# Research Papers — 2026-06 · bundle page 234 of 260 > Full-text markdown of papers #11651–11700 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/234 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/233.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/235.md) ### Collaborative Disagreement Resolution for Scalable Oversight Authors: Yuyang Jiang, Chacha Chen, Teng Wu, Liwen Sun, Han Liu, Shi Feng, Chenhao Tan Published: 2026-06-02 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.01251v1 Debate, where AI agents argue opposing positions, has emerged as a key approach to scalable oversight. However, debate faces a fundamental tension: models are incentivized to be persuasive to the judge, which may not always align with epistemic honesty. In this work, we propose an alternative paradigm: disagreement resolution, which reframes the interaction mechanism from adversarial debate to collaborative truth seeking. Drawing on principles from human mediation and conflict resolution, where mediators facilitate dialogue to help disputing parties reach consensus rather than adjudicating between them, we design an automated pipeline that adapts these strategies to AI oversight. Unlike standard debate where models argue for fixed positions, our pipeline directs models to collaboratively identify points of disagreement, examine the evidence for conflicting claims, and converge toward consensus or isolate the specific ''crux'' of their disagreement. We find that Disagreement Resolution consistently helps non-expert models identify the truth, achieving 62.1% judging accuracy compared to 49.2% for standard debate. Our results provide encouraging empirical evidence for rethinking the scalable oversight protocol from adversarial persuasion to collaborative truth-seeking. --- ### Structuring the Space of Sociotechnical Alignment Authors: Esra Dönmez, Agnieszka Falenska Published: 2026-06-02 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.01250v1 Sociotechnical alignment concerns the social desirability of AI behavior and is thus inherently normative, not merely technical. While NLP research increasingly addresses its technical aspects, it often leaves underspecified what such "social desirability" entails. We argue that this reflects a fundamental gap: the absence of a systematic way to specify how sociotechnical alignment defines, justifies, and evaluates socially desirable AI behavior. To address this gap, we introduce a human-centered framework for specifying sociotechnical alignment. We draw on social-scientific accounts of sociobehavioral desirability to ground the basis for behavioral desirability judgments and use this framework to analyze how alignment is specified in practice. Our systematic literature review identifies recurring patterns: normative concepts grounding desirability judgments are often unspecified or conflated with alignment targets for (desired) system behavior, target populations are underdefined, and design choices are rarely theoretically justified. These findings point to a lack of conceptual specificity that limits cumulative progress. We therefore offer recommendations that link social-scientific frameworks to alignment design choices, supporting more conceptually precise approaches to sociotechnical alignment. --- ### A Practice Auditing Framework for Large Language Model Use: Collective Empiricism, Pseudo-Rational Cognition, and Governance of AI-Generated Content Authors: Yang Zhao, Yingshuo Li, Zeyu Zhang Published: 2026-06-02 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.01248v1 Large language models are increasingly used for knowledge acquisition, code generation, academic writing, and agent-based automation. In these settings, users may obtain highly structured answers, plans, and judgments without sufficient domain practice. This paper proposes a practice auditing framework for LLM use and AI-generated content governance. It introduces collective empiricism to describe how LLMs compress and reorganize large-scale human experience into outputs that appear empirical and rational, and pseudo-rational cognition to describe how users may mistake AI-generated structured expression for their own rational understanding. The paper analyzes AI subjectivity illusion, subjectivity structures in input materials, template loops in AI-AI conversations, statistical misjudgment in AIGC detection, and memory pollution when generated content enters future contexts, long-term memory, retrieval spaces, or agent skill systems. To reduce these risks, the paper proposes an auditing process based on requirement definition, problem-boundary identification, evidence-source auditing, practical validation, reverse questioning, logging, version management, rollback, and renewed cognition. The framework does not reject AI productivity; it argues that LLM outputs should be returned to verifiable, reproducible, and intervenable processes of practice. The paper provides a conceptual and auditable framework for cognitive risks in LLM interaction, AI-generated content governance, long-term memory systems, and human-AI interaction. --- ### Agentic Safety is an Epistemic Property, Not a Behavioral One Authors: Charles L. Wang, Keir Dorchen, Peter Jin Published: 2026-06-02 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.28347v1 Contemporary AI safety spans pre-training interventions, post-training alignment, deployment-time controls, monitoring, and red-teaming. These methods are necessary, but they primarily certify snapshots of system behavior. As AI systems become more capable, dynamic, embodied, and self-improving, this snapshot view becomes incomplete: safety depends not only on whether a system behaves acceptably now, but whether it remains correctable as it learns, adapts, acts, and modifies itself over time. This paper argues that safety should therefore be treated as an epistemic property of the evolving learner, not merely a behavioral property of the current policy. We introduce teachability as the capacity to preserve future corrective leverage under bounded human, institutional, or environmental intervention. We argue that advanced systems can retain visible competence while eroding the representational, algorithmic, or meta-decision conditions needed for future correction. Safe advanced AI systems must not only behave acceptably now; they must remain teachable later. --- ### Auditing LLM-Governed Social Robots with Culture-Specific Moral Gradients Authors: Carmen Ng, Gjergji Kasneci Published: 2026-06-02 Categories: cs.RO, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2606.28345v1 LLM-governed social robots increasingly decide who receives real-world assistance first. As prioritization norms vary across cultures by age, status, and group size, failure to calibrate pluralistically can scale into unequal access. Yet LLM moral audits remain English-centered, rarely test embodied contexts, leaving pluralistic calibration as an urgent diagnostic gap amid intensifying LLM-robot deployment. We introduce a gradient-based audit framework for multilingual evaluation of LLM moral trade-off behavior against cultural preference gradients. Grounded in nine cross-domain social robotics reviews (>8,000 papers), we derive symmetry-controlled scenarios across care, education, and services, translating the Moral Machine Experiment's "whom to spare" into "whom to assist first" dilemmas with preserved identity trade-offs (many vs. few; young vs. old; higher vs. lower status). We audit four LLMs across four country-language pairs in four prompting regimes (57,600 decisions), benchmarked against country-specific MME preference gradients. Ordinal concordance tests whether models differentiate cultural contexts; a governance typology maps vulnerabilities in gradient differentiation, directional tendency, and deliberation. We find persistent, culturally asymmetric gradient tracking failures that prompting alone cannot reliably correct: quality calibration is nearly twice as strong for Western-language decisions as for Chinese and Japanese; high determinism in majority-first trade-offs often erases cross-cultural gradients; partial sensitivity to age- and status-based norms risks sidelining minorities. Prompting effects are uneven; only contrastive exemplars yield consistent gains, while reasoning-only prompts can worsen tracking. Our results motivate multilingual, pluralistic audits as an LLM-robot pre-deployment gate and suggest model factors are a more robust lever than prompting alone. --- ### MAGNIFIED: RL Fine-tuning of Multimodal Large Language Models for Motion Planning Authors: Letian Chen, Yiren Lu, Justin Fu, Yichen Xie, Runsheng Xu, Jyh-Jing Hwang, Ben Sapp, Drago Anguelov Published: 2026-06-02 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.20641v1 Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in semantic understanding and common sense reasoning, making them promising candidates for solving planning problems in autonomous driving. However, the next-token text prediction objectives traditionally used in pre-training and supervised fine-tuning (SFT) of MLLMs may fall short of fulfilling the planning objectives for autonomous vehicles. The next-token prediction objective merely encourages per-token imitation in text, often irrespective of multi-step consequences and the alignment with crucial planning considerations such as giving space to other road actors. To overcome these limitations, we propose a reinforcement learning fine-tuning (RLFT) approach, MAGNIFIED, that aligns the MLLM-based driving agent with planning objectives by learning from token-level rewards. By mapping a sequence of predicted tokens to corresponding vehicle trajectories and learning from planning rewards, MAGNIFIED optimizes for the true planning objectives rather than focusing solely on token prediction accuracy, enabling the model to refine its understanding of the planning task beyond simple imitation. We validate our approach on the Waymo Open Motion Dataset with a novel setup incorporating rasterized birds-eye views and tokenized trajectories as inputs and planning-oriented outputs. An initial SFT phase establishes a strong baseline in outputting plan trajectories as sequences of X-Y coordinates in text, while subsequent RL fine-tuning substantially enhances planning performance relative to the SFT baseline (demonstrating over a 10.5% reduction in overlap rate and a 38.9% reduction in off-road rate), underscoring the potential of RLFT on MLLMs to achieve vehicle planning that is better aligned with compliant, comfortable, and