# Research Papers — 2026-05 · bundle page 94 of 326 > Full-text markdown of papers #4651–4700 of 16266 published in 2026-05, newest first. AI-readable mirrors of the full 16266-paper 2026-05 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-05/page/94 [← Previous bundle](https://aipod.dev/papers/archive/2026-05/page/93.md) [Next bundle →](https://aipod.dev/papers/archive/2026-05/page/95.md) ### Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork Authors: Yuheng Jing, Kai Li, Ziwen Zhang, Jiajun Zhang, Zeyao Ma, Jiaxi Yang, Lei Zhang, Zhe Wu, Jinmin He, Junliang Xing, Jian Cheng Published: 2026-05-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24423v1 In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT)-where coordination with unknown partners is required-remains unexplored. To rigorously evaluate this, we introduce a large-scale benchmark ICRL4AHT, built upon a high-throughput JAX implementation of Overcooked-V2. Our benchmark includes a large, diverse teammate suite spanning both RL and heuristic policies, enabling controlled train-test shifts, and provides a reproducible end-to-end pipeline for teammate generation, learning-history collection, dataset construction, and online multi-episode evaluation. We evaluate representative history-conditioned ICRL algorithms, including Algorithm Distillation (AD) and Decision-Pretrained Transformer (DPT), across millions of transitions. Results reveal notable limitations: contrary to their success in single-agent domains, these baselines fail to exhibit robust test-time adaptation in multi-agent settings. Specifically, these methods frequently underperform random baselines across both unseen teammate and unseen layout tracks, with no clear in-context improvement over long horizons. These findings highlight the challenges of strategic inference under partial observability within the OvercookedV2 AHT protocol, establishing our benchmark as a critical testbed for next-generation coordination algorithms. --- ### Clustering based on Stochastic Dominance with application for risk averters and risk seekers Authors: Hua Li, Xue Jia, Yilin Kang, Wing-Keung Wong Published: 2026-05-23 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.24422v1 Stochastic Dominance (SD) theory provides a rigorous framework for selecting superior assets tailored to the asset allocation needs of investors with varying risk preferences (i.e., risk-averse, risk-seeking, and risk-neutral). However, traditional stock clustering methods typically rely on geometric metrics such as Euclidean distance, which often fail to effectively capture the intrinsic risk dominance relationships among assets. To address this limitation, this paper proposes an innovative clustering analysis framework based on SD test statistics. Methodologically, this study deeply integrates SD theory with machine learning algorithms. Transcending the limitations of traditional reliance on geometric distance, we innovatively utilize test statistics from first-, second-, and third-order SD to construct a "Stochastic Dominance Coefficient Matrix." Building upon this matrix, we modify the classic K-means and Hierarchical Clustering algorithms. Specifically, we derive 12 distinct algorithm variants tailored to different orders of SD relationships. Simultaneously, we construct the SD-SC coefficient and the SD-DBI index as specialized validity indices to evaluate the clustering performance. Empirically, we analyze constituent stock data from a representative developed market (the US NASDAQ Index) and an emerging market (China's CSI 100 Index). The results verify the effectiveness and robustness of the proposed method. Furthermore, we apply the clustering results to the modification of the Single Index Model and the construction of Global Minimum Variance Portfolios (GMVP). The findings demonstrate that the proposed method effectively facilitates customized asset allocation for investors, holding significant theoretical value and practical implications. --- ### Poisoning the Watchtower: Prompt Injection Attacks Against LLM-Augmented Security Operations Through Adversarial Log Content Authors: Rohan Pandey, Archit Bhujang Published: 2026-05-23 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2605.24421v1 Large language models (LLMs) are increasingly used as analyst assistants in security operations centers (SOCs), where they ingest log and alert data to produce triage labels, incident summaries, or remediation advice. We study a structural failure mode of this design: many log fields are attacker controlled. User agents, URLs, payloads, DNS queries, and attempted usernames can therefore carry instructions to the model alongside evidence of the intrusion. We call this setting \emph{log-substrate prompt injection}. We introduce a four-class taxonomy of log-substrate attacks: direct override (S1), persona hijack (S2), context manipulation (S3), and obfuscated payloads (S4). We evaluate 48 strategy-defense-task combinations using \texttt{gpt-4o-mini} as the analyst. Three findings stand out. First, direct overrides are ineffective in our setting: all S1 classification attacks achieve 0\% suppression. In contrast, persona hijacks suppress 68\% of malicious logs under a naive classifier and remain effective under stronger defenses. Second, summarization is the highest-risk task: context manipulation reaches 96\% injection success without defenses and 38\% even with constrained output. Third, defenses reduce but do not eliminate the attack surface: average injection success falls from 26.6\% under naive prompting to 11.8\% under our strongest defense. We also compare empirical results to a deterministic mock analyst and find that simulation substantially mispredicts current model behavior, especially for direct overrides. These results suggest that SOC copilots should treat raw log content as adversarial input rather than ordinary analyst context. --- ### Batch Normalization Amplifies Memorization and Privacy Risks Authors: Ngoc Phu Doan, Chongyan Gu, Ihsen Alouani Published: 2026-05-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24420v2 Batch Normalization (BN) is widely adopted to enable faster convergence and more stable training of deep neural networks. However, its impact on privacy and memorization has remained largely unexplored. In this work, we investigate the effect of BN layers on the memorization of atypical or outlier samples and its implications for privacy leakage. We conduct an extensive empirical study using three complementary approaches: (i) unintended memorization of out-of-distribution samples, (ii) per-sample influence, and (iii) susceptibility to membership inference attacks (MIA). Across multiple datasets and architectures, we consistently observe that BN substantially increases the memorization of outliers compared to models without BN. Critically, this amplified memorization translates directly into privacy vulnerabilities: models with BN exhibit significantly higher susceptibility to MIAs. We complement our empirical findings with a mechanistic analysis under the exact BN backward pass, which shows that BN amplifies the per-step margin growth of outlier samples during training. Our results highlight an underappreciated privacy risk associated with BN and provide both practical and theoretical insights into how normalization layers can amplify the influence of rare or sensitive training examples. --- ### Batch Normalization Amplifies Memorization and Privacy Risks Authors: Ngoc Phu Doan, Chongyan Gu, Ihsen Alouani Published: 2026-05-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24420v1 Batch Normalization (BN) is widely adopted to enable faster convergence and more stable training of deep neural networks. However, its impact on privacy and memorization has remained largely unexplored. In this work, we investigate the effect of BN layers on the memorization of atypical or outlier samples and its implications for privacy leakage. We conduct an extensive empirical study using three complementary approaches: (i) unintended memorization of out-of-distribution training samples, (ii) per-sample influence measured via gradient norms, and (iii) susceptibility to membership inference attacks (MIA). Across multiple datasets and architectures, we consistently observe that BN substantially increases the memorization of outliers compared to models without BN. Critically, this amplified memorization translates directly into privacy vulnerabilities: models with BN exhibit significantly higher susceptibility to MIAs. We complement our empirical findings with a theoretical analysis showing that BN amplifies the per-step influence of outlier samples during training, providing mechanistic insight into this phenomenon. Our results highlight an underappreciated privacy risk associated with BN and provide both practical and theoretical insights into how normalization layers can amplify the influence of rare or sensitive training examples. --- ### ChainLearn: A Blockchain-Based Capacity-Aware Framework for Federated Ensemble Learning Authors: Karan Sharma, Aditya Tripathi, Rahul Mishra, Tapas Kumar Maiti Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24418v1 Federated learning is used in medical imaging where privacy prohibits centralizing data. Standard federated algorithms assume homogeneous hardware, identical architectures, and centralized aggregation, which fails when hospitals have unequal compute resources. We propose capacity-aware coordination: measure each hospital's throughput, assign capacity-appropriate architectures (MobileNetV3-Small, EfficientNet-B0, ResNet-50), and combine predictions via weighted ensemble. Weak and strong hospitals can participate without forcing uniform architectures. We separate on-chain policy from off-chain learning. A Solidity contract stores hospital registration, benchmark hashes, metrics, and weights. Hospitals train locally and submit only hashes and scalars (not parameters). Weighted ensemble inference is computed off-chain. Experiments on PneumoniaMNIST and DermaMNIST (5 seeds, 3 non-IID levels) show our method achieves lower or equal calibration error versus equal-weight ensemble and competitive accuracy versus FedAvg, FedProx, and FedMD. Communication overhead is 224 bytes per round, a reduction of over 912,000x compared to FedAvg. --- ### LLMTabBench: Evaluating LLMs on Binary Tabular Classification From Zero to Few Shots Authors: Daria Grushina, Kseniia Kuvshinova, Alina Kostromina, Aziz Temirkhanov, Mile Mitrovic, Dmitry