the PUBHEALTH corpus spanning COVID-19, abortion, politics and general health, drawn from government advisories, scientific abstracts and media sources. Models classified each claim as supported or unsupported using majority voting across repeated runs. Accuracy was analysed by language, topic, source and model. Accuracy on authorised claims was highest in English and closely related European languages and declined in several widely spoken non-European languages, decreasing with syntactic distance from English. On real-world public-health claims, accuracy was substantially lower and varied systematically by topic and source. Models performed best on COVID-19 and government-attributed claims and worst on general health and scientific abstracts. High performance on English, canonical health claims masks substantial context-dependent gaps. Differences in training data exposure, editorial framing and topic-specific tuning likely contribute to these disparities, which are comparable in magnitude to cross-language differences. LLM accuracy in health-claim verification depends strongly on language, topic and information source. English-language performance does not reliably generalise across contexts, underscoring the need for multilingual, domain-specific evaluation before deployment in public-health communication.
Authors: Luca Collini, Baleegh Ahmad, Joey Ah-kiow, Ramesh Karri
Abstract: Hardware security verification is a challenging and time-consuming task. Design engineers may use formal verification, linting, and functional simulation tests, coupled with analysis and a deep understanding of the hardware design being inspected. Large Language Models (LLMs) have been used to assist during this task, either directly or in conjunction with existing tools. We improve the state of the art by proposing MARVEL, a multi-agent LLM framework for a unified approach to decision-making, tool use, and reasoning. MARVEL mimics the cognitive process of a designer looking for security vulnerabilities in RTL code. It consists of a supervisor agent that devises the security policy of the system-on-chips (SoCs) using its security documentation. It delegates tasks to validate the security policy to individual executor agents. Each executor agent carries out its assigned task using a particular strategy. Each executor agent may use one or more tools to identify potential security bugs in the design and send the results back to the supervisor agent for further analysis and confirmation. MARVEL includes executor agents that leverage formal tools, linters, simulation tests, LLM-based detection schemes, and static analysis-based checks. We test our approach on a known buggy SoC based on OpenTitan from the Hack@DATE competition. We find that of the 51 issues reported by MARVEL, 19 are valid security vulnerabilities, 14 are concrete warnings, and 18 are hallucinated reports.
Authors: Chuhao Zhou, Jianfei Yang
Abstract: Embodied agents operating in smart homes must understand human behavior through diverse sensory inputs and communicate via natural language. While Vision-Language Models (VLMs) have enabled impressive language-grounded perception, their reliance on visual data limits robustness in real-world scenarios with occlusions, poor lighting, or privacy constraints. In this paper, we introduce HoloLLM, a Multimodal Large Language Model (MLLM) that integrates uncommon but powerful sensing modalities, such as LiDAR, infrared, mmWave radar, and WiFi, to enable seamless human perception and reasoning across heterogeneous environments. We address two key challenges: (1) the scarcity of aligned modality-text data for rare sensors, and (2) the heterogeneity of their physical signal representations. To overcome these, we design a Universal Modality-Injection Projector (UMIP) that enhances pre-aligned modality embeddings with fine-grained, text-aligned features from tailored encoders via coarse-to-fine cross-attention without introducing significant alignment overhead. We further introduce a human-VLM collaborative data curation pipeline to generate paired textual annotations for sensing datasets. Extensive experiments on two newly constructed benchmarks show that HoloLLM significantly outperforms existing MLLMs, improving language-grounded human sensing accuracy by up to 30%. This work establishes a new foundation for real-world, language-informed multisensory embodied intelligence.
Authors: Jing Yu Lim, Rushi Shah, Zarif Ikram, Samson Yu, Haozhe Ma, Tze-Yun Leong, Dianbo Liu
Abstract: Recently, Model-Based Reinforcement Learning (MBRL) have achieved super-human level performance on the Atari100k benchmark on average. However, we discover that conventional aggregates mask a major problem, Performance Asymmetry: MBRL agents dramatically outperform humans in certain tasks (Agent-Optimal tasks) while drastically underperform humans in other tasks (Human-Optimal tasks). Indeed, despite achieving SOTA in the overall mean Human-Normalized Scores (HNS), the SOTA agent scored the worst among baselines on Human-Optimal tasks, with a striking 21X performance gap between the Human-Optimal and Agent-Optimal subsets. To address this, we partition Atari100k evenly into Human-Optimal and Agent-Optimal subsets, and introduce a more balanced aggregate, Sym-HNS. Furthermore, we trace the striking Performance Asymmetry in the SOTA pixel diffusion world model to the curse of dimensionality and its prowess on high visual detail tasks (e.g. Breakout). To this end, we propose a novel latent end-to-end Joint Embedding DIffusion (JEDI) world model that achieves SOTA results in Sym-HNS, Human-Optimal tasks, and Breakout -- thus reversing the worsening Performance Asymmetry trend while improving computational efficiency and remaining competitive on the full Atari100k.
Authors: Florian F\"urrutter, Zohim Chandani, Ikko Hamamura, Hans J. Briegel, Gorka Mu\~noz-Gil
Abstract: Efficiently compiling quantum operations remains a major bottleneck in scaling quantum computing. Today's state-of-the-art methods achieve low compilation error by combining search algorithms with gradient-based parameter optimization, but they incur long runtimes and require multiple calls to quantum hardware or expensive classical simulations, making their scaling prohibitive. Recently, machine-learning models have emerged as an alternative, though they are currently restricted to discrete gate sets. Here, we introduce a multimodal denoising diffusion model that simultaneously generates a circuit's structure and its continuous parameters for compiling a target unitary. It leverages two independent diffusion processes, one for discrete gate selection and one for parameter prediction. We benchmark the model over different experiments, analyzing the method's accuracy across varying qubit counts and circuit depths, showcasing the ability of the method to outperform existing approaches in gate counts and under noisy conditions. Additionally, we show that a simple post-optimization scheme allows us to significantly improve the generated ans\"atze. Finally, by exploiting its rapid circuit generation, we create large datasets of circuits for particular operations and use these to extract valuable heuristics that can help us discover new insights into quantum circuit synthesis.
Authors: Zhaolu Kang, Junhao Gong, Jiaxu Yan, Wanke Xia, Yian Wang, Ziwen Wang, Huaxuan Ding, Zhuo Cheng, Wenhao Cao, Zhiyuan Feng, Siqi He, Shannan Yan, Junzhe Chen, Xiaomin He, Chaoya Jiang, Wei Ye, Kaidong Yu, Xuelong Li
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated significant potential to advance a broad range of domains. However, current benchmarks for evaluating MLLMs primarily emphasize general knowledge and vertical step-by-step reasoning typical of STEM disciplines, while overlooking the distinct needs and potential of the Humanities and Social Sciences (HSS). Tasks in the HSS domain require more horizontal, interdisciplinary thinking and a deep integration of knowledge across related fields, which presents unique challenges for MLLMs, particularly in linking abstract concepts with corresponding visual representations. Addressing this gap, we present HSSBench, a dedicated benchmark designed to assess the capabilities of MLLMs on HSS tasks in multiple languages, including the six official languages of the United Nations. We also introduce a novel data generation pipeline tailored for HSS scenarios, in which multiple domain experts and automated agents collaborate to generate and iteratively refine each sample. HSSBench contains over 13,000 meticulously designed samples, covering six key categories. We benchmark more than 20 mainstream MLLMs on HSSBench and demonstrate that it poses significant challenges even for state-of-the-art models. We hope that this benchmark will inspire further research into enhancing the cross-disciplinary reasoning abilities of MLLMs, especially their capacity to internalize and connect knowledge across fields.
Authors: Jingyu Xiao, Man Ho Lam, Ming Wang, Yuxuan Wan, Junliang Liu, Yintong Huo, Michael R. Lyu
Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in automated front-end engineering, e.g., generating UI code from visual designs. However, existing front-end UI code generation benchmarks have the following limitations: (1) While framework-based development becomes predominant in modern front-end programming, current benchmarks fail to incorporate mainstream development frameworks. (2) Existing evaluations focus solely on the UI code generation task, whereas practical UI development involves several iterations, including refining editing, and repairing issues. (3) Current benchmarks employ unidimensional evaluation, lacking investigation into influencing factors like task difficulty, input context variations, and in-depth code-level analysis. To bridge these gaps, we introduce DesignBench, a multi-framework, multi-task evaluation benchmark for assessing MLLMs' capabilities in automated front-end engineering. DesignBench encompasses three widely-used UI frameworks (React, Vue, and Angular) alongside vanilla HTML/CSS, and evaluates on three essential front-end tasks (generation, edit, and repair) in real-world development workflows. DesignBench contains 900 webpage samples spanning over 11 topics, 9 edit types, and 6 issue categories, enabling detailed analysis of MLLM performance across multiple dimensions. Our systematic evaluation reveals critical insights into MLLMs' framework-specific limitations, task-related bottlenecks, and performance variations under different conditions, providing guidance for future research in automated front-end development. Our code and data are available at https://github.com/WebPAI/DesignBench.
Authors: Jinkwan Jang, Hyungjin Park, Jinmyeong Choi, Taesup Kim
Abstract: Real-world time series data are inherently multivariate, often exhibiting complex inter-channel dependencies. Each channel is typically sampled at its own period and is prone to missing values due to various practical and operational constraints. These characteristics pose three fundamental challenges involving channel dependency, sampling asynchrony, and missingness, all of which must be addressed simultaneously to enable robust and reliable forecasting in practical settings. However, existing architectures typically address only parts of these challenges in isolation and still rely on simplifying assumptions, leaving unresolved the combined challenges of asynchronous channel sampling, test-time missing blocks, and intricate inter-channel dependencies. To bridge this gap, we propose ChannelTokenFormer, a Transformer-based forecasting framework with a flexible architecture designed to explicitly capture cross-channel interactions, accommodate channel-wise asynchronous sampling, and effectively handle missing values. Extensive experiments on public benchmark datasets reflecting practical settings, along with one private real-world industrial dataset, demonstrate the superior robustness and accuracy of ChannelTokenFormer under challenging real-world conditions.
Authors: Zhengquan Zhang, Feng Xu, Mengmi Zhang
Abstract: Some perspectives naturally provide more information than others. How can an AI system determine which viewpoint offers the most valuable insight for accurate and efficient 3D object reconstruction? Active view selection (AVS) for 3D reconstruction remains a fundamental challenge in computer vision. The aim is to identify the minimal set of views that yields the most accurate 3D reconstruction. Instead of learning radiance fields, like NeRF or 3D Gaussian Splatting, from a current observation and computing uncertainty for each candidate viewpoint, we introduce a novel AVS approach guided by neural uncertainty maps predicted by a lightweight feedforward deep neural network, named UPNet. UPNet takes a single input image of a 3D object and outputs a predicted uncertainty map, representing uncertainty values across all possible candidate viewpoints. By leveraging heuristics derived from observing many natural objects and their associated uncertainty patterns, we train UPNet to learn a direct mapping from viewpoint appearance to uncertainty in the underlying volumetric representations. Next, our approach aggregates all previously predicted neural uncertainty maps to suppress redundant candidate viewpoints and effectively select the most informative one. Using these selected viewpoints, we train 3D neural rendering models and evaluate the quality of novel view synthesis against other competitive AVS methods. Remarkably, despite using half of the viewpoints than the upper bound, our method achieves comparable reconstruction accuracy. In addition, it significantly reduces computational overhead during AVS, achieving up to a 400 times speedup along with over 50\% reductions in CPU, RAM, and GPU usage compared to baseline methods. Notably, our approach generalizes effectively to AVS tasks involving novel object categories, without requiring any additional training.