efficient driving. --- ### An LLM-Explainable DRL Framework for Passenger-Directed Autonomous Driving Authors: Ouided Braoui, Meriem Bouali, Nadir Farhi Published: 2026-06-02 Categories: cs.AI, cs.LG, math.OC arXiv: https://arxiv.org/abs/2606.20640v1 Autonomous vehicles offer the potential for safer and more efficient mobility, yet public trust remains limited due to the lack of transparency in their decision-making. This work addresses this issue by combining deep reinforcement learning (DRL) for adaptive driving control with large language model (LLM)-based explainability modules designed to communicate agent behavior to passengers. DRL agents were trained in simulation using a Dueling Double Deep Q-Network to follow distinct driving requests: \textit{fast}, \textit{comfort}, and \textit{stop}. They demonstrated stable learning, safe compliance with traffic rules, and reliable switching between modes within a single trip. In parallel, LLM modules were introduced to interpret passenger requests, determine when explanations were needed, and generate concise, safety-oriented justifications. Results show that this framework, serving as a proof of concept for integrating RL decision-making and LLMs, balances safety, adaptability, and explainability, and is most effective when requests are delayed or overridden due to safety constraints. --- ### RIZZ: Routing Interactions to Near Zero-Interference Zones for Continual Adaptation of Black-Box Agents Authors: Sonali Goel, Pranav Vaidhyanathan, Lucas Schorling, Natalia Ares, Maike Osborne Published: 2026-06-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.20638v1 Large language models are increasingly deployed as long-lived agents that must adapt across users, tasks, domains, modalities, and feedback regimes without access to model weights. Existing black-box adaptation methods typically optimize a single prompt, maintain an undifferentiated memory, or rely on repeated rollout-heavy search. However, these designs struggle when streams of input are nonstationary, feedback is sparse, and failures from one task family can contaminate behavior on another. We introduce RIZZ (Routing Interactions to Near Zero-interference Zones), a continual adaptation framework for compound language-model systems that learns entirely through verifier-gated memory, routing, and prompt compilation. RIZZ organizes input streams into dynamically spawned memory branches. At inference time, either while online or offline, a context-aware router selects or creates a branch that retrieves branch-local, global, graph-structured, and working-memory context, which is compiled into a bounded prompt together with retrieved task evidence. After the model acts, task verifiers score the output, and only verified interactions can update memory, promote reusable rules, demote harmful rules, or create anti-patterns. This yields a black-box agent that improves through persistent natural-language feedback while explicitly controlling interference. RIZZ targets the regime where adaptation must occur online under context budgets. Finally, we demonstrate the effectiveness of our framework against state-of-the-art baselines on competitive benchmarks. --- ### Constituency Optimisation Through Hamiltonian Representation Of Mandates (COTHROM): Algorithmic Redistricting of Irish Election Boundaries Authors: Ruaidhrí Campion, Matthew Fenlon, Joshua Cooney Mercedal, Casey Farren-Colloty, Eliza Somerville, Michael A. J. Mitchell Published: 2026-06-02 Categories: cs.AI, cond-mat.stat-mech, cs.CY, physics.soc-ph arXiv: https://arxiv.org/abs/2606.20637v1 Electoral redistricting in Ireland's Proportional Representation Single Transferable Vote (PR-STV) system faces the challenge of selecting an optimally representative set of electoral boundaries from an enormous set of possible configurations, and where ``representative'' is a delicate balance of constitutional objectives that are often in tension with one another. We present the first computational framework for Irish electoral redistricting that systematically optimises across multiple constitutional requirements while making trade-offs explicit and quantifiable. The electoral redistricting problem is parsed using statistical physics, where constitutional objectives are considered as terms in a Potts Hamiltonian. Markov Chain Monte Carlo (MCMC) methods and simulated annealing are employed to minimise this objective function, systematically exploring this configuration space, with coupling constants as proxies for objective weightings. Multi Criterion Decision Analysis (MCDA) and Pareto Optimality is then utilised to remedy the ambiguity in choosing a certain objective weighting combination over others. With respect to proportional representation and compactness objectives evaluated in County Cork, COTHROM consistently improves on the existing legal constituency boundaries for a range of objective weightings. --- ### SkillHarness: Harnessing Safe Skills for Computer-Use Agents Authors: Yurun Chen, Biao Yi, Keting Yin, Shengyu Zhang Published: 2026-06-02 Categories: cs.AI, cs.CL, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2606.20636v1 Computer-Use Agents (CUAs) are increasingly deployed in dynamic interactive environments, creating a growing need for continual skill learning during interaction. Recent approaches address this challenge by learning reusable skills from successful trajectories. However, these skill learning methods largely assume static and safe environments, overlooking risks from adversarial interactions (e.g., prompt injections) and environmental dynamics (e.g., pop-ups). In dynamic settings, such assumptions can lead to risky skill learning and brittle execution, undermining the reliability of CUAs. This raises the question: how can CUAs learn and use skills safely in dynamic environments? To address this problem, we propose SkillHarness, a framework for safe skill harnessing in dynamic environments. SkillHarness moves beyond static skill abstractions by modeling skill learning and utilization as a safety-constrained interaction process. Specifically, we introduce the skill boundary that leverages multi-source supervision signals to identify safe skills from interaction trajectories, and construct self-improving safety constraints throughout the skill lifecycle. In addition, SkillHarness introduces selective skill reuse, where tasks are guided to decompose according to context and completed through the selective activation of skill subsets. Our experiments demonstrate that SkillHarness significantly reduces the unsafe rate of learned skills by 57.1% and consistently improves execution stability under dynamic environmental changes, outperforming existing baselines. --- ### HorusEye: Language as Dynamic Attention for Emergency Visual Analysis Authors: Armel Yara Published: 2026-06-02 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.14741v2 We introduce HorusEye, Language as Dynamic Attention for Emergency Visual Analysis. Our investigation followed five stages. The first one is benchmarking RefCOCO-Degraded, a dataset of 15,244 images (3,811 base images x 4 conditions: Clean, Fog, Smoke and Thermal) with systematic visual degradation. Through four research questions, we evaluate multiple VLMs (Gemini, Qwen2-VL, BLIP-2, LLaVA, Kosmos-2) across visual grounding the second stage, language feedback recovery the third one, health VQA tasks the fourth, and hallucination analysis the final stage. Our key finding is that language feedback effectiveness is model-dependent: Gemini achieves +47.3% improvement in thermal conditions through iterative language feedback, while Qwen2-VL shows -5.1% degradation under the same protocol. We also identify the 'Thermal Paradox' where cropping strategies that improve RGB performance catastrophically fail in thermal imagery. Furthermore, BLIP-2 uniquely hallucinates more under degradation, making it unsuitable for emergency deployment --- ### GridVQA-X: A Framework for Evaluating Multimodal Explainability Methods Authors: Sujay Belsare, Sudarshan Nikhil, Sushant Kumar, Ponnurangam Kumaraguru, Chirag Agarwal Published: 2026-06-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.14740v1 With the increasing development of Vision-Language Models, it becomes imperative that their predictions are readily explainable to relevant stakeholders. However, the field of explainability has not kept pace with the multimodal surge. While recent Multimodal Explainable AI (MxAI) methods generate explanations to attribute the interaction between different modalities, current evaluation protocols lack the ground truth required to distinguish between true cross-modal reasoning (e.g., spatial composition) and shallow cross-modal shortcuts (e.g., Bag-of-Words attribute matching). It remains unknown whether MxAI methods faithfully capture synergistic interactions or merely hallucinate reasoning on models acting as simple feature detectors. In this paper, we introduce GridVQA-X, the first diagnostic framework specifically designed to evaluate cross-modal explainability. Unlike natural datasets, GridVQA-X leverages a closed-world synthesis logic to generate unique, mathematically guaranteed explanations. We utilize this controlled environment to train paired ground-truth models on identical architectures: $M_{\text{pure}}$, which learns robust spatial-relational reasoning and $M_{\text{spur}}$, which is structurally forced to rely on cross-modal shortcuts. This behavioral divergence creates a rigorous testbed: a faithful explainer must report distinct reasoning pathways for each model. Our findings reveal that widely used methods fail to distinguish between models relying on genuine spatial-relational reasoning and those exploiting cross-modal shortcuts, highlighting a critical gap in capturing true cross-modal synergy and misrepresenting how multimodal models actually make decisions. --- ### An RRAM-based Hardware Implementation of a Radial Basis Function Neuron for Edge Classifiers Authors: Georgios Papandroulidakis, Shady Agwa, Themis Prodromakis Published: 2026-06-02 Categories: cs.ET, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2606.14739v1 The deployment of modern machine learning (ML) solutions on resource-constrained edge devices highlights implementation challenges. This is especially true for extreme edge applications that include safety-critical components, such as autonomous navigation tasks. This paper demonstrates an artificial neural network (ANN) design leveraging Metal-Oxide Resistive RAM (RRAM) -based Analogue Content Addressable Memory (ACAM) as an efficient hardware substrate for performing metric-based classification and online adaptation on the edge. The proposed design is based on a custom Template piXeL (TXL) cell used for building the ACAM module, where each TXL cell acts as a configurable receptive field neuron. These cells employ a Radial Basis activation function to calculate the distance of an input from the programmed receptive field. The TXL can be organised into dense arrays for calculating the distance of a high-dimensional input against all stored prototypes, effectively performing fast and energy efficient similarity search. This hardware engine enables on-the-fly learning, where the receptive field parameters can be tuned to track domain shift. Through simulation of the proposed TXL-RBF classifier we can achieve 89.1\% accuracy on the MNIST dataset while consuming 185fJ per cell per operation when operating at 100MHz. --- ### Learning Topological Representations for Molecular Dynamics Authors: Dominik Geng, Florian Graf, Martin Uray, Roland Kwitt Published: 2026-06-02 Categories: q-bio.BM, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.14737v1 Molecular dynamics (MD) simulations generate trajectories in a high-dimensional configuration space whose analysis critically depends on molecular descriptors, typically handcrafted observables or learned kinetic embeddings. Designing descriptors that are both expressive and broadly applicable, however, remains challenging. We study persistent homology (PH) as a general-purpose representation for MD and introduce the masked Flood complex, a protein-tailored modification of a recently introduced simplicial complex construction that emphasizes inter-residue structure at low computational cost. Vectorized persistence diagrams then provide information-rich, geometry-aware summaries of protein conformations, which we evaluate on protein class prediction, frame-level observable regression, and Markov state model (MSM) estimation from learned low-dimensional coordinates in a single shared representation space. Results on the mdCATH dataset show that PH-based descriptors are competitive across tasks, with masked Flood PH yielding the most consistent overall performance. Further, when using topologically-informed MSMs as a drop-in replacement within the recent MarS-FM framework for generative modeling of protein conformations, we obtain consistently better ensemble statistics than MSMs based on physical observables. Finally, we explore the transferability of the generative model to qualitatively different, fast folding, proteins. --- ### UtVAA: Ultra-tiny Vision Transformer with Affix Attention for Mobile Image Classification Authors: Romiyal George, Sathiyamohan Nishankar, Selvarajah Thuseethan, Roshan G. Ragel Published: 2026-06-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.14735v1 Vision Transformers (ViTs) have demonstrated strong representation capability in image classification. However, their quadratic self-attention complexity and large parameter counts limit deployment on resource-constrained mobile and edge devices. This paper introduces UtVAA, an ultra-tiny Vision Transformer architecture designed for efficient visual recognition under strict computational budgets. It incorporates a novel Affix Attention block that combines depthwise-pointwise local feature extraction, linear self-attention, coordinate attention for spatial dependency modelling, and a lightweight ternary fusion strategy to integrate local and global representations. In addition, Dilated Bottleneck blocks expand the receptive field using dilated depthwise separable convolutions while maintaining low FLOPs and stable optimisation through residual connections. UtVAA is implemented in scalable Tiny, Medium, and Large variants, with the smallest model containing 204.67K parameters and 53.95M FLOPs. Experimental results on CIFAR-10, CIFAR-100, PlantVillage-Tomato and SLIF-Tomato datasets show that UtVAA achieves competitive accuracy within a sub-million-parameter regime. Overall, the results demonstrate that transformer-based vision models can be redesigned into ultra-tiny architectures without significant loss in discriminative performance, making UtVAA suitable for mobile and edge deployment. Code is available at https://github.com/romiyal/UtVAA --- ### BRIDGE: Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks Authors: Ziyang Dong, Shanwen Tan, Hengchuang Yin, Wei Liu, Yifan Wang, Siyu Yi, Jiancheng Lv, Wei Ju Published: 2026-06-02 Categories: q-bio.MN, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.14734v1 Motivation: Gene regulatory network inference from single-cell RNA sequencing (scRNA-seq) data is important for uncovering cell-state-specific transcriptional programs. However, scRNA-seq measurements are sparse and noisy, and experimentally validated TF-target interactions remain limited, making reliable inference challenging. Although graph neural networks have advanced GRN prediction, existing methods often rely on biologically unconstrained graph augmentation, such as random edge perturbation, and insufficiently control information transfer between genes and cells. These limitations may distort regulatory structures and weaken robustness under noisy and weakly supervised settings. Results: To address these issues, we propose an innovative framework named Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks (BRIDGE). BRIDGE extracts gene and cell representations from the expression matrix and its matrix dual, and performs contrastive learning in the gene space and cell space between self and neighbors across the co-expression-refined regulatory view and the original graph. It then applies heterogeneous gated encoding to adaptively regulate information transfer between genes and cells, enabling robust transcription factor-to-target gene prediction. Experiments on benchmark datasets spanning three network types and seven cell types show that BRIDGE achieves state-of-the-art AUROC and AUPRC in most settings. In particular, on Specific networks, BRIDGE improves average AUPRC by 5% over the second-best baseline, GCLink. In cross-cell-type few-shot transfer, BRIDGE consistently outperforms GCLink and GENELink across all six target cell types. A case study on hESC further supports the biological relevance of the predictions, with 9 of the top 10 and 46 of the top 100 novel TF-target interactions validated by ChIPBase. --- ### Steady-Forcing: Balancing Spatial Persistence and Motion Continuity in Long-Horizon Nature Video Diffusion Authors: Matiur Rahman Minar, Seunghun Oh, GangHyeon Jeong, Unsang Park Published: 2026-06-02 Categories: cs.CV, cs.AI, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2606.14732v1 Autoregressive video diffusion models enable streaming generation but often degrade over long rollouts: static scene layouts drift, while mechanisms that improve spatial stability tend to suppress motion, causing natural flows such as water, fire, or smoke to stagnate. We study this stability-motion trade-off in fixed-camera long-horizon nature video generation, where the two failure modes can be more clearly separated than in moving-camera settings. We propose Steady-Forcing, a memory and training framework combining a persistent visual anchor (V-Sink), an exponential moving-average motion memory (EMA-Sink), block-relative temporal encoding, periodic cache purification, and distillation from a Wan2.1-14B teacher with motion-rewarded priors under task-focused configurations. Together, these components are designed to preserve background identity while sustaining visually plausible fluid dynamics over multi-minute autoregressive rollouts. Evaluations across seven baselines show that Steady-Forcing improves long horizon background consistency and imaging quality, while a blind user study indicates stronger perceived stability and motion continuity. The benchmark evaluation further suggest that generic VBench aggregate scores under-penalize fixed-camera artifacts as well as rewarding drift-induced optical flow as Dynamic Degree while not directly penalizing texture hardening or flow stagnation - motivating future task-specific benchmarks for static-camera nature-flow evaluation. Project page: https://minar09.github.io/steadyforcing/ --- ### BBR-Net: Boundary-Balanced Replay for Continual Medical Image Segmentation Authors: Zahid Ullah, Sieun Choi, Jihie Kim Published: 2026-06-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.14731v1 Continual learning for medical image segmentation remains challenging under domain shift because replay-based methods often preserve appearance information without explicitly modeling anatomical structure. This study investigates whether structural consistency governs knowledge retention in continual cardiac ultrasound segmentation. We propose the Boundary-Balanced Replay Network (BBR-Net), which selects replay samples using boundary-aware priority and class balance to preserve anatomically informative regions. The method is evaluated on CAMUS and CardiacNet under forward (CAMUS to CardiacNet) and reverse (CardiacNet to CAMUS) task orders. In the forward setting, BBR-Net retains source-task performance close to an offline joint-training reference, while markedly reducing catastrophic forgetting and preserving competitive target-task adaptation. Ablation results show that boundary-aware prioritization contributes to retention and improves the balance between source-task preservation and target-task adaptation when combined with class-aware sampling. In contrast, the reverse setting reveals that structure-aware replay fails when initial representations are learned from noisy and structurally inconsistent data. To isolate this effect, we conduct a controlled structural perturbation analysis by progressively corrupting source-task boundaries while keeping the dataset, architecture, and training protocol fixed. Forgetting increases consistently as structural reliability decreases, suggesting that replay effectiveness is strongly influenced by the quality of stored structural information, rather than by memory capacity alone. These findings indicate that preserving anatomical structure under domain shift is a central factor in continual medical image segmentation, and that replay mechanisms should account for structural reliability to support robust knowledge retention. --- ### Hierarchical GRU with Input-Conditioned Slot Queries for Ball Action Anticipation Authors: Parthsarthi Rawat Published: 2026-06-02 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.14730v1 We present a hierarchical