# Research Papers — 2026-10 · bundle page 147 of 156 > Full-text markdown of papers #7301–7350 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-10/page/147 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/146.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/148.md) ### Sequential Capacity of Quantum Processes with Finite Memory Authors: Yibin Wang Published: 2026-10-01 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2610.02068v1 How complex can the responses of a quantum device become as it runs longer with a fixed internal memory? We quantify this complexity through sequential response capacity: how many adaptive testing stages, each using a fresh run, can continue to separate possible processes by a prescribed gap in response probabilities. For fixed system and memory sizes, we establish a tight law relating this capacity to run length and probability resolution. At fixed resolution, the capacity grows on the order of $K\log K$, where $K$ is the number of time steps in each run. Our construction attains this growth using time-dependent phase rotations on a single visible qubit with no additional internal memory; its tests give response probabilities exactly zero or one. Under the same tests, classical stochastic processes that measure in a fixed basis at every step have only linear capacity at fixed sizes and resolution. For phase sequences selected by a stored classical label, we then quantify how known independent Pauli noise changes this logarithmic enhancement. With ideal controls and weak residual phase noise after correction, we prove matching capacity bounds at a fixed small probability gap. These bounds identify the inverse residual phase-flip probability as the coherence timescale that limits the extra logarithmic growth. --- ### Learn the Directions, Normalize the Gains: Post-Training Normalization for LoRA Authors: Zailong Tian, Yanzhe Chen, Zhuoheng Han, Houfeng Wang, Lizi Liao Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.02067v1 While Low-Rank Adaptation (LoRA) enables efficient task specialization, its learned updates can compromise capabilities beyond the target task. We identify \textbf{adaptation imbalance}: a few singular directions dominate the trained update, leaving its performance sensitive to how gains are allocated. We argue that \textbf{learning where to adapt does not ensure that adaptation gains are well balanced}. This motivates \textbf{LoRA-Norm}, a post-training normalization method that retains learned directions while rebalancing their gains. LoRA-Norm combines spectral rebalancing, a fixed nonlinear transformation of singular values, with nuclear-norm restoration, which preserves the original total spectral mass. It requires no calibration data or additional training and introduces no inference overhead. Across two backbones and three adaptation tasks, LoRA-Norm improves average specialization and capability retention, outperforming the evaluated post-hoc spectral pruning and gradient-guided editing configurations on both measures. Stronger functional equalization brings no consistent additional gains, revealing that balancing adapter gains and equalizing their responses are distinct objectives. --- ### External Observers May See More Clearly: Cross-Model Span-Level Hallucination Detection in Large Language Models via Hidden State Probing Authors: Kingshuk Gupta, Davide Buscaldi Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.02066v1 As Large Language Models (LLMs) increasingly serve as foundational reasoning engines, their tendency to hallucinate remains a critical vulnerability. While recent internal state probes offer a promising alternative to slow external retrieval systems, they largely reduce hallucination detection to a token-wise binary classification task, failing to capture the structured, sequential boundaries of semantic drift. Here, we introduce an internal hidden state framework for fine-grained, span-level hallucination detection. By inspecting layer-wise activation patterns, we attempt to detect the exact hallucination onset and continuation tokens in an LLM generation. Our experiments show that this approach successfully isolates hallucination onsets, achieving substantial improvements in Precision-Recall AUC over random baselines despite extreme class imbalance. Ultimately, we propose a novel cross-model detection framework in which one model observes the internal representations elicited by another model's generation. We find that an external observer can match or exceed a generator's self-detection of its own hallucination onsets, including when the observer is the smaller model, suggesting that self-detection is not the ceiling for onset localisation. --- ### Foundations without Fundamentals: Zero-Shot Blind Spots in Time Series FMs Authors: Nafiseh Ghoroghchian, Haipeng Zhang, Shuyi Han, Alex Labach, George Stein Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.02058v1 Despite the success of Time Series Foundation Models (TSFMs) on broad benchmarks, their ability to internalize basic temporal logic, especially in settings supported by exogenous covariates, remains under-examined. We introduce SimpleTimeBench, a diagnostic univariate and multivariate "unit test" suite for primitives such as monotonic trends, periodic signals and leading indicator covariates, scenarios where near-perfect forecasts should be trivial. Surprisingly, prominent multivariate TSFMs (Chronos-2, Moirai and Toto) frequently produce suboptimal zero-shot forecasts for these inputs. While fine-tuning Chronos-2 improves its behaviour on specific tasks, we show that this adaptation degrades performance on other fundamental patterns rather than enhancing its generalizable foundational capabilities. This reveals a gap between pre-training scale and basic temporal reasoning, suggesting that current TSFMs could potentially lack the inductive biases needed to capture simple predictable functions. We further demonstrate that these failures are not merely synthetic curiosities: they persist in real-world sensor forecasting, where TSFMs consistently underutilize leading indicators available in observed covariates. This inability to capture simple relationships limits the practical utility and reliability of current multivariate models. --- ### Learning from Failure: Leveraging Unreliable Predictions in Semi-Supervised Real-World Adverse Weather Removal Authors: Cap Dang Xuan Kiet, Tat-Jen Cham Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.02051v1 Adverse weather image restoration aims to recover images degraded by rain, haze, snow, and other weather-induced artifacts, thereby improving the robustness of outdoor vision systems. Existing unified restoration models exhibit limited generalization to real-world scenes due to their reliance on synthetic supervision and insufficient semantic constraints. In this paper, we propose a novel student--teacher semi-supervised framework that addresses both challenges. Specifically, we introduce an unreliable database that preserves failed teacher predictions as informative negative samples for contrastive learning, while a reliable database stores high-quality teacher predictions as positive samples. By jointly exploiting reliable pseudo-ground truths and unreliable teacher outputs, the proposed framework learns to enhance desirable restoration characteristics while avoiding common failures. We further propose a phase spectrum-based semantic constraint that replaces computationally expensive text-based supervision with an efficient and naturally aligned semantic prior. An adaptive phase consistency loss is also designed to dynamically balance supervision between the degraded input and teacher pseudo-ground truths according to degradation severity. Extensive experiments on real-world benchmarks demonstrate that the proposed method consistently outperforms existing state-of-the-art approaches in restoration quality and perceptual fidelity while exhibiting stronger generalization to real-world adverse weather conditions. --- ### HydroJEV: A one-second, training-free screen for cyber-attack and fault attribution in water distribution networks Authors: Tianwei Mu, Shengyan Jiang, Mingzhe Yuan, Qing Luo, Min Xiao, Wenhong Wang, Jun Li, Manhong Huang Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.02048v1 When a SCADA alarm is raised in a water distribution network, operators must decide quickly whether it reflects a cyberattack, a physical fault, a normal transient or a faulty sensor. Supervised classifiers need labelled incidents that utilities rarely have, and frontier large language models (LLMs) take tens of seconds per decision. We tested whether Jev, a training-free model that returns class probabilities in about one second, can serve as the first tier of this triage. On a four-class cause-attribution benchmark built on the C-Town network in EPANET, Jev was compared with a hand-written rule tree, a supervised classifier and seven cloud LLMs on identical evidence in four sealed, pre-registered rounds. With only a label-free prior correction, Jev matched the rule tree (macro-F1 0.62-0.64 against 0.56-0.61 in distribution) and exceeded the supervised classifier by 0.36-0.42 on event subtypes absent from its labels, in all four rounds, and it outperformed the classifier whenever fewer than about four labelled events per class were available. Jev also decided 20-40 times faster than frontier LLMs. Accepting only benign Jev verdicts confirmed by the rule tree spared an LLM reviewer 35-38% of windows on fresh sealed sets without loss of macro-F1. Transferred unchanged to two further networks, this gated cascade stayed within the non-inferiority margin of its reviewer on all four sets. A fast, training-free screen can therefore take over about a third of the review load in SCADA anomaly triage while preserving the accuracy of deliberate review. --- ### Form and Void: Entangled Composition through an Autonomous AI Agent Authors: Shiwen Wang, Jian Yang, Xu Wang, Xincan Wang, Weiming Dong Published: 2026-10-01 Categories: cs.CV, cs.MA arXiv: https://arxiv.org/abs/2610.02045v1 Positive and negative space is a fundamental principle in visual composition, supporting visually coherent forms and layered semantic relationships. Generating such compositions is challenging because it requires coordinated control over two semantic concepts that share a common boundary. Although