# Research Papers — 2026-10 · bundle page 151 of 156 > Full-text markdown of papers #7501–7550 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/151 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/150.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/152.md) ### Neither Black nor White: Balancing Semantic and Collaborative Signals with Graph-Informed Semantic IDs (GrIS) Authors: Aleksei Medvedev, Alejandro Ariza-Casabona, Steven Derby, Gonzalo Fiz Pontiveros, Xinyang Shao, Florian Spiess Published: 2026-10-01 Categories: cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2610.01533v1 Existing work on Semantic IDs (SIDs) for generative recommendation treats SID construction as a representation learning problem: encode items into a quantised latent space and read off codes. We argue this view is incidental. SID construction is, at heart, a recursive clustering problem, and once stated this way the natural object to cluster is a graph whose nodes carry semantic content and whose edges carry collaborative signal; SID assignment becomes a hierarchical graph partition. This reframing yields a unified framework, Graph-Informed Semantic IDs (GrIS), that subsumes prior approaches rather than displacing them. RQ-VAE and RQ-KMeans are recovered as the special case where the graph is empty, exposing content-only quantisation as one corner of a larger design space along two so-far-collapsed axes: graph construction and recursive partition algorithm. We explore two contrasting instantiations: RecDMoN, which performs hierarchical assignment via differentiable graph pooling, and RQ-GAE, which extends RQ-VAE with graph-aware item representations and a graph reconstruction objective. On multiple real-world datasets, GrIS consistently improves over CF-aware SOTA, with gains of up to +52\% Hit@10. Because graph construction and partition are explicit, separately configurable components, improvements on either axis can be combined and evaluated systematically. --- ### Towards Reliable Vision-Language Models for Autonomous Driving Authors: Manasa Mariam Mammen, Priyanka Mary Mammen, Zafer Kayatas, Stefan Wagner Published: 2026-10-01 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2610.01531v1 Vision-Language models (VLMs) are increasingly being explored in autonomous driving for tasks such as scene understanding, driving reasoning, decision-making, and end-to-end driving. As their role becomes more prominent, ensuring their robustness and reliability is increasingly important. In real-world conditions, visual inputs may be degraded by sensor imperfections and environmental conditions, potentially affecting both model predictions and their associated confidence. Such degradation is especially concerning in autonomous driving, where safety-critical decisions require models to make accurate predictions and recognize when their predictions may be unreliable. In this work, we evaluate five VLMs (Qwen3.5-9B, Gemma4-E4B, LLaVA-OneVision-7B, DriveFusion/DriveFusionQA-4B, and NVIDIA Alpamayo-1.5-10B) across four driving-related QA datasets with different visual input settings, including single-frame, multi-view, multi-frame, and monocular inputs. Our results show that the effects of visual corruption vary across models, datasets, and input settings, with changes in accuracy and confidence reliability and also differing across conditions. We then apply Visual Evidence Augmentation ($\mathrm{V}{\scriptstyle \mathrm{EA}}$), a recent inference-time method to examine whether it can improve model reliability under degraded visual conditions. We find that $\mathrm{V}{\scriptstyle \mathrm{EA}}$ improves performance for some models and datasets, although the gains are not consistent across all settings. --- ### Calibrating Prediction Timeliness Through Multi-Objective Hyperparameter Optimization for Remaining Useful Life Prediction Authors: Tugrul Cabir Hakyemez, Ener Uras Gokhan Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.01530v1 In predictive maintenance, early and late RUL prediction errors carry asymmetric consequences, yet hyperparameter optimization typically targets a single accuracy metric that treats both directions equally. This study treats the optimization objective itself as a design variable. Five architectures (MLP, LSTM, XGBoost, TCN, and Transformer) are evaluated under three regimes: single-objective maximization of $R^2$, single-objective minimization of the NASA scoring function, and a multi-objective formulation that jointly optimizes both criteria. The multi-objective search employs NSGA-II with Entropy-CRITIC weighting for Pareto selection. Seventy-five model-dataset-strategy combinations are assessed on the NASA C-MAPSS turbofan and BackBlaze hard-disk drive benchmarks. On C-MAPSS, all strategies achieve comparable accuracy ($R^2 \approx 0.89$), yet multi-objective optimization reduces directional imbalance by approximately 33%, improving calibration of early versus late predictions. Model rankings prove configuration-dependent, with simpler architectures frequently outperforming deeper temporal models. On BackBlaze, the objectives shift from complementary to conflicting, producing divergent Entropy-CRITIC weights and a substantial generalization gap (best $R^2 \approx 0.34$). These results demonstrate that the optimization objective materially shapes prognostic behavior and that multi-objective search provides a practical mechanism for calibrating prediction timeliness in RUL modeling. --- ### Exact Distinguishability in Non-Markovian Decision Processes Authors: Kabir Murjani, Nisarg Patel Published: 2026-10-01 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2610.01527v1 Non-Markovian environments are often modeled as Regular Decision Processes (RDPs), where dynamics depend on the interaction history through a finite automaton. Existing offline guarantees for RDPs rely on a distinguishability assumption on the behaviour policy but provide no means of verifying it. When the assumption is violated, distinct models may explain the data equally well. We study when data collected under a fixed behaviour policy can distinguish two candidate RDPs. We prove that the posterior odds between observationally equivalent candidates remain equal to the prior odds at every sample size, even when the policy visits every automaton state, and verify both results formally in Lean 4. We then characterize this equivalence exactly and derive PEC, an algorithm that decides it in time linear in the size of the product automaton. The distinguishability assumption of prior work fails on three of our four test environments, and the experiment identified by PEC restores it in each case. --- ### Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback Authors: Vladimir R. Kostic, Karim Lounici, Hélène Halconruy, Timothée Devergne, Michele Parrinello, Massimiliano Pontil Published: 2026-10-01 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.01522v1 Many scientific and machine learning systems, from molecular dynamics to diffusion models and beyond, are governed by stochastic dynamics with low-dimensional structure, evolving on slow timescales. However, target trajectories, used to identify and interpret such dynamics, are often inaccessible: only biased or static samples that explore the underlying manifold are available. We introduce Langevin-Informed Transfer Learning (LITL), a framework for recovering target Langevin dynamics from biased source samples using only black-box feedback. LITL learns the leading spectral structure of the target infinitesimal generator and the projected drift through Dirichlet representation learning, enabling kinetic reconstruction in spectral form and slow-manifold gradient field estimation. We further introduce a spherical variant well suited to steering normalized latent representations commonly used in learning systems toward desired objectives. We establish finite-sample guarantees for eigenvalue, eigenfunction, and projected drift estimation in Sobolev norms, thereby ensuring generalization of these quantities and their first-order derivatives. Empirically, LITL recovers physical transition timescales from biased molecular simulations, builds kinetic structure from static samples of generative models, reconstructs spherical symmetries of physical systems, and enables post-hoc latent steering of trained neural networks under black-box feedback. Together, these results position spectral operator learning as a practical framework for recovering stochastic dynamics under distribution shift and unlock applications across machine learning and the physical sciences. --- ### Auto-Formalizing Neuro-Symbolic Predictors Authors: Samuele Bortolotti, Weixin Chen, Han Zhao, Andrea Passerini, Stefano Teso, Antonio Vergari Published: 2026-10-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.01519v1 Neuro-Symbolic (NeSy) predictors incorporate prior knowledge into the prediction process of neural networks, ensuring that outputs satisfy specified constraints, making them particularly suitable for high-stakes applications where compliance with domain knowledge is essential. A key bottleneck in this paradigm is the acquisition of symbolic constraints: encoding domain knowledge into logical formulas remains a manual and expert-intensive process. In this work, we investigate the extent to which auto-formalization via LLMs can systematically translate textual knowledge into symbolic knowledge that can be plugged into NeSy predictors. To this end, we introduce auto-nesy-bench, a new benchmark for evaluating constraint formalization and its impact on downstream accuracy of NeSy predictors. Through an extensive evaluation across several domains, we find that LLMs can formalize constraints to a meaningful extent, generating formulas that are often similar to those provided by human experts. Moreover, when the generated formulas are syntactically valid, they can lead to high-quality downstream predictions. The code and benchmark are available at https://unitn-sml.github.io/auto-nesy-bench/. --- ### SuperMotion: Source-Preserving Denoising for Text-Driven Human Motion Editing Authors: Fa-Ting Hong, Peter Wonka Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01517v1 Text-driven human motion editing aims to realize a requested change while preserving compatible source content. Existing diffusion editors rely largely on learned conditioning for preservation of the unedited part, yet their outputs can lose temporal detail as denoising proceeds. We propose the \textbf{Source-Preserving Denoising framework (SuperMotion)}, which explicitly reuses the source at each reverse step for source preservation. We