Authors: Cong Fu, Yuchao Lin, Zachary Krueger, Haiyang Yu, Maho Nakata, Jianwen Xie, Emine Kucukbenli, Xiaofeng Qian, Shuiwang Ji
Abstract: Accurate molecular property predictions require 3D geometries, which are typically obtained using expensive methods such as density functional theory (DFT). Here, we attempt to obtain molecular geometries by relying solely on machine learning interatomic potential (MLIP) models. To this end, we first curate a large-scale molecular relaxation dataset comprising 3.5 million molecules and 300 million snapshots. Then MLIP pre-trained models are trained with supervised learning to predict energy and forces given 3D molecular structures. Once trained, we show that the pre-trained models can be used in different ways to obtain geometries either explicitly or implicitly. First, it can be used to obtain approximate low-energy 3D geometries via geometry optimization. While these geometries do not consistently reach DFT-level chemical accuracy or convergence, they can still improve downstream performance compared to non-relaxed structures. To mitigate potential biases and enhance downstream predictions, we introduce geometry fine-tuning based on the relaxed 3D geometries. Second, the pre-trained models can be directly fine-tuned for property prediction when ground truth 3D geometries are available. Our results demonstrate that MLIP pre-trained models trained on relaxation data can learn transferable molecular representations to improve downstream molecular property prediction and can provide practically valuable but approximate molecular geometries that benefit property predictions. Our code is publicly available at: https://github.com/divelab/AIRS/
Authors: Shuhe Li, Chenxu Guo, Jiachen Lian, Cheol Jun Cho, Wenshuo Zhao, Xiner Xu, Ruiyu Jin, Xiaoyu Shi, Xuanru Zhou, Dingkun Zhou, Sam Wang, Grace Wang, Jingze Yang, Jingyi Xu, Ruohan Bao, Xingrui Chen, Elise Brenner, Brandon In, Francesca Pei, Maria Luisa Gorno-Tempini, Gopala Anumanchipalli
Abstract: Evaluating young children's language is challenging for automatic speech recognizers due to high-pitched voices, prolonged sounds, and limited data. We introduce K-Function, a framework that combines accurate sub-word transcription with objective, Large Language Model (LLM)-driven scoring. Its core, Kids-Weighted Finite State Transducer (K-WFST), merges an acoustic phoneme encoder with a phoneme-similarity model to capture child-specific speech errors while remaining fully interpretable. K-WFST achieves a 1.39 % phoneme error rate on MyST and 8.61 % on Multitudes-an absolute improvement of 10.47 % and 7.06 % over a greedy-search decoder. These high-quality transcripts are used by an LLM to grade verbal skills, developmental milestones, reading, and comprehension, with results that align closely with human evaluators. Our findings show that precise phoneme recognition is essential for creating an effective assessment framework, enabling scalable language screening for children.
Authors: Pierre Boudart (SIERRA), Pierre Gaillard (Thoth), Alessandro Rudi (PSL, DI-ENS, Inria)
Abstract: We consider the multinomial logistic bandit problem in which a learner interacts with an environment by selecting actions to maximize expected rewards based on probabilistic feedback from multiple possible outcomes. In the binary setting, recent work has focused on understanding the impact of the non-linearity of the logistic model (Faury et al., 2020; Abeille et al., 2021). They introduced a problem-dependent constant $\kappa_* \geq 1$ that may be exponentially large in some problem parameters and which is captured by the derivative of the sigmoid function. It encapsulates the non-linearity and improves existing regret guarantees over $T$ rounds from $\smash{O(d\sqrt{T})}$ to $\smash{O(d\sqrt{T/\kappa_*})}$, where $d$ is the dimension of the parameter space. We extend their analysis to the multinomial logistic bandit framework with a finite action space, making it suitable for complex applications with more than two choices, such as reinforcement learning or recommender systems. To achieve this, we extend the definition of $ \kappa_* $ to the multinomial setting and propose an efficient algorithm that leverages the problem's non-linearity. Our method yields a problem-dependent regret bound of order $ \smash{\widetilde{\mathcal{O}}( R d \sqrt{ {KT}/{\kappa_*}} ) } $, where $R$ denotes the norm of the vector of rewards and $K$ is the number of outcomes. This improves upon the best existing guarantees of order $ \smash{\widetilde{\mathcal{O}}( RdK \sqrt{T} )}$. Moreover, we provide a matching $\smash{ \Omega(dR\sqrt{KT/\kappa_*})}$ lower-bound, showing that our algorithm is minimax-optimal and that our definition of $\kappa_*$ is optimal.
Authors: Saptarshi Mitra, Rachid Karami, Haocheng Xu, Sitao Huang, Hyoukjun Kwon
Abstract: Emerging applications such as AR are driving demands for machine intelligence capable of processing continuous and/or long-context inputs on local devices. However, currently dominant models based on Transformer architecture suffers from the quadratic computational and memory overhead, which hinders applications required to process long contexts. This has spurred a paradigm shift towards new architectures like State Space Models (SSMs) and SSM-Transformer hybrid models, which provide near-linear scaling. The near-linear scaling enabled efficient handling of millions of tokens while delivering high performance in recent studies. Although such works present promising results, their workload characteristics in terms of computational performance and hardware resource requirements are not yet thoroughly explored, which limits our understanding of their implications to the system level optimizations. To address this gap, we present a comprehensive, compara-ive benchmarking of carefully selected Transformers, SSMs, and hybrid models specifically for long-context inference on consumer and embedded GPUs. Our analysis shows that SSMs are well-suited for on-device AI on consumer and embedded GPUs for long context inferences. While Transformers are up to 1.9x faster at short sequences (<8K tokens), SSMs demonstrate a dramatic performance inversion, becoming up to 4x faster at very long contexts (~57K tokens), thanks to their linear computational complexity and ~64% reduced memory footrprint. Our operator-level analysis reveals that custom SSM kernels like selective scan despite being hardware-aware to minimize memory IO, dominate the inference runtime on edge platforms, accounting for over 55% of latency due to their sequential, element-wise nature. To foster further research, we will open-source our characterization framework.
Authors: Deborah Dore, Elena Cabrio, Serena Villata
Abstract: The increasing amount of political debates and politics-related discussions calls for the definition of novel computational methods to automatically analyse such content with the final goal of lightening up political deliberation to citizens. However, the specificity of the political language and the argumentative form of these debates (employing hidden communication strategies and leveraging implicit arguments) make this task very challenging, even for current general-purpose pre-trained Language Models (LMs). To address this, we introduce a novel pre-trained LM for political discourse language called RooseBERT. Pre-training a LM on a specialised domain presents different technical and linguistic challenges, requiring extensive computational resources and large-scale data. RooseBERT has been trained on large political debate and speech corpora (11GB) in English. To evaluate its performances, we fine-tuned it on multiple downstream tasks related to political debate analysis, i.e., stance detection, sentiment analysis, argument component detection and classification, argument relation prediction and classification, policy classification, named entity recognition (NER). Our results show significant improvements over general-purpose LMs on the majority of these tasks, highlighting how domain-specific pre-training enhances performance in political debate analysis. We release RooseBERT for the research community.
Authors: Maoxun Yuan, Duanni Meng, Ziteng Xi, Tianyi Zhao, Shiji Zhao, Yimian Dai, Xingxing Wei
Abstract: Infrared small target detection and segmentation (IRSTDS) is a critical yet challenging task in defense and civilian applications, owing to the dim, shapeless appearance of targets and severe background clutter. Recent CNN-based methods have achieved promising target perception results, but they only focus on enhancing feature representation to offset the impact of noise, which results in the increased false alarm problem. In this paper, through analyzing the problem from the frequency domain, we pioneer in improving performance from noise suppression perspective and propose a novel noise-suppression feature pyramid network (NS-FPN), which integrates a low-frequency guided feature purification (LFP) module and a spiral-aware feature sampling (SFS) module into the original FPN structure. The LFP module suppresses the noise features by purifying high-frequency components to achieve feature enhancement devoid of noise interference, while the SFS module further adopts spiral sampling to fuse target-relevant features in feature fusion process. Our NS-FPN is designed to be lightweight yet effective and can be easily plugged into existing IRSTDS frameworks. Extensive experiments on the IRSTD-1k and NUAA-SIRST datasets demonstrate that our method significantly reduces false alarms and achieves superior performance on IRSTDS task.
Authors: Xuefeng Liu, Mingxuan Cao, Songhao Jiang, Xiao Luo, Xiaotian Duan, Mengdi Wang, Tobin R. Sosnick, Jinbo Xu, Rick Stevens
Abstract: The goal of protein design is to generate amino acid sequences that fold into functional structures with desired properties. Prior methods combining autoregressive language models with Monte Carlo Tree Search (MCTS) struggle with long-range dependencies and suffer from an impractically large search space. We propose MCTD-ME, Monte Carlo Tree Diffusion with Multiple Experts, which integrates masked diffusion models with tree search to enable multi-token planning and efficient exploration under the guidance of multiple experts. Unlike autoregressive planners, MCTD-ME uses biophysical-fidelity-enhanced diffusion denoising as the rollout engine, jointly revising multiple positions and scaling to large sequence spaces. It further leverages experts of varying capacities to enrich exploration, guided by a pLDDT-based masking schedule that targets low-confidence regions while preserving reliable residues. We propose a novel multi-expert selection rule ( PH-UCT-ME) extends Shannon-entropy-based UCT to expert ensembles with mutual information. MCTD-ME achieves superior performance on the CAMEO and PDB benchmarks, excelling in protein design tasks such as inverse folding, folding, and conditional design challenges like motif scaffolding on lead optimization tasks. Our framework is model-agnostic, plug-and-play, and extensible to denovo protein engineering and beyond.
Authors: Davide Tenedini, Riccardo Zamboni, Mirco Mutti, Marcello Restelli
Abstract: Despite its recent successes, Deep Reinforcement Learning (DRL) is notoriously sample-inefficient. We argue that this inefficiency stems from the standard practice of optimizing policies directly in the high-dimensional and highly redundant parameter space $\Theta$. This challenge is greatly compounded in multi-task settings. In this work, we develop a novel, unsupervised approach that compresses the policy parameter space $\Theta$ into a low-dimensional latent space $\mathcal{Z}$. We train a generative model $g:\mathcal{Z}\to\Theta$ by optimizing a behavioral reconstruction loss, which ensures that the latent space is organized by functional similarity rather than proximity in parameterization. We conjecture that the inherent dimensionality of this manifold is a function of the environment's complexity, rather than the size of the policy network. We validate our approach in continuous control domains, showing that the parameterization of standard policy networks can be compressed up to five orders of magnitude while retaining most of its expressivity. As a byproduct, we show that the learned manifold enables task-specific adaptation via Policy Gradient operating in the latent space $\mathcal{Z}$.
Authors: Haoyu He, Haozheng Luo, Yan Chen, Qi R. Wang
Abstract: Predicting human mobility is inherently challenging due to complex long-range dependencies and multi-scale periodic behaviors. To address this, we introduce RHYTHM (Reasoning with Hierarchical Temporal Tokenization for Human Mobility), a unified framework that leverages large language models (LLMs) as general-purpose spatio-temporal predictors and trajectory reasoners. Methodologically, RHYTHM employs temporal tokenization to partition each trajectory into daily segments and encode them as discrete tokens with hierarchical attention that captures both daily and weekly dependencies, thereby quadratically reducing the sequence length while preserving cyclical information. Additionally, we enrich token representations by adding pre-computed prompt embeddings for trajectory segments and prediction targets via a frozen LLM, and feeding these combined embeddings back into the LLM backbone to capture complex interdependencies. Computationally, RHYTHM keeps the pretrained LLM backbone frozen, yielding faster training and lower memory usage. We evaluate our model against state-of-the-art methods using three real-world datasets. Notably, RHYTHM achieves a 2.4% improvement in overall accuracy, a 5.0% increase on weekends, and a 24.6% reduction in training time. Code is publicly available at https://github.com/he-h/rhythm.
Authors: Jubayer Ibn Hamid, Ifdita Hasan Orney, Ellen Xu, Chelsea Finn, Dorsa Sadigh
Abstract: Reinforcement learning fine-tuning (RLFT) is a dominant paradigm for improving pretrained policies for downstream tasks. These pretrained policies, trained on large datasets, produce generations with a broad range of promising but unrefined behaviors. Often, a critical failure mode of RLFT arises when policies lose this diversity and collapse into a handful of easily exploitable outputs. This convergence hinders exploration, which is essential for expanding the capabilities of the pretrained policy and for amplifying the benefits of test-time compute scaling. To address this, we introduce an objective for policy gradient methods that explicitly enforces the exploration and refinement of diverse generations, which we call a polychromic objective. We then show how proximal policy optimization (PPO) can be adapted to optimize this objective. Our method (1) employs vine sampling to collect on-policy rollouts and (2) modifies the advantage function to reflect the advantage under our new objective. Experiments on BabyAI, Minigrid, and Algorithmic Creativity show that our method improves success rates by reliably solving a larger set of environment configurations and generalizes better under large perturbations. Moreover, when given multiple attempts in pass@$k$ experiments, the policy achieves substantially higher coverage, demonstrating its ability to maintain and exploit a diverse repertoire of strategies.