recent text-to-image models and multimodal large language models (MLLMs) have achieved strong performance in image generation and visual understanding, positive-negative space generation remains difficult, particularly under direct single-pass prompting. In this work, we present the \textbf{F}orm \textbf{a}nd \textbf{V}oid \textbf{A}gent (\textbf{FaV-A}), a multimodal agent designed for staged positive-negative space generation. FaV-A follows a progressive workflow: it first generates a base object, then analyzes its shape and spatial structure to identify candidate negative-space semantics, and finally produces compositional instructions for the final image generation stage. Experimental results and ablation analyses suggest that FaV-A provides a more effective framework than direct zero-shot MLLM baselines for producing visually coherent and semantically aligned positive-negative space compositions. --- ### DiDE:Direct Injection with Color-Texture DEcoupling for 3D Stylization Authors: Tao Wu, Alexandra Gomez-Villa, Senmao Li, Yaxing Wang, Joost van de Weijer, Kai Wang Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.02044v1 Recent advances in rectified flow-based image-to-3D generative models have enabled high-fidelity 3D asset generation. Building on this, a growing line of work has exploited these strong 3D priors for training-free stylization, transferring visual attributes from a reference image onto a generated 3D asset. However, existing methods enforce an all-or-nothing paradigm: color and texture are transferred jointly, with no mechanism to control them independently -- a limitation we formalize as Disentangled 3D Stylization(Disen3D). To address this, we propose DiDE, the first training-free framework for Disen3D. Key to our approach is the observation that the structured latent space of image-to-3D models is overcomplete with respect to texture: texture information occupies only a small subset of the style-significant channels, leaving a free subspace available for independent color encoding. DiDE exploits this via a channel partition mechanism that processes a content image, a texture reference, and a color reference through dedicated branches and composes both style signals interference-free at every self-attention layer, preserving content geometry throughout. Experiments on Disen3D-Bench, our newly collected multi-reference benchmark, show that DiDE consistently outperforms 2D and 3D stylization baselines in color fidelity, texture transfer, and content preservation. --- ### Distributionally Robust Schrödinger Bridge Authors: Jinhwan Sul, Panagiotis Theodoropoulos, Vincent Pacelli, Jaemoo Choi, Evangelos Theodorou Published: 2026-10-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.02043v1 Schrödinger bridge (SB) learns stochastic transport between prescribed initial and target distributions. When the initial distribution shifts at test time, the learned dynamics can fail to recover the target distribution. We introduce the Distributionally Robust Schrödinger Bridge (DRSB), which learns a single controller that accounts for uncertainty in the initial distribution. The DRSB objective consists of control energy and a KL penalty between the resulting terminal distribution and the target distribution. DRSB seeks a single controller that minimizes the worst-case value of this objective as the initial distribution varies within an ambiguity set around the nominal distribution. We derive an exact variational formulation of this objective and connect its fixed-terminal-cost subproblem to stochastic optimal control and distributionally robust optimization. This formulation motivates an alternating algorithm that updates the adversarial initial distribution, estimates the terminal log-density ratio, and trains the controller. We develop Wasserstein and Sinkhorn variants using stochastic control optimality conditions to approximate the gradients required for adversarial updates. Experiments on two-dimensional transport tasks and image-to-image translation show improved robustness to input perturbations relative to standard SB, with a tradeoff in nominal performance. On Gaussian mixture transport, Sinkhorn DRSB also achieves lower mean sliced Wasserstein distance than fixed-level noise augmentation at both tested unseen noise levels. --- ### Typological Alignment of Stack-Based Language Models on Mildly Context-Sensitive Artificial Languages Authors: Nadine El-Naggar, Tatsuki Kuribayashi, Ted Briscoe Published: 2026-10-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.02040v1 Some properties of languages, e.g., subject-object-verb (SOV) word order, are more prevalent than others among the thousands of attested natural languages (NLs). Such typological commonality is often attributed to learning biases. Computational simulations, recently with language models (LMs), have facilitated the exploration of this theory. In this paper, we extend existing analyses of the relationship between LMs' learning biases and typological commonality on both data and model sides, focusing on: (i) cross-serial dependencies, the upper limit of attested syntactic complexity, and (ii) stack-based LMs (SLMs), potentially facilitating learning of hierarchical patterns. We first evaluate generalization of SLMs on cross-serial dependencies across diverse artificial languages and confirm that they struggle with such constructions. However, SLMs with limited working memory generalize better suggesting a possible basis for such inductive bias and thus the typological commonality of some word order configurations. --- ### CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning Authors: Yafei Zhang, Songshuo Lu, Sicong Liao, Zhi Chen, Yaohua Tang Published: 2026-10-01 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.02039v1 Recent years have witnessed the rapid adoption of reinforcement learning (RL) in large language model (LLM) post-training, with substantial gains in mathematical reasoning and code generation. In practical systems, however, policy updates and differences between rollout and training engines can make sampled responses off-policy. Sequence-level masking addresses this mismatch by deciding whether an entire response should contribute to optimization. A common masking rule uses the length-normalized geometric mean of sampled token probability ratios. Its signed log-ratios can cancel across positions, concealing substantial bidirectional policy drift. We propose \emph{Cancellation-Aware Response Masking} (CARM), a sequence-level mask that takes the absolute value of each token log-ratio before averaging, preventing opposing probability changes from canceling. We prove that accepted responses satisfy a joint bound on the fraction of sampled-token ratios outside a prescribed band and their mean log-distance beyond its boundaries. Experiments on mathematical reasoning and code generation show that CARM improves mean@16 averaged over AIME 2024/2025/2026 and BeyondAIME by up to $3.13$ percentage points over geometric-mean masking, and increases average pass@1 across four code benchmarks by $2.88$ points over the strongest evaluated baseline. These findings support CARM as a theoretically grounded and effective method for response-level off-policy control in LLM reinforcement learning. --- ### Mimir: Physics-Grounded LLM Agents for Long-Horizon Irrigation Control Authors: Yimeng Liu, Mi Zhang, Younsuk Dong, Zhichao Cao Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.02038v1 Large language model (LLM) agents increasingly combine reasoning, tool use, and action, but most evidence comes from episodic tasks with relatively immediate feedback and reset failures. Long-running physical control operates in a different regime: actions alter future states, errors compound across decisions, and an agent must improve from experience without being allowed to rewrite the physical rules that make execution safe. We study this regime through irrigation, where daily decisions interact with soil-water dynamics over entire growing seasons. We present Mimir, a physics-grounded LLM agent organized around two repair timescales. At the fast timescale, a structured physical interface and deterministic simulator turn an LLM output into a proposal that we numerically check, revise, and subject to bounded deterministic action selection before execution. At the slow timescale, recurrent failure patterns are consolidated into persistent contextual principles that condition future proposals, while the physical model, evaluator, and execution constraints remain immutable. Under a common retrospective evaluator across multiple sites, crops, and years, Mimir attains the lowest reported aggregate control cost among the evaluated references and uses about 51% less irrigation than the historical schedule replay. The ablation study show higher control cost when forward simulation, verified revision, or persistent context is removed; model-scale and model-family studies show no monotonic gain from increasing LLM size. The resulting lesson show that persistent physical agents can combine semantic reasoning with bounded, evidence-driven self-improvement while reserving physical truth and actuator authority for explicit numerical mechanisms. --- ### Global Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent Collaboration Authors: Xin Heng Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.02036v1 AI agents can each make locally valid decisions yet jointly produce an invalid result. We call this the global coherence problem: a failure of shared state, not merely of model intelligence. Our Observation-Aliasing Impossibility Theorem gives the exact boundary. A policy can guarantee a valid action exactly when all worlds producing the same observation share an admissible action. If k indistinguishable worlds require pairwise-disjoint actions, the best randomized worst-case success is 1/k; more reasoning, roles, messages, or samples cannot recover the missing distinction. A stronger model can reason better within its context, but it cannot see beyond it. We then give local-to-global runtime semantics X = (H, C, G, F; D): topology H records overlapping scopes; category C governs state-changing actions; groupoid G retains reversible translations; sheaf F tests whether local views glue into one world; and minimal history D keeps only distinctions that alter legal futures. Models