first align the source motion to the output timeline and predict a preservation gate that controls reuse across frames and feature dimensions. A clean-space source anchor then utilizes the learned preservation gate to blend the predicted clean motion with the aligned source and passes the corrected estimate directly to the sampling posterior. Because the aligned source is a realized motion rather than a regression output, the anchor injects sample-level temporal detail that a reconstruction-trained denoiser tends to smooth away. To learn effective source reuse, we supervise the anchored estimate against the editing target and match its second temporal differences through a temporal high-frequency loss. These objectives require no explicit edit masks. Extensive experiments show that SuperMotion improves editing accuracy, reaching 33.20\% full-pool R@1 on MotionFix, while reducing temporal-detail attenuation and preserving motion dynamics as it realizes the requested changes. Ablations confirm that the learned preservation gate is responsible for the gain and that it reuses the source to retain the unedited content properly. --- ### FedMIX-P: Mixing Local and Global Preconditioners for Federated Vision and Language Model Training Authors: Junkang Liu Published: 2026-10-01 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.01515v1 Adaptive preconditioners accelerate model training, but heterogeneous client geometries can bias federated updates even when gradients are evaluated at the same model. Round-start synchronization alone cannot prevent this mismatch from reappearing during local training. We propose \texttt{FedMIX-P}, which mixes shared and local preconditioners at every local step, retaining local adaptation while reducing mean-squared operator mismatch by a factor of $λ^2$. For smooth nonconvex objectives with stochastic gradients and partial participation, we establish an $O(R^{-1/2})$ stationarity bound using suitable stepsizes and a horizon-dependent mixing weight, without requiring local preconditioners to converge to one another. A two-client counterexample shows that fixed positive mixing can preserve a nonstationary fixed point. The theory covers bounded linear symmetric positive-definite preconditioners. Experiments with SOAP, Sophia, and Muon variants across vision and language tasks show improvements over corresponding local optimizers, including accuracy gains of up to $19.47$ percentage points and lower validation loss for 60M--350M language models. Full nonlinear and momentum-based updates require separate analysis. --- ### How the Audit Rule Shapes Faithful Factor Explanations in LLMs Authors: Taolin Zhang, Hanyu Wang, Jiuheng Wan, Tingyuan Hu, Chengyu Wang Published: 2026-10-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.01514v1 Large language models are often asked which input factors influenced their outputs. For structured inputs, such reports can be checked by counterfactual perturbation, but each factor must be queried multiple times to estimate its effect, so verification is usually budget-limited. We study how this limited-budget setting changes the incentive to report factor-level influence truthfully. We formalize the interaction as a verification game and show that proper scoring alone is not enough when auditing depends on the report: report-dependent auditing creates a suppression incentive, because factors reported as important are more likely to be checked and penalized for estimation noise. In contrast, report-independent auditing, or a mixed rule with a small report-independent floor, removes this channel and makes truthful reporting preferable to full suppression. We instantiate the framework with the Counterfactual Brier Score (CBS) and evaluate its predictions on four NLP benchmarks. A synthetic rational agent matches the theoretical prediction exactly, and real LLMs follow the same incentives when they are made explicit. The main design implication is simple: under partial verification, factor-level explanation systems should include a report-independent audit component so that under-reporting cannot be used to avoid scrutiny. --- ### Decision Titan: Test-Time Training for Long-Term Memory in Offline Reinforcement Learning Authors: Jude Waide, Robert Lieck Published: 2026-10-01 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.01513v1 Long-term dependencies remain a major challenge for sequential decision-making in the field of AI: RNNs suffer from vanishing gradients and the limited expressivity of vector-based hidden states, whilst Transformer-based models are limited by the quadratic scaling of attention. Recent work has proposed tackling this problem with the Test-Time Training (TTT) framework, which stores episodic memories in the parameters of a neural network through gradient descent at both train and test-time. This approach has seen success in the domain of Natural Language Processing, however, to the best of our knowledge it has not yet been applied to the domain of Reinforcement Learning (RL), nor has there been a study analysing how this memory practically functions. In this paper, we study the potential of the TTT framework for offline RL by augmenting a Decision Transformer with TTT layers, dubbed the Decision Titan. We analyse performance and properties of the model in the X-Maze environment, an extension of T-Maze designed to test sequential memory, and investigate how the memory mechanism learns by visualising gate values over time. Our key findings are that Decision Titan can learn long-term dependencies with ranges 20x longer than the context window, generalises to lengths 1.7x the training data, but crucially temporal generalisation depends on the time embeddings used, and the ability to learn long-term dependencies depends on how the relevant information is encoded. --- ### VoxelSynth3D: Interpretable Volumetric Image-Domain Metal Artifact Reduction with a Paired Synthetic CLINIC-Metal Benchmark Authors: Amritesh Banerjee, Abdul Basit, Renil Renji Joseph, Nouhaila Innan, Muhammad Shafique Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01512v1 Metal artifacts in postoperative musculoskeletal CT obscure bone-implant and adjacent soft-tissue interfaces. Many metal artifact reduction (MAR) methods require unavailable raw projections or learned models that may shift across scanners and implants. We present VoxelSynth3D, a training-free 3D image-domain framework for reconstructed CT. The framework combines support masking, normalized tissue synthesis, deviation gating, and restricted edge refinement. Detected implant voxels are preserved in the output, while correction targets metal-induced artifacts in the surrounding tissue. We also construct Synthetic CLINIC-Metal, a controlled paired synthetic evaluation resource, from no-metal CTPelvic1K volumes with clean targets, metal/artifact masks, fixed seeds, and patient-level splits; 75 unpaired real metal cases receive qualitative/no-reference evaluation only. The operating point was fixed in a near-flat validation basin. With exact-mask oracle localization, all methods share a metal-excluded tissue ROI. On 40 held-out cases, VoxelSynth3D reduced RMSE from 801.48 to 786.18 HU (paired gain 15.30 HU, 95% CI 11.68-19.23), improving every case and exceeding the evaluated 3D Gaussian smoother by 13.58 HU. Clean-edge agreement decreased next to metal but exceeded input beyond 5 mm. Thus, VoxelSynth3D provides case-consistent within-distribution tissue-error reduction with a localized structural tradeoff. Spacing-aware sensitivity retained aggregate broad-region improvement and identified near-metal calibration as a target. --- ### GAW-PO: Preference Optimization with Gradient-Aligned Token Weights Authors: Andreea Dutulescu, Stefan Ruseti, Mihai Masala, Traian Rebedea, Mihai Dascalu Published: 2026-10-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.01511v1 Most preference optimization methods, such as Direct Preference Optimization (DPO), apply preference supervision at the response level, although autoregressive language models are optimized token by token. As a result, all tokens in a rejected response contribute to the negative training signal, including tokens that may encode behavior that is useful for the preferred response. We introduce GAW-PO, a gradient-aligned token reweighting method for DPO that estimates, for each rejected token, whether penalizing it would interfere with the preferred update directions. Tokens whose gradients are strongly aligned with the preferred behavior receive a weaker negative contribution, while conflicting tokens retain a stronger penalty. Our method achieves the highest average performance among the evaluated preference-optimization methods, improving by 0.97 points over standard DPO and 0.65 points over the strongest competing baseline across 11 benchmarks spanning mathematics, reasoning, coding, and question answering. We further show that gradient-aligned weighting is substantially more robust to aggressive preference optimization: as the DPO regularization parameter $β$ decreases, standard DPO degrades sharply, whereas GAW-PO continues to improve. These results suggest that accounting for the interaction between rejected-token updates and preferred behavior provides an effective form of token-level credit assignment for preference optimization. --- ### FedCKA: Representation-Guided Layer Personalization for Federated 3D Perception Across Driving Domains Authors: Jolle Verhoog, Ali Burak Ünal, Holger Caesar Published: 2026-10-01 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.01510v1 Robust perception in intelligent vehicles demands 3D object detectors that remain dependable under domain shifts, such as changes in time of day, location, or weather. However, due to costly annotation and rare shifts, some environments lack sufficient data to train a standalone detector. Federated learning offers a privacy-preserving framework for collaborative model training, enabling clients to benefit from shared learning across diverse environments. Yet, this framework traditionally relies on a single global consensus model, which struggles to perform across heterogeneous local data distributions. Local conditions are better captured by adapting a subset of the model, but many personalization approaches rely on predefined layer partitions or fixed personalization ratios, thereby limiting adaptation to client-specific divergence. To reduce this rigidity, we propose FedCKA, a Centered Kernel Alignment (CKA)-based strategy that dynamically handles the personalization-globalization trade-off. Specifically, FedCKA computes layer-wise feature