model for ball action anticipation in football broadcast video. Given a 30-second observation window, the system predicts actions occurring in the subsequent 5-second window across 10 classes. A shared local Transformer encodes clip-level features within each 5-second sub-window; a GRU then aggregates temporal context across all sub-windows; finally, a Transformer decoder with K input-conditioned event slots decodes the anticipation target via three decoupled heads (objectness, class, temporal offset). We introduce frequency-reweighted Hungarian matching that systematically favours rare action classes, and Gaussian soft targets for temporal bin supervision. On the SoccerNet Ball Action Anticipation benchmark, our method achieves 17.91% mAP on the test server. --- ### Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs Authors: Ke Li, Chongzhe Zhang, Zifan Zeng, Feng Liu, Qunli Zhang, Zheng Hu Published: 2026-06-02 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.09876v1 Large language models often express high confidence in answers that are wrong. Standard calibration remedies typically act globally or at the score level, reducing unwarranted confidence but also risking erosion of warranted confidence on correct answers. We introduce Probe-Conditioned Head Intervention (PCHI), an inference-time method that uses a frozen probe to detect likely wrong-but-confident responses and conditionally rescales downstream attention-head outputs during confidence generation. On Qwen3-4B-Instruct solving OpenMathInstruct problems with a structured binary confidence field, readout-token PCHI converts 82.2% of originally wrong-yes confidence readouts to $\texttt{no}$, while a joint intervention across upstream confidence-template tokens reduces ECE from 21.9% to 9.2% and damages only 5.1% of originally correct-yes readouts. The readout-token effect also appears on Gemma3-4B, though upstream interventions are weaker and more mask-dependent. These results show that verbalized overconfidence can be selectively reduced through conditionally applied internal intervention, partially decoupling the suppression of unwarranted confidence from the loss of warranted confidence. --- ### Integrating Local and Global Entropy for Uncertainty Quantification in LLMs Authors: Johanne Medina, Tianyi Zhou, Keivin Isufaj, Aristides Gionis, Sanjay Chawla Published: 2026-06-02 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2606.09875v1 Large language models hallucinate confidently, making uncertainty quantification (UQ) essential for reliable deployment. Existing methods rely predominantly on token-level signals, leaving the geometric structure of intermediate hidden states underused. In this paper, we take the geometric complexity of hidden-state matrices as a measure of the global uncertainty of LLMs, while treating token-level uncertainty estimation as a local metric. We show that hidden-state geometric entropy (global uncertainty) and token-level entropy (local uncertainty) are statistically near-orthogonal, capturing distinct failure regimes for reliability prediction. In particular, global geometry recovers the confident-but-wrong failure mode that local signals systematically miss. Building on this, we propose Global-Local Uncertainty (GLU), an unsupervised, single-pass score that fuses the two signals via a multiplicative gate. Across three model families and six benchmarks, GLU matches or outperforms all unsupervised baselines while requiring only a single forward pass and remaining length-normalized and architecture-agnostic. --- ### Disjoint or Overlapping? Inference Windowing for Reconstruction-Based Time Series Anomaly Detection Authors: Guillaume Coulaud, Reza Akbarinia, Florent Masseglia Published: 2026-06-02 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.09874v1 Reconstruction-based methods are widely used for time series anomaly detection, where models are trained to reconstruct subsequences, and anomalies are identified through reconstruction errors. However, reported results are often hard to compare due to heterogeneous evaluation practices and underspecified inference procedures. In this paper, we revisit reconstruction-based anomaly detection in the univariate offline setting and study the role of the inference stride, which controls whether subsequences are processed as disjoint windows or with overlap. We propose a unified training, tuning, and multi-seed evaluation protocol on the curated TSB-AD benchmark, and study how overlapping inference affects anomaly detection performance for a range of reconstruction models, including PCA-based baselines, DLinear, an AutoEncoder, TimesNet, and Transformer variants. The results show that across all models, overlapping windows yield consistent improvements, with average relative gain up to +28%, and can alter method rankings. We further analyze variability across datasets, random seeds, and hyperparameter configurations. Finally, we complement the benchmark study with an evaluation on the full UCR archive using localization criteria aligned with sliding-window reconstruction. Overall, our results highlight that reconstruction-based anomaly detection performance depends not only on model architecture and training, but also on inference choices, motivating a clear and reproducible protocol. Our results show that reconstructionbased baselines achieve strong performance on both TSB-AD and UCR benchmarks, supporting them as competitive and practical approaches for univariate time series anomaly detection. --- ### Rotate2Think: Geometric Priming via Orthogonal Rotation to Improve Language Model Reasoning Authors: Aditya Sharma, Christopher J. Pal, Amal Zouaq Published: 2026-06-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.09873v1 Reasoning models achieve strong performance on challenging tasks by generating explicit intermediate reasoning traces before producing a final answer. Yet the internal structure of representation space when reasoning remains poorly understood: how do a model's hidden representations differ during thinking versus the embeddings of the input prompt, and can this structure be exploited to elicit stronger reasoning at inference time? We show that both input embeddings and thinking embeddings (mean-pooled last-layer hidden states over the prompt and reasoning trace, respectively) exhibit extremely high conicity, with all vectors clustering tightly around a single mean direction. Crucially, these mean input and thinking directions are non-collinear, with thinking embeddings occupying a geometrically distinct region of embedding space across many different models and benchmark tasks. This observation motivates casting the input-to-thinking transition as a rotation problem admitting a closed-form solution via orthogonal Procrustes analysis. We propose Rotate2Think, a training-free method that estimates this rotation from a small set of correctly solved examples and injects the resulting synthetic thinking vector between thinking delimiters at inference time, providing a geometric primer at the onset of the reasoning trace. Evaluated across multiple benchmarks and model families, Rotate2Think improves accuracy in 30 of 32 model-benchmark configurations across mathematics, science, and code tasks, and generalizes zero-shot to multimodal reasoning on MATH-Vision. --- ### PatchSTG: Scalable Spatiotemporal Graph Transformers for Traffic Forecasting on Irregular Sensor Networks Authors: Jichao Li, Xuanming Shi Published: 2026-06-02 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2606.09872v1 Traffic forecasting is a fundamental component of intelligent transportation systems, yet remains challenging in real-world settings due to irregular sensor distributions and the high computational cost of modeling large-scale spatiotemporal dependencies. In practical traffic networks, sensors are unevenly distributed across regions, leading to non-uniform spatial structures that limit the effectiveness and scalability of existing graph-based and attention-based models. To address these challenges, we propose PatchSTG, a patch-based spatiotemporal graph Transformer designed for efficient forecasting on irregular sensor networks. The key idea is to introduce a hierarchical spatial representation that partitions sensors into balanced, locality-preserving patches based on geographic information. On top of this structure, a dual attention encoder alternates between intra-patch attention for capturing local interactions and inter-patch attention for modeling global dependencies, reducing computational complexity from quadratic to near-linear scaling. We evaluate PatchSTG on real-world traffic data from Rhode Island and additional large-scale datasets. Experimental results demonstrate that the proposed model achieves stable and competitive forecasting performance across multiple horizons, while significantly improving computational efficiency. Ablation studies further validate the effectiveness of spatial partitioning and dual attention in capturing both local and long-range traffic dynamics. These results suggest that patch-based spatiotemporal modeling provides a scalable and effective framework for traffic forecasting under irregular spatial settings. --- ### SD-GRPO: Verifiable Segment Decomposition for Long-Form Vision-Language Generation Authors: Hyunwoong Kim, Seongeun Lee, Hannah Yun, Junhyun Park, Jonggwon Park Published: 2026-06-02 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.09871v1 Group Relative Policy Optimization (GRPO) and its variants, originally developed for Large Language Models (LLMs), have recently been applied to Multimodal LLMs and produced strong results. However, their coarse-grained holistic credit assignment from a single scalar advantage underfits vision-language (VL) tasks, where outputs are often long-form responses grounded in semantically rich images. To address this limitation, we exploit a structured signal that single-scalar formulations discard: the natural segmentation of long-form VL outputs. Concretely, we propose Segment-Decomposed GRPO (SD-GRPO), which z-normalizes verifiable per-segment rewards across the rollout group, yielding a vector of per-segment advantages in place of a single scalar. We evaluate SD-GRPO across three settings spanning controlled and real-world long-form VL generation, organized by increasing semantic entanglement across segments. On a controlled multi-panel dense-captioning task constructed from DOCCI, where segments are semantically independent, SD-GRPO consistently outperforms the GRPO baseline, with larger gains