propose; the harness owns shared state and governs commit. Nine studies test both the failure and its boundary. On a controlled revision benchmark, the same frontier model scores 40/40 when the deciding event is visible; when it is hidden, tested arms score 12--17/40, consistent with chance (1/3); restoring one authoritative fact returns 40/40. On TeamBench, ordinary teams exceed a shared budget in 5/5 runs, a visible live count leaves 4/5 violations, and commit enforcement leaves 0/5. In tau2-bench Telecom, current-state checks score 0.07 after silent reverts, while the harness scores 1.00. Where a conventional solver already owns the complete relevant state, it ties the harness as predicted. The counterintuitive conclusion is that local intelligence cannot substitute for missing global state. --- ### Relative Transitions, Not Absolute Destinations: A Transfer-and-Ground Framework for Target-Trajectory-Free Human Mobility Generation Authors: Yidi Wang, Yunhe Zhang, Bangchao Deng, Dingqi Yang, Pengyang Wang Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.02033v1 Individual mobility trajectories support urban analysis and location-based services, yet most trajectory generators require observations from their deployment city. This assumption excludes precisely the cities where trajectories are unavailable even though points of interest (POIs) and their attributes can be obtained from public maps. We study target-trajectory-free generation: learning from POIs and trajectories in source cities while utilizing only POI coordinates and categories in a target city, with no target trajectory or trajectory-derived statistic available for training, model selection, or generation. Existing trajectory generators typically predict absolute destinations, entangling reusable movement behavior with city-specific POI identities and spatial layouts. Our core insight is to replace this city-bound output with context-conditioned relative transitions. We propose Nomad, a transfer-and-ground framework that separates learning how people move from determining where those movements are realized. Specifically, a history-conditioned flow-matching model learns from source trajectories a transition prior over semantic displacement between POI contexts, geographic displacement, and elapsed time; at inference, a behavior graph and an exploration--return walk ground sampled transitions onto the target POI map. This factorization enables a direct test of representation level transferability without assuming invariance of the full mobility distribution. Extensive experiments across ten cities and 14 transfers show that Nomad outperforms adaptation baselines in trajectory fidelity and downstream utility, lowering the average error over the best baseline of each metric by about 15% in distributional fidelity and about 3% in downstream utility. --- ### SPHERE: Adaptive VR Indoor Scene Generation via LLM-Enhanced Spatial Preference Learning and Human-in-the-Loop RL Authors: Hyeonmin Lee, Zheng Wei, Kyungmin Kwon, Jumin Seo, Jiwon Park, Hayoung Oh Published: 2026-10-01 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2610.02023v1 While Large Language Models (LLMs) advance 3D indoor scene synthesis, current pipelines fail to retain user-specific preferences across sessions, making immersive authoring a repetitive and physically fatiguing process. We present SPHERE, an adaptive VR generation framework that transforms isolated synthesis into continuous human-AI co-creation. SPHERE extracts persistent spatial preferences from natural multimodal interactions (speech and controller edits). To ensure geometric resilience against spatial distortions, it abstracts these raw edits into hierarchical constraints modeling both local functional and global topological contexts. Furthermore, a human-in-the-loop reinforcement learning mechanism dynamically updates retrieval policies based on the user's final edited scenes. A mixed-design user study ($N=42$) and an offline ablation demonstrate that SPHERE significantly reduces corrective edits and physical demand, preventing bias toward shallow object-level traits to yield geometrically resilient, profile-aligned layouts. Ultimately, SPHERE demonstrates how capturing demonstrated spatial logic enables controlled spatial adaptation, establishing a reliable, governed human-AI collaboration framework for immersive authoring. Project page and source code will be available at: https://github.com/hyeonmin11/SPHERE --- ### Old Ideas, Novel Problems: The Instability of LLM-Based Novelty Evaluation Authors: Noy Sternlicht, Simra Shahid, Peter Jansen, Daniel S. Weld, Pao Siangliulue, Tom Hope Published: 2026-10-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.02022v1 Automated ideation systems are often evaluated on the novelty of the ideas they produce, and that judgment is increasingly delegated to large language models. Such judges are typically built ad hoc and validated, if at all, on human-authored papers rather than on the generated ideas they are meant to score. So, how do novelty judges perform? Not well. We present a systematic controlled study of novelty evaluation design choices. We first build an evaluation set automatically, mining OpenReview for passages where reviewers explicitly affirm or dispute a paper's originality and keeping only submissions with unanimous agreement at the extremes of their research area; we pair these with ideas from a vanilla LLM generator. Across six judges, we find that small prompt design choices have large consequences; e.g., simply telling the judge that reviewers found one idea novel and the other not can change its verdict on more than half of the identical idea pairs it is shown, shifting pairwise accuracy by over 50 points and occasionally pushing it below chance. The same change helps one judge and hurts another. Retrieval and larger reasoning budgets help little, and two purpose-built novelty evaluators are outperformed by our cheapest prompted baseline. These results raise questions about reported novelty gains of automated ideation systems, and call for robust novelty evaluation methods. --- ### Task-Adaptive Grounded 3D-Programmers Using 2D VLMs Authors: Arman Raayatsanati, Sombit Dey, Anna-Maria Halacheva, Jan-Nico Zaech, Luc Van Gool, Danda Pani Paudel Published: 2026-10-01 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.02021v1 Recent vision-language models (VLMs) exhibit remarkable generalization and reasoning abilities, yet 3D understanding in these models is limited by data scale, training diversity, and reasoning capacity. Instead of naively extending these models into 3D, we take a different approach: we enable powerful 2D VLMs to operate reliably in 3D by introducing 3D grounding and iterative feedback loops with two novel concepts: Canonical Coordinate Framing (CCF) and Task-Adaptive Feedback (TAF). CCF serves as a unified visual representation that anchors both inputs and outputs to a shared Euclidean coordinate system, solving common challenges in 3D grounding such as axis ambiguity, inconsistent metric scale, and floating references. Complementary to this structured framing of the 3D inputs, TAF closes the reasoning loop with task-adaptive dynamic feedback that enables 2D VLMs to perform varied open-vocabulary tasks within their native visual context. Building on this foundation, we introduce 3D-Prog, a 3D understanding, reasoning, and generation framework that jointly employs the capabilities of CCF and TAF together with powerful VLMs. Without requiring any retraining, 3D-Prog performs open-vocabulary 3D understanding, manipulation, and generation across both object-level and scene-level tasks. Our experiments show that the joint use of CCF and TAF transforms 2D VLMs into geometry-aware 3D programmers, achieving consistent, interpretable, and high-quality results across diverse 3D tasks. --- ### Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization Authors: Guangyu Yang, Jingbiao Mei, Mingsheng Sun, Jinghong Chen, Yingtong Bu, Pengda Qin, Da Chen, Bill Byrne Published: 2026-10-01 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2610.02019v1 The rapid growth of video-based social media has increased users' exposure to harmful content, creating a need for reliable automated video safety detection. Although recent Vision-Language Models (VLMs) show strong video understanding capabilities, existing harmful video detection systems face two key limitations: they typically reduce safety detection to binary classification, overlooking the inherently multi-label nature of unsafe videos, and they rely on static training objectives that do not support controllable precision-recall trade-offs, though the desired operating point may vary across moderation pipelines and unsafe categories. To address these gaps, we propose Adaptive Tversky Policy Optimization (ATPO), a reinforcement learning framework for Multi-label Video Safety Detection (Multi-VSD). ATPO introduces the Adaptive Tversky Reward (ATR), which dynamically adjusts false-positive and false-negative penalties during training to enable controllable precision-recall trade-offs. Experiments on SafeWatch-Bench and XD-Violence show that ATPO substantially improves multi-label performance, increasing the Jaccard Index from 40.66 to 75.44 on SafeWatch-Bench-Real. Moreover, ATR enables reliable steering of the precision-recall operating point, supporting deployment scenarios with heterogeneous policy requirements. Code and checkpoints are provided at https://bruceyg.github.io/ATPO-project-page/ . --- ### On Language Drift during RLVR Post-Training Authors: Michael Sullivan, Alexander Koller Published: 2026-10-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.02015v1 Recent advances in LLM reasoning models---driven primarily by the paradigm of post-training via reinforcement learning with verifiable reward (RLVR)---have enabled them to accomplish impressively complex tasks. However, in parallel with their rising capabilities, LLMs have increasingly displayed signs of language drift in their chains of thought (CoTs): unusual, non-standard, and seemingly nonsensical language use. Although it is well-documented---and can potentially impair CoT monitorability---the causes of language drift are thus far poorly understood. In this paper, we identify the conditions under which language drift occurs: we prove theoretically that RLVR optimization pressure permits unbounded language drift, while supervised fine-tuning does not. We then show empirically that language drift specifically arises during RLVR on novel reasoning tasks---i.e. when the target behavior cannot be drawn out of the base model. Finally, we prove that it is not possible to constrain language drift without constraining expected reward, suggesting that CoT monitorability cannot be improved without harming performance during RLVR post-training at the frontier. --- ### Atoms to Processes: The Role of Artificial Intelligence and Machine Learning in Chemical Engineering Authors: Michael Baldea, Linda J. Broadbelt, Marianthi G. Ierapetritou, Akhilesh Jain, Ankur Kumar, Thomas A. Kwan, Fèlix Llovell, Andrew J. Medford, Ilias Mitrai, Joel Paulson, Junyi Qiao, Matthew P. Rivera et al. Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.02014v1 The rapid maturation of artificial intelligence (AI) and machine learning (ML) has catalyzed a profound shift in how chemical engineering problems are formulated, analyzed, and solved. Advances in computing, data availability, and learning algorithms have enabled AI/ML methods to impact applications spanning atomic-scale simulations, materials and catalyst discovery, transport and thermodynamics, separations, process systems engineering, and industrial operations. This article provides a perspective on recent methodological developments and representative applications, emphasizing how AI/ML tools are being integrated with first-principles models to address challenges of predictive accuracy, data scarcity, extrapolation, interpretability, and model lifecycle management. Across domains, a unifying trend is the move away from purely black-box approaches toward hybrid and physics-informed frameworks that explicitly respect conservation laws, thermodynamic consistency, and known structural constraints. These approaches not only improve robustness and reliability, but also enable meaningful human-AI collaboration by providing information at an appropriate level of abstraction for the task and decision context. We conclude that AI and ML are not replacing the core principles of chemical engineering; rather, they are amplifying them. As the field advances toward increasingly autonomous, adaptive, and sustainable systems, the thoughtful integration of AI/ML with first-principles understanding and domain expertise will be essential to realizing their full potential across both research and industrial practice. --- ### BranchIP: Learning Adaptive Equivariant Computation for Interatomic Potentials Authors: Laura Zichi, Gil Harari, Chuin Wei Tan, Marc L. Descoteaux, Albert Zhu, Menghang Wang, Yoel Zimmermann, H. T. Kung, Boris Kozinsky Published: 2026-10-01 Categories: cs.LG, physics.app-ph, physics.chem-ph, physics.comp-ph arXiv: https://arxiv.org/abs/2610.02013v1 Equivariant machine learning interatomic potentials (MLIPs) have revolutionized atomistic modeling, but accurate treatment of complex materials and molecular systems demands expensive models. This limits simulation length- and time-scales, with tensor products a key computational bottleneck. The recent emergence of foundation-scale MLIPs further exacerbates this challenge. We present Branch Interatomic Potential (BranchIP), a single-model framework for learned adaptive tensor product computation, trained with a novel distillation loss. In our experiments on two systems of physical interest, a heterogeneous catalysis system and a proton-conducting solid acid electrolyte, BranchIP accelerates MLIPs across model sizes by up to $2.4\times$ while reducing memory usage by up to $2.6\times$. This is achieved while maintaining physical fidelity. Furthermore, the learned adaptive computation provides model interpretability by revealing which interactions demand deeper computation and showing how computational depth relates to chemical complexity and dynamics. --- ### Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering Chaos Authors: Tristan Shah, Wooyoung Chung, Volodomyr Makarenko, Juan Wachs, Stas Tiomkin Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.02012v1 Reinforcement learning (RL) is a powerful paradigm for training agents, yet its success rests on domain expertise of human engineers who design informative reward signals for every new task. Unsupervised RL aims to reduce this engineering with intrinsic motivation (IM): reward signals that emerge from the agent environment interaction itself. Existing IM objectives, however, involve the selection of information variables, which re-introduces domain expertise the field has sought to eliminate. We introduce Forward CIP (F-CIP), an RL-native formulation of the Controllable Information Production (CIP) objective, which is defined by the system's dynamics alone and requires no such selection. We prove that F-CIP is compatible with RL and demonstrate its effectiveness with existing algorithms. Training agents with F-CIP results in unsupervised discovery of primitive behaviors such as balancing and maintaining controllability, which are essential for more complex robot behaviors. Paired with a simple forward-velocity reward, our method produces coordinated gaits such as hopping and running which otherwise require reward engineering to learn. --- ### Exploring Weaknesses of Generative Image Watermarks against Latent Frequency Masking Authors: Kirill Aistov, Khaled Abud, Irina Serzhenko, Egor Kovalev, Aleksey Yakushev, Aleksandr Akimenkov, Dmitry Obydenkov, Yury Markin, Sergey Lavrushkin, Dmitriy Vatolin, Anastasia Antsiferova Published: 2026-10-01 Categories: cs.CV, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2610.02010v1 Invisible watermarking has become a central tool for tracing AI-generated images, but its robustness against adaptive removal attacks remains an open security question. We introduce Latent Frequency Masking, an attack that erases watermark evidence by replacing selected Fourier coefficients in the latent representation of a watermarked image. The replacement can be sampled from Gaussian noise for efficiency or derived from diffusion regeneration for improved image preservation. We provide a theoretical distortion bound relating the change between the reconstructed adversarial image and the masked latent-frequency perturbation. We evaluate the proposed attack against six diffusion watermarking methods on images generated from DiffusionDB and MS-COCO prompts. Latent Frequency Masking removes or substantially weakens several watermarks while preserving perceptual quality and achieving favorable runtime compared with existing attacks. These results identify latent-frequency manipulation as a practical attack surface and highlight the need to include such attacks in robustness evaluations of generative image watermarking. --- ### Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries Authors: Ionel Eduard Stan, Paolo Napoletano Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.02005v1 A multi-LLM \emph{council} lets several large language models (LLMs) deliberate on a question and return an answer together with a confidence estimate. As these systems become increasingly used for reasoning, that confidence should represent a calibrated \emph{probability of being correct}, and the decision should remain robust when some agents are persistently unreliable. Existing \emph{council aggregation} methods fail on both fronts: their confidence estimates measure decisiveness rather than correctness, and they cannot identify or discount persistently unreliable agents. We introduce Bayesian Dialectical Argumentation (BDA), which treats the council's \emph{typed} moves---who proposed, challenged, or conceded which answer---as observations of a classical annotator model with \emph{per-agent} reliabilities. This formulation recasts multi-agent deliberation as a reliability estimation problem, using the deliberation trace to infer agent reliability under persistent adversarial behavior. By weighting evidence according to inferred agent reliability, BDA yields calibrated posterior probabilities over candidate answers while allowing persistently unreliable agents to be inverted rather than merely outvoted. Across binary and multi-class benchmarks, BDA achieves the best calibration among zero-cost council aggregation methods, requiring no additional LLM calls, and improves robustness under persistent adversarial coalitions while remaining competitive in clean settings. --- ### Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents Authors: Ahmad Yehia, Aly O. Abdelkareem, Islam Ahmed, Hesham Omran, Khaled Alashmouny, Christian Claudel, Abduallah Mohamed Published: 2026-10-01 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.02002v1 Large Language Model (LLM) agents now take part in organizational work, where many authors record decisions across documents over months. Because a revised decision arrives as a new document rather than an edit, answering a question requires knowing which version held at a given time. However, most memory systems compress the record at write time. By distilling each document into facts, notes or graph edges, these methods fix what can be answered before any question is asked. To address this, we propose Mem++, a non-destructive memory framework shifting from write-time distillation to read-time selection. Mem++ stores every document whole with its date and author, and it calls no generative model at write time. At read time, it retrieves only documents dated up to the time a question asks about and fuses lexical and semantic rankings. Unlike systems that overwrite older versions, Mem++ keeps them and leaves the choice to the answering model. Evaluations on the organizational benchmark OrgMemBench demonstrate that Mem++ surpasses the strongest memory system baseline by 8.0 to 13.1 points across two answering models. With gpt-4.1-mini, it also achieves the best overall score, 2.6 points above RAG. In addition, Mem++ achieves the best average LLM-judge score on LoCoMo and ranks second on LongMemEval-S, behind only its entity-graph variant. Code for benchmark evaluation is available at https://github.com/AIDAChip-Inc/mem-plus-plus. --- ### Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks Authors: Hao Wang, Ting Huang Published: 2026-10-01 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.02001v1 Small open-weight models (2-9B) run on