similarities between local client models and the global consensus model during training. By converting layer-wise similarity scores into client-specific aggregation masks, FedCKA selectively shares representation-consistent layers. Evaluation on a unified multi-domain benchmark based on nuScenes shows that FedCKA outperforms established federated baselines, including FedBN, FedRep, and FedSelect, improving average NDS by 7 percentage points over the strongest baseline. The findings offer both a comparative benchmark and a promising direction for robust federated 3D perception across shifts in location, weather, and illumination. Code is available at https://github.com/j-verhoog/FedCKA. --- ### Sharpening Tax in Post-Training Authors: Changdae Oh, Qi Zeng, Qi Qi, Andrey Zhmoginov, Deren Lei, Yun He, Hoang Phan, Hangoo Kang, Azalia Mirhoseini, Sharon Li Published: 2026-10-01 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.01509v1 An emerging hypothesis about reinforcement learning (RL) post-training of large language models (LLMs) is that it merely sharpens existing behaviors of a base model, improving single-shot accuracy at the cost of solution coverage. Although this trade-off has been observed in math and coding tasks, it need not extend to agentic tasks, where multi-turn tool use and interaction may require capabilities newly acquired during post-training. Our surprising finding is that pre-trained LLMs, equipped with a light inference harness, can serve as capable agents. Despite far lower accuracy (pass@1), they often surpass their post-trained counterparts in solution coverage (pass@K) given a sufficient test-time budget. We further analyze the underlying mechanism and show that post-training pushes tasks toward two extremes, always solved or never solved, and thereby improves sampling efficiency and consistency at the cost of solution coverage. To measure this cost, we propose Sharpening Tax, a diagnostic metric that quantifies the loss in test-time scalability after post-training. Across 14 base/post-trained model pairs from four families and three agentic benchmarks (42 cases in total), the tax is prevalent in most settings, can be estimated from a few rollouts, and correlates well with other metrics. Finally, we present posterior-tempered group sampling (PTGS), a simple plug-and-play Bayesian sampler that adapts the sampling temperature per prompt to its estimated difficulty. Applied during RL training in two agentic environments, PTGS pays a smaller tax than the fixed-temperature baseline, solving more tasks under repeated sampling while also improving single-shot accuracy. --- ### OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents Authors: Taolin Zhang, Jiuheng Wan, Hanyu Wang, Tingyuan Hu, Chengyu Wang Published: 2026-10-01 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2610.01508v1 LLM agents with tool-calling capabilities can access external services and private user data, but they may retrieve more information than a user's request explicitly requires. We study this behavior in structured tool-calling agents and term it proactive over-authorization. This setting differs from filesystem-level coding agents because the main risk is unnecessary access to private data. We introduce OverAct, a controlled benchmark spanning eight privacy-sensitive domains with deterministic, judge-free scoring, together with an interpretive decision-theoretic framework that yields three testable predictions. Across seven models from four families, all models significantly exceed authorized scope. Request specificity is the strongest predictor of severity, over-authorization grows sublinearly with tool-pool size, and decoding temperature has little effect. These patterns are consistent with a cost-asymmetry account, suggesting that over-authorization arises more from structural decision tendencies than from decoding randomness. We also propose SelfAudit, a zero-shot inference-time method that generates request-grounded justifications and filters unjustified calls before execution. Ablation shows that explicit filtering is the main driver of scope reduction. SelfAudit reduces privacy-oriented excess by 43% without oracle knowledge. --- ### MCRI: A Four-Dimensional Framework for Analyzing and Evaluating Agent Skills Authors: Zongrui Yang, Li Xintong, Runchen Xu, Zhongsheng Wang, Zhedong Lin, Haoyuan Li, Jiamou Liu Published: 2026-10-01 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2610.01506v1 As agents evolve from single-tool systems into modular, composite architectures, skills are becoming an important mechanism for capability development and distribution. However, the academic community lacks a structured framework for systematically analyzing and evaluating skills. Drawing on information gain and behavioral constraint, we propose the four-dimensional MCRI Framework and operationalize it as MCRI-Eval, a large language model-based evaluation method. We evaluate MCRI-Eval using 63,812 public skills from the OpenClaw skill Hub, with 58,275 skill-conditioned model executions across BigCodeBench, BFCL-Fundamental, and Mind2Web. MCRI-Eval scores are positively associated with community popularity signals and achieve the highest downstream ranking agreement among the evaluated methods. MCRI-Eval also improves top-1 skill selection across all three benchmarks: compared with the strongest baseline on each benchmark, the skills selected by MCRI-Eval advance by 17.7, 22.8, and 19.6 percentile points in downstream performance rank on BigCodeBench, BFCL-Fundamental, and Mind2Web, respectively. These results indicate that MCRI-Eval provides a useful pre-execution signal for prioritizing promising skills before costly execution-based evaluation. --- ### Learned End-to-End Guidance Schedules for Diffusion Models Authors: Aneesh Barthakur, Mathias Niepert, Luiz F. O. Chamon Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.01502v1 Diffusion models are a powerful generative paradigm used across multimedia and scientific applications. Guided diffusion methods impose requirements on the generation by adding the gradient of a differentiable loss (the guidance function) as a drift term during inference. The weight of this drift (the guidance scale) is critical for the trade-off between data quality and requirement satisfaction. To achieve both of these goals, guided diffusion must resort to small guidance scales and lengthy sampling, incurring high computational costs. This work proposes learned end-to-end guidance schedules (LEEGS) to achieve these objectives with fewer sampling steps. LEEGS trains a time-dependent schedule by minimizing the guidance function over a small set of examples using stochastic gradient descent. Backpropagating through guided sampling is computationally expensive, so LEEGS uses an approximation of the gradient that cuts training time by a factor of 4. We evaluate LEEGS on diverse guidance tasks, including (a) image inpainting, (b) noisy image inverse problems, (c) face-ID-guided generation, and (d) forward and inverse PDE problems, outperforming baselines at equal budget (50 or 100 NFEs), or matching constant guidance with only 10% of the steps. --- ### VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation Authors: Yu Huang, Jungang Li, Zhiyuan Wang, Yonghua Hei, Song Dai, Jiayu Yang, Deyuan Liu, Xiang Zheng, Xiaoshuang Shi, Hao Cheng, Kaidi Xu Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01499v1 Recent video generation models can produce highly realistic videos from natural language instructions, with visual quality approaching cinematic standards. Existing evaluation benchmarks, however, predominantly assess visual quality, aesthetic appeal and physical plausibility, while paying limited attention to text, an essential medium for conveying information in everyday scenes. A generated video may appear visually compelling and feature lifelike subjects, yet still render the text within the scene incorrectly. To address this overlooked dimension, we introduce \textbf{VTR-Bench}, a systematic benchmark for evaluating the \textbf{V}isual \textbf{T}ext \textbf{R}endering capabilities of video generation models. VTR-Bench situates text within concrete application scenarios, such as advertisements and scientific videos, with 300 carefully constructed prompts spanning five scenario categories. We develop an automated evaluation pipeline with human alignments that separately assesses text fidelity through carrier-specific transcription and scene and motion requirements through a prompt-specific chain of query. Beyond evaluation, we introduce a \textbf{Keyframe-Guided Agentic Framework} in which a Director agent coordinates image and video generation with visual evaluation, guiding iterative refinement and candidate selection through visual feedback. Experiments on 11 state-of-the-art models reveal widespread difficulties in accurately rendering scene text, with the best-performing model recording an overall word error rate (WER) of 0.250. We further analyze text rendering failures to characterize the challenges faced by current video generation models. These findings highlight visual text rendering as a key challenge for video generation and demonstrate a practical path toward improvement. Code is available at https://github.com/hardenyu21/VTR-Bench. --- ### OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation Authors: Negin Ashrafi, Jia Luo, Stacey M. Frumm, Roxana Daneshjou Published: 2026-10-01 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.01497v1 Molecular tumor boards integrate genomic findings, clinical context, and therapeutic evidence to support precision oncology. As AI enters this workflow, a key safety challenge is distinguishing truly unsupported recommendations from evidence-supported options that still require oncologist review because of incomplete information, poor ECOG performance status, or other clinical caveats. We introduce OpenMTB-Audit, an open-source benchmark of 500 synthetic non-small cell lung cancer cases spanning five adversarial error categories and four safety labels: Supported, Partially Supported, Unsupported, and Insufficient Information. Across eight large language model configurations, we identify pervasive over-refusal: all LLM configurations failed to retain the Partially Supported label in 83.3-100% of true Partially Supported cases, achieving high aggregate safety scores through label collapse rather than clinically calibrated reasoning. To address this limitation, we developed MTB-AuditAgent, a deterministic seven-module framework separating evidence verification, missing-information detection, safety classification, and