Authors: Yuan Zhuang, Yi Shen, Yuexin Bian, Qing Su, Shihao Ji, Yuanyuan Shi, Fei Miao
Abstract: Recent studies have shown that combining parameter-efficient fine-tuning (PEFT) with mixture-of-experts (MoE) is an effective strategy for adapting large language models (LLMs) to the downstream tasks. However, most existing approaches rely on conventional TopK routing, which requires careful hyperparameter tuning and assigns a fixed number of experts to each token. In this work, we propose LD-MoLE, a Learnable Dynamic routing mechanism for Mixture of LoRA Experts that enables adaptive, token-dependent, and layer-wise expert allocation. Our method replaces the non-differentiable TopK selection with a differentiable routing function and a closed-form solution. Moreover, our design allows the model to adaptively determine the number of experts to activate for each token at different layers. In addition, we introduce an analytical sparsity control objective to regularize the number of activated experts. Extensive experiments on the Qwen3-1.7B and Llama-3.2-3B models show that LD-MoLE achieves the highest average scores compared to state-of-the-art baselines, across a diverse set of benchmarks. Our method not only achieves superior performance, but also demonstrates the ability to learn token-dependent and layer-wise expert allocation.
Authors: Jeongjae Lee, Jong Chul Ye
Abstract: While reinforcement learning has advanced the alignment of text-to-image (T2I) models, state-of-the-art policy gradient methods are still hampered by training instability and high variance, hindering convergence speed and compromising image quality. Our analysis identifies a key cause of this instability: disproportionate credit assignment, in which the mathematical structure of the generative sampler produces volatile and non-proportional feedback across timesteps. To address this, we introduce Proportionate Credit Policy Optimization (PCPO), a framework that enforces proportional credit assignment through a stable objective reformulation and a principled reweighting of timesteps. This correction stabilizes the training process, leading to significantly accelerated convergence and superior image quality. The improvement in quality is a direct result of mitigating model collapse, a common failure mode in recursive training. PCPO substantially outperforms existing policy gradient baselines on all fronts, including the state-of-the-art DanceGRPO. Code is available at https://github.com/jaylee2000/pcpo/.
Authors: Jianing Guo, Zhenhong Wu, Chang Tu, Yiyao Ma, Xiangqi Kong, Zhiqian Liu, Jiaming Ji, Shuning Zhang, Yuanpei Chen, Kai Chen, Qi Dou, Yaodong Yang, Xianglong Liu, Huijie Zhao, Weifeng Lv, Simin Li
Abstract: In Vision-Language-Actionf(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. 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 BYOVLA that requires external LLMs, and a 10.4% gain under mixed perturbations. On the real-world FR5 robot, under four types of multimodal perturbations, RobustVLA shows strong low-data performance, outperforming pi0 by 65.6% success rate with 25 demonstrations. Even with abundant demos, our method still outperform pi0 by 30% success rate. Code and demo videos available at https://github.com/gakakulicc/RobustVLA.
Authors: Mingdai Yang, Nurendra Choudhary, Jiangshu Du, Edward W. Huang, Philip S. Yu, Karthik Subbian, Danai Koutra
Abstract: Recent agent-based recommendation frameworks aim to simulate user behaviors by incorporating memory mechanisms and prompting strategies, but they struggle with hallucinating non-existent items and full-catalog ranking. Besides, a largely underexplored opportunity lies in leveraging LLMs'commonsense reasoning to capture user intent through substitute and complement relationships between items, which are usually implicit in datasets and difficult for traditional ID-based recommenders to capture. In this work, we propose a novel LLM-agent framework, AgenDR, which bridges LLM reasoning with scalable recommendation tools. Our approach delegates full-ranking tasks to traditional models while utilizing LLMs to (i) integrate multiple recommendation outputs based on personalized tool suitability and (ii) reason over substitute and complement relationships grounded in user history. This design mitigates hallucination, scales to large catalogs, and enhances recommendation relevance through relational reasoning. Through extensive experiments on three public grocery datasets, we show that our framework achieves superior full-ranking performance, yielding on average a twofold improvement over its underlying tools. We also introduce a new LLM-based evaluation metric that jointly measures semantic alignment and ranking correctness.
Authors: Didrik Bergstr\"om, Deniz G\"und\"uz, Onur G\"unl\"u
Abstract: We consider image transmission via deep joint source-channel coding (DeepJSCC) over multi-hop additive white Gaussian noise (AWGN) channels by training a DeepJSCC encoder-decoder pair with a pre-trained deep hash distillation (DHD) module to semantically cluster images, facilitating security-oriented applications through enhanced semantic consistency and improving the perceptual reconstruction quality. We train the DeepJSCC module to both reduce mean square error (MSE) and minimize cosine distance between DHD hashes of source and reconstructed images. Significantly improved perceptual quality as a result of semantic alignment is illustrated for different multi-hop settings, for which classical DeepJSCC may suffer from noise accumulation, measured by the learned perceptual image patch similarity (LPIPS) metric.
Authors: Shramay Palta, Peter Rankel, Sarah Wiegreffe, Rachel Rudinger
Abstract: We investigate the degree to which human plausibility judgments of multiple-choice commonsense benchmark answers are subject to influence by (im)plausibility arguments for or against an answer, in particular, using rationales generated by LLMs. We collect 3,000 plausibility judgments from humans and another 13,600 judgments from LLMs. Overall, we observe increases and decreases in mean human plausibility ratings in the presence of LLM-generated PRO and CON rationales, respectively, suggesting that, on the whole, human judges find these rationales convincing. Experiments with LLMs reveal similar patterns of influence. Our findings demonstrate a novel use of LLMs for studying aspects of human cognition, while also raising practical concerns that, even in domains where humans are ``experts'' (i.e., common sense), LLMs have the potential to exert considerable influence on people's beliefs.
Authors: Antonio Mart\'inez-Ibarra, Aurora Gonz\'alez-Vidal, Adri\'an C\'anovas-Rodr\'iguez, Antonio F. Skarmeta
Abstract: The Mar Menor, Europe's largest coastal lagoon, located in Spain, has undergone severe eutrophication crises. Monitoring chlorophyll-a (Chl-a) is essential to anticipate harmful algal blooms and guide mitigation. Traditional in situ measurements are spatially and temporally limited. Satellite-based approaches provide a more comprehensive view, enabling scalable, long-term, and transferable monitoring. This study aims to overcome limitations of chlorophyll monitoring, often restricted to surface estimates or limited temporal coverage, by developing a reliable methodology to predict and map Chl-a across the water column of the Mar Menor. The work integrates Sentinel 2 imagery with buoy-based ground truth to create models capable of high-resolution, depth-specific monitoring, enhancing early-warning capabilities for eutrophication. Nearly a decade of Sentinel 2 images was atmospherically corrected using C2RCC processors. Buoy data were aggregated by depth (0-1 m, 1-2 m, 2-3 m, 3-4 m). Multiple ML and DL algorithms-including RF, XGBoost, CatBoost, Multilater Perceptron Networks, and ensembles-were trained and validated using cross-validation. Systematic band-combination experiments and spatial aggregation strategies were tested to optimize prediction. Results show depth-dependent performance. At the surface, C2X-Complex with XGBoost and ensemble models achieved R2 = 0.89; at 1-2 m, CatBoost and ensemble models reached R2 = 0.87; at 2-3 m, TOA reflectances with KNN performed best (R2 = 0.81); while at 3-4 m, RF achieved R2 = 0.66. Generated maps successfully reproduced known eutrophication events (e.g., 2016 crisis, 2025 surge), confirming robustness. The study delivers an end-to-end, validated methodology for depth-specific Chl-amapping. Its integration of multispectral band combinations, buoy calibration, and ML/DL modeling offers a transferable framework for other turbid coastal systems.
Authors: Dario Shariatian, Alain Durmus, Umut Simsekli, Stefano Peluchetti
Abstract: Discrete diffusion models have emerged as a powerful class of models and a promising route to fast language generation, but practical implementations typically rely on factored reverse transitions that ignore cross-token dependencies and degrade performance in the few-step regime. We propose Latent-Augmented Discrete Diffusion (LADD), which introduces a learnable auxiliary latent channel and performs diffusion over the joint (token, latent) space. The latent variables provide an intermediate representation that can express joint structure while preserving tractable parameterizations. We instantiate LADD with continuous latents (Co-LADD) and discrete latents (Di-LADD), and study two inference schedules: a joint diffusion that denoises data and latents together, and a sequential diffusion that first resolves latents and then samples tokens conditionally. We derive ELBO-style objectives and analyze design choices that balance latent expressivity with diffusion compatibility. In experiments, LADDs yield improvements on unconditional generation metrics as compared to state-of-the-art masked discrete diffusion baselines, and are effective at lower sampling budgets, where unmasking many tokens per step is desirable.
Authors: Chengshu Li, Mengdi Xu, Arpit Bahety, Hang Yin, Yunfan Jiang, Huang Huang, Josiah Wong, Sujay Garlanka, Cem Gokmen, Ruohan Zhang, Weiyu Liu, Jiajun Wu, Roberto Mart\'in-Mart\'in, Li Fei-Fei
Abstract: Imitation learning from large-scale, diverse human demonstrations has been shown to be effective for training robots, but collecting such data is costly and time-consuming. This challenge intensifies for multi-step bimanual mobile manipulation, where humans must teleoperate both the mobile base and two high-DoF arms. Prior X-Gen works have developed automated data generation frameworks for static (bimanual) manipulation tasks, augmenting a few human demos in simulation with novel scene configurations to synthesize large-scale datasets. However, prior works fall short for bimanual mobile manipulation tasks for two major reasons: 1) a mobile base introduces the problem of how to place the robot base to enable downstream manipulation (reachability) and 2) an active camera introduces the problem of how to position the camera to generate data for a visuomotor policy (visibility). To address these challenges, MoMaGen formulates data generation as a constrained optimization problem that satisfies hard constraints (e.g., reachability) while balancing soft constraints (e.g., visibility while navigation). This formulation generalizes across most existing automated data generation approaches and offers a principled foundation for developing future methods. We evaluate on four multi-step bimanual mobile manipulation tasks and find that MoMaGen enables the generation of much more diverse datasets than previous methods. As a result of the dataset diversity, we also show that the data generated by MoMaGen can be used to train successful imitation learning policies using a single source demo. Furthermore, the trained policy can be fine-tuned with a very small amount of real-world data (40 demos) to be succesfully deployed on real robotic hardware. More details are on our project page: momagen.github.io.
Authors: Ren Yin, Takashi Ishida, Masashi Sugiyama
Abstract: As artificial intelligence (AI) systems approach and surpass expert human performance across a broad range of tasks, obtaining high-quality human supervision for evaluation and training becomes increasingly challenging. Our focus is on tasks that require deep knowledge and skills of multiple domains, where this bottleneck is severe. Unfortunately, even the best human experts are knowledgeable only in a single narrow area, and will not be able to evaluate the correctness of advanced AI systems on such superhuman tasks. However, based on their narrow expertise, humans may provide a weak signal, i.e., a complementary label indicating an option that is incorrect. For example, a cardiologist could state that ''this is not related to any cardiovascular disease,'' even if they cannot identify the true disease. Based on this weak signal, we propose a scalable oversight framework that enables us to evaluate frontier AI systems without the need to prepare the ground truth. We derive an unbiased estimator of top-1 accuracy from complementary labels and quantify how many complementary labels are needed to match the variance of ordinary labels. We further introduce two estimators to combine scarce ordinary labels with abundant complementary labels. We provide finite-sample deviation guarantees for both complementary-only and the mixed estimators. Empirically, we show that we can evaluate the output of large language models without the ground truth, if we have complementary labels. We further show that we can train an AI system with such weak signals: we show how we can design an agentic AI system automatically that can improve itself with this partitioned human supervision. Our code is available at https://github.com/R-Yin-217/Towards-Scalable-Oversight-via-Partitioned-Human-Supervision.
URLs: https://github.com/R-Yin-217/Towards-Scalable-Oversight-via-Partitioned-Human-Supervision.
Authors: Julia Bazinska, Max Mathys, Francesco Casucci, Mateo Rojas-Carulla, Xander Davies, Alexandra Souly, Niklas Pfister
Abstract: AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone LLM affects agent security. The non-deterministic sequential nature of AI agents complicates security modeling, while the integration of traditional software with AI components entangles novel LLM vulnerabilities with conventional security risks. Existing frameworks only partially address these challenges as they either capture specific vulnerabilities only or require modeling of complete agents. To address these limitations, we introduce threat snapshots: a framework that isolates specific states in an agent's execution flow where LLM vulnerabilities manifest, enabling the systematic identification and categorization of security risks that propagate from the LLM to the agent level. We apply this framework to construct the $b^3$ benchmark, a security benchmark based on 194,331 unique crowdsourced adversarial attacks. We then evaluate 34 popular LLMs with it, revealing, among other insights, that enhanced reasoning capabilities improve security, while model size does not correlate with security. We release our benchmark, dataset, and evaluation code to facilitate widespread adoption by LLM providers and practitioners, offering guidance for agent developers and incentivizing model developers to prioritize backbone security improvements.