ordinary laptops, but under cloud-scale agent harnesses they rarely complete real tasks: tool prefill overflows the context, self-correction diverges, tool demonstrations loop, and tasks are silently abandoned. We present evidence, from a controlled single-machine comparison and one third-party benchmark, that a substantial share of these failures is attributable to the harness rather than the model. We introduce Mingbird, a local-first agent harness for Windows and Ollama whose ten mechanisms compensate point-by-point for small-model failure forms, three of them representative: a byte-level net-zero prefill budget, a finish gate that re-reads the task before accepting completion, and signature-level loop detection. On LRAB, a controlled comparison holding machine, models, budgets, and scoring fixed (4 harnesses $\times$ 4 open models (2B-35B) $\times$ 18 real tasks, deterministic artifact scoring), Mingbird reaches 0.886 overall against 0.631 (goose), 0.479 (opencode), and 0.405 (agent-mini), with all 288 cells published; on $τ^2$-bench (278 tasks, three arms, one protocol) it totals 0.856 against 0.791 and 0.737; and a frontier-model probe on the same 18 tasks spans 0.997 to 0.478 across harnesses, with well-formed scaffolds staying within 0.072 of each other. A leave-one-mechanism-out ablation is reported as directional only: same-night replications of the same arm move its mean by up to 0.069, the size of every nominal single-trial delta, and the one batch-matched comparison (full mechanism stack versus text re-read alone) gives the executable completion guards a paired +0.10 across three replications. The evidence carries stated limits: a self-built benchmark, a single machine, and single-trial scoring. --- ### Weather-Aware Domain Adaptation for Street-View Weather Recognition Authors: Hossein Maghsoumi, George Atia, Yaser P. Fallah Published: 2026-10-01 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.02000v1 Adverse conditions such as rain, snow, fog, and dust remain challenging for camera-based perception in autonomous driving. We study multi-class weather recognition from street-view images under domain shift, where most available training data come from non-street-view sources that differ markedly from real driving scenes. We propose Weather-Aware Adversarial Discriminative Domain Adaptation (WA-ADDA), which conditions the domain discriminator on predicted weather to promote features that are both domain-invariant and weather-sensitive. We also assemble a multi-dataset benchmark by unifying diverse non-street-view weather collections as sources and real street-view images as targets, and define a standardized evaluation protocol with macro accuracy as the primary metric. Across backbones (ResNet-50, EfficientNet, VGG, DenseNet), WA-ADDA consistently improves street-view performance and yields strong per-class recalls in challenging conditions while preserving clear-weather accuracy. These findings highlight the feasibility of domain-adapted weather recognition and the value of our benchmark for advancing robust, on-board perception. --- ### From Reasoning Failures to Composable Video Spatial Intelligence Authors: Pengzhan Sun, Junbin Xiao, Ramanathan Rajaraman, Shiu-hong Kao, Angela Yao Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01999v1 Spatial reasoning benchmarks evaluate vision-language models across diverse tasks, but task-level scores do not reveal which underlying capabilities account for success or failure. Each task requires recovering spatial evidence, representing geometry, and reasoning over it. We disentangle these capabilities by comparing predicted and ground-truth spatial context under a shared schema and coordinate contract. This comparison reveals four recurring sources of error: inaccurate perception, missing information in the spatial context, selection of the wrong measurement, and errors in reference frames or in tracking position and orientation. Guided by this diagnosis, we develop CROSS, a training-free library of typed geometric operators and spatial skills that function over available evidence to support reliable video spatial reasoning. The resulting library supplies verified context to non-coding VLMs or callable skills to a SpatialClaw agent. We evaluate \methodname{} on five benchmarks. \methodname{} raises the average score from 55.9\% to 60.2\% on ReVSI and improves the SpatialClaw result from 62.8\% to 66.3\% on DSI-Bench. These gains demonstrate that explicit handling of spatial conventions can repair systematic reasoning failures without additional training. --- ### Can AI Oversight Be Zero Knowledge? Authors: Alessandro Chiesa, Ziyi Guan, Burcu Yildiz Published: 2026-10-01 Categories: cs.AI, cs.CC, cs.CR arXiv: https://arxiv.org/abs/2610.01995v1 AI systems increasingly produce outputs from confidential data, such as a fitness-for-duty assessment from medical records or the predicted properties of a drug candidate from its secret structure. It is important to verify that such outputs are correct without revealing the underlying data. A recent line of work studies verification of AI outputs via interactive proofs and debate for oracle-aided computation, where correctness may depend on an oracle such as human judgment, a physical experiment, or the web. These works focus on verification by a verifier that runs much faster than the computation. However, such efficient verification is impossible for general oracle-aided computation, and these works therefore rely on additional assumptions. We focus instead on privacy: allowing the verifier to run in time polynomial in the computation, we ask whether interactive arguments for oracle-aided computation can be zero knowledge, so that the verifier learns nothing about the confidential data beyond the correctness of the output. We prove that, in general, they cannot. In the random oracle model, there are no zero-knowledge proofs for all oracle-aided computations, even if both the prover and the verifier are allowed to run much longer than the computation itself. The impossibility extends to debate, a canonical model for scalable oversight. On the positive side, we show that if the oracle attaches a cryptographic signature to each of its answers, then every oracle-aided computation can be verified in zero knowledge with an efficient prover and verifier, assuming only collision-resistant hash functions. Beyond privacy, this also gives an alternative approach to scalable oversight that relies neither on an honest opponent, as in debate, nor on the robustness of the computation, as in prior single-prover protocols. --- ### Comparing a gradient boosting algorithm to the GOES FDC for wildfire detection Authors: Asaf Vanunu, Boaz Nadler, Arnon Karnieli Published: 2026-10-01 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.01994v1 Wildfires pose severe risks to human life, ecosystems, and property. This study presents a machine learning approach for wildfire detection from GOES ABI imagery. A CatBoost model was trained on a large dataset with thousands of ABI images and over 300,000 matching VIIRS fire detections. An evaluation on a separate dataset across five regions showed that the learned CatBoost model outperformed the operational GOES Fire Detection and Characterization (FDC) product. It achieved higher precision, recall, and F1 scores both within and outside the training area. The CatBoost model achieved F1 scores that were 0.16 to 0.38 higher than the GOES FDC in all regions. In addition, out of 51 historical fire events, the CatBoost detected 26 fires before both VIIRS and GOES FDC, compared to only six earlier detections by the GOES FDC. Importantly, the CatBoost model achieved accurate wildfire detection also during nighttime, whereas the GOES FDC obtained very low recall values, around 0.03. This study demonstrates that machine learning models may offer significant improvements over existing geostationary fire products, including higher accuracy, fewer false alarms, and earlier detection. --- ### Continual Concept Erasure in Diffusion Models by Suppressing Cross-Edit Interference Authors: Yongliang Wu, Haori Lu, Jinqi Luo, Wei Cao, Xingyu Zhu, Yaoyao Liu Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01989v1 Concept erasure removes copyright-protected, privacy-sensitive, or otherwise undesirable concepts from pretrained text-to-image diffusion models to support content governance and compliance. As erasure requests arrive over time, models must remove new targets without undoing prior erasures. Existing methods do not constrain interference across edits: residual perturbations outside the retain set interact and accumulate, degrading unrelated generations and sometimes collapsing previously erased targets into noise. We propose CEASE (Continual Erasure via Adaptive Subspace Editing), a training-free method that imposes two subspace constraints on a closed-form solver. CEASE adds the token representation of the shared replacement to the solver's invariance matrix and, when interference is detected, projects the current update onto the orthogonal complement of dominant output directions extracted from cumulative past updates. A closed-form decomposition attributes the accumulated interference to repeated activation of the shared replacement and overlap between successive update directions, showing that the two constraints suppress these respective sources. Across continual erasure of celebrities, artistic styles, and instances, CEASE achieves the most consistent erase-preserve trade-off, while existing methods either degrade general generation or insufficiently erase targets. --- ### Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities Authors: Hyunsik Kim, Youngmoon Jung Published: 2026-10-01 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.01984v1 Byte-level byte-pair encoding (BBPE) tokenizers are attractive for multilingual large language models (LLMs) because they cover all Unicode text. In UTF-8-based BBPE, however, many scripts start from a higher fallback cost than English: when no learned merges can be applied, a multibyte character requires multiple byte-derived symbols. We call this worst-case pre-merge cost the encoding floor. A higher floor can increase token counts and per-request cost and shrink usable context. Changing the text encoding can reduce this gap, but a single global encoding can make already-efficient