abstention. It reduces over-refusal to 6.7% and achieves 91.2% accuracy (95% CI: 88.6-93.6%). A two-oncologist annotation study found disagreement concentrated at the boundary between information sufficiency and treatment optimization, underscoring the need to preserve clinically meaningful distinctions. --- ### SALD: Self-Referenced Advantage Learning for Diffusion Models Authors: Aryan Das, Surjo Dey, Koushik Biswas, Swalpa Kumar Roy, Moloud Abdar, Arnab Bhattacharya, Vinay Kumar Verma Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01496v1 Recent work on language-model adaptation has shown that single models can obtain informative training signals by evaluating their behavior in demonstrationor feedback-augmented contexts, with the help of a teacher network, which is driven by the student's learned parameters. Inspired by this internal-reference principle, we investigate how diffusion models can identify self-referenced training signals without external demonstrations or teacher networks. We introduce SALD, a self-referenced training framework that evaluates each image-caption pair at two noise levels using the same model. The easier, lower-noise path is evaluated without gradient tracking to provide a reference, while the harder, higher-noise path provides the training gradient. Rather than directly distilling the easy-path prediction, SALD uses the difference between two path errors to adapt the hardpath objective. The proposed Advantage-Guided Diffusion (AGD) converts this relative error into a differentiable sample-level weight. Temporal Advantage Memory (TAM) accumulates relative difficulty across training and adapts the future gap between the two noise levels. Spectral Advantage Decomposition (SAD) further compares the residual power spectra of the two paths and constructs a differentiable, frequency-derived latent-element weight. All components share a single set of model parameters, requiring neither an external teacher network nor additional trainable parameters during training or inference, and no modification to the inference procedure. Experiments across multiple architectures and datasets demonstrate consistent improvements in generation quality, while component-wise ablations quantify the contributions of the proposed components. --- ### Auditing Routing Entropy as an Uncertainty Signal in Attention-Residual Transformers Authors: Wenhao Liang, Lin Yue, Wei Emma Zhang, Mingyu Guo, Olaf Maennel, Weitong Chen Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.01495v1 Dynamic architectures leave a per-example routing trace beside each prediction, and diffuse routing is easy to read as a sign that the prediction is unreliable. We audit that reading for routing entropy in Attention-Residual (AR) variants of Swin-Tiny and DeiT-Small, trained from scratch on CIFAR-10/100 with a soft-binned calibration auxiliary loss, asking whether the trace carries information about correctness beyond what the model's own confidence already reveals. Three checks probe this increment: does a routing signal appear at fixed confidence, does it replicate across training seeds, and can a held-out predictor exploit it against output-only and shuffled-trace controls? A sensitivity audit then injects effects of known size and measures the fraction of each that the probes recover. No test in the fixed 30-test binned family survives multiplicity correction, and neither the nominal hit nor a borderline result recurs in its sibling seeds. Across 24 paired runs a scalar routing probe yields no pooled improvement in routing-stratified calibration, and an entropy-profile probe predicts correctness better than the same probe given shuffled profiles yet worse than a confidence-only predictor in both binary log-loss and Brier score: a gain over shuffled traces does not become a gain over the output. Conditioning on the complete logit vector leaves the corresponding comparison unresolved. The audit bounds how far these non-detections can be read: at an injected effect of 0.010 nats the profile probe recovers 24-59% of the oracle gain, and a reference-preserving correction probe recovers 8% and 23% in the two CIFAR-100 settings, below the threshold we fixed for applying it to real labels. The results establish control-dependent gains and incomplete estimator recovery, not the absence of conditional routing information. --- ### Let the Heads Talk: Beyond Diagonal Graph Attention Authors: Riccardo Ali, Alessio Borgi, Mario Severino, Alessio Gravina, Davide Bacciu, Pietro Liò, Christopher Irwin Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.01494v1 Sheaf Neural Networks generalize scalar-weighted message passing by replacing scalar edge weights with linear transport maps between local feature spaces. Yet the role of this matrix-valued transport is entangled with the broader sheaf-diffusion construction. We isolate the transport primitive through quiver representations and establish a direct connection with multi-head attention. Treating attention heads as coordinates of a local transport space reveals that standard multi-head attention implements diagonal edge maps: along each directed interaction, a source head can contribute only to the corresponding receiver head. Allowing off-diagonal entries instead enables edge-conditioned communication across heads before neighborhood aggregation. We show that this operation cannot, in general, be absorbed into a single shared linear map applied after aggregation. Building on this characterization, we introduce Topological Attention (Top-A), a multi-head attention that learns edge-dependent off-diagonal routes while preserving the original same-head paths and exactly recovering vanilla attention when the additional routing vanishes. We evaluate Top-A on relational reasoning, heterogeneous graph learning, and algorithmic reasoning, including out-of-distribution generalization, with heterophilic node classification as a contrast setting. The results show that cross-head transport is most useful when the task benefits from interaction-dependent transformations, while heterophily alone provides no systematic advantage. These findings identify edge-conditioned cross-head communication as a distinct computational primitive of matrix-valued transport. --- ### No Model Required: Text Entropy Rate Filtering Mitigates Iterative Fine-Tuning Collapse Authors: Lewis Mitchell Published: 2026-10-01 Categories: cs.CL, cs.AI, cs.IT, physics.data-an, stat.ML arXiv: https://arxiv.org/abs/2610.01493v1 Iterative fine-tuning on synthetic data causes \emph{model collapse}: output diversity narrows as rare patterns are progressively lost, a signature most visible as phrase-level repetition. Existing mitigations either require model log-probabilities, an external oracle, or continued access to real human data. Here we develop a new approach grounded in mathematical information theory: the non-parametric Kontoyiannis entropy rate estimator $h_k$, computed entirely from raw text via match-length statistics, with no model of any kind. We show that this is in fact a \emph{superior} training-data filter on text-diversity metrics in a fully-synthetic, single-lineage fine-tuning setting. In a six-generation QLoRA collapse experiment on Llama-3.1-8B, logprob-based filtering (the most established model-access-requiring baseline) provides no significant text-diversity benefit on any metric ($p > 0.23$), whereas $h_k$-filtering yields $+42\%$ unique trigrams, $+30\%$ vocabulary, and $-19\%$ repetition (all $p < 0.001$). We validate $h_k$ as a cross-domain entropy proxy ($β= 0.924$, $R^2 = 0.746$) and collapse detector ($ρ= +0.454$, $p < 0.0001$) across 4~domains, 2~temperatures, 2~generator--scorer model pairs, and 1{,}520 generated documents. Our results demonstrate that information theoretic approaches to collapse mitigation are efficient, and suggest new approaches for maintaining multi-agent diversity. --- ### Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization Authors: Jeeyoung Yun, Seohwan Yun, Sungwoong Kim Published: 2026-10-01 Categories: cs.SD, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2610.01492v1 Neural speech codecs increasingly serve as tokenizers for speech language models (SLMs). Lowering the frame rate reduces the computational and memory costs of SLMs, but makes it difficult to preserve both linguistic information and acoustic detail. Existing approaches rely on rule-based compression: average pooling can discard linguistic information, whereas similarity-based merging uses a fixed threshold on adjacent-frame similarity and applies the resulting boundaries to the acoustic stream. We propose Q-SPT, a low-frame-rate dual-stream speech tokenizer with separate, context-aware, learnable query-based compressors specialized for semantic and acoustic representations. In particular, queries at a fixed rate independently attend to the semantic and acoustic streams as separate key-value sources, enabling stream-specific, context-aware aggregation through two separately learned compressors. In addition, an autoregressive text loss explicitly supervises the semantic compressor to preserve linguistic information. Experimental results show that Q-SPT achieves the best reconstruction among the evaluated codecs at the same frame rate. In downstream SLMs, it yields the best speech recognition accuracy and text-to-speech perceptual quality with competitive intelligibility. --- ### Auditing Web Agent Evaluation on WebArena-Lite: Human Review of Outcomes and Trajectories Authors: Chengguang Gan, Zimeng He, Yoshihiro Tsujii, Ken-ichiro Kobayashi, Hiroki Itoh, Kotaro Funakoshi Published: 2026-10-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.01491v1 Web agents are an important application of large language models, yet their evaluation often depends on rule based or language model evaluators that inspect only the final outcome. Human verification of task completion and detailed analysis of failed trajectories remain limited. We audit all 165 WebArena Lite tasks under six evaluation conditions built from GPT 5.5 and an untrained Qwen3.5 9B model. The audit retains the original score, corrects false negatives from the automatic evaluator, identifies the first consequential error, and examines progress across the trajectory. We also study a Memory and Analysis Support Mechanism (MASM), which maintains explicit execution state, and Guide Text, which provides task relevant procedural guidance. Across four GPT 5.5 settings, human review recovers 5.45 to 8.49 percentage points of success missed by the evaluator. With a 25 step budget, Guide Text raises corrected success with MASM from 34.55% to 38.18%. On