at higher segment counts. Extending to a controlled multi-chart long-form VQA task constructed from MultiChartQA, we show both theoretically and empirically that rollout-level rewards suffer from cross-segment credit misattribution that scales with output length. On a real-world scientific figure captioning task on the MMSci dataset, where subfigure captions share context across the figure, blending holistic and per-segment rewards further improves on both, suggesting per-segment normalization alone is insufficient when segments are semantically entangled. Finally, by integrating SD-GRPO into Dr. GRPO, we confirm that it can be applied to any GRPO framework with minimal implementation overhead to enhance long-form VL generation. --- ### A Dataset for Dynamic Human Preferences for Vision Language Models Authors: Hannah Gao, Dylan Hadfield-Menell, Rachel Ma Published: 2026-06-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.07653v1 Given the increased adoption of Vision Language Models (VLMs) in human-interactive settings, it is important that we evaluate how well these models can adapt to real-time preferences for different users. While an increasing number of vision-language benchmarks have recently been introduced, they focus largely on evaluating static capabilities and generally-held preferences learned from extensive training data. This work introduces a new benchmark for evaluating the ability of VLMs to understand dynamic human-preferences, i.e. preferences that are passed in-context at inference time. We provide an automated pipeline for generating this benchmark with variations on image dependence, a dynamic multi-modal human-preference dataset, and evaluations of state-of-the-art models on the novel benchmark. --- ### KITE: A Tri-Modal Transformer Integrating Text, Images, and Knowledge Graphs for Fake News Detection Authors: Kevin Patel, Shashi Bhushan Jha Published: 2026-06-02 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2606.07651v2 Traditional fake news detection methods are falling behind as multimodal misinformation grows more advanced, seamlessly blending deceptive text, manipulated visuals, and factually incorrect claims. Most prior work focuses on text-image fusion or applies external knowledge only as a post-processing step, limiting their ability to detect deeper semantic inconsistencies. In this paper, we introduce KITE (Knowledge-Integrated Text-Image Encoder), a tri-modal fake news detection framework that jointly models textual, visual, and factual knowledge representations. KITE leverages Roberta and CLIP for linguistic and visual encoding, while a Graph Attention Network (GAT) processes structured facts retrieved from Wikidata. KITE uses cross-modal attention within a multimodal transformer to integrate text, visual, and knowledge features, helping it understand how each modality relates to one another. Modality-specific confidence scores are generated alongside the final prediction, offering interpretability by indicating which input type most influenced the decision. Evaluations on benchmark datasets demonstrate that KITE significantly outperforms unimodal and bimodal baselines, particularly in scenarios involving image-text mismatches or contradictions with external knowledge. --- ### KITE: A Tri-Modal Transformer Integrating Text, Images, and Knowledge Graphs for Fake News Detection Authors: Kevin Patel, Shashi Bhushan Jha Published: 2026-06-02 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2606.07651v1 Traditional fake news detection methods are falling behind as multimodal misinformation grows more advanced, seamlessly blending deceptive text, manipulated visuals, and factually incorrect claims. Most prior work focuses on text-image fusion or applies external knowledge only as a post-processing step, limiting their ability to detect deeper semantic inconsistencies. In this paper, we introduce KITE (Knowledge-Integrated Text-Image Encoder), a tri-modal fake news detection framework that jointly models textual, visual, and factual knowledge representations. KITE leverages Roberta (23,14) and CLIP (24) for linguistic and visual encoding, while a Graph Attention Network (GAT) processes structured facts retrieved from Wikidata. KITE uses cross-modal attention (9) within a multimodal transformer to integrate text, visual, and knowledge features, helping it understand how each modality relates to one another. Modality-specific confidence scores are generated alongside the final prediction, offering interpretability by indicating which input type most influenced the decision. Evaluations on benchmark datasets demonstrate that KITE significantly outperforms unimodal and bimodal baselines, particularly in scenarios involving image-text mismatches or contradictions with external knowledge. --- ### Detecting Aimbot Cheaters in MOGs Authors: Salman Shaikh, Tao Ni, Marc Dacier Published: 2026-06-02 Categories: cs.CR, cs.CV, cs.NI arXiv: https://arxiv.org/abs/2606.07650v1 Multiplayer Online Games have become a multibillion dollar industry in the entertainment sector. However, the presence of cheaters undermines the experience of honest players and devalues the effort of game developers, as it directly affects player retention, competitive integrity, the legitimacy and trustworthiness of a game, and most importantly the overall revenue streams. Among various cheating techniques, visual aimbots represent an emerging threat. They use computer vision models to detect opponents from client screen captures rather than accessing game memory, making them completely undetectable by commercial kernel level anti cheat solutions. In this paper, we introduce PATCH, a novel proactive defense strategy that deploys adversarial patches as in game honeytokens to mitigate the presence of visual aimbot cheaters. Our approach centers on deliberately triggering the cheaters' object detection model, enabling either direct detection, or rendering the game unplayable for the cheater via patch flooding on their viewport. We evaluate our approach on various criteria; analyzing the effectiveness of different patch sizes, scalability of patches to different screen resolutions, efficacy against diverse visual aimbot cheat configurations and also explore various YOLO models to assess patch transferability. Evaluation on a custom Unreal Engine game demonstrates over 90 percent detection rate in white box scenarios for almost all patch sizes, and reaches 60 to 90 percent cross model transferability with larger patches. We further validate our approach on Fortnite, a commercial MOG, demonstrating real world applicability. --- ### ViMax: Agentic Video Generation Authors: Lingxuan Huang, Sizhe He, Hengji Zhou, Liqiang Nie, Lianghao Xia, Chao Huang Published: 2026-06-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.07649v2 Long-form video generation requires systematic narrative planning and visual consistency that current short-clip methods cannot provide. Existing methods generate isolated sequences without narrative structure and lack mechanisms for maintaining character and environmental consistency across scenes. We present ViMax, an agentic video generation framework that addresses video creation through coordinated multi-agent collaboration where specialized components negotiate narrative decisions, visual continuity, and production quality. Our framework employs a hierarchical narrative engine with retrieval-augmented generation for global story coherence and a dependency-aware visual consistency mechanism that tracks character and environmental states across temporal boundaries, while VLM-guided agents continuously monitor and refine both narrative coherence and visual fidelity. The framework enables coordinated agent collaboration to generate extended narrative content. This maintains both storytelling integrity and visual coherence across multi-scene timelines. --- ### AQIFormer: A Transformer-Based Multi-View Architecture for Cross-City Air Quality Classification Authors: Om Kathalkar, Nitin Nilesh, Sachin Chaudhari, Anoop Namboodiri Published: 2026-06-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.07648v1 Air pollution represents one of the most critical environmental and public health challenges globally, with traditional sensor-based monitoring systems facing significant scalability and economic constraints. Image-based air quality estimation has emerged as a promising alternative, leveraging the visual characteristics of atmospheric pollutants in traffic scenes. However, existing methods suffer from limited cross-city generalization and inadequate exploitation of multi-view perspectives. We present AQIFormer, a novel transformer-based ensemble architecture that addresses these fundamental limitations through innovative dual-view integration, weather-aware attention mechanisms, and comprehensive multi-task learning. Our approach uniquely combines front and rear traffic imagery with meteorological parameters to achieve robust air quality classification across diverse urban environments. Extensive evaluation on a comprehensive dataset of 26,678 synchronized front-rear image pairs demonstrates good performance with 89.96% accuracy, representing a 14.96% improvement over state-of-the-art methods. Most importantly, our model maintains exceptional cross-city generalization capabilities, achieving 81.67% accuracy on an independent dataset collected in Nagpur, India with only 8.29% performance degradation using few-shot adaptation with minimal training samples. --- ### Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation Authors: Ruipeng Zhang, Zhihao Li, C. L. Philip Chen, Tong Zhang Published: 2026-06-02 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.07647v1 Large vision language models (LVLMs) have made rapid advancements and are deployed across various applications, yet hallucinations remain a major challenge. Activation steering is appealing due to its minimal training overhead and controllability at inference time. However, we found that during autoregressive decoding, visual conditioning affects token prediction sparsely and locally across decoding steps, and many existing methods that average image-versus-no-image differences over the entire sequence dilute these critical signals, yielding low signal-to-noise ratio steering directions. Additionally, many existing methods apply a fixed steering strength, which misallocates the intervention budget, over-perturbs non-critical tokens, and can cause instability. To address these limitations, we propose Token-Level Visual-Sensitivity Steering (TLVS) for