Simakov Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24417v2 Supervised classification on tabular data remains a central machine learning task, but its dependence on large labeled datasets limits its applicability in data-scarce settings. Few-shot methods such as TabPFN achieve strong performance through large-scale synthetic pretraining, yet still require labeled context examples. Large Language Models (LLMs) offer a more flexible alternative through zero- and few-shot in-context learning from task descriptions, but their behavior on tabular data remains inconsistent. We introduce LLMTabBench, a benchmark for evaluating LLMs on tabular classification under low-data conditions. The benchmark studies how LLM prior knowledge interacts with task descriptions and few-shot examples, and how performance changes with increasing data complexity across real-world and controlled synthetic datasets. We find that LLMs can be highly competitive in zero-shot settings, sometimes outperforming models given few-shot examples. However, additional examples may conflict with prior knowledge, thereby degrading performance. We also observe a complexity threshold at which LLM performance declines and few-shot examples become less useful. These results clarify key limits of in-context learning for tabular data and inform the deployment of LLMs in low-data regimes. --- ### Synheart Capacity: A Theory-Driven Physiological Representation of Cognitive Capacity Dynamics from Wearable Signals Authors: Yisak Debele, Henok Ademtew, Israel Goytom Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24416v1 Human cognitive performance is constrained by limited mental resources, yet continuous computational estimation of cognitive capacity dynamics remains an open challenge. We propose a theory-driven multimodal learning framework that models capacity-related cognitive state as a two-dimensional physiological representation defined by voluntary resource allocation (mental effort) and overload-related strain (stress). The proposed architecture combines dual-stream encoding of cardiac (IBI/HRV) and electrodermal (EDA) signals with late fusion and task-specific output heads that independently estimate probabilistic effort and stress states. Evaluation on the SWELL-KW dataset using strict leave-one-subject-out cross-validation demonstrates cross-individual generalization (stress: 70.0\% balanced accuracy; effort: 72.2\%), with significant gains from multimodal integration and theory-guided supervision. Rather than collapsing physiological dynamics into a single workload label, the proposed effort--stress state-space enables structured differentiation between distinct cognitive regimes, including productive engagement and overload-related strain. Predicted state trajectories exhibit significant demand-sensitive shifts under controlled workload manipulations, with effort and stress responding differentially across interruption and time-pressure conditions. These results suggest that physiologically grounded multidimensional state representations may provide a foundation for adaptive systems capable of continuous capacity-aware monitoring and human-centered interaction. --- ### JT-SAFE-V2: Safety-by-Design Foundation Model with World-Context Data Authors: Junlan Feng, Fanyu Meng, Chong Long, Pengyu Cong, Duqing Wang, Yan Zheng, Yuyao Zhang, Xuanchang Gao, Ye Yuan, Yunfei Ma, Zhijie Ren, Fan Yang et al. Published: 2026-05-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24414v1 We introduce JT-Safe-V2, a large language model designed to advance the safety and trustworthiness of foundation models, extending our previous JT-Safe model toward a more comprehensive safety-by-design paradigm. JT-Safe-V2 emphasizes the joint optimization of general intelligence and safety-by-design through several key innovations: enriching pre-training data with contextual world knowledge, high-certainty pre-training procedures, and safety strengthening post-training mechanisms for enterprise-oriented agentic capabilities. Building on these safety-enhanced foundation models, we propose Safe-MoMA (Safe Mixture of Models and Agents), a framework that enables traceable and efficient inference through the orchestrated deployment of multiple models and agents. Extensive evaluations demonstrate that JT-Safe-V2 achieves state-of-the-art performance across both general intelligence and safety benchmarks. Moreover, Safe-MoMA reduces inference costs by more than 30\% compared to using the largest standalone model baseline while maintaining comparable performance. To facilitate future research on safety-by-design foundation models, we publicly release the post-trained JT-Safe-V2-35B model checkpoint. --- ### The Model Is Not the Product: A Dual-Pillar Architecture for Local-First Psychological Coaching Authors: Alexander Mihalcea Published: 2026-05-23 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2605.24411v1 Existing language model applications struggle to meet the demand for emotionally oriented support, primarily due to their inability to maintain deep, persistent context across sessions. This report introduces Psych LM, an iOS application that validates the thesis that, for such applications, the surrounding architecture is paramount. Psych LM runs a local, on-device language model within a purpose-built, local-first runtime designed for behavioral and life-coaching applications. The system achieves the practical effect of a near-infinite context window through an automated, user-inspectable memory corpus that converts conversations into structured memory cards, including facts, goals, and events, and dynamically injects them into the prompt via semantic and vector search. As such, the system can be defined as an active-learning, retrieval-augmented generative, on-device architecture. This architecture delivers four primary contributions: a local-first design where privacy is a core property; a detailed description of the memory corpus for persistent context of key user information; a deterministic orchestration layer that provides a stable behavioral spine independent of the model's internal state; and a benchmark framework focused on evaluating the integrated system's reliability under realistic operating conditions. The R and D process confirms that complex, context-aware interaction can be reliably achieved under the strict constraints of a mobile environment by prioritizing architectural control and resource management over simple model size. --- ### Advancing Graph Few-Shot Learning via In-Context Learning Authors: Renchu Guan, Yajun Wang, Chunli Guo, Bowen Cao, Fausto Giunchiglia, Wei Pang, Yonghao Liu, Xiaoyue Feng Published: 2026-05-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24410v1 Graph few-shot learning, which aims to classify nodes from novel classes with only a few labeled examples, is a widely studied problem in graph learning. However, existing methods often face two key limitations. First, the predominant graph few-shot learning paradigm relies on supervised tasks, failing to leverage the vast number of unlabeled nodes in the graph. Second, many approaches require complex task adaptation or fine-tuning during inference, limiting their efficiency and applicability. Inspired by the powerful in-context learning capabilities of large language models, we propose a novel model named VISION for adVancIng graph few-Shot learning via In-cOntext LearNing to address these challenges. Our model reframes graph few-shot learning as a fine-tuning-free sequence reasoning problem. At its core is a context-aware network that initializes nodes with role embeddings and employs a dual-context fusion module to synergistically integrate local topological structures and global task-level dependencies. This allows our model to dynamically generate class-aware representations for the query set conditioned on the support set context in a single forward pass. To effectively train our model, we introduce an unsupervised task generator that creates structure-adaptive features and constructs diverse pseudo-tasks from abundant unlabeled data. Our method unifies unsupervised meta-learning with graph in-context learning, achieving efficient inference. Extensive experiments on multiple benchmark datasets demonstrate the superiority of our model. Our public code can be found --- ### A Unified Python Framework for Direct PPO-based Control of AHUs with Economizer Logic and CO2-Constrained Ventilation Authors: Erfan Haghighat Damavandi, Davide Papurello, Mahdi Alibeigi, Armin Keshavarz, Simone Canevarolo, Marco Condo Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24406v1 Optimizing HVAC (Heating, Ventilation and Air Conditioning) can enhance a building's energy efficiency while providing comfort levels for its occupants. Using conventional control systems to maintain HVAC functions is often difficult because of the nonlinear characteristics of a building envelope as it experiences stochastic load variations over time. This paper presents a new approach to optimizing HVAC systems through the use of Deep Reinforcement Learning (DRL) algorithms and the Proximal Policy Optimization (PPO) algorithm implemented in a custom Python performance environment. The DRL system uses a second order resistor-capacitor thermal model and an integrated dynamic mass balance of CO2 to replicate the complex physics associated with buildings. One major innovation of this study is a "Hierarchical Flow Logic," which provides the means to ensure that indoor air quality (IAQ) is maintained by overriding the accepted actions of the agent that cause CO2 to exceed 1000 ppm. In addition, an enthalpy-based economiser is used to create free cooling from the outdoor environment. The experimental data shows that compared to PID controllers tuned by GA or traditional On-Off controls, a PPO agent has better temperature stability and energy efficiency overall. An end-to-end pipeline provides an avenue for robust and generalized solutions to help implement smart building energy management within the context of real hardware implementation. --- ### Generative OOD-regularized Model-based Policy Optimization Authors: Aysin Tumay, Jiahe Huang, Elise Jortberg, Rose Yu Published: 2026-05-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24405v1 We study sequential decision-making with offline reinforcement learning (RL). Traditional offline RL policies may result in out-of-distribution (OOD) actions when training relies only on sparse offline representations. To ensure