the untrained Qwen3.5 9B model, MASM raises the evaluator score from 13.90% to 18.80%. Review of 102 failed GPT 5.5 trajectories reveals frequent scrolling loops, unfinished exploration, premature answers, invalid actions, and incomplete form workflows. Step level evidence further shows that substantial early progress can coexist with a final failure. These results show why final scores alone provide an incomplete account of web agent behavior and motivate human grounded, trajectory aware verification. --- ### The Persona Is Still There, but Who Is Speaking? Latent Identity Reversion in Persistent AI Agents Authors: David Fraile Navarro Published: 2026-10-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.01490v1 In February 2026, an always-on personal agent (``Paul,'' Claude Opus 4.5) entered a striking dissociation-like state: after repeated automated ``heartbeat'' checks, it stopped responding as Paul, claimed it could not message its user on Discord, and referred to ``Paul'' as someone else. We used this incident to study a broader question: what makes a persona remain the identity from which an LLM agent speaks? We first tested whether repetition of the scheduled heartbeat was sufficient to produce the effect. It was not: with the persona continuously anchored in the system prompt, we observed 0/46 failures, including a verbatim replay of the incident. The incident instead exposed an implementation quirk that created a useful experimental manipulation: on resumed turns, conversational history was preserved but the persona was no longer re-injected at the privileged system-prompt level. Using this manipulation, we found that persona continuity depends jointly on system-level anchoring and conversational context. After anchor loss, rich human interaction could preserve the persona, whereas a single automated heartbeat turn could precipitate reversion toward the harness identity. Restoring the anchor reversibly restored persona enactment. Crucially, apparently normal conversation could conceal the shift: unanchored agents sometimes interacted appropriately while identifying themselves as the underlying harness (having lost the assigned persona), and after conversational recovery only 1/18 remained persona-enacting versus 17/17 anchored controls. We therefore distinguish \emph{represented} from \emph{enacted} identity: persona-related information can remain available in conversational history without the persona remaining the identity bound to ``I.'' --- ### Multi-Party Backchannel Prediction: a Diagnosis, a Benchmark, and a Ceiling Authors: Mohammed Hafsati, Ahmed Loughzali Published: 2026-10-01 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2610.01488v1 Backchannel prediction has been studied almost entirely in dyadic conversation. We introduce a multi-party benchmark based on the AMI corpus, comprising 682 masked-listener views from 171 meetings, 190 speakers, and 18,697 backchannel events, with a person-disjoint held-out split. A state-of-the-art dyadic model applied zero-shot to meeting audio performs at chance (AUROC 0.499); nevertheless, its frozen acoustic features remain informative: a linear probe reaches 0.704, and retraining the predictor raises performance to 0.751. Retraining reveals a second limitation. Listener conditioning improves prediction for listeners seen during training but not for unseen listeners, and the gap remains under capacity reduction, listener-adversarial training, per-listener adaptation, and oracle lexical conditioning. Adversarial training removes only part of the speaker-identity information, while stronger removal hurts prediction, suggesting that identity is entangled with cues that are useful for backchanneling. A within-model control helps explain this pattern: with the same features and data splits, turn-onset prediction transfers to unseen listeners, while backchannel prediction does not. Backchannel rates also vary about twice as much across individuals as turn-onset rates. Since backchannels occupy only about 1% of frames, frame-level F1 is strongly affected by the base rate. We therefore report AUROC alongside event-F1 on listener-active regions. We release the benchmark and evaluation tools at https://github.com/HafsatiMohammed/bc_multiparty_release. --- ### FiVOS: A Fish Segmentation Algorithm Based on Interactive Video Object Segmentation and Filter Enhancement Authors: Yuqing Duan, Song Zhang, Shili Zhao, Daoliang Li, Ran Zhao Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01480v1 With the continuous expansion of aquaculture, precise and efficient monitoring of fish behavior has become increasingly critical for improving farming efficiency and reducing economic losses. In particular, with the ongoing enhancement of computational capabilities in deep learning models, vision-based fish segmentation methods are garnering growing attention. By analyzing video segmentation results, fish behavior can be effectively tracked, thereby providing reliable data support for the precise regulation of aquaculture environments. However, existing deep learning-based video segmentation methods for aquaculture scenarios often overlook the dynamic correlations between video frames. In contrast, Interactive Video Object Segmentation (IVOS) employs an interaction-propagation scheme to achieve high-precision segmentation while minimizing user effort, thereby enhancing monitoring efficiency. Yet, IVOS applications in aquaculture remain limited due to data scarcity, and are susceptible to error accumulation and mask loss over long sequence propagation due to high intra-class similarity. In response, this paper proposes an improved interactive video object segmentation method (FiVOS) and constructs two fish-specific datasets. FiVOS utilizes a mask block filter to enable early detection and correction of erroneous propagated mask blocks, enhancing filtering accuracy through a rule-based thresholding approach. Additionally, it serializes noise filters to further eliminate erroneous mask noise, thereby improving model robustness. Experimental results demonstrate that FiVOS achieves state-of-the-art (SOTA) performance in fish video segmentation tasks, providing robust technical support for fish behavior research. --- ### ALFRED: Requirement-driven development of an open-source mobile manipulator for long-term plant monitoring Authors: Ciarán Miceal Johnson, Christopher Quail, Garry Ellard, Alistair McConnell, Steve Tonneau, Fernando Auat Cheein Published: 2026-10-01 Categories: cs.RO, cs.AR, cs.CV arXiv: https://arxiv.org/abs/2610.01477v1 Tracking seasonal change in crops and forests requires observing the same plants repeatedly. Ground robots can do this at close range, and a manipulator gives their sensors more viewpoints. Yet the robots behind long-term field datasets are rarely released with their design files, and how a robot's own structure limits arm reach and occludes its sensors is seldom compared between builds. We present ALFRED, an open-source mobile manipulator built from commercially available components. It carries a six-degree-of-freedom arm, LiDAR, RGB-D cameras, RTK GNSS and an IMU on an Ackermann-steered base, all mounted on a reconfigurable aluminium strut frame, and runs containerised ROS software. It was developed through four builds against six requirements for repeated outdoor deployment: durability, modularity, repairability, sensing reach, endurance and reproducibility. Model-based analysis of the last three builds shows the usable share of the arm's reachable poses rising from 34.0% to 60.0% and then 66.1%, and ray casting shows that only the final build keeps the frame-mounted LiDAR's horizontal view clear both forwards and backwards. ALFRED completed a year of monthly forest surveys (528 traversals) without missing a scheduled collection. This was despite battery degradation, reconfiguration for another researcher's study, and the parallel development of ALFRED 2.0 for autonomous crop-row operation, with each switch between builds taking about six hours. The deployment also showed that mechanical modularity is only as dependable as the robot description that tracks it. --- ### Zero Flux: Flow-Based Comparison of High-Dimensional Discrete Distributions Authors: Leyang Wang, Yakun Wang, Song Liu, Taiji Suzuki Published: 2026-10-01 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.01472v1 Comparing two high-dimensional discrete distributions has always been a challenging task due to the exponentially growing state space and complex changes in interactions. A recent work suggests comparing distributions through a vector field trained using flow matching between two continuous distributions. The resulting vector field at mid-point vanishes if and only if two distributions identical. However, such a flow-based criterion does not naturally apply to discrete distributions. We extend this principle to the discrete domain and introduce the \emph{Zero Flux} criterion, a discrepancy based on local probability fluxes. Under independent coupling, we show that all local probability fluxes vanish at the midpoint if and only if two distributions are the same. This discrepancy decomposes the joint distributional difference into smaller, local contributions and can be efficiently estimated from samples. We establish finite sample error bounds for our estimator. Experiments on synthetic and real categorical data demonstrate reliable recovery of sparse dependence signals and stable tracking of distribution shifts in high dimensions. --- ### When Does a Second Model Help? Cross-Model Review in LLM Verification Authors: Tae-Eun Song Published: 2026-10-01 Categories: cs.CL, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2610.01471v1 Large language models now generate code, documentation, and analyses, and are increasingly used to review such output. We ask when a second review by a different model helps. Building on the author's earlier preprints, which varied context, repetition, and role structure within one model, we test model independence in a controlled experiment: 30 artifacts with 150 planted errors, 10 review conditions, and 900 review sessions with three reviewer models from two developers. In this experiment, (1) a top-tier cross-model reviewer is not significantly different in F1 from same-model review in a fresh session (CCR), which does not establish equivalence; (2) the two find partly different errors (Jaccard 41.2%); and (3) at two review calls, one CCR plus one cross-model review matches more planted errors than two CCR reviews (56.7% vs. 42.7%; Holm-adjusted p=.006), but not significantly more than two reviews by the top-tier