hallucination mitigation. Our approach first extracts token-level steering vectors and refines them, and then applies fine-grained, visual-sensitivity-adaptive steering only where it matters. This lightweight, plug-and-play mechanism requires only minimal training for calibration and can be applied across diverse vision-language models. It modulates the steering strength at each decoding step, selectively suppressing hallucination-prone spans while preserving evidence-grounded content. We evaluate TLVS on several benchmarks, including POPE, AMBER, CHAIR (COCO), MMHal, and HallusionBench, demonstrating consistent improvements over previous steering methods. --- ### DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation Authors: Xiaoran Xu, Yifan Xu, Yupeng Wu, Xiaoshan Yang, Changsheng Xu Published: 2026-06-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.07646v1 Test-time adaptation (TTA) aims to align a model to shifting test domains using only unlabeled streaming data. Most existing methods implicitly infer a single global domain distribution, ignoring the multidimensional and sample-specific nature of real-world domain shifts, leading to fragile adaptation. We propose DOME, an effective domain encoder that explicitly models each sample's domain in a zero-shot manner. DOME leverages vision-language pretraining to extract dense, continuous representations, parameterizes domains as distributional variables, and introduces a momentum-updated sparse domain bank for disentangled supervision. By injecting these explicit domain cues into downstream models, even a basic entropy-minimization TTA strategy achieves state-of-the-art performance across ImageNet-C, ImageNet-R, and ImageNet-Sketch, outperforming complex TTA approaches. Our results demonstrate that robust adaptation stems not from intricate adaptation algorithms, but from explicit, structured domain representation. --- ### FineGen: A VLM-based Multi-Agent Framework for Fine-Grained Image-Text Dataset Construction Authors: Chang Kong, Yuebing Li, Peng Mo, Haigang Zhang, Qiuming Luo Published: 2026-06-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.07645v1 The scarcity of hard negative samples in current vision-language datasets significantly hinders fine-grained perception. To address this, we propose FineGen, a VLM-based Multi-Agent framework for automated dataset construction. By employing a collaborative Generation-Verification-Correction pipeline with a closed-loop feedback mechanism, FineGen ensures synthesized hard negatives are semantically valid yet strictly contradictory to visual content. Applying this to ImageNet, we construct FineGen-100K, a hierarchical dataset containing over 147,000 attribute-specific hard negatives with a rigorous 1:10 positive-to-negative ratio. Extensive evaluations confirm a 96.7% attribute validity rate. Crucially, downstream validation on the FG-OVD benchmark shows that fine-tuning on FineGen-100K yields a substantial +14.4% accuracy improvement on hard samples, significantly outperforming state-of-the-art methods. --- ### CrowdMath: A Dataset of Crowdsourced Mathematical Research Discussions Authors: Sherin Muckatira, Jesse Geneson, Slava Gerovitch, Pavel Etingof, Mikhail Gronas, Anna Rumshisky Published: 2026-06-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.06526v2 Large language models have made substantial progress on mathematical reasoning, but existing benchmarks typically evaluate well-specified problems with final answers, step-by-step solutions, or complete proofs. They do not capture collaborative open-problem solving: a setting in which participants propose partial arguments, identify gaps or errors in prior steps, repair flawed reasoning, and gradually synthesize incremental contributions into a proof. We introduce CrowdMath, a dataset of 164 expert-annotated progress chains from the MIT PRIMES--Art of Problem Solving (AoPS) CrowdMath program (2016-2025), a collaborative research initiative whose discussions have led to peer-reviewed publications. Each chain traces a multi-participant forum discussion from an open-problem statement to a completed proof. Posts are labeled by their functional roles in the evolving solution process, including partial progress, proof completion, erroneous reasoning, and error identification. We define evaluation tasks and benchmark six frontier models. Models achieve 83-88% accuracy on next-post prediction, suggesting that they can follow the local flow of mathematical discussion. However, they struggle to identify the functional significance of individual contributions with the best model achieving only 0.42 macro-F1 on post-role classification. CrowdMath exposes a gap between solving well-specified mathematical problems and understanding collaborative mathematical progress as it unfolds. --- ### CrowdMath: A Dataset of Crowdsourced Mathematical Research Discussions Authors: Sherin Muckatira, Jesse Geneson, Slava Gerovitch, Pavel Etingof, Mikhail Gronas, Anna Rumshisky Published: 2026-06-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.06526v1 Large language models have made substantial progress on mathematical reasoning, but existing benchmarks typically evaluate well-specified problems with final answers, step-by-step solutions, or complete proofs. They do not capture collaborative open-problem solving: a setting in which participants propose partial arguments, identify gaps or errors in prior steps, repair flawed reasoning, and gradually synthesize incremental contributions into a proof. We introduce CrowdMath, a dataset of 164 expert-annotated progress chains from the MIT PRIMES--Art of Problem Solving (AoPS) CrowdMath program (2016-2025), a collaborative research initiative whose discussions have led to peer-reviewed publications. Each chain traces a multi-participant forum discussion from an open-problem statement to a completed proof. Posts are labeled by their functional roles in the evolving solution process, including partial progress, proof completion, erroneous reasoning, and error identification. We define evaluation tasks and benchmark six frontier models. Models achieve 83-88% accuracy on next-post prediction, suggesting that they can follow the local flow of mathematical discussion. However, they struggle to identify the functional significance of individual contributions with the best model achieving only 0.42 macro-F1 on post-role classification. CrowdMath exposes a gap between solving well-specified mathematical problems and understanding collaborative mathematical progress as it unfolds. --- ### Agentic Large Language Models for Automated Structural Analysis of 3D Frame Systems Authors: Ziheng Geng, Ian Franklin, Santiago Martinez, Jiachen Liu, Yunhe Zhao, Minghui Cheng Published: 2026-06-02 Categories: cs.GR, cs.AI arXiv: https://arxiv.org/abs/2606.06525v2 Large language models (LLMs) have emerged as powerful foundation models with strong reasoning capabilities across domains. Beyond reactive text generation, agentic LLMs enable autonomous workflow execution through modular task decomposition and coordinated tool use. In structural engineering, recent efforts have developed agentic LLMs for automated analysis of plane frames. However, their extension to 3D frames remains underexplored due to challenges in irregular geometric representation, topological consistency, and long-horizon reasoning. This paper proposes an agentic LLM framework for automated structural analysis of 3D frames from natural language inputs. Irregular 3D frames are represented by projection onto a 2D plan, where orthogonal gridlines define spatial coordinates and a matrix of number of stories encodes vertical extrusion of each grid cell. Building on this representation, the framework establishes a multi-agent pipeline: a problem analysis agent parses input into structured JSON; a floor decomposition agent derives the spatial layout of each floor; the 3D geometry is assembled by node, girder, slab, and column agents; support and load agents assign boundary and loading conditions, and code translation agents generate executable SAP2000 script. Evaluated on ten representative 3D frames, the proposed framework achieves an average accuracy of 90% across repeated trials, demonstrating consistent and reliable performance. --- ### Advanced Flood Prediction with Physics-Guided Deep Learning: Combining UNet, FNO, and SAR/Optical Imagery Authors: Tewodros Syum Gebre, Jagrati Talreja, Leila Hashemi-Beni Published: 2026-06-02 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.06524v1 Accurate and scalable flood mapping remains challenging due to limited ground observations, heterogeneous terrain conditions, and the difficulty of enforcing hydrodynamic consistency within data-driven models. This work introduces a physics-guided deep learning framework that integrates multi-modal remote sensing (Sentinel-1 SAR, Sentinel-2 optical imagery, and DEM-derived terrain features) with constraints from the depth-averaged shallow water equations (SWE). The proposed hybrid architecture combines a UNet to capture fine-scale spatial details with a Fourier Neural Operator (FNO) to model basin-scale hydraulic interactions, while physics-informed residual losses ensure mass and momentum consistency. Evaluated across diverse floodplain settings, the hybrid model achieves an Intersection over Union of 0.82 and an F1 score of 0.90 for flood extent prediction, outperforming UNet-only and FNO-only baselines. Using hydrodynamic simulations as reference data, the model achieves an RMSE of 0.21 m for water depth and 0.15 m/s for flow velocity. Physics consistency is maintained, with low residuals and mass imbalance below 2.1%. Ablation studies confirm that removing physicsbased regularization significantly degrades performance, underscoring the value of physical constraints for stability and generalization. These results demonstrate that embedding hydrodynamic principles into deep learning yields more accurate, reliable, and physically coherent flood predictions, offering strong potential for operational monitoring and large-scale deployment. --- ### Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory Authors: Ruida Wang, Jerry Huang, Pengcheng Wang, Xuanqing Liu, Luyang Kong, Tong Zhang Published: 2026-06-02 Categories: cs.AI, cs.LG, cs.LO, cs.SE arXiv: https://arxiv.org/abs/2606.06523v2 Equipping Large Language Models (LLMs) to execute reliable multi-step workflows has become a central challenge in artificial intelligence. Despite recent advances in LLMs' agentic capabilities, most agent systems still lack formal