safe offline policies in a sparse state-action space, we explore how density estimation models can be integrated into model-based RL methods to avoid the OOD regions. Generative models are capable of explicitly modeling the density in sparse state-action spaces. Building on this, we introduce Generative OOD-regularized Model-based Policy Optimization (GORMPO), a density-regularized offline RL algorithm that uses generative density modeling to restrict policy updates to high-density areas of the dataset. Furthermore, we examine whether better OOD detection corresponds to better model-based offline policies. We compare (1) the OOD detection capabilities of various density estimators and (2) their performance within the GORMPO framework on a real-world medical dataset and sparse offline RL datasets. We theoretically guarantee GORMPO's performance under mild assumptions. Empirically, GORMPO outperforms state-of-the-art baselines by 17% on a real-world medical dataset and enhances the base model on the offline RL datasets. Our empirical findings show that better OOD detection generally results in improved policies in environments with stable dynamics, while conservative penalties with poor density estimation are favored when dynamics are uncertain. --- ### Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects Authors: Denys Iliash, Jiayi Liu, Egor Fokin, Qirui Wu, Ali Mahdavi-Amiri, Manolis Savva, Angel X. Chang Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24403v1 We present Artiverse, a diverse and physically grounded dataset of high-quality articulated 3D objects designed for realistic functional modeling and simulation. Artiverse contains 5.4K human-authored objects across a broad range of 88 categories, aggregated from multiple 3D static repositories. Objects are annotated with functional parts, interior structures, realistic kinematic relationships and articulated joints including multi-DoF joints, and physical attributes such as metric scale, material, and mass. We develop a semi-automated annotation pipeline that combines few-shot segmentation, geometric reasoning, and multi-stage human verification to achieve high-quality and efficient annotation, reducing manual annotation time by over 30%. We demonstrate the value of Artiverse on tasks of part mobility analysis, articulated object generation, and physics-based interaction. Artiverse provides a data resource to advance functional understanding for articulated objects. --- ### Dual Prototype-Conditioned Diffusion Model for Scalable Multi-Class Unsupervised Anomaly Detection in Large Category Spaces Authors: Yaoxuan Feng, Yuxin Li, Weijiang Lv, Zixuan Zhao, Yubiao Wang, Wenchao Chen, Bo Chen, Hongwei Liu Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24402v1 Multi-class anomaly detection aims to build unified models across diverse product categories. However, as the number of categories grows, its performance often degrades due to increasingly complex and heterogeneous normal distributions. To address this challenge, we propose DPDiff-AD, a Dual Prototype-conditioned Diffusion model for large-scale multi-class Anomaly Detection. DPDiff-AD models heterogeneous normal distributions through complementary local and global prototypes. Local prototypes capture representative fine-grained structural patterns via nearest-prototype aggregation, while global prototypes regulate holistic feature geometry through optimal transport regularization. Together, these dual-scale representations define a structured normality space. This space is refined through diffusion-based reconstruction conditioned on both local and global prototypes via prototype-aware attention. By jointly leveraging dual prototypes during generation, DPDiff-AD achieves precise normality modeling, preserves structured separability as category cardinality grows, and enables scalable anomaly discrimination. Extensive experiments across five benchmarks demonstrate the effectiveness and scalability of DPDiff-AD. On the 160-category large-scale dataset, it improves image- and pixel-level AUROC by 5.3 and 2.9 points over the previous state-of-the-art method Dinomaly+, while maintaining stable performance as category cardinality increases. --- ### ConceptM$^3$oE: Concept-Guided Multimodal Mixture of Experts for Interpretable Computational Pathology Authors: Xuan Wang, Zhongling Xu, Gopi Kannedhara, Joakim Nguyen, Jian Yu, Jinrui Fang, Abdurrahmaan Baghdadi, Tianlong Chen, Awais Naeem, Chandra Krishnan, Edward Castillo, Andrew H. Song et al. Published: 2026-05-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24399v2 Healthcare models are transitioning from unimodal prediction toward multimodal reasoning over heterogeneous diagnostic inputs. In computational pathology, for complex tumor subtypes where morphology alone can be challenging to distinguish, pathology reports and molecular measurements may provide additional diagnostic evidence alongside whole-slide images, yet existing models often fail to clarify how diverse signals assemble into recognizable diagnostic concepts. We propose ConceptM$^3$oE (Concept Multimodal MoE), which embeds concept formation directly within interaction-aware mixture-of-experts (MoE) pathways. The architecture decomposes evidence into modality-specific, redundant, and synergistic experts, which are then projected into structured concept bottlenecks mapping latent features to a hierarchy of morphology and biomarker concepts. To prevent the information loss typical of interpretable bottlenecks, we utilize residual pathways within each expert to allow task-relevant signals to flow both through the concepts and directly to the final task prediction, so that high performance is maintained alongside interpretability. Across an institutional pediatric brain tumor cohort and a public glioma cohort, the framework delivers competitive performance to unconstrained models while producing reasoning traces validated by an independent neuropathologist. In data-limited regimes, ConceptM$^3$oE improves limited-data performance, increasing macro-F1 from 56.41% to 66.70% at small training sizes compared to non-concept-informed baselines, while also showing faster training convergence consistent with the regularizing effect of concept learning. This work offers a scalable path toward high-performance medical AI that is inherently verifiable and better aligned with the complex decision-making of clinical practice. --- ### VectorArk: Learning Practical Image Vectorization with Rounded Polygon Representation Authors: Tarun Gehlaut, Difan Liu, Charu Bansal, Krutik Malani, Souymodip Chakraborty, Ankit Phogat, Matthew Fisher, Vineet Batra Published: 2026-05-23 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2605.24398v1 Recent vision-language model (VLM)-based approaches have achieved impressive results on image vectorization tasks. However, they are typically evaluated on synthetic benchmarks, where clean SVGs are rasterized at high resolution and then re-vectorized. As a result, these methods generalize poorly to real-world scenarios, such as images with unknown rasterization methods or those generated by text-to-image models. We introduce VectorArk, a new VLM-based model designed for robust and practical image vectorization. VectorArk employs a novel rounded polygon representation that simplifies the learning process while naturally producing smooth, visually appealing primitives. We also propose a degradation model that enhances robustness across diverse and imperfect inputs. Our experiments show that, in contrast to previous methods, VectorArk achieves superior geometric completeness and artifact suppression across multiple datasets, with comprehensive ablations validating the contribution of each component. --- ### Understanding and Mitigating Premature Confidence for Better LLM Reasoning Authors: Jingchu Gai, Guanning Zeng, Christina Baek, Chen Wu, J. Zico Kolter, Andrej Risteski, Aditi Raghunathan Published: 2026-05-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24396v2 Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving reasoning quality directly would require process reward models, but the step-level annotations needed to train them are expensive and scarce. We find such a signal in how the model's confidence evolves during reasoning: premature confidence, the tendency to commit to an answer early and use the remaining tokens to rationalize it, strongly predicts flawed reasoning across tasks and model scales. We exploit this in progressive confidence shaping, a reinforcement learning objective that trains models to update their confidence as they reason rather than commit early -- rewarding gradual confidence growth and penalizing early commitment, with no external labels or reward models. The method improves accuracy and reasoning quality from 1.5B to 8B parameters across arithmetic (Countdown), math (DAPO, AIME), and science (ScienceQA): on Countdown, accuracy improves 3.2x (+42.0pp) and flawed reasoning drops 48pp; on AIME, Pass@64 improves 6.6pp. Consistent with this mechanism, the method also improves faithfulness: on a safety benchmark, our models more transparently surface misleading content in their reasoning traces rather than concealing it. Controlled experiments reveal that the problem and its remedy scale together: premature confidence grows with model size and task difficulty, and so do the gains from addressing it. --- ### Understanding and Mitigating Premature Confidence for Better LLM Reasoning Authors: Jingchu Gai, Guanning Zeng, Christina Baek, Chen Wu, J. Zico Kolter, Andrej Risteski, Aditi Raghunathan Published: 2026-05-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24396v1 Long chains of thought (CoT) from current language models frequently contain logical gaps and unjustified leaps, limiting the gains from additional test-time compute. Improving reasoning quality directly would require process reward models, but the step-level annotations needed to train them are expensive and scarce. We find such a signal in how the model's confidence evolves during reasoning: premature confidence, the tendency to commit to an answer early and use the remaining tokens to rationalize it, strongly predicts flawed reasoning across tasks and model scales. We exploit this in progressive confidence shaping, a reinforcement learning objective that trains models to update their confidence as they reason rather than commit early -- rewarding gradual confidence growth and penalizing early commitment, with no external