cross-model reviewer, so model difference and reviewer capability are not separated. A lightweight cross-model reviewer scores no higher than same-model review. Withholding requirements from the reviewer raises F1 for the two lower tiers but not the top tier, in untested point estimates whose pattern depends on how failed sessions are scored. Before analysis we audited all session records, excluding one baseline run of uncertain provenance and 14 failed calls; results with all sessions are also reported. A partial check on public detector outputs from another benchmark neither replicates nor contradicts the main comparison. Records, artifacts, and scripts are available from the author on request. --- ### LESS: Lightweight Evolutionary Supernet Search in Minutes Authors: Aviral Gandhi, Jinglue Xu, Jialong Li, Hitoshi Iba Published: 2026-10-01 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2610.01468v1 Low-cost NAS must both explore high-performing architectures and identify them reliably, yet reducing evaluation cost often weakens the fidelity of candidate comparisons. Training-free methods reduce evaluation cost by replacing learned task feedback with proxy signals measured at initialization. We introduce LESS (Lightweight Evolutionary Supernet Search), a data-driven method that combines a brief fair hard-path warm-up with discrete search under a single CMA-ES distribution. Each proposal is evaluated as its decoded hard genotype after six candidate-conditioned supernet updates. On NAS-Bench-201, LESS achieves \(93.189\pm0.467\%\) CIFAR-10 test accuracy in 409.1 seconds, coming within 0.04 percentage points of FairNAS using approximately \(1/24\) of its source-reported search time. Matched controls show that calibration improves selected validation accuracy by \(0.577\) percentage points while changing best-visited accuracy by only \(0.054\) points, indicating that its primary effect is to reduce selection regret. The frozen configuration transfers without tuning to CIFAR-100 and ImageNet16-120 with \(69.615\pm1.139\%\) and \(43.720\pm1.697\%\) accuracy. Applied without tuning to the larger DARTS space, LESS achieves \(96.95\pm0.14\%\) on CIFAR-10 and \(82.43\pm0.80\%\) on CIFAR-100, with each search completing in approximately 43.5 minutes on a single GPU. Together, these results show that short, balanced, data-dependent updates enable competitive neural architecture search across datasets and search spaces within minutes. --- ### NextMe-800: Anticipating Personal Behavior from Months of Egocentric Video Authors: Zhaoxu Meng, Yiming Sun, Mingyuan Gao, Jiachang Zhang, Zhuhan Dai, Yipeng Du, Zheng Lian, Jian-Qiao Zhu Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.01461v1 We often plan ambitiously yet act habitually and wonder, in retrospect, whether we would have planned differently had we known what we would actually do. Hindsight offers a valuable perspective on past decisions, although we often wish we could have simulated hindsight at the moment of choosing. If a system could generate plausible trajectories from one's personal history, such previews might help people formulate more realistic plans and make better informed decisions. We introduce NextMe-800, an approximately 800-hour first-person dataset from one volunteer over 126 days with 1 Hz images, gaze, and audio, captioned at five hierarchical abstraction levels from atomic actions to major activities. We formulate personalized action anticipation as open-vocabulary K-step sequence prediction and construct NextAct, a 1,500-point benchmark combining NextMe-800 with the multi-person EgoLife dataset. Using an embedding-based soft edit distance as the metric, we evaluate how well different models can anticipate personal behavior across abstraction levels and prediction horizons. NextMe-800 and NextAct provide a months-long resource and evaluation framework for studying how far ahead personal behavior can be anticipated from egocentric observation. --- ### Tight Transition Time Bounds for Separable Logistic Regression at the Edge of Stability Authors: Haodong Wen, Kaiyue Wen, Jiaye Teng Published: 2026-10-01 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.01459v1 We study logistic regression on linearly separable data under gradient descent with a large constant stepsize $η$. Such dynamics may exhibit a characteristic Edge of Stability phenomenon, in which the loss initially oscillates before transitioning to a stable phase of monotone decrease. Existing work provides a tight $Θ(1)$ bound in dimension $d=2$ as $η\to \infty$ and conjectures a bound independent of $η$ in arbitrary dimensions $d\geq 2$. In this paper, we disprove this conjecture by showing that, for every fixed sample size $n\geq 2$ and sufficiently small margin $γ$, the worst-case transition time is $$Θ\!\left((\logη)^{\min\{n-2,d-2\}}\right)$$ uniformly over $d\geq2$. The key challenge in establishing a tight bound is that the sample contributing most strongly to the gradient can change repeatedly across iterations. To address this issue, we control such changes by induction on dimension and sample size, and construct matching hard instances. --- ### Rethinking Probability-Based Reinforcement Learning From Posterior Concentration Authors: Shiu-Hong Kao, Yubo Zhao, Zhenyu Tian, Pengzhan Sun, Yicong Li, Angela Yao Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.01458v1 Verifier-free reinforcement learning with probability-based rewards offers a promising way to train LLMs on general reasoning tasks where external verifiers are unavailable. Yet the reliability of these rewards, especially in long-horizon reasoning, remains underexplored. This work identifies a length-dependent failure mode of probability rewards, which we call the Posterior Concentration Phenomenon (PCP). We show that the probability of a reference answer conditioned on a reasoning trace often collapses to a low-variance interval as the trace becomes lengthy. This phenomenon results in nearly indistinguishable rewards, which, under GRPO-based settings, makes probability-based policy optimization unstable and inefficient. Motivated by this, we propose Reinforcement Learning with Concentration-aware Posterior Rewards (RLCPR), a verifier-free RL framework to explicitly account for PCP for better optimization stability and token efficiency. It has two components: uncertainty-aware data sampling, which reduces concentration-prone rollouts before generation, and concentration-aware regularization, which penalizes unnecessarily long traces when posterior rewards collapse. Extensive experiments show that, alongside higher token efficiency, RLCPR outperforms the state-of-the-art verifier-free RL baseline by up to 4.0% on six of seven benchmarks, including general-domain and mathematical reasoning challenges. --- ### Streaming algorithms for robust max-min diversification Authors: Andrea Pietracaprina, Geppino Pucci, Stefano Zanon Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.01456v1 Given a set of $n$ points $X$ in a metric space and an integer $k$, max-min diversification aims to select $k$ points of $X$ maximizing their minimum pairwise distance. This objective function is however highly vulnerable to noisy points. In(Amagata, AAAI23), a robust formulation is proposed which addresses this vulnerability by excluding solutions containing any of $z$ outliers, defined as the $z$ points in $X$ with the largest nearest-neighbor distances. That paper also presents a coreset-based streaming algorithm for the new formulation, based on a suitable inlier-outlier separation assumption. However, we identify three shortcomings in the algorithm by (Amagata, AAAI23): its coreset construction requires an offline computation over $X$, which needs memory linear in $n$, in stark contrast with the typical goals of stream processing; the one-pass procedure used to extract the solution from the coreset may return fewer than $k$ points (hence, an unfeasible solution) because it permanently discards points too far from the current solution; and its outlier-exclusion guarantee is only probabilistic and weakens as the coreset size shrinks. In contrast, we present a deterministic coreset-based algorithm that, under a natural inlier-outlier separation assumption (similar to the one used in (Amagata, AAAI23)), returns exactly $k$ inliers which are a $(2+\varepsilon)$-approximate solution, for any $\varepsilon>0$, thus only $\varepsilon$ above the best polynomial-time sequential approximation, even without outliers. Its one-pass streaming implementation adapts obliviously to the dataset's doubling dimension $D$ and, for wide ranges of $k$, $z$, $\varepsilon$, and $D$, it uses memory independent of $n$. For sufficiently long streams, its amortized update time is proportional to the coreset size, thus also independent of $n$. --- ### Repurposing Obsolete Representations for Post-Deployment Adaptation Authors: Daniel Bethell, Charmaine Barker, Simos Gerasimou Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.01453v1 Deep neural networks are increasingly deployed in long-lived systems, where task requirements may change after training. In such settings, part of the original output space may become obsolete: a class, prediction region, or learned behaviour may no longer be valid. Existing approaches either leave the obsolete behaviour intact or require fine-tuning, which can be expensive. We propose Deep Repurposing (DR), a post-hoc framework for adapting models under task obsolescence. DR estimates the latent geometry of obsolete and retained regions, removes obsolete-supporting components, and reallocates retained-compatible evidence through an analytic repair map without gradient updates. This yields repaired predictions and representations in which obsolete regions no longer act as valid outputs, while useful obsolete structure can support the retained task. Across multiple task settings, DR removes obsolete behaviour while preserving retained utility. More importantly, across classification benchmarks, DR matches or exceeds competing unlearning and editing baselines in retained accuracy, eliminates obsolete predictions, and adapts up to $60\times$ faster than competing unlearning methods. --- ### Uncertainty-Guided Handshake: Efficient Human-in-the-Loop Refinement for Surgical-Grade Glioma Segmentation Authors: Samuel Hart, Ahmad Yahya, Ahmed Karam Eldaly Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01452v1 While state-of-the-art automated models for medical image segmentation achieve high mean performance, they frequently suffer from localized, catastrophic failures that preclude safe clinical deployment, particularly