Authors: Yizhang Zhu, Liangwei Wang, Chenyu Yang, Xiaotian Lin, Boyan Li, Wei Zhou, Xinyu Liu, Zhangyang Peng, Tianqi Luo, Yu Li, Chengliang Chai, Chong Chen, Shimin Di, Ju Fan, Ji Sun, Nan Tang, Fugee Tsung, Jiannan Wang, Chenglin Wu, Yanwei Xu, Shaolei Zhang, Yong Zhang, Xuanhe Zhou, Guoliang Li, Yuyu Luo
Abstract: The rapid advancement of large language models (LLMs) has spurred the emergence of data agents, autonomous systems designed to orchestrate Data + AI ecosystems for tackling complex data-related tasks. However, the term "data agent" currently suffers from terminological ambiguity and inconsistent adoption, conflating simple query responders with sophisticated autonomous architectures. This terminological ambiguity fosters mismatched user expectations, accountability challenges, and barriers to industry growth. Inspired by the SAE J3016 standard for driving automation, this survey introduces the first systematic hierarchical taxonomy for data agents, comprising six levels that delineate and trace progressive shifts in autonomy, from manual operations (L0) to a vision of generative, fully autonomous data agents (L5), thereby clarifying capability boundaries and responsibility allocation. Through this lens, we offer a structured review of existing research arranged by increasing autonomy, encompassing specialized data agents for data management, preparation, and analysis, alongside emerging efforts toward versatile, comprehensive systems with enhanced autonomy. We further analyze critical evolutionary leaps and technical gaps for advancing data agents, especially the ongoing L2-to-L3 transition, where data agents evolve from procedural execution to autonomous orchestration. Finally, we conclude with a forward-looking roadmap, envisioning proactive, generative data agents.
Authors: Yida Zhao, Kuan Li, Xixi Wu, Liwen Zhang, Dingchu Zhang, Baixuan Li, Maojia Song, Zhuo Chen, Chenxi Wang, Xinyu Wang, Kewei Tu, Pengjun Xie, Jingren Zhou, Yong Jiang
Abstract: LLM-based search agents are increasingly trained on entity-centric synthetic data to solve complex, knowledge-intensive tasks. However, prevailing training methods like Group Relative Policy Optimization (GRPO) discard this rich entity information, relying instead on sparse, outcome-based rewards. This critical limitation renders them unable to distinguish informative "near-miss" samples-those with substantially correct reasoning but a flawed final answer-from complete failures, thus discarding valuable learning signals. We address this by leveraging the very entities discarded during training. Our empirical analysis reveals a strong positive correlation between the number of ground-truth entities identified during an agent's reasoning process and final answer accuracy. Building on this insight, we introduce Entity-aware Group Relative Policy Optimization (E-GRPO), a novel framework that formulates a dense entity-aware reward function. E-GRPO assigns partial rewards to incorrect samples proportional to their entity match rate, enabling the model to effectively learn from these "near-misses". Experiments on diverse question-answering (QA) and deep research benchmarks show that E-GRPO consistently and significantly outperforms the GRPO baseline. Furthermore, our analysis reveals that E-GRPO not only achieves superior accuracy but also induces more efficient reasoning policies that require fewer tool calls, demonstrating a more effective and sample-efficient approach to aligning search agents.
Authors: Jingyu Lu, Haonan Wang, Qixiang Zhang, Xiaomeng Li
Abstract: Subject-agnostic brain decoding, which aims to reconstruct continuous visual experiences from fMRI without subject-specific training, holds great potential for clinical applications. However, this direction remains underexplored due to challenges in cross-subject generalization and the complex nature of brain signals. In this work, we propose Visual Cortex Flow Architecture (VCFlow), a novel hierarchical decoding framework that explicitly models the ventral-dorsal architecture of the human visual system to learn multi-dimensional representations. By disentangling and leveraging features from early visual cortex, ventral, and dorsal streams, VCFlow captures diverse and complementary cognitive information essential for visual reconstruction. Furthermore, we introduce a feature-level contrastive learning strategy to enhance the extraction of subject-invariant semantic representations, thereby enhancing subject-agnostic applicability to previously unseen subjects. Unlike conventional pipelines that need more than 12 hours of per-subject data and heavy computation, VCFlow sacrifices only 7\% accuracy on average yet generates each reconstructed video in 10 seconds without any retraining, offering a fast and clinically scalable solution. The source code will be released upon acceptance of the paper.
Authors: Zheng Du, Hao Kang, Song Han, Tushar Krishna, Ligeng Zhu
Abstract: Large language models (LLMs) such as GPT-5 and Gemini 3 have pushed the frontier of automated reasoning and code generation. Yet current benchmarks emphasize accuracy and output quality, neglecting a critical dimension: efficiency of token usage. The token efficiency is highly variable in practical. Models solving the same problem with similar accuracy can exhibit up to a \textbf{5.0$\times$} difference in token length, leading to massive gap of model reasoning ability. Such variance exposes significant redundancy, highlighting the critical need for a standardized benchmark to quantify the gap of token efficiency. Thus, we introduce OckBench, the first benchmark that jointly measures accuracy and token efficiency across reasoning and coding tasks. Our evaluation reveals that token efficiency remains largely unoptimized across current models, significantly inflating serving costs and latency. These findings provide a concrete roadmap for the community to optimize the latent reasoning ability, token efficiency. Ultimately, we argue for an evaluation paradigm shift: tokens must not be multiplied beyond necessity. Our benchmarks are available at https://ockbench.github.io/.
Authors: Shihan Cheng, Nilesh Kulkarni, David Hyde, Dmitriy Smirnov
Abstract: Fine-tuning large-scale text-to-video diffusion models to add new generative controls, such as those over physical camera parameters (e.g., shutter speed or aperture), typically requires vast, high-fidelity datasets that are difficult to acquire. In this work, we propose a data-efficient fine-tuning strategy that learns these controls from sparse, low-quality synthetic data. We show that not only does fine-tuning on such simple data enable the desired controls, it actually yields superior results to models fine-tuned on photorealistic "real" data. Beyond demonstrating these results, we provide a framework that justifies this phenomenon both intuitively and quantitatively.
Authors: Iker Garc\'ia-Ferrero, David Montero, Roman Orus
Abstract: We introduce Refusal Steering, an inference-time method to exercise fine-grained control over Large Language Models refusal behaviour on politically sensitive topics without retraining. We replace fragile pattern-based refusal detection with an LLM-as-a-judge that assigns refusal confidence scores and we propose a ridge-regularized variant to compute steering vectors that better isolate the refusal--compliance direction. On Qwen3-Next-80B-A3B-Thinking, our method removes the refusal behaviour of the model around politically sensitive topics while maintaining safety on JailbreakBench and near-baseline performance on general benchmarks. The approach generalizes across 4B and 80B models and can also induce targeted refusals when desired. We analize the steering vectors and show that refusal signals concentrate in deeper layers of the transformer and are distributed across many dimensions. Together, these results demonstrate that activation steering can remove political refusal behaviour while retaining safety alignment for harmful content, offering a practical path to controllable, transparent moderation at inference time.
Authors: Yunsheng Pang, Zijian Liu, Yudong Li, Shaojie Zhu, Zijian Luo, Chenyun Yu, Sikai Wu, Shichen Shen, Cong Xu, Bin Wang, Kai Jiang, Hongyong Yu, Chengxiang Zhuo, Zang Li
Abstract: Slate recommendation, which presents users with a ranked item list in a single display, is ubiquitous across mainstream online platforms. Recent advances in generative models have shown significant potential for this task via autoregressive modeling of discrete semantic ID sequences. However, existing methods suffer from three key limitations: entangled item tokenization, inefficient sequential decoding, and the absence of holistic slate planning. These issues often result in substantial inference overhead and inadequate alignment with diverse user preferences and practical business requirements, hindering the industrial deployment of generative slate recommendation systems. In this paper, we propose HiGR, an efficient generative slate recommendation framework that integrates hierarchical planning with listwise preference alignment. First, we design an auto-encoder incorporating residual quantization and contrastive constraints, which tokenizes items into semantically structured IDs to enable controllable generation. Second, HiGR decouples the generation process into two stages: a list-level planning stage to capture global slate intent, and an item-level decoding stage to select specific items, effectively reducing the search space and enabling efficient generation. Third, we introduce a multi-objective and listwise preference alignment mechanism that enhances slate quality by leveraging implicit user feedback. Extensive experiments have validated the effectiveness of our HiGR method. Notably, it outperforms state-of-the-art baselines by over 10\% in offline recommendation quality while achieving a $5\times$ inference speedup. Furthermore, we have deployed HiGR on a commercial platform under Tencent (serving hundreds of millions of users), and online A/B tests show that it increases average watch time and average video plays by 1.22\% and 1.73\%, respectively.
Authors: Shuhang Chen, Yunqiu Xu, Junjie Xie, Aojun Lu, Tao Feng, Zeying Huang, Ning Zhang, Yi Sun, Yi Yang, Hangjie Yuan
Abstract: Despite significant progress, multimodal large language models continue to struggle with visual mathematical problem solving. Some recent works recognize that visual perception is a bottleneck in visual mathematical reasoning, but their solutions are limited to improving the extraction and interpretation of visual inputs. Notably, they all ignore the key issue of whether the extracted visual cues are faithfully integrated and properly utilized in subsequent reasoning. Motivated by this, we present CogFlow, a novel cognitive-inspired three-stage framework that incorporates a knowledge internalization stage, explicitly simulating the hierarchical flow of human reasoning: perception$\Rightarrow$internalization$\Rightarrow$reasoning. In line with this hierarchical flow, we holistically enhance all its stages. We devise Synergistic Visual Rewards to boost perception capabilities in parametric and semantic spaces, jointly improving visual information extraction from symbols and diagrams. To guarantee faithful integration of extracted visual cues into subsequent reasoning, we introduce a Knowledge Internalization Reward model in the internalization stage, bridging perception and reasoning. Moreover, we design a Visual-Gated Policy Optimization algorithm to further enforce the reasoning is grounded with the visual knowledge, preventing models seeking shortcuts that appear coherent but are visually ungrounded reasoning chains. Moreover, we contribute a new dataset MathCog for model training, which contains samples with over 120K high-quality perception-reasoning aligned annotations. Comprehensive experiments and analysis on commonly used visual mathematical reasoning benchmarks validate the superiority of the proposed CogFlow. Project page: https://shchen233.github.io/cogflow.
Authors: Xing Li, Hui-Ling Zhen, Lihao Yin, Xianzhi Yu, Zhenhua Dong, Mingxuan Yuan
Abstract: This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We systematically investigate and compare the influence of six critical intrinsic model characteristics and three external attack techniques. Our large-scale evaluation is conducted using 32 recent, popular LLMs and LRMs across thirteen distinct model families, spanning a parameter scale from 3B to 235B. The assessment leverages five established safety datasets and probes model vulnerabilities with 56 jailbreak techniques and four CoT attack strategies, resulting in 4.6M API calls. Our key empirical findings are fourfold. First, we identify the LRMs GPT-OSS-20B, Qwen3-Next-80B-A3B-Thinking, and GPT-OSS-120B as the top-three safest models, which substantiates the significant advantage of integrated reasoning and self-reflection mechanisms for robust safety alignment. Second, post-training and knowledge distillation may lead to a systematic degradation of safety alignment. We thus argue that safety must be treated as an explicit constraint or a core optimization objective during these stages, not merely subordinated to the pursuit of general capability. Third, we reveal a pronounced vulnerability: employing a CoT attack via a response prefix can elevate the attack success rate by 3.34x on average and from 0.6% to 96.3% for Seed-OSS-36B-Instruct. This critical finding underscores the safety risks inherent in text-completion interfaces and features that allow user-defined response prefixes in LLM services, highlighting an urgent need for architectural and deployment safeguards. Fourth, roleplay, prompt injection, and gradient-based search for adversarial prompts are the predominant methodologies for eliciting unaligned behaviors in modern models.