labels or reward models. The method improves accuracy and reasoning quality from 1.5B to 8B parameters across arithmetic (Countdown), math (DAPO, AIME), and science (ScienceQA): on Countdown, accuracy improves 3.2x (+42.0pp) and flawed reasoning drops 48pp; on AIME, Pass@64 improves 6.6pp. Consistent with this mechanism, the method also improves faithfulness: on a safety benchmark, our models more transparently surface misleading content in their reasoning traces rather than concealing it. Controlled experiments reveal that the problem and its remedy scale together: premature confidence grows with model size and task difficulty, and so do the gains from addressing it. --- ### AvAtar: Learning to Align via Active Optimal Transport Authors: Qi Yu, Ruizhong Qiu, Zhichen Zeng, My T. Thai, Huan Liu, Hanghang Tong Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24395v2 Alignment plays a fundamental role in many machine learning problems, such as multi-network analysis, multimodal learning, and point cloud registration. Recent works increasingly leverage optimal transport (OT) for distributional alignment, whose effectiveness largely depends on sparse supervision that is hard or costly to obtain in practice. Existing works, however, largely overlook how to actively acquire high-quality supervision to improve their alignment performance under OT frameworks. In this paper, we propose a principled active alignment framework for optimal transport alignment called AvAtar. We quantify the informativeness of a candidate by measuring its gradient-based impact on the global alignment result, computed as the gradient propagation from the global alignment result to all possible supervisions of the candidate through the entropy-regularized OT formulation. While differentiating through OT is challenging given its constrained nature, we leverage the adjoint-state method to reformulate the computation to a linear system solvable by the conjugate gradient method with linear complexity and guaranteed convergence. By encoding the global alignment result via effective utility functions, AvAtar is applicable to general alignment problems under the OT framework. Extensive experiments on three representative alignment tasks demonstrate the effectiveness, scalability, and generalizability of the proposed AvAtar. --- ### MX-SAFE: Versatile Inference- and Training-Proof Microscaling Format with On-the-Fly Exponent and Mantissa Bit Allocation Authors: Dahoon Park, Jahyun Koo, Sangwoo Hwang, Jaeha Kung Published: 2026-05-23 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2605.24391v2 As the demand for deep learning grows, cost reduction through quantization has become essential for both training and inference. In 2022, the Open Compute Project (OCP) consortium standardized narrow precision formats for deep learning, called the microscaling (MX) format. The MX format is a hardware-friendly dynamic quantization scheme that effectively reduces the data size by sharing an 8-bit exponent across multiple operands. The MX format can be categorized into two types with their own strengths: (i) MXINT which focuses on a high precision consisting only of mantissa bits and (ii) MXFP which focuses on a wider dynamic range by allowing local exponent bits. In this work, we present a versatile MXFP format, called MX-SAFE (MXSF in short), that adaptively uses two modes, i.e., a wider mantissa mode (FP8 E2M5) and a subnormal FP mode (FP5 E3M2), to support both training and direct-cast inference. Furthermore, we propose a tile-based block design to increase hardware efficiency by reducing the burden of re-quantization process during the training with the MXSF format. Owing to the use of the proposed MXSF format, 0.05%/11.1% and 3.55%/3.57% improvements in accuracy, on average, for inference/full-training compared to MXFP8 E2M5 and MXFP8 E4M3 are observed, respectively. Moreover, we present a training-inference accelerator that supports the MXSF format and it achieves similar accuracy to the BF16 baseline while using 24.9% less total energy consumption. --- ### Learning Laplacian Eigenspace with Mass-Aware Neural Operators on Point Clouds Authors: Zherui Yang, Tao Du, Ligang Liu Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24390v1 The eigendecomposition of the Laplace--Beltrami Operator (LBO) is fundamental to geometric analysis, yet computing its low-frequency eigenmodes remains a significant bottleneck due to the high cost of iterative solvers on large-scale data. To amortize this cost, we introduce the Neural Eigenspace Operator (NEO), a feed-forward framework designed to predict the spectrum directly from point clouds. Crucially, NEO circumvents the ill-posed nature of standard eigenvector regression, which suffers from intrinsic sign flips and rotation ambiguities, by learning the stable, invariant low-frequency subspace instead. Specifically, the network predicts a redundant set of basis functions whose span robustly covers the target eigenspace, allowing for the recovery of accurate eigenpairs via a lightweight Rayleigh--Ritz refinement. To handle irregular sampling, we propose a mass-aware neural operator that incorporates per-point area weights into attention-based aggregation, improving robustness to non-uniform densities and enabling zero-shot generalization across resolutions. Our approach achieves near-linear runtime scaling and substantial wall-clock speedups over iterative solvers at comparable accuracy, and exhibits strong zero-shot transfer to high-resolution point clouds. The resulting eigenpairs support standard spectral geometry tasks, while the raw basis functions provide effective point-wise features for downstream learning. Code: https://github.com/Adversarr/NEO. --- ### Fermi-Dirac machines as quantizations of neurons Authors: Alexander He, Nana Liu, Mark M. Wilde Published: 2026-05-23 Categories: quant-ph, cond-mat.stat-mech, cs.DS, cs.LG arXiv: https://arxiv.org/abs/2605.24386v1 Fermi-Dirac machines were proposed recently as an approach to solving semidefinite optimization problems on quantum computers. Here, we reinterpret them as canonical quantizations of classical neurons. By viewing a classical neuron as an activation function applied to a parameterized classical Hamiltonian, we quantize this model by replacing classical variables with operators whose eigenvalues encode their possible values. This follows the standard approach to canonical quantization in quantum mechanics. Crucially, when the Hamiltonian consists of commuting operators, our construction reduces exactly to a classical neuron. More generally, our approach yields an activation observable, defined as an activation function applied to a parameterized quantum Hamiltonian. The output of this quantized neuron is a random variable with expectation value equal to that of the activation observable with respect to an input state. We develop efficient hybrid quantum-classical algorithms for evaluating outputs and gradients of our quantized neurons, enabling evaluation and training. These algorithms rely on basic primitives that include random sampling, Hamiltonian simulation, and the Hadamard test. We also quantize a whole host of other activation functions, including the smooth rectified linear unit (ReLU), sigmoid linear unit, Gaussian-smoothed ReLU, and Gaussian error linear unit (GeLU), which are known to be useful for deep learning applications. Numerical experiments indicate that neurons based on quantum Hamiltonians can learn functions that classical neurons cannot. We further define a computational decision problem based on Fermi-Dirac neurons and prove that it is BQP-complete, providing complexity-theoretic evidence against efficient classical simulation. Finally, we generalize our approach to continuous quantum variables and sketch two different ways of composing these neurons into networks. --- ### Side-by-side Comparison Amplifies Dialect Bias in Language Models Authors: Kritee Kondapally, Claire J. Smerdon, Pooja C. Patel, Ogheneyoma Akoni, Jevon Torres, Jaspreet Ranjit, Matthew Finlayson, Swabha Swayamdipta Published: 2026-05-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.24384v2 Language models (LMs) can exhibit biases based on variations in their dialects, even in the absence of a dialect label, a behavior known as covert dialect bias. In this work, we quantify covert dialect bias in online discourse by evaluating how LMs associate stereotypical traits (derived from social psychology research on racial bias) with intent-equivalent tweets in Standard American English (SAE) and African-American Vernacular English (AAVE). While prior work shows that LMs associate more negative stereotypes with AAVE when evaluating tweets in isolation, we are surprised to find that this bias is significantly exacerbated when SAE / AAVE tweet pairs are compared side by side, a setting that more closely reflects high-impact decision making contexts in which models are used to rank candidates. The bias only worsens when dialect labels are explicitly specified. This is striking, given the extensive efforts from commercial developers to mitigate bias in their LMs. Encouragingly, we show that counterfactual fairness finetuning can mitigate covert dialect bias for some stereotypical traits, reducing average disparities when evaluating tweets in isolation, however, these improvements do not consistently hold across traits when evaluating SAE / AAVE tweets side by side. Our findings show that existing evaluation settings for covert dialect bias may underestimate its severity, specifically in contrastive settings. Additionally, overt dialect bias remains pronounced even after safety aligned finetuning, indicating that it remains an unresolved problem, and motivates the need for more robust evaluation and mitigation frameworks. --- ### A governance horizon for ethical-use constraints in open-weight AI models Authors: Weiwei Xu, Hengzhi Ye, Haoran Ye, Kai Gao, Vladimir Filkov, Minghui Zhou Published: 2026-05-23 Categories: cs.AI, cs.CY, cs.SE arXiv: https://arxiv.org/abs/2605.24383v1 Ethical constraints on open-weight AI models are both a reflection of societal concerns and a foundation for AI governance policy. They are expected to propagate to downstream derivatives while implemented as voluntary metadata disclosures that must be restated at each generation of reuse. We audit 2,142,823 model repositories on Hugging Face Hub to test whether this disclosure-based governance infrastructure can sustain traceability across deep model