English spans more expensive in mixed-script text. We propose Universal Byte-Level Encoding (UBE), a dual-alphabet tokenizer that keeps 1-2-byte UTF-8 characters on the UTF-8 path while routing 3-4-byte UTF-8 characters through UTF-16. This lowers the encoding floor for 3-byte Basic Multilingual Plane (BMP) characters in scripts with high token premiums (token counts relative to English) without raising it for already-efficient spans in mixed-script text. UBE changes only the byte representation presented to byte-pair encoding (BPE); the merge rule remains standard, and exact decoding is preserved. UBE also composes with alternative boundary policies and morphology-based representations. In a Unicode 17 audit, UBE exactly round-trips all Unicode scalar values and all inputs in the official normalization, grapheme-break, and emoji test suites. Across intrinsic evaluations, UBE lowers dispersion in English-normalized token-count ratios, reducing cross-lingual token-budget disparity. In multilingual language model (LM) experiments, UBE matches BBPE's LM quality. In the main multilingual settings, UBE reduces token counts most for high-premium scripts and slightly lowers English token counts, yielding more usable context under fixed token budgets and faster prompt processing in content-matched benchmarks. --- ### Universal interpolation for deep residual self-attention networks Authors: Sibylle Marcotte, Joan Bruna Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.01981v1 Universal approximation is a necessary qualitative property of learning architectures to benefit from scaling laws. While it is generically verified on a variety of neural architectures and random feature models, it typically involves infinite width limits. In this work, we focus on deep self-attention models and consider instead the `dual' regime, where approximation power is enabled entirely by depth, and featuring strong parameter sharing across layers, motivated by recent models such as the Looped Transformers. More specifically, we ask whether one can find a predefined finite set of parameters, each defining an attention block, such that the resulting finite set of transformations can map any collection of $N$ sequences of $n$ tokens to any other collection of $N$ sequences of $n$ tokens. Crucially, these transformations are \emph{fixed independently of the input and output} collections: only the order in which the blocks are applied, their signs, and their durations depend on the particular interpolation task. Our main result establishes it for residual softmax attention using only two frozen single-head blocks with Gaussian-initialized projection matrices. The result holds at both continuous and finite depth. We also characterize the restrictions imposed by causal masking and establish corresponding universal interpolation guarantees. --- ### The Curvature of Regret in Contextual Linear Optimization Authors: Konstantinos Ziliaskopoulos, Alexander Vinel, Alice E. Smith Published: 2026-10-01 Categories: cs.LG, math.OC, stat.ML arXiv: https://arxiv.org/abs/2610.01980v1 Decision-focused learning for linear optimization is complicated by the discontinuity of the optimizer, where small cost errors may leave the decision unchanged or move it to a different vertex. We show that this non-smooth pointwise behavior becomes locally quadratic after averaging over the data distribution, and we derive the curvature in closed form, specifically, a matrix-valued measure supported on the walls of the normal fan. This measure depends only on the feasible set, with the data distribution entering only as a weight. We then offer a tractable approximation for this curvature, computable with just one projection to the feasible set. We prove that the approximation weakly converges to the true population curvature. We offer one application of our findings, a decision-aware scenario generation method for expected-cost linear optimization. Our experiments test the quadratic and weak convergence laws and show a 30.8% regret improvement over uniform allocation on battery arbitrage. --- ### Sim+Real: Joint Simulation - Experiment Training Improves Balanced Prediction in Physical Systems Authors: Mahindra Rautela, Alexander Scheinker, Ayan Biswas, Diane Oyen, Nathan DeBardeleben, Earl Lawrence Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.01974v1 Simulation and experimental measurements provide complementary data for learning spatiotemporal physical systems, but standard simulation-to-experiment fine-tuning optimizes only the experimental objective after transfer and can degrade simulation performance. We formulate simulation--experiment prediction as a multi-objective learning problem with domain-specific simulation and experimental risks. On four fluid systems from RealPDEBench and two model capacities, we compare Simulation only, Experiment only, Sim$\rightarrow$Exp, and Joint training, evaluating every final model on both held-out domains. Sim$\rightarrow$Exp tends to specialize more strongly to experimental data at the cost of simulation-domain forgetting. Joint training consistently achieves the best balanced performance over a broad range of simulation--experiment evaluation weightings, while substantially improving simulation retention over Sim$\rightarrow$Exp. Joint also better preserves simulation-only fields absent from experimental measurements. Project page: https://mahindrautela.github.io/morph. --- ### Token-Level Video Reinforcement Learning Authors: Yifan Wang, Gordon Guocheng Qian, Yanyu Li, Anil Kag, Yun Fu Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01973v1 Reinforcement learning (RL) for video generation usually assigns one scalar reward to an entire sampled video. Yet a video is not uniformly flawed: some visual tokens may already satisfy the prompt, whereas others require correction. A scalar reward cannot localize errors, causing optimization to perturb satisfactory tokens while under-targeting the tokens that actually need to change. We introduce Token-Level Video Reinforcement Learning, TVRL, a framework that derives token-level credit from the reward being optimized. Our key insight is that the answer likelihood of a frozen vision-language model provides both signals: its outputs contribute to the video-level reward, while magnitudes of its video-input gradients reveal which generated video tokens most affect that score. We instantiate TVRL in Group Relative Policy Optimization by averaging prompt-derived question rewards into one group-relative advantage and using detached, question-conditioned token-credit maps to reweight dense denoising-transition log-probabilities inside the clipped policy ratio. On VBench-2.0, TVRL achieves an Overall score of 57.69, outperforming the base model by 3.60 points. TVRL also improves matched GRPO baselines across three SDE samplers (SAGE, Flow, and Dance) by 2.68--3.15 points and across four reward models (VideoAlign, VideoScore2, UnifiedReward2, and Qwen3.5-9B) by 1.33--3.15 points. --- ### RASteer: Retain-Aware Activation Steering for Concept Erasure in Diffusion Models Authors: Yongliang Wu, Haori Lu, Yulun Wu, Jinqi Luo, Xingyu Zhu, Yaoyao Liu Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01969v1 Concept erasure aims to remove a target concept, such as a copyrighted style, a recognizable character, or unsafe content, from a pretrained text-to-image diffusion model while preserving its ability to generate other content. Existing activation steering methods build an erasure direction mainly from the target concept and adjust model activations along it at inference time. However, target and retained concepts often overlap in the model's representation space, so this direction also contains shared components that retained concepts rely on. Steering directly along this direction can therefore suppress retained concepts and harm the generation of non-target content. To address this issue, we propose Retain-aware Activation Steering (RASteer), a training-free method. RASteer first builds a retain subspace from the concepts to preserve. Retain-Orthogonal Steering (ROS) then removes components aligned with this subspace from the erasure direction, making steering more specific to the target. Since fully removing the shared components can weaken erasure, we further introduce Overlap-Adaptive Calibration (OAC). At each layer and denoising step, OAC uses the overlap between the erasure direction and the retain subspace to control how much of each shared component is removed, balancing target erasure and concept preservation. Experiments on unsafe-content, instance, and artistic-style erasure across multiple backbones and benchmarks show that RASteer matches or outperforms the activation steering and weight editing baselines we evaluate, achieving a better balance between erasure and preservation. --- ### FastCI: Efficient GPU-Intensive CI for LLM Training Frameworks Authors: Tianshuo Qiao, Naiqian Zheng, Xiaopeng Liu, Shuguang Wang, Diandian Gu, Xuanzhe Liu, Xin Jin Published: 2026-10-01 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2610.01967v1 As large language models (LLMs) keep growing in size and complexity, their training frameworks evolve at a rapid pace as well. Therefore, continuous integration (CI) is critical for maintaining the quality and stability of these frameworks. However, unlike traditional software, CI for LLM training frameworks relies on GPU-intensive tests, which usually involve complete model training or evaluation. This leads CI itself to become a new bottleneck for fast-paced development. In this paper, we introduce FastCI, a framework that improves the efficiency of CI for LLM training frameworks. FastCI leverages runtime evidence to select affected tests and prune tests that execute changed code in equivalent contexts. Then FastCI prioritizes high-risk tests to expose potential failures earlier, and optimizes test workloads along dimensions outside the intended validation scope of each test. Evaluated on the CI workload of our LLM training framework, FastCI reduces the CI latency by 77.5% and the GPU resource usage by 63.9%, while improving the modified code coverage retention by 3.2%, compared with the currently deployed CI pipelines. FastCI has now been integrated into the CI pipelines of our LLM training framework at ByteDance. --- ### Counterfactual Auditing of Bias in Open-Source Large Language