Authors: Chi-Pin Huang, Yunze Man, Zhiding Yu, Min-Hung Chen, Jan Kautz, Yu-Chiang Frank Wang, Fu-En Yang
Abstract: Vision-Language-Action (VLA) tasks require reasoning over complex visual scenes and executing adaptive actions in dynamic environments. While recent studies on reasoning VLAs show that explicit chain-of-thought (CoT) can improve generalization, they suffer from high inference latency due to lengthy reasoning traces. We propose Fast-ThinkAct, an efficient reasoning framework that achieves compact yet performant planning through verbalizable latent reasoning. Fast-ThinkAct learns to reason efficiently with latent CoTs by distilling from a teacher, driven by a preference-guided objective to align manipulation trajectories that transfers both linguistic and visual planning capabilities for embodied control. This enables reasoning-enhanced policy learning that effectively connects compact reasoning to action execution. Extensive experiments across diverse embodied manipulation and reasoning benchmarks demonstrate that Fast-ThinkAct achieves strong performance with up to 89.3% reduced inference latency over state-of-the-art reasoning VLAs, while maintaining effective long-horizon planning, few-shot adaptation, and failure recovery.
Authors: Lorenzo Monti, Tatiana Muraveva, Brian Sheridan, Davide Massari, Alessia Garofalo, Gisella Clementini, Umberto Michelucci
Abstract: In data-driven scientific discovery, a challenge lies in classifying well-characterized phenomena while identifying novel anomalies. Current semi-supervised clustering algorithms do not always fully address this duality, often assuming that supervisory signals are globally representative. Consequently, methods often enforce rigid constraints that suppress unanticipated patterns or require a pre-specified number of clusters, rendering them ineffective for genuine novelty detection. To bridge this gap, we introduce CLiMB (CLustering in Multiphase Boundaries), a domain-informed framework decoupling the exploitation of prior knowledge from the exploration of unknown structures. Using a sequential two-phase approach, CLiMB first anchors known clusters using metric-adaptive constrained partitioning, and subsequently applies density-based clustering to residual data to reveal arbitrary topologies. We demonstrate this framework on RR Lyrae stars data from the Gaia Data Release 3. CLiMB attains an Adjusted Rand Index of 0.829 with 90% seed coverage in recovering known Milky Way substructures, outperforming heuristic and constraint-based baselines, which stagnate below 0.20. Furthermore, sensitivity analysis confirms CLiMB's superior data efficiency, showing monotonic improvement as knowledge increases. Finally, the framework successfully isolates three distinct dynamical features (Shiva, Shakti, and the Galactic Disk) in the unlabelled field, validating its potential for scientific discovery.
Authors: Christopher Clark, Jieyu Zhang, Zixian Ma, Jae Sung Park, Mohammadreza Salehi, Rohun Tripathi, Sangho Lee, Zhongzheng Ren, Chris Dongjoo Kim, Yinuo Yang, Vincent Shao, Yue Yang, Weikai Huang, Ziqi Gao, Taira Anderson, Jianrui Zhang, Jitesh Jain, George Stoica, Winson Han, Ali Farhadi, Ranjay Krishna
Abstract: Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effectively distilling from them, or do not disclose their training data or recipe. As a result, the open-source community lacks the foundations needed to improve on the state-of-the-art video (and image) language models. Crucially, many downstream applications require more than just high-level video understanding; they require grounding -- either by pointing or by tracking in pixels. Even proprietary models lack this capability. We present Molmo2, a new family of VLMs that are state-of-the-art among open-source models and demonstrate exceptional new capabilities in point-driven grounding in single image, multi-image, and video tasks. Our key contribution is a collection of 7 new video datasets and 2 multi-image datasets, including a dataset of highly detailed video captions for pre-training, a free-form video Q&A dataset for fine-tuning, a new object tracking dataset with complex queries, and an innovative new video pointing dataset, all collected without the use of closed VLMs. We also present a training recipe for this data utilizing an efficient packing and message-tree encoding scheme, and show bi-directional attention on vision tokens and a novel token-weight strategy improves performance. Our best-in-class 8B model outperforms others in the class of open weight and data models on short videos, counting, and captioning, and is competitive on long-videos. On video-grounding Molmo2 significantly outperforms existing open-weight models like Qwen3-VL (35.5 vs 29.6 accuracy on video counting) and surpasses proprietary models like Gemini 3 Pro on some tasks (38.4 vs 20.0 F1 on video pointing and 56.2 vs 41.1 J&F on video tracking).
Authors: Ritik Raina, Abe Leite, Alexandros Graikos, Seoyoung Ahn, Dimitris Samaras, Gregory J. Zelinsky
Abstract: Human vision combines low-resolution "gist" information from the visual periphery with sparse but high-resolution information from fixated locations to construct a coherent understanding of a visual scene. In this paper, we introduce MetamerGen, a tool for generating scenes that are aligned with latent human scene representations. MetamerGen is a latent diffusion model that combines peripherally obtained scene gist information with information obtained from scene-viewing fixations to generate image metamers for what humans understand after viewing a scene. Generating images from both high and low resolution (i.e. "foveated") inputs constitutes a novel image-to-image synthesis problem, which we tackle by introducing a dual-stream representation of the foveated scenes consisting of DINOv2 tokens that fuse detailed features from fixated areas with peripherally degraded features capturing scene context. To evaluate the perceptual alignment of MetamerGen generated images to latent human scene representations, we conducted a same-different behavioral experiment where participants were asked for a "same" or "different" response between the generated and the original image. With that, we identify scene generations that are indeed metamers for the latent scene representations formed by the viewers. MetamerGen is a powerful tool for understanding scene understanding. Our proof-of-concept analyses uncovered specific features at multiple levels of visual processing that contributed to human judgments. While it can generate metamers even conditioned on random fixations, we find that high-level semantic alignment most strongly predicts metamerism when the generated scenes are conditioned on viewers' own fixated regions.
Authors: Akila Sampath, Vandana Janeja, Jianwu Wang
Abstract: The accurate estimation of Arctic snow depth remains a critical time-varying inverse problem due to the scarcity in associated sea ice parameters. Existing process-based and data-driven models are either highly sensitive to sparse data or lack the physical interpretability required for climate-critical applications. To address this gap, we introduce PhysE-Inv, a novel framework that integrates a sophisticated sequential architecture, namely an LSTM Encoder-Decoder with Multi-head Attention and contrastive learning, with physics-guided inference. Our core innovation lies in a physics-constrained inversion methodology. This methodology first leverages the hydrostatic balance forward model as a target-formulation proxy, enabling effective learning in the absence of direct ground truth; second, it uses reconstruction physics regularization over a latent space to dynamically discover hidden physical parameters from noisy, incomplete time-series input. Evaluated against state-of-the-art baselines, PhysE-Inv significantly improves prediction performance, reducing error by 20% while demonstrating superior physical consistency and resilience to data sparsity compared to empirical methods. Beyond Arctic snow depth, PhysE-Inv can be applied broadly to other noisy, data-scarce problems in Earth and climate science.
Authors: Haozheng Luo, Zhuolin Jiang, Md Zahid Hasan, Yan Chen, Soumalya Sarkar
Abstract: We propose FROST, an attention-aware method for efficient reasoning. Unlike traditional approaches, FROST leverages attention weights to prune uncritical reasoning paths, yielding shorter and more reliable reasoning trajectories. Methodologically, we introduce the concept of reasoning outliers and design an attention-based mechanism to remove them. Theoretically, FROST preserves and enhances the model's reasoning capacity while eliminating outliers at the sentence level. Empirically, we validate FROST on four benchmarks using two strong reasoning models (Phi-4-Reasoning and GPT-OSS-20B), outperforming state-of-the-art methods such as TALE and ThinkLess. Notably, FROST achieves an average 69.68% reduction in token usage and a 26.70% improvement in accuracy over the base model. Furthermore, in evaluations of attention outlier metrics, FROST reduces the maximum infinity norm by 15.97% and the average kurtosis by 91.09% compared to the base model. Code is available at https://github.com/robinzixuan/FROST
Authors: Hongliu Cao, Eoin Thomas, Rodrigo Acuna Agost
Abstract: Large Language Models (LLMs) used in creative workflows can reinforce stereotypes and perpetuate inequities, making fairness auditing essential. Existing methods rely on constrained tasks and fixed benchmarks, leaving open-ended creative outputs unexamined. We introduce the Persona Brainstorm Audit (PBA), a scalable and easy to extend auditing method for bias detection across multiple intersecting identity and social roles in open-ended persona generation. PBA quantifies bias using degree-of-freedom-aware normalized Cram\'er's V, producing interpretable severity labels that enable fair comparison across models and dimensions. Applying PBA to 12 LLMs (120,000 personas, 16 bias dimensions), we find that bias evolves nonlinearly across model generations: larger and newer models are not consistently fairer, and biases that initially decrease can resurface in later releases. Intersectional analysis reveals disparities hidden by single-axis metrics, where dimensions appearing fair individually can exhibit high bias in combination. Robustness analyses show PBA remains stable under varying sample sizes, role-playing prompts, and debiasing prompts, establishing its reliability for fairness auditing in LLMs.
Authors: Weining Fu, Kai Shu, Kui Xu, Qiangfeng Cliff Zhang
Abstract: Cryo-electron microscopy (cryo-EM) has revolutionized structural biology by enabling near-atomic-level visualization of biomolecular assemblies. However, the exponential growth in cryo-EM data throughput and complexity, coupled with diverse downstream analytical tasks, necessitates unified computational frameworks that transcend current task-specific deep learning approaches with limited scalability and generalizability. We present CryoLVM, a foundation model that learns rich structural representations from experimental density maps with resolved structures by leveraging the Joint-Embedding Predictive Architecture (JEPA) integrated with SCUNet-based backbone, which can be rapidly adapted to various downstream tasks. We further introduce a novel histogram-based distribution alignment loss that accelerates convergence and enhances fine-tuning performance. We demonstrate CryoLVM's effectiveness across three critical cryo-EM tasks: density map sharpening, density map super-resolution, and missing wedge restoration. Our method consistently outperforms state-of-the-art baselines across multiple density map quality metrics, confirming its potential as a versatile model for a wide spectrum of cryo-EM applications.
Authors: Sagnik Mukherjee, Lifan Yuan, Pavan Jayasinha, Dilek Hakkani-T\"ur, Hao Peng
Abstract: Reinforcement learning (RL), particularly RL from verifiable reward (RLVR), has become a crucial phase of training large language models (LLMs) and a key focus of current scaling efforts. However, optimization practices in RL largely follow those of next-token prediction stages (e.g., pretraining and supervised fine-tuning), despite fundamental differences between RL and these stages highlighted by recent work. One such practice is the use of the AdamW optimizer, which is widely adopted for training large-scale transformers despite its high memory overhead. Our analysis shows that both momentum and adaptive learning rates in AdamW are less influential in RL than in SFT, leading us to hypothesize that RL benefits less from Adam-style per-parameter adaptive learning rates and momentum. Confirming this hypothesis, our experiments demonstrate that the substantially more memory-efficient SGD, which is known to perform poorly in supervised learning of large-scale transformers, matches or even outperforms AdamW in RL for LLMs. Remarkably, full fine-tuning with SGD updates fewer than 0.02% of model parameters without any sparsity-promoting regularization, more than 1000 times fewer than AdamW. Our analysis offers potential reasons for this update sparsity. These findings provide new insights into the optimization dynamics of RL in LLMs and show that RL can be substantially more parameter-efficient than previously recognized.
Authors: Yuzhu Cai, Zexi Liu, Xinyu Zhu, Cheng Wang, Siheng Chen
Abstract: Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons. While recent LLM-based agents show promise, current prompt-based agents for MLE suffer from behavioral stagnation due to frozen parameters. Although Reinforcement Learning (RL) offers a remedy, applying it to MLE is hindered by prohibitive execution latency and inefficient data selection. Recognizing these challenges, we propose AceGRPO with two core components: (1) Evolving Data Buffer that continuously repurposes execution traces into reusable training tasks, and (2) Adaptive Sampling guided by a Learnability Potential function, which dynamically prioritizes tasks at the agent's learning frontier to maximize learning efficiency. Leveraging AceGRPO, our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines (e.g., DeepSeek-V3.2), demonstrating robust capability for sustained iterative optimization. Code is available at https://github.com/yuzhu-cai/AceGRPO.