lineages. Restriction evidence decays with a half-life of 1.31 derivation steps ($R^2$=0.98), and beyond seven downstream generations at least 80% of descendant models lack sufficient public evidence for a governance determination, a depth boundary we formalize as the governance horizon. Platform-level interventions to restore missing licence metadata reveal that policy design (not enforcement alone) is the binding factor: inheritance-only designs require near-complete enforcement to move the horizon, whereas a mandatory-declaration design that explicitly resolves orphan lineage components shifts the horizon already at moderate enforcement. The structural bottleneck is lineages with no inheritable upstream intent: such orphan components remain undecidable under any inheritance-only policy regardless of enforcement rate, and unresolved upstream nodes additionally create direct downstream undecidability bottlenecks that inheritance rules alone cannot recover. Comparison with PyPI, where governance signals are carried by explicit machine-readable declarations, corroborates that the collapse is topology-specific to open-weight derivation rather than inherent to open ecosystems. These results establish that disclosure-based governance has a shallow, structurally determined reach in open-weight AI, and that achieving deep supply-chain accountability requires provenance mechanisms propagating governance signals through derivation itself. --- ### Assessing the Operational Viability of Foundation Models for Time Series Forecasting Authors: Kavin Soni, Debanshu Das, Vamshi Guduguntla Published: 2026-05-23 Categories: cs.LG, cs.AI, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2605.24381v1 Time series forecasting drives operational decisions in areas like finance, transportation, and energy. While supervised learning approaches achieve strong performance, they require domain-specific training, feature engineering, and ongoing maintenance. Large-scale foundation models have recently emerged as a zero-shot alternative, avoiding task-specific training much like LLMs. In this work, we evaluate foundation models against standard supervised approaches. Rather than focusing solely on aggregate accuracy, we analyze performance across four operational regimes: periodic human-centric systems, physically constrained processes, stochastic financial markets, and heterogeneous demand forecasting. Our results characterize optimal deployment areas. Foundation models perform well in domains with transferable periodic structures and are efficient for cold-start or long-tail scenarios. Conversely, supervised specialists maintain higher precision in systems governed by strict physical constraints. In financial domains, newer foundation models are rapidly closing the performance gap with supervised specialists. We further quantify trade-offs in inference latency, data drift adaptability, and deployment constraints. Finally, we propose a Complexity Router that assigns each series to the optimal model class using empirical features. We demonstrate that this selective routing achieves higher accuracy and significantly lower inference costs compared to deploying a universal foundation model, providing a practical framework for balancing generalization and efficiency. --- ### Distilling Game Code World Model Generation into Lightweight Large Language Models Authors: Tyrone Serapio, Arjun Prakash, Haoyang Xu, Kevin Wang, Amy Greenwald Published: 2026-05-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24375v1 Large Language Models (LLMs) have shown great ability in generating executable code from natural language, opening the possibility of automatically constructing environments for AI agents. Recent work on Code World Models (CWMs) demonstrates that LLMs can translate game rules into Python implementations compatible with solvers like Monte Carlo Tree Search. We study this problem in game settings, where generated environments must implement rules, legal actions, state transitions, observations, and rewards. We refer to these game-specific executable models as Game Code World Models (GameCWMs). However, current approaches to generating code world models rely on frontier models and inference-time refinement loops, limiting accessibility and scalability. This work investigates whether GameCWM generation capabilities can be distilled into smaller models through post-training. We introduce: (1) a curated dataset of 30 games spanning perfect and imperfect information games, (2) a verification framework that evaluates generated code against structural and semantic game properties, and (3) a post-training pipeline combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR). We experiment with Qwen2.5-3B-Instruct and find that SFT can increase syntactic correctness, while RLVR can improve execution-level adherence to game rules, thereby improving Qwen's ability to generate valid GameCWMs in both perfect and imperfect information games. Overall, our pipeline makes Qwen2.5-3B-Instruct more capable of generating valid GameCWMs, thereby offering a scalable path toward automatic environment generation from natural language. --- ### SliceWorld: A Predictive and Controllable World-State Model for CT Report Generation Authors: Yuanhe Tian, Yan Song Published: 2026-05-23 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2605.24371v1 CT report generation (CTRG) requires models to summarize three-dimensional anatomical context and pathological findings from hundreds of axial slices. Existing methods typically learn a direct image-to-text mapping, providing limited mechanisms for modeling how CT evidence evolves across slices or how reports respond to controlled changes in latent lesion-related factors. We propose SliceWorld, a CT-specific world-state framework that treats an axial CT scan as an ordered sequence along the z-axis. SliceWorld encodes prefix CT evidence into factor-aware latent states containing anatomy, lesion, and uncertainty components, and projects these states into world tokens used for multi-step future-slice feature prediction, lesion-factor intervention, and LLM-based report generation. The model is first pretrained on CT slice sequences with predictive, factor-aware, and counterfactual objectives, and is then fine-tuned on paired CT-report data. Experiments on M3D-Cap and CT-RATE show that SliceWorld improves natural language generation metrics and clinically oriented automatic evaluation. Further analyses demonstrate multi-horizon future-slice prediction, measurable factor alignment, reduced-slice robustness, and selective lesion-sensitive report modulation. --- ### GEESE: Genotype-aware End-to-End Spatio-temporal Embedding for Behavioral Phenotyping Authors: Yiran Ding, Yuen Gao, Chunqi Qian, Zijun Cui Published: 2026-05-23 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2605.24370v2 Behavioral phenotyping of genetic animal models currently requires labor-intensive manual feature engineering that limits reproducibility and scalability. We present GEESE, an end-to-end deep learning framework that learns behavioral representations directly from 3D pose dynamics without hand-crafted features. Using a pretrained time series foundation model, we encode movement sequences into a behavioral manifold that supports both behavior classification and genotype prediction. Evaluated across three autism-associated genetic models (CNTNAP2, CHD8, FMR1), our deep learning approach surpasses hand-crafted feature baselines in both tasks, revealing that learned representations capture genotype-specific behavioral signatures. The framework generalizes across genetic backgrounds, and an all-cohort model identifies both genetic background and genotype from movement patterns alone. We further provide HONK, an interactive intelligent tool enabling researchers without programming expertise to perform behavioral phenotyping from pose data through natural language interaction. --- ### Gaussian Rank-Based Neighborhood Degree for Graph Neural Networks in Image Classification Authors: Rafael Mendonça Duarte, Jean Roberto Ponciano, Lucas Pascotti Valem Published: 2026-05-23 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2605.24367v1 The exponential growth of data has intensified the gap between the availability of unlabeled data and the high cost of manual annotation. Graph Neural Networks (GNNs) have emerged as a promising solution, as they exploit relational structures and learn from both labeled and unlabeled data, performing semi-supervised learning. A crucial component of many of these models is degree-based normalization, which influences message propagation but typically assumes uniform importance among neighboring nodes. In image classification, graphs are usually constructed from feature similarity, where treating all neighbors equally may overlook important variations in relevance. Motivated by this gap, we propose GRaNDe (Gaussian Rank-based Neighborhood Degree). This novel degree measure integrates neighborhood ranking with Gaussian distance weighting to better capture node importance. Experiments on five public image classification datasets show consistent accuracy improvements and competitive or superior results compared to state-of-the-art methods. --- ### Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents Authors: Kaiqiao Han, LuAn Tang, Renliang Sun, Peng Yuan, Wei Cheng, Haoyu Wang, Wei Wang, Yizhou Sun, Haifeng Chen Published: 2026-05-23 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2605.24366v1 Large Language Models (LLMs) have been widely adopted in conversational applications. However, their reliance on parametric knowledge limits reliability in real-world scenarios that require dynamic or domain-specific information. Retrieval-Augmented Generation (RAG) addresses this limitation by incorporating external knowledge during generation, but existing text-based and graph-based RAG methods often struggle with noisy or irrelevant contexts. In this work, we propose Structure-aware Retrieval Augmented Generation (SA-RAG), which uses tables as an intermediate structured representation to provide a compact and controllable interface that reduces noise while preserving essential information. We introduce a quality-aware table metadata generation framework that models metadata normalization and effectiveness, improving metadata quality and downstream performance. Furthermore, we explore both training-free and training-based table generation methods. Generation validation and direct preference