Models for Clinical Triage Authors: Manar Aljohani, Brandon Ho, Kenneth McKinley, Dennis Ren, Xuan Wang Published: 2026-10-01 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.01963v1 Emergency department (ED) triage is a high-stakes prioritization task in which demographic, socioeconomic, and system-context information may improperly influence acuity assignment. Although open-source large language models (LLMs) are increasingly considered for local and privacy-preserving clinical decision support, it remains unclear how counterfactual bias varies across model families, sizes, medical-domain models, and domain-adapted models. We present a comparative counterfactual audit of ten open-source LLMs for pediatric Emergency Severity Index (ESI) prediction. Starting from real and handbook-style clinical vignettes, we construct paired counterfactual variants that change only one injected demographic, socioeconomic, healthcare-access, behavioral, social, or system-context variable while holding the clinical presentation fixed. Models include Qwen2.5-7B, Qwen2.5-14B-Instruct, a QLoRA fine-tuned Qwen2.5-7B, MedGemma variants, MedLLaMA2-7B, GPT-OSS-20B, and GPT-OSS-120B. We measure any counterfactual shift, undertriage, overtriage, shifts greater than one ESI level, mean shift, and mean absolute shift. Counterfactual sensitivity varied substantially and did not consistently decrease with larger model size or medical-domain pretraining. The fine-tuned Qwen2.5-7B showed the lowest overall sensitivity, with a 5.27% any-shift rate and mean absolute shift of 0.0534, versus 16.02% and 0.1706 for the base model. Several larger or medical-domain models showed more significant shifts. Stratified and correlation analyses further revealed clinically important directionality and shared failure patterns hidden by aggregate rates. These findings support counterfactual auditing as a lightweight, clinically interpretable framework for comparing fairness risks in open-source LLMs before clinical deployment. --- ### SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning Authors: Si Qi Goh, Cap Dang Xuan Kiet, Tat-Jen Cham, Kwok-Yan Lam Published: 2026-10-01 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2610.01962v1 The ability of vision-language models (VLMs) to associate visual identities with biographical information creates a need for selective unlearning of personally identifiable information (PII) while preserving permitted knowledge about the same individual. This setting is challenging because both sensitive and retained information can share the same visual inputs and intermediate representations. We introduce SIEVE, a simple and effective framework for selective VLM unlearning. SIEVE directly regularizes attention-value representations while also controlling model outputs. SIEVE suppresses attention values for forget examples toward a constant zero, while preserving retain-example representations by matching them to a frozen reference model. These objectives are combined with sequence-level forget and retain supervision, enabling targeted forgetting without largely affecting retained knowledge. Extensive experiments show that SIEVE achieves state-of-the-art performance on unlearning with multiple model-modality settings, while maintaining competitive retained utility. Ablation studies further show that value suppression and negative cross-entropy contribute complementary forgetting signals, while reference-based value matching substantially reduces utility degradation. These results demonstrate that attention values provide an effective intervention point for selective multimodal unlearning when sensitive and retained knowledge are closely related. --- ### Training-Free Diffusion Planning with Analytical Local Scores Authors: Michael Y. Fatemi, Jinhao Liang, Ferdinando Fioretto Published: 2026-10-01 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2610.01959v1 Path finding and multi-robot motion planning require trajectories that are smooth, goal-directed, and collision-free in environments with complex geometric constraints. Recent diffusion-based planners have shown that trajectory generation can be cast as iterative denoising which has opened the doors to learning-based approaches that can handle multi-modal trajectory distributions and refine entire trajectories. However, a key limitation is that diffusion planners require training on large collections of feasible trajectories, rendering them map-specific, and difficult to deploy when high-quality demonstrations are unavailable. This paper introduces a training-free diffusion-based motion planner that replaces learned global trajectory scores with analytical local scores derived from obstacle, smoothness, velocity, and inter-agent feasibility terms. The proposed idea relies on a key observation: the score of a trajectory can be reconstructed by considering only local interactions between neighboring waypoints and nearby constraints. This structure exploitation yields a decomposed denoising procedure that retains the optimization structure of classical trajectory methods while inheriting the iterative refinement behavior of diffusion models. Experiments on a large collection of complex environments and large multi-agent planning tasks show that the proposed analytical score produces smooth and feasible trajectories within limited computational costs, for example in generating feasible paths for 300+ agents in environments containing 100+ obstacles in under 6 seconds on a GPU, outperforming strong learning-based and optimization baselines, while avoiding the data requirements of learned diffusion planners. --- ### EndoLive: Real-Time Style Transfer for Endoscopic Endonasal Skull Base Surgical Video Authors: Griffin Hurt, Calvin Brinkman Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01956v1 Complex surgical procedures around critical anatomy, such as the endoscopic endonasal skull base surgery, requires significant practice and training on the part of the surgeon before they are allowed to perform the operation on a live patient. This training in typically done in cadaveric specimens, due to them containing the same critical structures as a living human. However, cadavers are not a perfect 1-to-1 substitute for a living patient. The dead and preserved tissues of a cadaver are colored completely differently than a living human, and -- without complex and expensive pumping systems -- do not bleed in the same way. As a result, identifying the critical pieces of anatomy that make this procedure so complex can be quite different in a live case than in a surgeon's cadaveric practice. This paper presents EndoLive, a framework for real-time style transfer between cadaveric endoscopic video and living human endoscopic video. Our method combines the ConStructS GAN model for realistic style transfer for surgical applications, with the HyPER-GAN model that can learn complex translations and perform them in real-time. We train EndoLive on unpaired cadaveric and live images taken from an endoscope, and test the trained model with cadaveric video, on a variety of devices. Experimental results demonstrate that EndoLive can perform cadaveric-to-live translation at speeds well above the minimum necessary for real-time, while maintaining semantic consistency of critical anatomical structures. Our source code is available at https://github.com/griffhurt/endolive. --- ### Do Your Own Research: Learning to Forecast by Learning to Search Authors: Yusuf Afifi, Artur Kiulian, Anton Polishko, Mykola Khandoga, Hamudi Naanaa, Alina Krasnobrizha Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.01955v1 Outcome-based reinforcement learning can train language models to forecast real-world events, but prior forecasting work either freezes research context before training or deploys agentic research only at test time, so the skill of gathering evidence is never shaped by the reward. We introduce an agentic forecasting environment, dataset, and harness built from 2,100+ resolved Polymarket questions; the agent acquires its own context at rollout time (web search, page reading, and financial time series, all restricted by layered leak filtering to information published before each question's cutoff), and we train Qwen3.5-35B-A3B (3B active parameters) on it with single-epoch GRPO under a Brier-score reward. Training changes how the agent interacts with information: calibration improves 30-40%, and search attempts fall from 3.8 to 2.25 per rollout as evidence discipline is learned. Evaluated in an identical harness against four frontier models, the trained policy also finishes ahead of every frontier model tested at evidence-based forecasting, including Claude Opus 4.5 (soft-Brier 0.254 vs. 0.256, n=265), at about 5% of the inference cost, and its margin is widest on the hardest questions, the ones the crowd itself had not decided. We release the environment, dataset, and per-rollout records as a reusable harness for temporal forecasting agents. --- ### Sharp Non-Asymptotic Analysis of the Penalized Challenger in $β$-EB-TCI for Bernoulli Bandits Authors: Nam Nguyen, Tuan Quang Dam Published: 2026-10-01 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.01951v1 Top-two algorithms are simple and effective for fixed-confidence best-arm identification, but their sharp non-asymptotic behavior is still not well understood. We study this problem for Bernoulli bandits through $β$-EB-TCI, the empirical-best top-two rule of Jourdan et al., whose challenger is chosen using a Bernoulli transportation cost with a logarithmic count penalty. We prove that, after the empirical leader has become the true best arm and its sampling fraction stays close to $β$, the stopping time is $T_β^{\star}(μ)\log(1/δ)$ up to lower-order concentration terms. We also show that, in this regime, every challenger is sampled linearly often. Thus, for the original algorithm without forced exploration, the main remaining difficulty is to control when the empirical leader becomes permanently correct. These results imply a non-asymptotic high-probability bound for all Bernoulli instances with a unique best arm. If the algorithm satisfies a finite-mean sufficient-exploration condition, the bound further yields the sharp expected sample complexity. In particular, this gives the sharp expectation result for the unguarded Bernoulli rule when all arm means are pairwise