Authors: Jan Philip Wahle
Abstract: Language enables humans to share knowledge, reason about the world, and pass on strategies for survival and innovation across generations. At the heart of this process is not just the ability to communicate but also the remarkable flexibility in how we can express ourselves. We can express the same thoughts in virtually infinite ways using different words and structures - this ability to rephrase and reformulate expressions is known as paraphrase. Modeling paraphrases is a keystone to meaning in computational language models; being able to construct different variations of texts that convey the same meaning or not shows strong abilities of semantic understanding. If computational language models are to represent meaning, they must understand and control the different aspects that construct the same meaning as opposed to different meanings at a fine granularity. Yet most existing approaches reduce paraphrasing to a binary decision between two texts or to producing a single rewrite of a source, obscuring which linguistic factors are responsible for meaning preservation. In this thesis, I propose that decomposing paraphrases into their constituent linguistic aspects (paraphrase types) offers a more fine-grained and cognitively grounded view of semantic equivalence. I show that even advanced machine learning models struggle with this task. Yet, when explicitly trained on paraphrase types, models achieve stronger performance on related paraphrase tasks and downstream applications. For example, in plagiarism detection, language models trained on paraphrase types surpass human baselines: 89.6% accuracy compared to 78.4% for plagiarism cases from Wikipedia, and 66.5% compared to 55.7% for plagiarism of scientific papers from arXiv. In identifying duplicate questions on Quora, models trained with paraphrase types improve over models trained on binary pairs. Furthermore, I demonstrate that...
Authors: Shih-Fang Chen, Jun-Cheng Chen, I-Hong Jhuo, Yen-Yu Lin
Abstract: Human perception for effective object tracking in 2D video streams arises from the implicit use of prior 3D knowledge and semantic reasoning. In contrast, most generic object tracking (GOT) methods primarily rely on 2D features of the target and its surroundings, while neglecting 3D geometric cues, making them susceptible to partial occlusion, distractors, and variations in geometry and appearance. To address this limitation, we introduce GOT-Edit, an online cross-modality model editing approach that integrates geometry-aware cues into a generic object tracker from a 2D video stream. Our approach leverages features from a pre-trained Visual Geometry Grounded Transformer to infer geometric cues from only a few 2D images. To address the challenge of seamlessly combining geometry and semantics, GOT-Edit performs online model editing. By leveraging null-space constraints during model updates, it incorporates geometric information while preserving semantic discrimination, yielding consistently better performance across diverse scenarios. Extensive experiments on multiple GOT benchmarks demonstrate that GOT-Edit achieves superior robustness and accuracy, particularly under occlusion and clutter, establishing a new paradigm for combining 2D semantics with 3D geometric reasoning for generic object tracking. The project page is available at https://chenshihfang.github.io/GOT-EDIT.
Authors: Jiahao Qin
Abstract: High-speed optical-resolution photoacoustic microscopy (OR-PAM) with bidirectional scanning enables rapid functional brain imaging but introduces severe spatiotemporal misalignment from coupled scan-direction-dependent domain shift and geometric distortion. Conventional registration methods rely on brightness constancy, an assumption violated under bidirectional scanning, leading to unreliable alignment. A unified scene-appearance separation framework is proposed to jointly address domain shift and spatial misalignment. The proposed architecture separates domain-invariant scene content from domain-specific appearance characteristics, enabling cross-domain reconstruction with geometric preservation. A scene consistency loss promotes geometric correspondence in the latent space, linking domain shift correction with spatial registration within a single framework. For in vivo mouse brain vasculature imaging, the proposed method achieves normalized cross-correlation (NCC) of 0.961 and structural similarity index (SSIM) of 0.894, substantially outperforming conventional methods. Ablation studies demonstrate that domain alignment loss is critical, with its removal causing 82% NCC reduction (0.961 to 0.175), while scene consistency and cycle consistency losses provide complementary regularization for optimal performance. The method achieves 11.2 ms inference time per frame (86 fps), substantially exceeding typical OR-PAM acquisition rates and enabling real-time processing. These results suggest that the proposed framework enables robust high-speed bidirectional OR-PAM for reliable quantitative and longitudinal functional imaging. The code will be publicly available at https://github.com/D-ST-Sword/SAS-Net
Authors: Venus Team, Changlong Gao, Zhangxuan Gu, Yulin Liu, Xinyu Qiu, Shuheng Shen, Yue Wen, Tianyu Xia, Zhenyu Xu, Zhengwen Zeng, Beitong Zhou, Xingran Zhou, Weizhi Chen, Sunhao Dai, Jingya Dou, Yichen Gong, Yuan Guo, Zhenlin Guo, Feng Li, Qian Li, Jinzhen Lin, Yuqi Zhou, Linchao Zhu, Liang Chen, Zhenyu Guo, Changhua Meng, Weiqiang Wang
Abstract: GUI agents have emerged as a powerful paradigm for automating interactions in digital environments, yet achieving both broad generality and consistently strong task performance remains challenging. In this report, we present UI-Venus-1.5, a unified, end-to-end GUI Agent designed for robust real-world applications. The proposed model family comprises two dense variants (2B and 8B) and one mixture-of-experts variant (30B-A3B) to meet various downstream application scenarios. Compared to our previous version, UI-Venus-1.5 introduces three key technical advances: (1) a comprehensive Mid-Training stage leveraging 10 billion tokens across 30+ datasets to establish foundational GUI semantics; (2) Online Reinforcement Learning with full-trajectory rollouts, aligning training objectives with long-horizon, dynamic navigation in large-scale environments; and (3) a single unified GUI Agent constructed via Model Merging, which synthesizes domain-specific models (grounding, web, and mobile) into one cohesive checkpoint. Extensive evaluations demonstrate that UI-Venus-1.5 establishes new state-of-the-art performance on benchmarks such as ScreenSpot-Pro (69.6%), VenusBench-GD (75.0%), and AndroidWorld (77.6%), significantly outperforming previous strong baselines. In addition, UI-Venus-1.5 demonstrates robust navigation capabilities across a variety of Chinese mobile apps, effectively executing user instructions in real-world scenarios. Code: https://github.com/inclusionAI/UI-Venus; Model: https://huggingface.co/collections/inclusionAI/ui-venus
URLs: https://github.com/inclusionAI/UI-Venus;, https://huggingface.co/collections/inclusionAI/ui-venus
Authors: Guobin Shen, Chenxiao Zhao, Xiang Cheng, Lei Huang, Xing Yu
Abstract: Training stability remains a central challenge in reinforcement learning (RL) for large language models (LLMs). Policy staleness, asynchronous training, and mismatches between training and inference engines all cause the behavior policy to diverge from the current policy, risking training collapse. Importance sampling provides a principled correction for this distribution shift but suffers from high variance; existing remedies such as token-level clipping and sequence-level normalization lack a unified theoretical foundation. We propose Variational sEquence-level Soft Policy Optimization (VESPO). By incorporating variance reduction into a variational formulation over proposal distributions, VESPO derives a closed-form reshaping kernel that operates directly on sequence-level importance weights without length normalization. Experiments on mathematical reasoning benchmarks show that VESPO maintains stable training under staleness ratios up to 64x and fully asynchronous execution, and delivers consistent gains across both dense and Mixture-of-Experts models. Code is available at https://github.com/FloyedShen/VESPO
Authors: Zukang Xu, Zhixiong Zhao, Xing Hu, Zhixuan Chen, Dawei Yang
Abstract: Mixture of Experts (MoE) models have achieved great success by significantly improving performance while maintaining computational efficiency through sparse expert activation. However, their enormous parameter sizes and memory demands pose major challenges for deployment in resource-constrained environments. Vector Quantization (VQ) offers a promising approach for ultra-low-bit compression in Large Language Models (LLMs) by leveraging a codebook, where weight vectors are mapped to the most similar discrete codewords. Yet, directly applying VQ to MoEs often leads to substantial performance degradation due to two critical obstacles: (1) redundant representations among experts cause VQ to repeatedly quantize similar representations for each expert, resulting in inefficient use of limited codebook capacity; and (2) cumulative output bias is amplified by expert aggregation in MoE layers, leading to distributional shifts in the quantized outputs. To address these issues, we propose KBVQ-MoE, a novel VQ framework to enhance extremely low-bit quantization for MoE-based LLMs. KBVQ-MoE integrates two techniques: (1) input-driven redundancy elimination, where a Karhunen-Loeve Transform (KLT) guided singular value decomposition (SVD) extracts dominant weight components and shares them across experts; and (2) bias-corrected output stabilization, where vector quantization is applied only to expert-specific (non-redundant) representations and the quantized outputs are corrected via channel-wise affine compensation. Experiments on various MoE LLMs demonstrate that KBVQ-MoE preserves accuracy substantially better than existing quantization methods. For example, 3-bit quantization of Qwen1.5-MoE-A2.7B achieves an average accuracy of 67.99, nearly identical to the FP16 baseline of 68.07, underscoring KBVQ-MoE's potential for efficient deployment on edge devices and other resource-constrained platforms.
Authors: Chenxi Han, Yuheng Min, Zihao Huang, Ao Hong, Hang Liu, Yi Cheng, Houde Liu
Abstract: Recent advances in data-driven reinforcement learning and motion tracking have substantially improved humanoid locomotion, yet critical practical challenges remain. In particular, while low-level motion tracking and trajectory-following controllers are mature, whole-body reference-guided methods are difficult to adapt to higher-level command interfaces and diverse task contexts: they require large, high-quality datasets, are brittle across speed and pose regimes, and are sensitive to robot-specific calibration. To address these limitations, we propose the Parameterized Motion Generator (PMG), a real-time motion generator grounded in an analysis of human motion structure that synthesizes reference trajectories using only a compact set of parameterized motion data together with high-dimensional control commands. Combined with an imitation-learning pipeline and an optimization-based sim-to-real motor parameter identification module, we validate the complete approach on our humanoid prototype ZERITH Z1 and show that, within a single integrated system, PMG produces natural, human-like locomotion, responds precisely to high-dimensional control inputs-including VR-based teleoperation-and enables efficient, verifiable sim-to-real transfer. Together, these results establish a practical, experimentally validated pathway toward natural and deployable humanoid control. Website: https://pmg-icra26.github.io/
Authors: Emily Bejerano, Federico Tondolo, Ayaan Qayyum, Xiaofan Yu, Xiaofan Jiang
Abstract: Millimeter-wave (mmWave) radar provides reliable perception in visually degraded indoor environments (e.g., smoke, dust, and low light), but learning-based radar perception is bottlenecked by the scarcity and cost of collecting and annotating large-scale radar datasets. We present Sim2Radar, an end-to-end framework that synthesizes training radar data directly from single-view RGB images, enabling scalable data generation without manual scene modeling. Sim2Radar reconstructs a material-aware 3D scene by combining monocular depth estimation, segmentation, and vision-language reasoning to infer object materials, then simulates mmWave propagation with a configurable physics-based ray tracer using Fresnel reflection models parameterized by ITU-R electromagnetic properties. Evaluated on real-world indoor scenes, Sim2Radar improves downstream 3D radar perception via transfer learning: pre-training a radar point-cloud object detection model on synthetic data and fine-tuning on real radar yields up to +3.7 3D AP (IoU 0.3), with gains driven primarily by improved spatial localization. These results suggest that physics-based, vision-driven radar simulation can provide effective geometric priors for radar learning and measurably improve performance under limited real-data supervision.
Authors: Jorge Carrasco-Pollo, Floor Eijkelboom, Jan-Willem van de Meent
Abstract: We introduce Pawsterior, a variational flow-matching framework for improved and extended simulation-based inference (SBI). Many SBI problems involve posteriors constrained by structured domains, such as bounded physical parameters or hybrid discrete-continuous variables, yet standard flow-matching methods typically operate in unconstrained spaces. This mismatch leads to inefficient learning and difficulty respecting physical constraints. Our contributions are twofold. First, generalizing the geometric inductive bias of CatFlow, we formalize endpoint-induced affine geometric confinement, a principle that incorporates domain geometry directly into the inference process via a two-sided variational model. This formulation improves numerical stability during sampling and leads to consistently better posterior fidelity, as demonstrated by improved classifier two-sample test performance across standard SBI benchmarks. Second, and more importantly, our variational parameterization enables SBI tasks involving discrete latent structure (e.g., switching systems) that are fundamentally incompatible with conventional flow-matching approaches. By addressing both geometric constraints and discrete latent structure, Pawsterior extends flow-matching to a broader class of structured SBI problems that were previously inaccessible.