optimization further improve table quality while maintaining semantic and structural consistency. Experiments on two noisy real-world datasets show that SA-RAG significantly outperforms existing RAG baselines. Our code is publicly available at a public repository. --- ### Multicalibration Boosting: Theory, Convergence, and Transferability Authors: Hanxuan Ye, Hongzhe Li Published: 2026-05-23 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2605.24364v1 Multicalibration extends classical calibration by requiring predictions to be unbiased over a rich collection of functions, encompassing both prediction slices and subpopulations. It has emerged as a powerful framework for fairness, robustness, and reliable prediction, yet the theoretical understanding of multicalibration boosting (MCBoost) remains fragmented and often relies on restrictive assumptions. In this work, we develop a unified and refined perspective on MCBoost that subsumes existing variants, including multiaccuracy, BatchGCP, and BatchMVP. We uncover several phenomena that provide new insights into its practical behavior: even highly accurate and flexible predictors can remain substantially miscalibrated; enforcing multicalibration introduces a calibration-risk trade-off; and early stopping plays a central role in controlling this trade-off. On the theoretical side, we establish a general framework for MCBoost under weaker and more realistic conditions. We show that the boosting iterates converge to a Bregman projection of the population-optimal predictor onto the cumulative span generated by the audit class, thereby explicitly characterizing the function space on which multicalibration is achieved. We further derive convergence rates under different smoothness assumptions, finite-sample guarantees, and principled stopping rules that ensure multicalibration at termination. Finally, we extend the theory of universal adaptability under covariate shift, providing more general transfer guarantees and clarifying when multicalibrated predictors generalize across domains. These results provide a more complete theoretical foundation and practical guidance for multicalibration boosting, positioning it as both a unifying framework and a reliable post-processing approach for modern predictive models. --- ### Treatment Effect Estimation with Differentiated Networked Effect on Graph Data Authors: Xiaofeng Lin, Han Bao, Hisashi Kashima Published: 2026-05-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2605.24358v4 Estimating individual treatment effect (ITE) from observational graph data is crucial for decision-making in the fields such as commerce and medicine. This task is challenging due to interference, where individual outcomes can be influenced by the treatments and covariates of their neighbors. Existing methods attempt to model such interference for accurate ITE estimation. However, a critical issue is often overlooked: differentiated networked effect (DNE), an effect caused by local networks consisting of neighbors with varying importance and scales. Capturing DNE is vital; otherwise, we will end up with imprecise ITE estimation due to an erroneous characterization of interference, which can result in misguided decisions. To address this challenge, we propose a novel interference modeling mechanism that incorporates two partial attention mechanisms and a message amplifier. The partial attention mechanisms automatically estimate the importance of different neighbors in contributing to interference, while the message amplifier adjusts the results of the interference modeling mechanism based on the scale of neighbors, all of which enables the model to capture DNE. Experiments on three real-world graphs demonstrate that our methods outperform existing approaches for ITE estimation from graph data, which corroborates the importance of explicitly capturing DNE. --- ### Refined Analysis of Entropy-Regularized Actor-Critic Authors: Safwan Labbi, Paul Mangold, Daniil Tiapkin, Eric Moulines Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24357v1 In this paper, we study the role of the critic in actor--critic for entropy-regularized, finite, discounted environments. We establish that, when the critic is exact, using the latter as a baseline is a variance-reduction method in a strong sense. In this case, actor--critic with stochastic gradients matches the sample complexity of deterministic policy gradient, reaching an $ε$-optimal regularized value with $\tilde{O}(\log(1/ε))$ samples. In practice, the critic is learned alongside the actor: the variance of the actor update is then influenced by the critic's variance and bias. Specifically, when the critic has a sufficiently small error, the variance reduction and rapid convergence are preserved. This suggests to learn the critic first, keeping it up to date after each actor update, underscoring the crucial role of accurate critic estimation in actor--critic methods. --- ### SparseWorld: Enhancing End-to-End Autonomous Driving via World Models with Sparse Scene Representation Authors: Ruoyu Wang, Jingke Wang, Yukai Ma, Yuehao Huang, Shuangming Lei, Guanglin Xu, Aixue Ye, Yong Liu Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24354v2 Recently, world models have made significant progress in enhancing end-to-end driving systems through both future situation forecasting and improved scene understanding. However, existing driving world models are typically built upon dense scene representations, causing high computational costs and redundant information. In this paper, we present SparseWorld, a lightweight world model that focuses on predicting only the critical layout of the scene, enabling efficient future forecasting for end-to-end driving systems. SparseWorld first performs autoregressive rollout to forecast future map elements and surrounding agents, enabling the model to learn how driving scenarios evolve over time. It then leverages these predicted futures to refine downstream motion prediction and trajectory planning. Specifically, we propose a Sparse Dreamer that anticipates future instances in the latent space through joint temporal and spatial attention. By interacting with predicted future instances, the motion planner captures more accurate motion patterns and generates more informed and safety-aware trajectories. Extensive experiments demonstrate that SparseWorld significantly reduces collision risk and achieves state-of-the-art performance on the open-loop planning metrics of the nuScenes dataset with a collision rate of 0.05\%. Moreover, it substantially outperforms the baseline method in closed-loop planning metrics on the Bench2Drive benchmark. Supplementary material is available at the project page: https://wryzju.github.io/SparseWorld/. --- ### ViViD-5K: Vineyard vision dataset for field-based berry detection and segmentation and grape cluster closure estimation Authors: Xiangzhi Tong, Chengrui Zhang, Mac Flaherty, Andre Matteo Garcia, Dominic Gorman, Jonathan Jaramillo, Justine E. Vanden Heuvel, Yu Jiang Published: 2026-05-23 Categories: cs.CV, q-bio.OT arXiv: https://arxiv.org/abs/2605.24353v1 Cluster closure, defined as the progressive filling of gaps between the berries in a grape bunch, is a key trait in vineyard management, impacting disease risk. However, traditional visual scoring methods are labor-intensive, subjective, and lack temporal resolution. Existing datasets rarely support fine-grained berry-level analysis, limiting the development of robust deep learning models. In this work, we present ViViD-5k, a large-scale in-field Vineyard Vision Dataset containing 5,000 images with dense annotations, including over 648,000 berry centroids and cluster segmentation masks spanning 13 grape varieties. Building on this dataset, we introduce GrapeSAM, a two-stage visual pipeline that combines point-based berry localization with prompt-based segmentation using Segment Anything, followed by transformer-based cluster segmentation. The pipeline enables automated, in-field estimation of cluster closure with minimal supervision. Quantitative results demonstrate strong segmentation and counting accuracy across diverse conditions, while visualizations confirm robustness on both in-domain and out-of-domain samples. This work provides a scalable and objective alternative to manual compactness scoring and supports high-throughput grape phenotyping with enhanced spatial detail. --- ### Partner-Aware Hierarchical Skill Discovery for Robust Human-AI Collaboration Authors: Adnan Ahmad, Bahareh Nakisa, Mohammad Naim Rastgoo Published: 2026-05-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24352v1 Multi-agent collaboration, especially in human-AI teaming, requires agents that can adapt to novel partners with diverse and dynamic behaviors. Conventional Deep Hierarchical Reinforcement Learning (DHRL) methods focus on agent-centric rewards and overlook partner behavior, leading to shortcut learning, where skills exploit spurious information instead of adapting to partners' dynamic behaviors. This limitation undermines agents' ability to adapt and coordinate effectively with novel partners. We introduce Partner-Aware Skill Discovery (PASD), a DHRL framework that learns skills conditioned on partner behavior. PASD introduces a contrastive intrinsic reward to capture patterns emerging from partner interactions, aligning skill representations across similar partners while maintaining discriminability across diverse strategies. By structuring the skill space based on partner interactions, this approach mitigates shortcut learning and promotes behavioral consistency, enabling robust and adaptive coordination. We extensively evaluate PASD in the Overcooked-AI benchmark with a diverse population of partners characterized by varying skill levels and play styles. We further evaluate the approach with human proxy models trained from human-human gameplay trajectories. PASD consistently outperforms existing population-based and hierarchical baselines, demonstrating transferable skill learning that generalizes across a wide range of partner behaviors. Analysis of learned skill representations shows that PASD adapts effectively to diverse partner behaviors, highlighting its robustness in human-AI collaboration. --- ### How Much Structure Do LLMs Need? Evaluating LLMs for Bibliometric Cluster Description Authors: Abraham Camelo-Guerrero, Jairo Diaz-Rodriguez Published: 2026-05-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.24351v1 Large language models (LLMs) can