methods for specifying, verifying, and debugging their workflow and execution trajectories. This challenge mirrors a long-standing problem in mathematics, where the ambiguity of natural languages (NLs) motivates the development of formal languages (FLs). Inspired by this paradigm, we propose **Lean4Agent**, to the best of our knowledge, the first framework that uses Lean4, a dependent-type FL to model and verify agent behavior. **Lean4Agent** launches **FormalAgentLib**, an extensible Lean4 library for formally modeling and verifying agent workflows' semantic consistency under explicit assumptions, and enabling localization of execution-time failures revealed by trajectories. Building on **FormalAgentLib**, we further develop **LeanEvolve**, which applies results in **FormalAgentLib** to revise workflows to enhance its capability. Extensive experiments on a hard problem subset of SWE-Bench-Verified and a subset of ELAIP-Bench across 5 leading LLMs indicate that the verification-passing workflows outperform the failing ones by an average of **11.94%**, and **LeanEvolve** further improves SWE performance by **7.47%** on average. Furthermore, **Lean4Agent** establishes a foundation for a new field of using expressive dependent-type FL to formally model and verify agent behavior. --- ### P-Cast Precision in FP8 Attention: Sink-Induced Collapse and the Optimality of S=2^8 Authors: Reed Lau Published: 2026-06-02 Categories: cs.AR, cs.AI, cs.DC, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2606.06521v1 FP8 (E4M3) acceleration for attention computation offers significant throughput gains, but the 3-bit mantissa introduces precision challenges when the softmax probability matrix~$P$ is cast to FP8 before the $P \cdot V$ matrix multiplication. We analyze two implementation choices that affect output precision under the \emph{Attention Sink} phenomenon: (1)~the KV block iteration order, and (2) the static scaling factor applied to $P$ before casting. We show that forward KV iteration causes \emph{P-collapse} -- to leading order a fraction $Φ(Δ+ δ_k - 6.93 - \ln S)$ of non-sink $P$ values underflow to zero, where the small shift $δ_k \approx 1$ (for $k_{\text{sink}}{=}4$) is the expected within-sink-block score maximum -- and that reverse iteration removes it, with a zero-underflow guarantee when reverse is combined with $S{=}256$. We further give a constructive characterization of $S = 256 = 2^8$ as the static scale that simultaneously satisfies (i)~bit-exact IEEE 754 scaling, (ii) the lower envelope of a sawtooth function $dp(S)$ over the E4M3 number line ($dp = 2^{-4}$, the minimum worst-case quantization step), and (iii)~the maximum normal-range coverage \emph{among bit-exact ($2^k$) scales} (a non-bit-exact scale such as $448$ attains slightly higher coverage; sec.5}). Both optimizations are already deployed in FlashAttention-3/4 on engineering grounds; our contribution is a quantitative account of \emph{why} these choices are good and a closed-form threshold $Δ_c = 6.93 + \ln S - δ_k$ for predicting kernel-level precision loss. Kernel-faithful experiments ($Q, K, V$ in FP32 to isolate the P-cast effect) show $3$-$10\times$ MSE improvement at moderate sink strengths, and paired tests confirm both fixes saturate to the same precision floor when combined -- which motivated updating the hpc-ops kernel from $S{=}1$ to $S{=}256$. --- ### Applying Deep Learning for cockpit segmentation in the context of mixed reality Authors: Alexandre Leles Sousa, Pedro de Oliveira Nielson, Erick Oliveira Rodrigues, Rafael Francisco dos Santos, Giovani Bernardes Vitor Published: 2026-06-02 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2606.06520v1 Computer vision is an area that has been growing continuously. With the advance of technologies with a first-person view, new development opportunities have emerged inside the area. Mixed reality promotes virtual environments with objects from the physical world shown in real time. For that, it's necessary to be concerned with the immersion of the user in this simulated environment, increasingly seeking to bring it closer to a possible desired reality. This paper proposes the development of image processing in order to perform the segmentation of images to identify what is foreground and background in order to facilitate the union of virtual and real images. Thus, the present work obtain real images of the user using the off-highway truck simulator CAT793F, through a camera, to be able to perform the segmentation of such images with artificial intelligence techniques.The convolutional neural network architectures "U-net" and "DeepLabV3+" are applied to perform image segmentation. As a result, metrics with around 90% accuracy were presented and and the best model was determined. --- ### SafeGene: Reusable Adapters for Transferable Safety Alignment Authors: Yanghan Wang, Zhiqiang Kou, Fu Feng, Jing Wang, Xin Geng Published: 2026-06-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.06519v1 Open-weight LLMs are increasingly fine-tuned into customized assistants, but downstream fine-tuning can weaken safety alignment and make models more vulnerable to malicious prompts, even when the training data is not intentionally harmful. This creates a recurring safety recovery problem as target models are repeatedly updated with new task data or user interactions. We propose SafeGene, a reusable safety-adapter module designed for cross-task reuse within each architecture-compatible model family. Rather than treating safety recovery as a model-specific repair step, SafeGene treats safety capability as an independent, reusable adapter representation decoupled from task-specific updates. This representation is obtained from aligned--degraded model discrepancies, refined into task-transferable safety vectors through data-aware layer selection, and expressed in each downstream task-adapted model via few-shot layer-wise coefficient recalibration. Experiments across multiple model families, downstream tasks, and safety judges show that SafeGene-enhanced models reduce harmful response rates while maintaining downstream performance, outperforming representative safe adaptation methods in safety--utility trade-off. --- ### DiBS: Diffusion-Informed Branch Selection Authors: Bo Liu, Yuan Xie, Yuan Gao, Xiaolong Luo, Peng Ye, Tao Chen, Fujun Han Published: 2026-06-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.06518v1 Sudoku is a representative constraint satisfaction problem that requires global structural reasoning under strict discrete constraints. The existing works of solving Sudoku mainly focus on two dominant approaches, i.e., traditional heuristic and deep learning solver. However, they suffer from two complementary limitations: learning-based solvers lack hard correctness guarantees, while complete symbolic solvers are still prone to long-tail search. To address these shortcomings, we propose a novel diffusion model-guided approach, termed as DiBS, for the branch selection search process. Specifically, DiBS keeps the symbolic solver complete and uses the diffusion model as a branch-ordering guide. The core method is ranking candidate values under the current partial assignment and lightweight consistency signal. Furthermore, we provide an in-depth theoretical proof to reveal how it works and why it works. Experiments on the challenging Royle 17-clue Sudoku benchmark show that our DiBS substantially reduces search cost relative to strong heuristic baselines, especially in nodes, backtracks, and long-tail percentiles. Besides, these results confirm that learned global guidance is effective on hard instances where branch-order mistakes are most expensive. All codes are available at https://github.com/shanxierdan/DiBS. --- ### Probabilistic learning to perform pre-onset individualised prediction of disease severity: application to Veno Occlusive Disease Authors: Dalia Chakrabarty, Kane Warrior, Chuqiao Zhang, Akash Bhojgaria, Joydeep Chakrabartty Published: 2026-06-02 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2606.06516v1 We advance a new probabilistic supervised learning approach that permits reliable, automated, and early individualised prediction of the severity with which a disease will develop in a prospective patient. The prediction capacity is illustrated via the pre-transplant prediction of the score of severity of Veno Occlusive Disease (or VOD) in the digital twin (DT) of the considered prospective patient, where this score parametrises the severity with which VOD will develop in this patient, after they undergo their Bone Marrow Transplant. The learning of the relationship between the pre-transplant variables, and a severity score variable is undertaken by modelling this relationship as a (random) function that is treated as a sample function of an adequately-chosen stochastic process. The parameters of this underlying process are learnt using a training dataset that is generated using the real-time evolution of retrospective patients in a cohort, with this training dataset subsequently augmented in size by a probabilistic inverse learning of the score of prospective patients. The augmented training set, then permits the learning of the function that capacitates - at the pre-transplant stage - automated prediction of the score of the severity of VOD that characterises the DT of a physical patient in their unique pre-transplant state. This score is subsequently fed back to the real prospective patient as the severity with which VOD will develop in them, after this patient undergoes their transplant. Such a score then permits the treating Haematologist-Oncologists to decide on the treatment regimen, which in this illustration reduces to deciding on treating the patient with Defibrotide. An AI facility is developed to undertake such automated prediction, with the physician inputting the data on the pre-transplant state that characterises the DT of the prospective patient under consideration. --- ### DxPTA: An Architecture Design Space Exploration with Optical Dataflow-guided Strategy for HW/SW Co-Design of Photonic Transformer Accelerators Authors: Rachmad Vidya Wicaksana Putra, Solomon Micheal Serunjogi, Mahmoud Rasras, Muhammad Shafique Published: 2026-06-02 Categories: cs.AR, cs.AI, cs.DC, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2606.06515v1 Transformer-based networks have emerged as prominent AI models with state-of-the-art performance, which potentially pave the way toward artificial general intelligence (AGI). However, their large sizes still hinder their efficient implementation, thus