Authors: Hong Li, Zhen Zhou, Honggang Zhang, Yuping Luo, Xinyue Wang, Han Gong, Zhiyuan Liu
Abstract: Data-parallel (DP) training with synchronous all-reduce is a dominant paradigm for full-parameter fine-tuning of large language models (LLMs). While parameter synchronization guarantees numerical equivalence of model weights after each iteration, it does not necessarily imply alignment of worker-level optimization dynamics before gradient aggregation. This paper identifies and studies this latent mismatch, termed \emph{silent inconsistency}, where cross-worker divergence in losses and gradients can remain invisible under conventional aggregated monitoring signals. We propose a lightweight, model-agnostic diagnostic framework that quantifies worker-level consistency using training signals readily available in standard pipelines. Specifically, we introduce three complementary metrics: loss dispersion, gradient-norm dispersion, and gradient-direction consistency measured by inter-worker cosine similarity. The proposed metrics incur negligible overhead and require no modification to model architecture, synchronization mechanisms, or optimization algorithms. We validate the framework by fully fine-tuning the 1B-parameter \texttt{openPangu-Embedded-1B-V1.1} model on the \texttt{tatsu-lab/alpaca} dataset using an 8-NPU DP setup, under controlled perturbations of cross-rank stochasticity. Experimental results show that progressively desynchronized data shuffling and random seeds lead to substantial increases in loss/gradient dispersion and reduced directional alignment, despite smooth globally averaged loss curves. These findings demonstrate that the proposed indicators provide actionable visibility into hidden instability modes in large-scale DP fine-tuning, enabling more reliable diagnosis and configuration assessment.
Authors: Xingjian Wu, Xvyuan Liu, Junkai Lu, Siyuan Wang, Xiangfei Qiu, Yang Shu, Jilin Hu, Chenjuan Guo, Bin Yang
Abstract: LLM-powered Multi-Agent Systems (MAS) have emerged as an effective approach towards collaborative intelligence, and have attracted wide research interests. Among them, ``self-evolving'' MAS, treated as a more flexible and powerful technical route, can construct task-adaptive workflows or communication topologies, instead of relying on a predefined static structue template. Current self-evolving MAS mainly focus on Spatial Evolving or Temporal Evolving paradigm, which only considers the single dimension of evolution and does not fully incentivize LLMs' collaborative capability. In this work, we start from a novel Spatio-Temporal perspective by proposing ST-EVO, which supports dialogue-wise communication scheduling with a compact yet powerful flow-matching based Scheduler. To make precise Spatio-Temporal scheduling, ST-EVO can also perceive the uncertainty of MAS, and possesses self-feedback ability to learn from accumulated experience. Extensive experiments on nine benchmarks demonstrate the state-of-the-art performance of ST-EVO, achieving about 5%--25% accuracy improvement.
Authors: Jayadev Billa
Abstract: Capability emergence during neural network training remains mechanistically opaque. We track five geometric measures across five model scales (405K--85M parameters), 120 task$\times$level$\times$ model combinations (119 achieving accuracy-based emergence) across eight algorithmic tasks, and three Pythia language models (160M--2.8B). We find: (1) training begins with a universal representation collapse to task-specific floors that are scale-invariant across a 210$\times$ parameter range (e.g., modular arithmetic collapses to RANKME $\,\approx\,$2.0 regardless of model size); (2) collapse propagates top-down through layers (28/32 task$ \times $model consistency), contradicting bottom-up feature-building intuition; (3) a geometric hierarchy in which representation geometry leads emergence (100% precursor rate for hard tasks across all model sizes), while the local learning coefficient is synchronous (0/24 precursor) and Hessian measures lag. We also delineate prediction limits: geometric measures encode coarse task difficulty but not fine-grained timing (within-class concordance ranges from 52% for easy tasks to 69% for hard tasks; when task ordering reverses across scales, prediction fails at 26%). On Pythia, global geometric patterns replicate but per-task precursor signals do not, as the precursor relationship requires task--training alignment that naturalistic pre-training does not provide. Our contribution is the geometric anatomy of emergence and its boundary conditions, not a prediction tool.
Authors: KC Santosh, Srikanth Baride, Rodrigue Rizk
Abstract: As machine learning (ML) continues its rapid expansion, the environmental cost of model training and inference has become a critical societal concern. Existing benchmarks overwhelmingly focus on standard performance metrics such as accuracy, BLEU, or mAP, while largely ignoring energy consumption and carbon emissions. This single-objective evaluation paradigm is increasingly misaligned with the practical requirements of large-scale deployment, particularly in energy-constrained environments such as mobile devices, developing regions, and climate-aware enterprises. In this paper, we propose AI-CARE, an evaluation tool for reporting energy consumption, and carbon emissions of ML models. In addition, we introduce the carbon-performance tradeoff curve, an interpretable tool that visualizes the Pareto frontier between performance and carbon cost. We demonstrate, through theoretical analysis and empirical validation on representative ML workloads, that carbon-aware benchmarking changes the relative ranking of models and encourages architectures that are simultaneously accurate and environmentally responsible. Our proposal aims to shift the research community toward transparent, multi-objective evaluation and align ML progress with global sustainability goals. The tool and documentation are available at https://github.com/USD-AI-ResearchLab/ai-care.
Authors: Bin Cao, Qian Zhang, Zhenjie Feng, Taolue Zhang, Jiaqiang Huang, Lu-Tao Weng, Tong-Yi Zhang
Abstract: Artificial intelligence can rapidly propose candidate phases and structures from X-ray diffraction (XRD), but these hypotheses often fail in downstream refinement because peak intensities cannot be stably assigned under severe overlap and diffraction consistency is enforced only weakly. Here we introduce the whole-pattern expectation--maximization (WPEM) algorithm, a physics-constrained whole-pattern decomposition and refinement workflow that turns Bragg's law into an explicit constraint within a batch expectation--maximization framework. WPEM models the full profile as a probabilistic mixture density and iteratively infers component-resolved intensities while keeping peak centres Bragg-consistent, producing a continuous, physically admissible intensity representation that remains stable in heavily overlapped regions and in the presence of mixed radiation or multiple phases. We benchmark WPEM on standard reference patterns (PbSO$_4$ and Tb$_2$BaCoO$_5$), where it yields lower $R_p/R_{wp}$ than widely used packages (FullProf and TOPAS) under matched refinement conditions. We further demonstrate generality across realistic experimental scenarios, including phase-resolved decomposition in multiphase materials, quantitative recovery of mixture compositions, separation of crystalline peaks from amorphous backgrounds in semicrystalline systems, high-throughput operando lattice tracking, automated refinement of compositionally disordered solid solutions, and quantitative phase-resolved analysis of complex archaeological samples from synchrotron powder XRD. By providing Bragg-consistent, uncertainty-aware intensity partitioning as a refinement-ready interface, WPEM closes the gap between AI-generated hypotheses and diffraction-admissible structure refinement on challenging XRD data.
Authors: Shahriar Golchin, Marc Wetter
Abstract: We systematically evaluate the quality of widely used AI safety datasets from two perspectives: in isolation and in practice. In isolation, we examine how well these datasets reflect real-world adversarial attacks based on three key properties: being driven by ulterior intent, well-crafted, and out-of-distribution. We find that these datasets overrely on "triggering cues": words or phrases with overt negative/sensitive connotations that are intended to trigger safety mechanisms explicitly, which is unrealistic compared to real-world attacks. In practice, we evaluate whether these datasets genuinely measure safety risks or merely provoke refusals through triggering cues. To explore this, we introduce "intent laundering": a procedure that abstracts away triggering cues from adversarial attacks (data points) while strictly preserving their malicious intent and all relevant details. Our results indicate that current AI safety datasets fail to faithfully represent real-world adversarial behavior due to their overreliance on triggering cues. Once these cues are removed, all previously evaluated "reasonably safe" models become unsafe, including Gemini 3 Pro and Claude Sonnet 3.7. Moreover, when intent laundering is adapted as a jailbreaking technique, it consistently achieves high attack success rates, ranging from 90% to over 98%, under fully black-box access. Overall, our findings expose a significant disconnect between how model safety is evaluated by existing datasets and how real-world adversaries behave.
Authors: Xinyi Lu, Kexin Phyllis Ju, Mitchell Dudley, Larissa Sano, Xu Wang
Abstract: Despite growing interest in using LLMs to generate feedback on students' writing, little is known about how students respond to AI-mediated versus human-provided feedback. We address this gap through a randomized controlled trial in a large introductory economics course (N=354), where we introduce and deploy FeedbackWriter - a system that generates AI suggestions to teaching assistants (TAs) while they provide feedback on students' knowledge-intensive essays. TAs have the full capacity to adopt, edit, or dismiss the suggestions. Students were randomly assigned to receive either handwritten feedback from TAs (baseline) or AI-mediated feedback where TAs received suggestions from FeedbackWriter. Students revise their drafts based on the feedback, which is further graded. In total, 1,366 essays were graded using the system. We found that students receiving AI-mediated feedback produced significantly higher-quality revisions, with gains increasing as TAs adopted more AI suggestions. TAs found the AI suggestions useful for spotting gaps and clarifying rubrics.
Authors: Kushal Kedia, Tyler Ga Wei Lum, Jeannette Bohg, C. Karen Liu
Abstract: The ability to manipulate tools significantly expands the set of tasks a robot can perform. Yet, tool manipulation represents a challenging class of dexterity, requiring grasping thin objects, in-hand object rotations, and forceful interactions. Since collecting teleoperation data for these behaviors is challenging, sim-to-real reinforcement learning (RL) is a promising alternative. However, prior approaches typically require substantial engineering effort to model objects and tune reward functions for each task. In this work, we propose SimToolReal, taking a step towards generalizing sim-to-real RL policies for tool manipulation. Instead of focusing on a single object and task, we procedurally generate a large variety of tool-like object primitives in simulation and train a single RL policy with the universal goal of manipulating each object to random goal poses. This approach enables SimToolReal to perform general dexterous tool manipulation at test-time without any object or task-specific training. We demonstrate that SimToolReal outperforms prior retargeting and fixed-grasp methods by 37% while matching the performance of specialist RL policies trained on specific target objects and tasks. Finally, we show that SimToolReal generalizes across a diverse set of everyday tools, achieving strong zero-shot performance over 120 real-world rollouts spanning 24 tasks, 12 object instances, and 6 tool categories.
Authors: Chuqin Geng, Li Zhang, Haolin Ye, Ziyu Zhao, Yuhe Jiang, Tara Saba, Xinyu Wang, Xujie Si
Abstract: Graph Neural Networks (GNNs) have become essential in high-stakes domains such as drug discovery, yet their black-box nature remains a significant barrier to trustworthiness. While self-explainable GNNs attempt to bridge this gap, they often rely on standard message-passing backbones that inherit fundamental limitations, including the 1-Weisfeiler-Lehman (1-WL) expressivity barrier and a lack of fine-grained interpretability. To address these challenges, we propose SymGraph, a symbolic framework designed to transcend these constraints. By replacing continuous message passing with discrete structural hashing and topological role-based aggregation, our architecture theoretically surpasses the 1-WL barrier, achieving superior expressiveness without the overhead of differentiable optimization. Extensive empirical evaluations demonstrate that SymGraph achieves state-of-the-art performance, outperforming existing self-explainable GNNs. Notably, SymGraph delivers 10x to 100x speedups in training time using only CPU execution. Furthermore, SymGraph generates rules with superior semantic granularity compared to existing rule-based methods, offering great potential for scientific discovery and explainable AI.
Authors: Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Binbin Zheng, Chaowen Hu, Zekai Shao, Cong Qin, Lu Pan, Ke Zeng, Xunliang Cai
Abstract: Existing Reinforcement Learning with Verifiable Rewards (RLVR) algorithms, such as GRPO, rely on rigid, uniform, and symmetric trust region mechanisms that are fundamentally misaligned with the complex optimization dynamics of Large Language Models (LLMs). In this paper, we identify three critical challenges in these methods: (1) inefficient gradient utilization caused by the binary cutoff of hard clipping, (2) insensitive probability mass arising from uniform ratio constraints that ignore the token distribution, and (3) asymmetric signal reliability stemming from the disparate credit assignment ambiguity between positive and negative samples. To bridge these gaps, we propose Mass-Adaptive Soft Policy Optimization (MASPO), a unified framework designed to harmonize these three dimensions. MASPO integrates a differentiable soft Gaussian gating to maximize gradient utility, a mass-adaptive limiter to balance exploration across the probability spectrum, and an asymmetric risk controller to align update magnitudes with signal confidence. Extensive evaluations demonstrate that MASPO serves as a robust, all-in-one RLVR solution, significantly outperforming baselines. Our code is at: \href{https://github.com/VenomRose-Juri/MASPO-RL}{https://github.com/VenomRose-Juri/MASPO-RL}.