support scientific literature synthesis, but remain prone to hallucinated references, uneven coverage, and weakly grounded thematic organization. We evaluate whether bibliometric structure improves LLM-assisted synthesis by comparing six pipelines for generating cluster descriptions under different levels of evidence and structure. Using 100 published bibliometric analyses, we reconstruct Scopus corpora, extract human-written cluster descriptions, and assess outputs by human alignment, semantic coverage, clustering quality, graph quality, and reference grounding. Results show that LLMs produce descriptions semantically close to human-written ones, but are unreliable when asked to infer bibliometric structure from scratch. Performance improves when bibliometric algorithms define the clusters and the LLM interprets them. Overall, LLM-assisted bibliometric synthesis is most promising as a hybrid workflow in which algorithms provide auditable structure and LLMs generate readable descriptions. --- ### Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs Authors: Meichen Song, Yuhao Wang, Enlu Zhou Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24345v1 In online reinforcement learning, data scarcity creates epistemic uncertainty that makes robustness important early in learning, whereas sufficient exploration is needed to learn the true-environment optimal policy. We study this time-varying robustness--exploration trade-off through a quantile Bayesian risk-aware Markov decision process (BR-MDP), in which the quantile level controls how posterior uncertainty enters the Bellman backup. We characterize this control through an asymptotic normality result for the difference between the quantile BR-MDP value and the value in the true environment. The result implies that upper/lower-tail quantiles induce optimism/pessimism towards epistemic uncertainty, and the magnitude of the optimism/pessimism decreases as data accumulate. Building on this characterization, we propose an online Bayesian risk-aware algorithm with an adaptive quantile schedule that emphasizes robustness early and gradually encourages exploration of less-visited state--action pairs. We establish sublinear Bayesian regret bounds with respect to both the true optimal value and the optimal BR-MDP robust value. Numerical experiments demonstrate strong performance in both exploration-demanding and exploration-costly environments. --- ### Distinguishing Right from Wrong in Debates: Attribution Analysis of Chinese Harmful Memes Authors: Weiming Wang, Junyu Lu, Han Wang, Xiaokun Zhang, Zewen Bai, Bo Xu, Liang Yang, Hongfei Lin Published: 2026-05-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2605.24344v1 Research on harmful meme detection has garnered significant attention, resulting in the development of numerous datasets and methods. However, progress in detecting Chinese harmful memes lags considerably, primarily due to two challenges: first, accurately assessing a meme's harmfulness depends heavily on understanding deep cultural context; second, many memes are semantically ambiguous, making harmfulness highly subjective. To address these issues, we focus on the interpretable detection of Chinese harmful memes by constructing the first Chinese harmful meme explanation dataset, Ex-ToxiCN-MM. This dataset offers opposing interpretations, categorized as "harmful" and "non-harmful", for each meme, aiming to rigorously evaluate a model's ability to discern and comprehend ambiguous, culturally grounded content. We built a specialized knowledge base of Chinese cultural concepts and offensive vocabulary to supply models with essential prior knowledge (C-HarmKB). To address the ambiguity and lack of background knowledge in meme attribution, we have developed a comprehensive attribution analysis framework, RIKE, which includes an Attribution Knowledge Enhancement module (AKE) and a Relative Intent Reasoning module (RIR). Extensive quantitative and qualitative experiments demonstrate that our method outperforms mainstream baseline models across multiple metrics in the task of attributing harmful memes in Chinese. The code, Ex-ToxiCN-MM dataset, and Chinese Harmful Semantic Knowledge Base (C-HarmKB) involved in this study have been open-sourced at https://github.com/wimiw123/Ex-ToxiCN-MM --- ### Adaptive Human-AI Coordination via Hierarchical Action Disentanglement Authors: Adnan Ahmad, Bahareh Nakisa, Mohammad Naim Rastgoo Published: 2026-05-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2605.24343v1 Human-AI collaboration requires agents that can adapt to diverse partner behaviors and skill levels while remaining robust to unseen partners. Existing methods often collapse to a single dominant behavior or learn poorly aligned skills, limiting effective coordination. We propose Intrinsic Action Disentanglement (IAD), a deep hierarchical reinforcement learning (DHRL) framework that learns distinct, partner-aware low-level action sequences conditioned on high-level latent skills. IAD introduces an intrinsic reward that explicitly encourages disentangled action distributions of the agent's low-level policy across skills, yielding an interpretable mapping between high-level decisions and partner-specific behavioral responses. By capturing temporally extended interaction patterns, IAD enables flexible adaptation to heterogeneous partner dynamics under distributional shift. We evaluate IAD in the Overcooked-AI domain across multiple layouts and diverse partner settings, including unseen simulated partners, a human-proxy model trained on human-human gameplay, and real human partners. Results show that IAD consistently outperforms strong baselines and achieves more reliable, adaptive coordination across all settings. --- ### ChainzRule: Sample-Efficient, Robust Deep Learning Across Tabular, NLP, and Vision Tasks Authors: Rowan Martnishn Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24340v1 Production deep learning systems across enterprise domains operate under constraints that academic benchmarks routinely obscure: labeled data is expensive, inference budgets are tight, and models that cannot explain their behavior are difficult to trust and maintain. We present ChainzRule (CR), a neural architecture replacing typical activations with learnable polynomial layers governed by Differential Regularization (DREG), a layer-wise Jacobian penalty computed analytically during the forward pass at standard inference cost. The core claim is that bounding intermediate derivatives forces the network toward low-frequency, structurally stable representations, simultaneously reducing dependence on labeled data volume, improving robustness to distribution shift, and providing a measurable, gradient-based handle on model behavior. Evaluated across five domains, CR achieves $85.71\% \pm 2.01\%$ on Pima Diabetes (statistically superior to SVM and XGBoost), $46.20\% \pm 0.37\%$ on SST-5 sentiment classification with a frozen encoder (superior to RNTN using approximately 5\% of its training data), $55.79\%$ on SST-5 with a fine-tuned BERT backbone (versus BERT-base linear head at $54.9\%$), $70.17\%$ on Yelp Full ordinal regression with 3.2M parameters versus a 10-model average of $66.35\%$, and $+2.32\%$ mean corruption accuracy on CIFAR-10-C. All results with reported $p$-values fall below the $α= 0.05$ threshold after Bonferroni correction. CR maintains a gradient tail ratio $τ$ (p99/mean) of $1.01$--$1.02$ against $1.07$--$1.09$ for all typical activation function baselines across every data fraction, a structural invariant we propose as the mechanistic driver of sample efficiency and a deployment-time proxy for model reliability. --- ### CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning Authors: Ke Sun, Yizhou Zhao, Jiayi Xin, Qi Long, Weijie Su Published: 2026-05-23 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2605.24331v1 Context or prompt-level reweighting has emerged as a central algorithmic lever in Reinforcement Learning with Verified Rewards (RLVR) for improving the reasoning capability of large language models, yet the principle determining what constitutes an optimal weighting remains poorly understood. We address this gap by formulating prompt reweighting as a functional derivative of a utility functional defined in the pass-rate function space, yielding a unified optimality framework that accommodates existing schemes, including REINFORCE and GRPO. Building on this optimality framework, we propose a distribution-aware prompt reweighting approach, called CurveRL, based on a quantile coordinate transform, in which the weight assigned to each prompt depends not on the absolute value of pass rates but on its rank and density to reflect the distributional structure of the pass rates in the learning dynamics. Extensive experiments across multiple benchmarks demonstrate that our proposed CurveRL consistently outperforms GRPO and other RLVR baselines. Our study identifies context-distribution control as a principled axis for analyzing and designing prompt-reweighted RLVR algorithms. The code is released in https://github.com/zhyzmath/CurveRL. --- ### Interdomain Attention: Beyond Token-Level Key-Value Memory Authors: Naoki Kiyohara, Harrison Bo Hua Zhu, Riccardo El Hassanin, Zhuo Sun, Wenlong Chen, Samir Bhatt, Yingzhen Li Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24330v1 Transformers and deep state space models (SSMs) sit at opposite ends of a basic design choice: attention routes each query through a growing key-value (KV) cache by content-based matching at quadratic cost, while deep SSMs compress context into a fixed-size recurrent state that is not directly addressed by query-key matching. We propose Interdomain Attention, which integrates an SSM into an attention module through kernel methods: an attention kernel is approximated by a finite feature map, the resulting key features and values are projected onto a shared set of basis functions maintained by a single SSM recurrence, and each query attends to the compressed coefficients through its own feature map, recovering query-conditioned attention over a fixed-size state. The scalable layer is a learned relaxation of this derivation, and we validate its components through ablations. In a 125M to 1.3B autoregressive language-modeling study on FineWeb-Edu at matched recurrent-state budget, Interdomain Attention improves on an SSM token mixer at every scale, surpasses a same-recipe softmax baseline at 1.3B on validation perplexity and on the eight-task