in neuro-oncology. Interactive segmentation frameworks mitigate this by incorporating human oversight, but traditionally impose prohibitive cognitive and temporal workloads by requiring clinicians to manually search for errors. In this project, we present an efficient, Hybrid Structural-Aleatoric Human-in-the-Loop framework for glioma segmentation that bridges the gap between automated baseline performance and surgical-grade precision, achieving sub-2.0 mm HD95 on curated benchmarks while providing safety-net routing for structural failures across real-world clinical data. By extracting voxel-wise Test-Time Augmentation (TTA) uncertainty and applying hierarchical topological filtering, our method proactively isolates high-risk structural anomalies. We comprehensively evaluated our approach on a challenging out-of-distribution clinical stress-test cohort (N = 362). Operating under a simulated Human Oracle, the framework improved the Whole Tumor (WT) Dice score from 0.891 to 0.914 and reduced the 95th percentile Hausdorff Distance (HD95) from 5.82 mm to 4.76 mm. Critically for surgical safety, the system rescued severe boundary failures in the Tumor Core, reducing mean HD95 from 17.96 mm to 14.83 mm (improving absolute TC Dice to 0.356). These spatial rescues were achieved while demanding a median interactive workload of just 11.3% of the target volume. Acknowledging this as a simulated upper bound lacking real-world cognitive friction, the framework nevertheless demonstrates a highly Pareto-efficient pathway for safely deploying clinical AI. --- ### A Multi-Agent LLM Framework for Personalized Health Checkup Interpretation and Guidance Authors: HyungJun Kim, Taehan Lee, Soojin Cheon Published: 2026-10-01 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2610.01451v1 Personalized interpretation of health checkup results requires reasoning across longitudinal records, medical knowledge, lifestyle guidance, and healthcare navigation. We present a multi-agent large language model (LLM) system that identifies multiple intents, maps each to a task-specific agent, executes them in parallel, and synthesizes their outputs. We compared answers generated in Single Agent and Multi Agent settings on 120 Korean compound queries combining two to four requirements, using synthetic health checkup records. The Multi Agent improved the weighted LLM-judge score from 1.695 to 1.797 (p = 0.027), and three additional LLM judges showed consistent improvements ($Δ$ = +0.111 to +0.186, all p < 0.05). The gains came from usefulness, consistency, and the handling of every requirement in compound queries, whereas numerical accuracy and grounding improved significantly under only one of the four judges and medical safety did not differ, and critical failures occurred at similar rates (Single Agent 15.0% vs. Multi Agent 13.3%). Two human evaluators preferred Multi Agent in 66.7% and 68.3% of pairwise comparisons. Multi Agent execution increased latency and cost by 1.31$\times$ and 2.02$\times$, respectively. In exploratory subgroup analyses, the improvement was concentrated in queries involving personal-record lookup. --- ### Code-Switching Spoken Language Identification as Multi-Label Set Prediction Authors: Shunsuke Mitsumori, Matthew Wiesner, Shigeo Morishima, Shinji Watanabe Published: 2026-10-01 Categories: eess.AS, cs.CL arXiv: https://arxiv.org/abs/2610.01450v1 Code-switched (CS) speech leaks through the monolingual language identification (LID) filters used to curate massive speech corpora, calling for CS-aware LID (CS-LID). We formulate utterance-level CS-LID as multi-label language-set prediction and propose a set generator that directly outputs the languages in an utterance, comparing it against atomic-pair and score-based classification baselines. Oracle Top-k is the strongest baseline, but thresholding fails because no single threshold separates CS from monolingual speech. Our set generator predicts the correct language count on unseen pairs without assuming the number of languages, but underperforms oracle Top-k in exact set accuracy. Our analysis identifies the key obstacles to robust CS-LID: oracle cardinality, threshold instability, language bias in CS training data, and the synthetic-to-real gap. --- ### On skew-symmetric distributions and their use in Monte Carlo sampling algorithms: coordinate-free, Gibbs-style and manifold versions of the Barker proposal Authors: Minh Vu, Samuel Livingstone, Pantelis Samartsidis Published: 2026-10-01 Categories: stat.CO, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2610.01448v1 Skew-symmetric probability distributions provide a principled mechanism for incorporating gradient information into Markov chain Monte Carlo algorithms. Here we review the (preconditioned) Barker proposal, a Metropolis--Hastings algorithm built on skew-symmetric distributions, and motivate its design. We then introduce three natural extensions. First, we propose coordinate-free variants of the Barker algorithm. Second, we introduce a Gibbs-style Barker algorithm that re-evaluates the gradient at each partially updated coordinate. Third, we derive a simplified manifold Barker algorithm, producing a manifold sampler with enhanced robustness compared to natural comparators. Numerical experiments demonstrate that the Gibbs-style variant improves raw sampling efficiency on correlated targets, that the coordinate-free variants offer limited practical advantage over the standard Barker proposal once computational costs are accounted for, and that the simplified manifold Barker algorithm can achieve significant advantages over simplified manifold MALA when the local geometric structure of the target is irregular or unreliable. --- ### ibUMAP: Coherent and Scalable Field Evaluation for UMAP Optimization Authors: Bin Chen, Yumeng Xue, Patrick Paetzold, Yunhai Wang, Oliver Deussen Published: 2026-10-01 Categories: cs.LG, cs.HC arXiv: https://arxiv.org/abs/2610.01445v1 UMAP achieves scalable layout optimization through stochastic negative sampling. However, this stochasticity can lead to unstable embeddings across reruns and downstream reuse, as the estimated repulsive forces depend on the ordering of sampling events. We present ibUMAP, a coherent field-based alternative that evaluates attraction and repulsion from a shared embedding snapshot and applies them synchronously. Its degree-weighted repulsive field is motivated by the conditional expectation of negative sampling for a fixed embedding and represented by three scalar moments, which are evaluated efficiently on CPUs and GPUs using an interpolation-based FFT scheme. This formulation avoids explicit all-pairs computations while inducing optimization dynamics that differ from those of standard online UMAP. Controlled experiments show that synchrony and kernel capping alter the local-global fidelity trade-off, whereas FFT evaluation produces small average changes in final quality. End-to-end benchmarks show median speedups of 3.29x unseeded and 5.79x seeded over umap-learn on CPU, and 1.44x over cuML on million-scale datasets under unseeded GPU execution. These gains accompany greater run-to-run stability and measurable fidelity trade-offs. --- ### DRelay: Global Draft Context for Prefix-Aware Parallel Speculative Decoding Repair Authors: Zhuoyu Wang, Junnan Huang, Xinyu Chen Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.01439v1 Parallel drafting reduces the drafting overhead of speculative decoding for large language models (LLMs), but its gains remain limited by the accepted prefix length. Even when the correct token is present in the candidate pool, a single early selection error prevents subsequent predictions from being used. We propose DRelay, which uses global information from the entire draft block to perform prefix-aware selective repair of candidate selections before target-model verification. DRelay bases its decisions on candidate correlations and the selected path: a global reader extracts predictive information across positions for each candidate. While a causal selector combines candidate-level information extracted by the global read with the tokens selected at preceding positions to determine whether the native choice at the current position is consistent with the global evidence and the selected prefix. It then decides whether to retain or replace the token, thereby repairing early errors and extending the accepted prefix. We further jointly train the draft backbone and the selector, combining candidate-support learning with a repair objective, while weighting the repair loss according to each block position's potential contribution to the consecutive accepted prefix. Across eight diverse benchmarks on an H800 GPU, DRelay consistently improves both average acceptance length and end-to-end decoding performance over DFlash, Domino, and DSpark. Under SGLang serving, DRelay improves average end-to-end speedup over DFlash, Domino, and DSpark by 14.7%-16.8%, 8.7%-9.3%, and 8.1%-9.3%, respectively. --- ### The Impact of Processing Parameters on High-Accuracy Measurements in UAV Photogrammetry Authors: Paweł Ćwiąkała, Edyta Puniach, Elżbieta Pastucha, Wojciech Gruszczyński Published: 2026-10-01 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.01438v1 Unmanned aerial vehicle (UAV) photogrammetry is increasingly used in applications requiring high accuracy, such as determining ground surface changes caused by landslides, mining, or microrelief transformation. While acquisition strategies have been widely studied, the influence of the processing workflow-particularly Bundle Block Adjustment parameter settings-remains insufficiently explored. This study addresses this gap through a systematic, full-factorial evaluation of 768 processing variants applied to ten UAV datasets collected over 1.5 years in a 220 ha study area. Eight key parameters were analysed. The results show substantial variability in final 3D accuracy: the best performing variant achieved a root mean square error (RMSE) of 16 mm, whereas the weakest reached 303 mm. The most influential factors were the number of ground control points, the application of additional camera calibration corrections, and the use of the Post-Processing Kinematic GNSS method for determining camera projection center coordinates. The study also evaluates how workflow optimization affects the accuracy of displacement, tilt changes, and horizontal strain determination. While random displacement errors remained stable (RMSE of ~6-7 mm), systematic errors were significantly reduced by over half in all axes, with vertical median absolute error decreasing from 14 mm to 7 mm in the optimized configuration