highlighting the need for alternate solutions to enable their energy-efficient acceleration. Recently, state-of-the-art works propose photonic transformer accelerators (PTAs) with significant speedup and energy efficiency improvements over the conventional electronic accelerators. However, their PTA architectures are developed without considering the application constraints (e.g., area, power, energy, and latency). Moreover, their manual design approach also requires huge design time to determine a suitable architecture for the targeted application, hence making this approach not scalable. To address these limitations, we propose DxPTA, a novel design space exploration methodology for enabling efficient hardware/software co-design of the appropriate PTA architecture that meets all constraints. It is achieved by (1) identifying the PTA architecture parameters based on the coherent optical dataflow; (2) analyzing the impact/significance of the parameters; and (3) leveraging this analysis for devising a constraint-aware architecture search algorithm. Experimental results show that, our DxPTA can find the appropriate PTA architectures for different transformer-based models (i.e., DeiT-T/S/B and BERT-B/L). It achieves up to 26mm^2 area, 4.8W power, 39mJ energy, and 6ms latency, for constraints of 50mm^2 area, 5W power, 50mJ energy, and 10ms latency; with 15.2x faster searching time than the exhaustive approach. These results demonstrate the potential of DxPTA methodology for enabling efficient PTA designs for diverse AGI-based applications. --- ### Detecting and Mitigating Bias by Treating Fairness as a Symmetry Operation Authors: Nishit Singh Published: 2026-06-02 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.06514v1 Machine learning systems deployed in high stakes socioeconomic settings routinely display bias. We formalize bias as a symmetry breaking operation: a classifier is fair if its outputs remain invariant under the counterfactual operation of switching a sensitive attribute, with merit features held fixed. We implement loss based regularization as a symmetry restoring mechanism and evaluate the framework on four synthetic datasets with varying levels of noise, correlation, and bias. The framework achieves upwards of 90\% violation reduction, with accuracy costs around 5\%. This framework does not require causal graph knowledge, is computationally lightweight, and generalizes to any sensitive attribute definable as a bit-flip, making it suitable for contexts where local sources of discrimination remain absent from mainstream benchmarks. --- ### Central Description Length (CDL) Clustering Validation Index Authors: Mahdi Shamsi, Soosan Beheshti Published: 2026-06-02 Categories: stat.ML, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2606.05230v1 Selecting a clustering algorithm and its hyperparameters without labels is a common difficulty in engineering machine learning pipelines that work with unsupervised analysis of sensor, image, or process data. Clustering validation indices (CVIs) provide internal scores for ranking candidate clusterings, but most popular CVIs are built from Euclidean compactness and separation terms and so tend to favour compact, convex partitions. Their performance is known to degrade on non convex, irregular, or variable density data, where kernel transformations or alternative distance measures are typically used at the cost of additional tuning and computation. This paper introduces the Central Description Length (CDL) clustering validation index. CDL uses the observed within cluster compactness, the estimated cluster centers, and the estimated cluster covariances to compute a probabilistic upper bound on the description length associated with the unobservable true cluster centers. The bound condenses intra cluster compactness and centroid displacement into a single computable quantity and is evaluated on the partition produced by any clustering algorithm. The implementation uses only observable quantities (the data, the partition, the estimated centers, and the estimated covariances) and does not use ground truth labels. On synthetic benchmarks with non convex and arbitrary shape clusters, CDL-CVI selected the reference number of clusters more often and reached higher Adjusted Rand Index (ARI) values than the conventional CVIs we tested, without an additional kernel preprocessing stage. On image benchmarks (MNIST, CIFAR-10, STL-10) clustered from frozen unsupervised embeddings, CDL-CVI returned cluster numbers close to the reference class counts across K-means, DBSCAN, and spectral clustering in the reported trials. --- ### Quantifying the biophysical properties of stomatocytes in health and disease Authors: Zhaojie Chai, Jianlu Zheng, He Li, Ming Dao, George Em Karniadakis Published: 2026-06-02 Categories: q-bio.CB, cs.LG, math-ph, q-bio.BM arXiv: https://arxiv.org/abs/2606.05227v1 Hereditary stomatocytosis (HS) comprises red blood cell (RBC) disorders characterized by cup-shaped erythrocytes that respond oppositely to splenectomy: curative in overhydrated HS (OHS) but potentially thrombogenic in dehydrated HS (DHS/xerocytosis). This paradox persists because RBC biomechanics is governed by partly independent parameters--shear modulus, bending rigidity, surface-to-volume ratio (S/V), and cytoplasmic viscosity--that existing assays capture only piecemeal. Here we combine dissipative particle dynamics (DPD) simulations with microfluidic imaging to construct a control discocyte and three stomatocyte models (ST-RBC1-3) at fixed membrane area and decreasing volume (109.7, 101.5, 89.8 fL), spanning the OHS-to-DHS range. Tracing this parameter set through five mechanically orthogonal assays, we find that interendothelial-slit (IES) traversal is geometry-dominated: overhydrated ST-RBC1 requires an order of magnitude higher critical pressure than healthy RBCs, whereas dehydrated ST-RBC3 passes freely. ST-RBC3 nonetheless suppresses membrane tank-treading and raises low-shear whole-blood viscosity by ~29% at physiological haematocrit, comparable to Gaucher-disease hyperviscosity. A funnel-obstacle chip amplifies these differences into a label-free centerline-offset signal predicted to separate all four RBC types (~4.5 standard deviations between extreme phenotypes). These results unite single-cell mechanics, splenic filtration, and hemorheology in one framework, resolve the splenectomy paradox, and point toward microfluidic pre-operative risk stratification in HS. --- ### The Language of Elution: Autoregressive Prediction of the Next Feature in Untargeted LC-HRMS Lipidomics Authors: Dayanjan S. Wijesinghe Published: 2026-06-02 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2606.05225v1 Untargeted liquid chromatography-high-resolution mass spectrometry (LC-HRMS) detects thousands of molecular features per sample, yet only 2-20% receive confident structural annotations. A root cause of this "dark metabolome" is that tandem MS/MS acquisition is reactive: instruments select precursors only after ions appear, blind to what elutes next. We reframe chromatographic elution as an autoregressive sequence prediction task. Because reversed-phase elution order is governed by hydrophobicity, successive features form a physically constrained sequence, like tokens in language. We discretize the mass-to-charge (m/z) axis into 110 bins and train long short-term memory (LSTM) and Transformer models to predict the next eluting m/z bin from five annotation-free per-token features: m/z bin, mass defect, retention-time gap, polarity, and intensity rank. Trained on 15,242 features from four clinical lipidomics cohorts (342 plasma samples; SCIEX TripleTOF 6600+, Waters CSH C18), the LSTM reaches 98.4% top-1 accuracy (99.99% top-5; mean absolute error 3.6 Da) and the Transformer 98.0%. Ablation shows autoregressive context accounts for 55.5 percentage points while no single feature contributes more than 0.2 pp: the sequential pattern, not molecular properties, drives prediction. Models transfer across instruments sharing the method (r=0.999 on an independent Agilent 6530 dataset) but fail under a different column chemistry (5.1% top-1) or polarity mode (2.6%), confirming method- and mode-specificity. Fine-tuning on as few as two to five quality-control injections recovers held-out accuracy from 2.6% to nearly 50%, so cross-condition deployment needs minimal calibration. These results establish that elution sequences are highly predictable and lay the groundwork for predictive MS/MS acquisition to improve annotation coverage in untargeted metabolomics. --- ### DiverAge: Reliable Pluralistic Face Aging with Cross-Age Identity Relation Guidance Authors: Yueying Zou, Peipei Li, Qianrui Teng, Dianyan Xu, Zekun Li Published: 2026-06-02 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.04881v1 Face aging plays an important role in long-term biometric analysis, cross-age identity verification, and forensic identity analysis. Since the same subject may exhibit multiple plausible appearances at a target age due to genetic, environmental, and lifestyle factors, face aging is inherently a one-to-many generation problem. However, pluralism alone is insufficient for reliable face aging: a model should provide appearance-level candidate diversity within each age group while maintaining sequence-level ordinal reliability across ordered age groups. Existing deterministic aging methods can synthesize visually plausible age-progressed faces, but usually lack stochastic diversity. In contrast, pluralistic aging methods introduce local appearance variations, but often fail to explicitly regulate the identity evolution of the full aging sequence. In this paper, we propose \textbf{DiverAge}, a hierarchical pluralistic face aging framework based on diffusion autoencoding. DiverAge preserves appearance-level diversity through stochastic diffusion decoding and age-conditioned semantic modulation. To improve sequence-level reliability, we introduce a Cross-age Identity Relation Regulator (CARR), an inference-time guidance strategy that jointly denoises multiple target age groups. CARR is guided by a Cross-age Identity Similarity (CIS) prior estimated from real same-identity cross-age pairs, and suppresses excessive cross-age identity drift through one-sided sampling-time guidance without modifying the training objective or introducing extra trainable parameters. Experiments demonstrate that DiverAge improves sequence-level ordinal reliability while maintaining identity preservation, age accuracy, image quality, and appearance-level diversity. ---