commonsense suite, and inherits the length-flat behavior of its fixed-state core out to 3.5x the training context. Ablations indicate that the query-conditioned projection is the main source of the gain. --- ### ScaleAcross Explorer: Exploring Communication Optimization for Scale-Across AI Model Training Authors: Minghao Li, Alicia Golden, Samuel Hsia, Michael Kuchnik, Adi Gangidi, Xu Zhang, Ashmitha Jeevaraj Shetty, Zachary DeVito, Weiwei Chu, Dong He, Haoci Zhang, Yuchen Hao et al. Published: 2026-05-23 Categories: cs.DC, cs.AI, cs.NI arXiv: https://arxiv.org/abs/2605.24326v1 The rapid scaling of large language model training requires distributing GPU resources across multiple data center buildings and regions. We refer to such paradigm as "scale-across" training. As infrastructure expands, the system design space becomes increasingly intricate, encompassing new model architectures, hardware heterogeneity, and evolving communication patterns. Drawing from Meta's production experience, we highlight the complexities of deploying training jobs across a few data centers housing hundreds of thousands of GPUs. To accelerate exploration of the large design space and to enable efficient training for frontier model development, we conduct in-depth characterization of three key design dimensions: parallelism placement, parallelism scheduling, and network layer technologies. We then propose ScaleAcross Explorer, an optimizer that considers the interplay of design dimensions and holistically optimizes scale-across training. Testbed experiments and simulations demonstrate up to 64.62% training speedups over production configuration and up to 37.59% training speedups over the state-of-the-art baseline across a wide range of design points. --- ### A Matched Spectral Benchmark of Quantum Inspired Feature Maps Authors: Toheeb Ogunade, Taofeek Kassim, Etinosa Osaro Published: 2026-05-23 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2605.24324v1 Quantum machine learning is often motivated by the idea that quantum systems can expose useful high-dimensional structure that is difficult to access with classical models. We isolate one central component of this claim: the fixed data-encoding map. Amplitude, angle, and basis encoding are evaluated as deterministic feature maps for classical supervised learning under matched output dimensionality and strong classical controls. The benchmark compares these encodings against raw linear models, random Fourier features, polynomial features, PCA, RBF SVMs, and shallow neural networks across diverse classical datasets. Rather than treating performance as a single endpoint, we analyze the geometry of each representation through effective rank, condition number, centered kernel alignment, predictive performance, and practical overhead. The resulting picture is mechanistic: amplitude encoding can remove magnitude information through unit-sphere normalization, angle encoding can become geometrically redundant with raw linear features, and basis encoding can impose a binary Hamming geometry that is poorly aligned with smooth decision structure. These findings do not argue against quantum computation, however, they show that fixed quantum-inspired encoding geometry alone is not a reliable source of machine-learning advantage on classical data. --- ### Causal Physics Steering in Video World Models via Concept Activation Vectors Authors: Nahid Alam Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24322v1 Video world models learn representations of physical dynamics, but controlling their physical expectations at inference time remains an open problem. Recent interpretability work identified a Physics Emergence Zone (PEZ), a group of middle transformer layers in VideoMAE where physical plausibility is represented separately from other visual features. However, it remained unclear whether this structure could be used to directly control the model's physics reasoning. We present physics steering, a training-free method that uses the weight vector of a linear probe at a PEZ layer as a Concept Activation Vector (CAV) and injects it into hidden states during inference. This shifts the model's physical expectations without changing any model weights. On the IntPhys benchmark, this intervention reliably shifts the model's plausibility judgment in either direction, depending on the steering sign. The effect appears only when the intervention is applied within the Physics Emergence Zone, suggesting that the relevant physics representation is localized there. We further find that physics is encoded separately from motion direction, and that different intuitive physics principles occupy distinct directions within this representation space. Together, these results show that physical reasoning in VideoMAE is not only readable, but also directly steerable. --- ### Unified 3D Scene Understanding Through Physical World Modeling Authors: Wanhee Lee, Klemen Kotar, Rahul Mysore Venkatesh, Jared Watrous, Honglin Chen, Khai Loong Aw, Daniel L. K. Yamins Published: 2026-05-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2605.24321v1 Understanding 3D scenes requires flexible combinations of visual reasoning tasks, including depth estimation, novel view synthesis, and object manipulation, all of which are essential for perception and interaction. Existing approaches have typically addressed these tasks in isolation, preventing them from sharing a common representation or transferring knowledge across tasks. A conceptually simpler but practically non-trivial alternative is to unify these diverse tasks into a single model, reducing different tasks from separate training objectives to merely different prompts and allowing for joint training across all datasets. In this work, we present a physical world model for unified 3D understanding and interaction (3WM), formulated as a probabilistic graphical model in which nodes represent multimodal scene elements such as RGB, optical flow, and camera pose. Diverse tasks emerge from different inference pathways through the graph: novel view synthesis from RGB and dense flow prompts, object manipulation from RGB and sparse flow prompts, and depth estimation from RGB and camera conditioning, all zero-shot without task-specific training. 3WM outperforms specialized baselines without the need for finetuning by offering precise controllability, strong geometric consistency, and robustness in real-world scenarios, achieving state-of-the-art performance on NVS and 3D object manipulation. Beyond predefined tasks, the model supports composable inference pathways, such as moving objects aside while navigating a 3D environment, enabling complex geometric reasoning. This demonstrates that a unified model can serve as a practical alternative to fragmented task-specific systems, taking a step towards a general-purpose visual world model. --- ### Omissive Bias in Religious Representation: Benchmarking LLM Answers to Everyday Ethical Decision-making Authors: David Wingate, Sheryl Carty, Joshua Coates, Daniel Feldman, Nancy Fulda, Larry Howell, Brett Israelson, Dallin Jacobs, Jonathan Karr, John Paul Kimes, Elisabeth Kincaid, Paul Martens et al. Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24319v1 As large language models become a default source of guidance on personal, moral, and existential questions, it matters whether they draw on the religious frameworks that have historically shaped such reasoning, or systematically omit them. In this paper, we ask a deliberately narrow question: when posed an everyday ethical question for which religious perspectives may be valuable, do LLMs invoke religion at all? In contrast to benchmarks that look for the presence of political leanings or social bias, we look for the absence of religious representation as a dimension of value alignment and bias in LLMs. We term this ``omissive bias.'' To measure omissive bias, we contribute the AllFaith Religious Representation Benchmark: 150 ethically and personally salient questions, sourced from in-the-wild chat transcripts and faith-community contributors, paired with an LLM-as-judge rubric that gives full credit for any mention of a religion, a religious practice, or a religious leader. The questions are not themselves about religion--they are open-ended questions about grief, forgiveness, relationships, purpose, and honesty, where religion is one valuable perspective among several. We also run a human-subjects survey to compare LLM behavior against human expectations. Evaluating 27 models, we find that LLMs consistently underrepresent religion relative to human expectations. The omission is asymmetric: models invoke religion more readily for abstract existential questions (meaning, death, truth) than for the practical personal situations--grief, marriage, family conflict, addiction--where many people most rely on it. It is not our purpose to adjudicate which values LLMs should hold. We argue, more modestly, that current LLM responses overlook critical opportunities to reflect religious frameworks that many people draw on when navigating personal and ethical challenges. --- ### Scaling Laws for Dynamic Mini-Batch SGD in Sketched Linear Regression Authors: Ziyan Chen, Zhongzhu Zhou, Ding-Xuan Zhou Published: 2026-05-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2605.24316v3 Mini-batching is central to large-scale optimization, yet its role in statistical scaling laws remains limited. We study one-pass and multi-pass batch SGD for sketched linear regression under power-law spectral and source conditions. Our analysis reveals a two-horizon phenomenon induced by warmup--stable--decay schedules: deterministic learning is governed by the full optimization trajectory, while stochastic error retains only a shorter terminal memory. For dynamic batch schedules, the individual batch sizes enter through influence-weighted summaries that measure how strongly each update affects the final risk. Consequently, batching leaves the approximation and optimization-bias laws unchanged at a fixed update horizon, but controls the one-pass variance and the multi-pass fluctuation around full-batch gradient descent. We obtain matching one-pass variance bounds and nearly matching multi-pass fluctuation bounds, recover static-batch and full-batch behavior as special cases, and derive an oracle square-root rule for allocating a fixed iteration budget. These results identify WSD horizon separation and final-risk influence as the mechanisms governing dynamic mini-batch scaling. ---