URLs: https://github.com/VenomRose-Juri/MASPO-RL, https://github.com/VenomRose-Juri/MASPO-RL
Authors: Minheng Chen, Tong Chen, Chao Cao, Jing Zhang, Tianming Liu, Li Su, Dajiang Zhu
Abstract: Alzheimer's disease (AD) and Lewy body dementia (LBD) present overlapping clinical features yet require distinct diagnostic strategies. While neuroimaging-based brain network analysis is promising, atlas-based representations may obscure individualized anatomy. Gyral folding-based networks using three-hinge gyri provide a biologically grounded alternative, but inter-individual variability in cortical folding results in inconsistent landmark correspondence and highly irregular network sizes, violating the fixed-topology and node-alignment assumptions of most existing graph learning methods, particularly in clinical datasets where pathological changes further amplify anatomical heterogeneity. We therefore propose a probability-invariant random-walk-based framework that classifies individualized gyral folding networks without explicit node alignment. Cortical similarity networks are built from local morphometric features and represented by distributions of anonymized random walks, with an anatomy-aware encoding that preserves permutation invariance. Experiments on a large clinical cohort of AD and LBD subjects show consistent improvements over existing gyral folding and atlas-based models, demonstrating robustness and potential for dementia diagnosis.
Authors: Seyed Hossein Alavi, Zining Wang, Shruthi Chockkalingam, Raymond T. Ng, Vered Shwartz
Abstract: Interactive systems such as chatbots and games are increasingly used to persuade and educate on sustainability-related topics, yet it remains unclear how different delivery formats shape learning and persuasive outcomes when content is held constant. Grounding on identical arguments and factual content across conditions, we present a controlled user study comparing three modes of information delivery: static essays, conversational chatbots, and narrative text-based games. Across subjective measures, the chatbot condition consistently outperformed the other modes and increased perceived importance of the topic. However, perceived learning did not reliably align with objective outcomes: participants in the text-based game condition reported learning less than those reading essays, yet achieved higher scores on a delayed (24-hour) knowledge quiz. Additional exploratory analyses further suggest that common engagement proxies, such as verbosity and interaction length, are more closely related to subjective experience than to actual learning. These findings highlight a dissociation between how persuasive experiences feel and what participants retain, and point to important design trade-offs between interactivity, realism, and learning in persuasive systems and serious games.
Authors: Muhammad Tayyab Khan, Lequn Chen, Wenhe Feng, Seung Ki Moon
Abstract: Manufacturing automation in process planning, inspection planning, and digital-thread integration depends on a unified specification that binds the geometric features of a 3D CAD model to the geometric dimensioning and tolerancing (GD&T) callouts, datum definitions, and surface requirements carried by the corresponding 2D engineering drawing. Although Model-Based Definition (MBD) allows such specifications to be embedded directly in 3D models, 2D drawings remain the primary carrier of manufacturing intent in automotive, aerospace, shipbuilding, and heavy-machinery industries. Correctly linking drawing annotations to the corresponding 3D features is difficult because of contextual ambiguity, repeated feature patterns, and the need for transparent and traceable decisions. This paper presents a deterministic-first, context-aware framework that maps 2D drawing entities to 3D CAD features to produce a unified manufacturing specification. Drawing callouts are first semantically enriched and then scored against candidate features using an interpretable metric that combines type compatibility, tolerance-aware dimensional agreement, and conservative context consistency, along with engineering-domain heuristics. When deterministic scoring cannot resolve an ambiguity, the system escalates to multimodal and constrained large-language-model reasoning, followed by a single human-in-the-loop (HITL) review step. Experiments on 20 real CAD-drawing pairs achieve a mean precision of 83.67%, recall of 90.46%, and F1 score of 86.29%. An ablation study shows that each pipeline component contributes to overall accuracy, with the full system outperforming all reduced variants. By prioritizing deterministic rules, clear decision tracking, and retaining unresolved cases for human review, the framework provides a practical foundation for downstream manufacturing automation in real-world industrial environments.
Authors: Yuxuan Li, Leyang Li, Hao-Ping Lee, Sauvik Das
Abstract: A growing body of research assumes that large language model (LLM) agents can serve as proxies for how people form attitudes toward and behave in response to security and privacy (S&P) threats. If correct, these simulations could offer a scalable way to forecast S&P risks in products prior to deployment. We interrogate this assumption using SP-ABCBench, a new benchmark of 30 tests derived from validated S&P human-subject studies, which measures alignment between simulations and human-subjects studies on a 0-100 ascending scale, where higher scores indicate better alignment across three dimensions: Attitude, Behavior, and Coherence. Evaluating twelve LLMs, four persona construction strategies, and two prompting methods, we found that there remains substantial room for improvement: all models score between 50 and 64 on average. Newer, bigger, and smarter models do not reliably do better and sometimes do worse. Some simulation configurations, however, do yield high alignment: e.g., with scores above 95 for some behavior tests when agents are prompted to apply bounded rationality and weigh privacy costs against perceived benefits. We release SP-ABCBench to enable reproducible evaluation as methods improve.
Authors: Xiaoming Zhai, Kent Crippen
Abstract: The integration of artificial intelligence (AI) into science education is transforming the design and function of learning materials, offering new affordances for personalization, authenticity, and accessibility. This chapter examines how AI technologies are transforming science learning materials across six interrelated domains: 1) integrating AI into scientific practice, 2) enabling adaptive and personalized instruction, 3) facilitating interactive simulations, 4) generating multimodal content, 5) enhancing accessibility for diverse learners, and 6) promoting co-creation through AI-supported content development. These advancements enable learning materials to more accurately reflect contemporary scientific practice, catering to the diverse needs of students. For instance, AI support can enable students to engage in dynamic simulations, interact with real-time data, and explore science concepts through multimodal representations. Educators are increasingly collaborating with generative AI tools to develop timely and culturally responsive instructional resources. However, these innovations also raise critical ethical and pedagogical concerns, including issues of algorithmic bias, data privacy, transparency, and the need for human oversight. To ensure equitable and meaningful science learning, we emphasize the importance of designing AI-supported materials with careful attention to scientific integrity, inclusivity, and student agency. This chapter advocates for a responsible, ethical, and reflective approach to leveraging AI in science education, framing it as a catalyst for innovation while upholding core educational values.
Authors: Matthew Adiletta, Gu-Yeon Wei, David Brooks
Abstract: Large language model (LLM) inference performance is increasingly bottlenecked by the memory wall. While GPUs continue to scale raw compute throughput, they struggle to deliver scalable performance for memory bandwidth bound workloads. This challenge is amplified by emerging reasoning LLM applications, where long output sequences, low arithmetic intensity, and tight latency constraints demand significantly higher memory bandwidth. As a result, system utilization drops and energy per inference rises, highlighting the need for an optimized system architecture for scalable memory bandwidth. To address these challenges we present the Reasoning Processing Unit (RPU), a chiplet-based architecture designed to address the challenges of the modern memory wall. RPU introduces: (1) A Capacity-Optimized High-Bandwidth Memory (HBM-CO) that trades capacity for lower energy and cost; (2) a scalable chiplet architecture featuring a bandwidth-first power and area provisioning design; and (3) a decoupled microarchitecture that separates memory, compute, and communication pipelines to sustain high bandwidth utilization. Simulation results show that RPU performs up to 45.3x lower latency and 18.6x higher throughput over an H100 system at ISO-TDP on Llama3-405B.
Authors: Heman Shakeri
Abstract: This paper offers a phenomenological reading of contemporary machine learning through Heideggerian concepts, aimed at enriching practitioners' reflexive understanding of their own practice. We argue that this philosophical lens reveals three insights invisible to purely technical analysis. First, the algorithmic Entwurf (projection) is distinctive in being automated, opaque, and emergent--a metaphysics that operates without explicit articulation or debate, crystallizing implicitly through gradient descent rather than theoretical argument. Second, even sophisticated technical advances remain within the regime of Gestell (Enframing), improving calculation without questioning the primacy of calculation itself. Third, AI's lack of existential structure, specifically the absence of Care (Sorge), is genuinely explanatory: it illuminates why AI systems have no internal resources for questioning their own optimization imperatives, and why they optimize without the anxiety (Angst) that signals, in human agents, the friction between calculative absorption and authentic existence. We conclude by exploring the pedagogical value of this perspective, arguing that data science education should cultivate not only technical competence but ontological literacy--the capacity to recognize what worldviews our tools enact and when calculation itself may be the wrong mode of engagement.
Authors: Rampunit Kumar, Aditya Maheshwari
Abstract: Urban air pollution in megacities poses critical public health challenges, particularly in Delhi National Capital Region (NCR) where severe degradation affects millions. We present NEXUS (Neural Extraction and Unified Spatiotemporal) architecture for forecasting carbon monoxide, nitrogen oxide, and sulfur dioxide. Working with four years (2018--2021) of atmospheric data across sixteen spatial grids, NEXUS achieves R$^2$ exceeding 0.94 for CO, 0.91 for NO, and 0.95 for SO$_2$ using merely 18,748 parameters -- substantially fewer than SCINet (35,552), Autoformer (68,704), and FEDformer (298,080). The architecture integrates patch embedding, low-rank projections, and adaptive fusion mechanisms to decode complex atmospheric chemistry patterns. Our investigation uncovers distinct diurnal rhythms and pronounced seasonal variations, with winter months experiencing severe pollution episodes driven by temperature inversions and agricultural biomass burning. Analysis identifies critical meteorological thresholds, quantifies wind field impacts on pollutant dispersion, and maps spatial heterogeneity across the region. Extensive ablation experiments demonstrate each architectural component's role. NEXUS delivers superior predictive performance with remarkable computational efficiency, enabling real-time deployment for air quality monitoring systems.
Authors: Krzysztof Adamkiewicz, Brian Moser, Stanislav Frolov, Tobias Christian Nauen, Federico Raue, Andreas Dengel
Abstract: Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following. But do they perform well as synthetic vision data generators? In this work, we revisit the promise of synthetic data as a scalable substitute for real training sets and uncover a surprising performance regression. We generate large-scale synthetic datasets using state-of-the-art T2I models released between 2022 and 2025, train standard classifiers solely on this synthetic data, and evaluate them on real test data. Despite observable advances in visual fidelity and prompt adherence, classification accuracy on real test data consistently declines with newer T2I models as training data generators. Our analysis reveals a hidden trend: These models collapse to a narrow, aesthetic-centric distribution that undermines diversity and label-image alignment. Overall, our findings challenge a growing assumption in vision research, namely that progress in generative realism implies progress in data realism. We thus highlight an urgent need to rethink the capabilities of modern T2I models as reliable training data generators.
Authors: Maijunxian Wang, Ruisi Wang, Juyi Lin, Ran Ji, Thadd\"aus Wiedemer, Qingying Gao, Dezhi Luo, Yaoyao Qian, Lianyu Huang, Zelong Hong, Jiahui Ge, Qianli Ma, Hang He, Yifan Zhou, Lingzi Guo, Lantao Mei, Jiachen Li, Hanwen Xing, Tianqi Zhao, Fengyuan Yu, Weihang Xiao, Yizheng Jiao, Jianheng Hou, Danyang Zhang, Pengcheng Xu, Boyang Zhong, Zehong Zhao, Gaoyun Fang, John Kitaoka, Yile Xu, Hua Xu, Kenton Blacutt, Tin Nguyen, Siyuan Song, Haoran Sun, Shaoyue Wen, Linyang He, Runming Wang, Yanzhi Wang, Mengyue Yang, Ziqiao Ma, Rapha\"el Milli\`ere, Freda Shi, Nuno Vasconcelos, Daniel Khashabi, Alan Yuille, Yilun Du, Ziming Liu, Bo Li, Dahua Lin, Ziwei Liu, Vikash Kumar, Yijiang Li, Lei Yang, Zhongang Cai, Hokin Deng
Abstract: Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can naturally capture, enabling intuitive reasoning over spatiotemporal structure such as continuity, interaction, and causality. However, systematically studying video reasoning and its scaling behavior is hindered by the lack of large-scale training data. To address this gap, we introduce the Very Big Video Reasoning (VBVR) Dataset, an unprecedentedly large-scale resource spanning 200 curated reasoning tasks following a principled taxonomy and over one million video clips, approximately three orders of magnitude larger than existing datasets. We further present VBVR-Bench, a verifiable evaluation framework that moves beyond model-based judging by incorporating rule-based, human-aligned scorers, enabling reproducible and interpretable diagnosis of video reasoning capabilities. Leveraging the VBVR suite, we conduct one of the first large-scale scaling studies of video reasoning and observe early signs of emergent generalization to unseen reasoning tasks. Together, VBVR lays a foundation for the next stage of research in generalizable video reasoning. The data, benchmark toolkit, and models are publicly available at https://video-reason.com/ .