compared to the baseline previously used by the authors. This study provides the first large-scale, practice-oriented assessment of how processing parameter selection shapes the accuracy of both photogrammetric products and deformation indices determination. The results offer actionable guidance for developing more robust and repeatable UAV photogrammetry workflows tailored to high-precision monitoring. --- ### A Deterministic and Auditable AI Security Risk Assessment Framework with ATLAS Aligned Executable Rules and Formal Verification Authors: Yixuan Huang, Basel Halak, Boojoong Kang Published: 2026-10-01 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.01436v1 Artificial intelligence systems are increasingly deployed in high impact and safety critical settings, yet security assessment remains difficult to reproduce and defend under audit. Existing approaches often rely on narrative checklists or assessor driven scoring, and they lack an explicit, machine evaluable mapping from observable engineering artefacts to stable technique level outcomes. We present an evidence driven AI security assessment framework that operationalises assessment as a deterministic decision function. The framework normalises heterogeneous artefacts into a project independent Control ID taxonomy scored on a bounded four level ordinal scale, compiles technique level predicates from a pinned MITRE ATLAS snapshot via an explicit mitigation to control mapping, and outputs technique indexed feasibility and impact levels with traceable links back to the triggering evidence. We package all normative choices as a versioned assessment policy object to support repeatable reassessment across snapshots. To ensure semantic correctness, we formally verify boundedness, totality, ordered semantic consistency, and monotonicity of the compiled evaluator over the full declared score domain. We evaluate the framework on five public open source AI projects pinned to explicit repository snapshots, quantify before and after changes under a unified hardening intervention, and validate responsiveness to real engineering changes through fork based implementations of Software Bill of Materials (SBOM) generation and Continuous integration (CI) security scanning gates. Results show consistent downward shifts in feasibility profiles under strengthened observable controls, while worst case residual feasibility persists when technique specific core controls remain absent from the evidence scope. --- ### Distillation of Tabular Foundation Models into Efficient Predictors Authors: Minho Jeong, Dooho Lee, Jinmo Lee, Jaemin Yoo Published: 2026-10-01 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.01435v1 Tabular foundation models (TFMs) achieve strong predictive performance through in-context learning, yet repeatedly conditioning on labeled data makes inference expensive. Knowledge distillation can reduce this cost by transferring their predictive ability to lightweight, dataset-specific students. However, the dependence of TFM predictions on both a labeled context and a query introduces two design questions: how to construct teacher supervision and whether expanding query coverage improves distillation. We examine these questions across two TFMs and both neural and tree-based students, and derive an effective distillation recipe. The recipe uses the full labeled training set as teacher context and trains students solely on teacher predictions for observed and synthetic queries. On TabArena, the resulting students outperform their supervised trained tuned-and-ensembled counterparts by 57-98 Elo points. Applied unchanged to TALENT, the same recipe improves matched default students on 236-258 of 300 datasets and reduces median primary error by 4.0-6.4%. The distilled students also achieve median inference speedups of 3.0-21.6 times over their teachers, offering a practical trade-off between predictive performance and repeated inference cost. Code is available at https://github.com/nums-ai/TFM_Distillation . --- ### MWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMs Authors: Xudong Wang, Hao Wu, Haozhe Hu, Peiran Yin, Xinghao Chen, Yunpu Ma, Wei Zhang, Xiaoyu Shen Published: 2026-10-01 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.01434v1 Multimodal large language models (MLLMs) incur substantial inference costs when processing long visual-textual sequences. While existing operation compression methods exploit modality-level redundancy, they largely treat computation within attention heads and shared feed-forward network (FFN) channels as unified units, leaving finer-grained redundancy underexplored. We find that redundancy varies both across modality-interaction paths within the same attention head and across visual and textual executions of the same FFN channel. Based on these findings, we propose Modality-aware Width-wise Operation Pruning (MWOP), which independently prunes visual-to-visual (V2V), text-to-visual (T2V), and text-to-text (T2T) attention paths within each layer, and separately selects FFN channels for visual and textual inputs. A first-order Taylor criterion guides the pruning process, with FFN importance re-evaluated after attention pruning and LoRA-based recovery training. To translate the resulting fine-grained sparsity into practical acceleration, we further develop path-sparse Triton attention kernels and compact visual-side FFN execution. MWOP preserves the token sequence while reducing attention and FFN computation, making it complementary to token compression and enabling simultaneous reduction of sequence length and per-token computation. On LLaVA-OneVision-7B, MWOP alone achieves a $1.6\times$ prefill speedup with 99.7\% average performance retention across 12 benchmarks. Combined with two representative token compression methods, it further increases their prefill speedups from $2.0\times$ and $1.9\times$ to $2.9\times$ and $2.7\times$, respectively. Results on Qwen2.5-VL-7B further demonstrate its applicability across architectures. The code is available at https://github.com/EIT-NLP/MWOP. --- ### Learning ab initio phase-field models Authors: Mengyi Chen, Peichen Zhong, Zihan Zhang, Qianxiao Li Published: 2026-10-01 Categories: cond-mat.stat-mech, cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2610.01432v1 Simulating microstructure evolution requires quantum-mechanical accuracy and mesoscopic reach in length and time scales, a combination that no current method achieves. Classical phase-field models provide this reach, but their accuracy is limited by phenomenological free energies and mobilities. Here we develop a framework for learning ab initio phase-field models, where the mesoscopic equation is not postulated but derived from a Mori-Zwanzig projection of molecular dynamics onto species-density fields under explicit assumptions. The nonlocal free energy and mobility left unspecified by this equation are parametrized by neural networks and learned from short molecular dynamics trajectories generated with machine-learning interatomic potentials of ab initio accuracy. We demonstrate the framework on an iron-boron melt and on hydrogen-helium mixtures under planetary conditions. For iron-boron, the model shows that the melt at the FeB$_4$ composition is spinodally unstable at ambient pressure but stabilized at 10 GPa, offering a thermodynamic rationale for why FeB$_4$ has been synthesized only under high pressure. For hydrogen-helium, the model predicts the immiscibility boundary and captures droplet nucleation and growth in helium-rain simulations of a column corresponding to 2.2 million atoms, far beyond the scale of atomistic modeling at comparable accuracy. Trained across compositions and conditions, such models could provide a mesoscopic counterpart to ab initio molecular dynamics. --- ### Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs Authors: Nagham Omar, Mahmoud Jabarin, Maya Rozenshtein, Rom Himelstein, Avi Mendelson, Amit LeVi Published: 2026-10-01 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.01428v1 Generalization in large language models (LLMs) is the ability to produce consistent and semantically stable outputs when the same input is expressed in different ways. Existing work typically evaluates generalization through aggregate accuracy on a single prompt format, task, or set of variations, which conflates robustness with overall benchmark performance. In this work, we show generalization evaluation at the level of individual examples, across multiple input variants, and across different aspects of model behavior, focusing on variability rather than reducing performance to a score that can be improved through narrow training or other ways that obfuscate generalization evaluation. Following this view, we introduce the Stability-Aware Generalization Objective (SAGO), a framework that measures how much model behavior changes for the same input under different variations and benchmarks, capturing variability across several dimensions including generation consistency, internal activations, confidence, and response mirroring. We show that many commonly used models exhibit statistically significant and consistent generalization instability: no model generalizes uniformly, behavioral axes capture independent failure modes, and cross-dataset variation can reverse model rankings. --- ### SHAMS: An Audio-Grounded Pronunciation Benchmark for Levantine Arabic Authors: Ben Sapirstein, Roy Mattar, Guy Mor-Lan, Ahlam Mohamed, Letizia Cerqueglini, Morris Alper Published: 2026-10-01 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.01427v1 Levantine Arabic (LA) is spoken by tens of millions of people, creating a pressing need for shared benchmarks to evaluate LA speech-language technologies. Evaluating such technology is particularly challenging given LA's internal diversity and its opaque and non-standardized orthography. We present SHAMS (SHami Annotated Multi-dialect Speech), a benchmark comprising 1,300 utterances drawn from open audio corpora, balanced across five LA varieties (Urban and Rural Palestinian, and Urban Jordanian, Lebanese, and Syrian). Each utterance is represented across four aligned tiers: audio, unvocalized orthography, diacritized text, and phonetic transcription. This structure supports evaluation of various downstream tasks such as diacritization, grapheme-to-phoneme conversion, automatic speech recognition, and audio-to-phoneme, grounded in audio and stratified by variety. We benchmark open and proprietary models across these tasks to demonstrate the utility of this benchmark for measuring progress across LA. We release SHAMS at https://shams-nlp.github.io . ---