distinct, using the sufficient-exploration result of Jourdan et al. Finally, if we add a mild forced-exploration rule that contributes only $O(\sqrt{Kt})$ pulls up to time $t$, we obtain a self-contained expected sample-complexity theorem for any number of arms under the unique-best-arm assumption. We also identify a limitation of proof strategies that try to handle equal suboptimal means through a single index-comparison argument. --- ### A Hybrid Approach to Malware Detection: Integrating Few-Shot Model-Agnostic Meta-Learning with Autoencoders Authors: Emmanuela Andam, Yasir Abbas Zaidi, Abdelali Hadir, Emmanuel Grant, Naima Kaabouch Published: 2026-10-01 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.01949v1 Ransomware has emerged as a major cybersecurity threat, with incidents increasing in frequency and impact across critical sectors. These attacks are typically launched through phishing emails, malicious downloads, or exploitation of software vulnerabilities to gain system access. Once inside, the malware encrypts files and demands a ransom, often in cryptocurrency, for the decryption key. Conventional detection methods often struggle with novel or scarce samples, leaving systems vulnerable. To address these challenges, this paper proposes a hybrid deep learning framework that combines an Autoencoder Feature Extractor (AFE) with a Model Agnostic Meta Learning (MAML) classifier for few shot malware detection. The AFE generates compact latent features that reduce noise and dimensionality, while the MAML classifier rapidly adapts to new threats using limited labeled data. Experiments conducted on the Ransomware Dataset 2024 demonstrate the effectiveness of the framework in binary classification tasks. Across one to fifty shot settings, the proposed model consistently achieves high accuracy, F1 score, and Matthews Correlation Coefficient values, maintaining reliable classification even under extreme scarcity. These results highlight the model's robustness and effectiveness in adapting to limited data scenarios, demonstrating the potential of combining feature extraction with meta learning to enhance resilience against malware, particularly in sectors such as healthcare, manufacturing, and public infrastructure, where cyberattacks can cause significant operational and financial disruption. --- ### Latent JEPA: Abstract Future Prediction for Latent Reasoning in Chemistry Authors: Xinjian Zhao, Yaoyao Xu, Xuemin Chen, Xiaozhuang Song, Tianshu Yu Published: 2026-10-01 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.01947v1 Large language models offer a promising foundation for chemical reasoning, bringing together chemical knowledge and multistep problem solving. Chemical intuition can provide an initial sense of plausible outcomes before the details of a solution are fully worked out. Inspired by how such expectations complement explicit analysis, we study how continuous latent thoughts can be trained to anticipate informative aspects of future solutions without verbalizing every intermediate step. We introduce Latent JEPA, a framework that combines autoregressive learning with joint-embedding prediction of one or more future views. For chemical reasoning, we develop textual and molecular prediction objectives that connect latent thoughts to both subsequent reasoning and molecular outcomes. Experiments on ChemCoTBench show gains in molecular optimization and on several editing and reaction metrics. Representation analyses show that future prediction makes latent thoughts more informative about molecular outcomes and strengthens their correspondence with chemical structure. These findings support abstract future prediction as a learning principle for connecting continuous latent reasoning with scientific outcomes. --- ### Anti-Persona: Disrupting Unauthorized Identity Binding and Recognition in Personalized Vision--Language Models Authors: Abhishek Basu, Fahad Shamshad, Karthik Nandakumar Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01944v1 Few-shot personalization enables large vision--language models (LVLMs) to learn user-specific visual concepts for applications such as personalized retrieval and subject-aware querying. However, it also creates a privacy risk: an adversary can bind a target identity from a few reference images and subsequently detect that identity in new images through natural-language queries. We introduce Anti-Persona, an image-level defense against unauthorized identity binding and recognition in personalized LVLMs. Our key insight is that identity personalization relies on visual features shared across multiple reference images. We aggregate these features into an identity prototype and optimize visually subtle perturbations that disrupt prototype alignment in the vision-encoder space. Spatial smoothing and low-frequency preservation further promote visual fidelity and practical resilience to image compression. The resulting protection does not depend on a specific prompt and supports both proactive anti-personalization and reactive image protection. Experiments on two representative personalized LVLMs demonstrate protection rates of up to $95.0\%$ while preserving visual fidelity. The method remains stable across prompt variations and evaluated identity-query tasks, and improves black-box transfer under encoder mismatch. --- ### Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Models Authors: Efstathios Karypidis, Spyros Gidaris, Nikos Komodakis Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01942v1 Predicting the future evolution of a scene is a fundamental capability for world modeling. Recent work has shown that operating in the feature space of Vision Foundation Models (VFMs) yields semantically rich representations that support diverse future scene understanding tasks. However, existing approaches rely on two-stage pipelines, where VFM features are first compressed using fixed dimensionality reduction (e.g., PCA) or independently trained autoencoders, and a separate predictor is trained on top of the resulting frozen latent space. This decoupling between representation learning and temporal prediction, as well as approaches that apply predictors directly on raw VFM features, provides no guarantee that the latent space is structured for predictable dynamics. In this work, we propose Latent-Foresight, an end-to-end framework that jointly learns a latent tokenizer and a flow-based generative dynamics model, explicitly shaping the representation to support temporal predictability. To enable stable joint optimization, we introduce several key design choices that prevent latent collapse and align reconstruction with generative objectives. Extensive experiments show that our approach learns more temporally coherent latent representations and consistently outperforms two-stage baselines across multiple future scene understanding tasks and prediction horizons, while eliminating separate training stages, including during high-resolution adaptation. We provide the implementation code and model weights at https://github.com/Sta8is/Latent-Foresight --- ### Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens Authors: Ruiyang Si, Jianxin Bi, Shunyu Yang, Rui Ni, Wenbo Huang, Qiang Wang, Shulong Jiang, Duomin Wang, Xiuyu Li, Haiwen Feng, Zhen Dong, Daquan Zhou Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01939v1 Vision language model (VLM) agents can control robots through visual feedback and action primitives, but repeated model invocations and redundant observations incur substantial token overhead. We introduce PyRUA-Lean, an interactive code-execution framework that couples feedback-driven primitive composition with selective observation: the agent composes classical robot primitives and learned vision-language-action (VLA) policies into Python cells that perform conditional checks and local retries, returning only explicitly requested images and state feedback for replanning. Across 700 simulated task instances from LIBERO-PRO, RoboTwin 2.0, and RoboCasa365, we compare PyRUA-Lean with a tool-calling baseline using the same GPT-6 Astra planner and underlying robot primitives. Under equal LLM-call budgets, PyRUA-Lean increases overall success from 63.1% to 71.7%. On instances solved by both agents, it uses 49% fewer LLM calls and 65% fewer input tokens. --- ### A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined Authors: Zhangshu Joshua Jiang, Zina Ibrahim, James T. Teo Published: 2026-10-01 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.01938v1 Exam-style accuracy does not establish whether large language models (LLMs) reason well over clinical records. We define clinical reasoning as integrating and updating evidence across time and sources to form, revise and justify a patient's problem representation and a defensible plan. This structured narrative review maps three literatures: medical education assessment instruments, clinical LLM benchmarks published from 2023 onwards, and general-domain methods for evaluating long-form generation. We examine six dimensions: problem representation, temporal synthesis, differential and management reasoning, counterfactual reasoning, calibrated uncertainty, and reasoning faithfulness. Preprints are included and flagged. No single instrument covers all six dimensions. Problem representation and differential or management reasoning are reasonably covered, although reliability varies by instrument and setting. TIMER-Eval targets temporal synthesis, and ER-Reason assesses sequential diagnostic belief updating. Dedicated uncertainty and counterfactual evaluations are emerging, but their applicability to longitudinal free-text reasoning remains limited. Factual completeness is well theorised in general-domain evaluation, with early clinical evidence of important omissions. Faithfulness remains the weakest dimension, with one identified clinical causal-ablation study on multiple-choice questions. Existing tools should be combined through binary rubric items, separate completeness and correctness scores, case-specific importance weighting with non-compensable safety caps, temporal order-consistency checks, and chance-corrected reliability reporting. Further design work is needed for calibrated uncertainty, counterfactual reasoning and faithfulness over longitudinal free-text records. This review provides a design rationale, not a validated instrument. ---