# Research Papers — 2026-08 · bundle page 55 of 240 > Full-text markdown of papers #2701–2750 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/55 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/54.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/56.md) ### Sequential operator learning under dependent data Authors: Rafael Oliveira Published: 2026-08-25 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.24426v2 Learning operators from sequentially collected data arises in adaptive experimental design, Bayesian optimization, and dynamical-system modelling, where observations may be dependent, and future inputs or sensing operators may depend on preceding data. We derive time-uniform self-normalized concentration bounds for stochastic processes in Hilbert spaces with vector-valued noise. We use these bounds to obtain regression-error guarantees for linear operators, including targets outside the Hilbert estimation space, and for nonlinear parametric operators trained with strongly convex losses and regularizers. Our results allow possibly infinite-dimensional inputs and outputs without independence or mixing assumptions, providing a major step towards convergence guarantees for adaptive operator learning and learning from stochastic dynamical data. --- ### ZODIAC: Zero-shot Octree-based Diffusion for Anatomical Completion Authors: Miruna-Alexandra Gafencu, Vlad Bratulescu, Yordanka Velikova, Mohammad Farid Azampour, Nassir Navab Published: 2026-08-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.24422v1 Recovering the full 3D spine anatomy from intraoperative ultrasound is an ill-posed inverse problem, as the complete structure must be inferred from incomplete and noisy observations. Acoustic occlusions and limited field of view create large unobserved regions, while view-dependent artifacts lead to variability in expert annotations of the visible anatomy. Current supervised ultrasound shape completion methods rely on synthetically generated incomplete-complete paired data to learn conditional mappings under a predefined distribution of simulated occlusions. However, real intraoperative occlusions do not necessarily follow this distribution, which can limit generalization to patient data. As a result, accurate and robust completion from noisy partial observations remains an unsolved problem. We propose a zero-shot shape completion framework that reconstructs the entire lumbar spine from partial ultrasound observations without relying on simulated training data. To accommodate unseen and irregular patterns of missing structures, we introduce blended completion, a mechanism that integrates the learned anatomical prior with incoming partial geometry at inference time. The method learns a generative diffusion prior over full anatomical shapes represented in an adaptive octree structure, enabling efficient modeling of the complete spine in a single forward pass. Validation on phantom and volunteer data shows that decoupling completion from a predefined corruption distribution improves generalisation under real occlusions, outperforming a fully supervised variant by 22% on HD95 completion error. Code and data are available at https://github.com/miruna20/ZODIAC. --- ### A Judge Should Know What Changed:Construct Validity for LLM-as-a-Judge Evaluation Authors: Jianlin Chen, Wenhui Chen, Ziyao Lin, Chi Man Vong Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.24419v1 LLM-as-a-judge evaluation is usually assessed by agreement and robustness to surface perturbations, but reliability does not establish construct validity. We formalize construct validity for an evaluator as a two-dimensional profile: invariance S, the probability that a verdict is unchanged under construct-preserving edits, and construct sensitivity R, the probability that it changes under minimal construct-changing edits. We show that S and R are independent and that no scalar summary preserves all relevant comparisons. We measure the profile across 7 judges and 4 domains using 7 construct-changing intervention types and 5 register-only controls, with intervention direction determined by human annotators and generation, verification, and judging assigned to disjoint model families. At matched invariance S >= 0.90, judges average S = 0.945 but R = 0.319. Sensitivity also differs between scope and strength edits: R_scope = 0.383 versus R_strength = 0.262, a +0.121 gap with the same sign for all 7 judges. We further audit five public label sets and find that surface-only predictors reproduce 55%-67% of labels in paired mode, including 67.4% of MT-Bench human votes. These results show that high judge agreement can coexist with weak sensitivity to changes in the construct being evaluated, motivating joint reporting of invariance and sensitivity and auditing the validation set itself. --- ### MRI-based Deep Radiomic Phenotyping of Neuromuscular Disorders: A Topology-driven Characterization Authors: Martyna Żur, Łukasz Piórecki, Marek Socha, Jose Verdu Diaz, Ana Topf, Michael Obach, Marco Savarese, Jocelyn Laporte, Benedikt Schoeser, Filippo Santorelli, Jordi Diaz-Manera, Volker Straub et al. Published: 2026-08-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.24415v3 Quantitative assessment of muscle MRI is crucial for monitoring neuromuscular disorders (NMD). This study introduces an automated radiomic phenotyping framework based on original features engineered across five main architectural domains: quantitative morphometry, spatial distribution, geometric shape, interactions between progressive fat replacement stages, and graph-based topology. Utilizing 1184 MRI scans from the CoMPaSS-NMD project, we map the complex 3D architecture of heterogeneous intramuscular lipodegeneration into objective, morphologically interpretable biomarkers. We introduce a graph-based skeletonization of fat infiltrates to quantify muscle architectural changes, establishing a multi-dimensional extension of traditional, spatially-agnostic volume metrics by mapping topological networks across the entire 3D muscle volume. Statistical screening via non-parametric Kruskal-Wallis analysis confirmed the discriminative power of these novel descriptors across the genetic hierarchy. Notably, topological network metrics (e.g., SF1_Skel_Nodes, $ε^2$ = 0.2656) and interface dynamics metrics (e.g., SF2_To_SF1_Dist_Min, $ε^2$ = 0.2092) demonstrated substantial effect sizes, providing deeper structural insights than classical volumetric assessments. Post-hoc pairwise evaluations and UMAP projections further indicated the capability of these topological and 3D geometric invariants to capture disease-specific macroscopic infiltration patterns. These results demonstrate that global architectural features represent a highly promising class of biomarkers for differential diagnosis, offering new avenues for tracking longitudinal disease dynamics in neuromuscular diagnostics. The developed automated feature extraction pipeline is integrated and available within the MUSCAT (MUSCle fAt Topology) library. --- ### ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping Authors: Zhi-Kai Chen, Jun-Jie Tao, Wei-Xiang Mao, De-Chuan Zhan, Han-Jia Ye Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.24411v1 The efficiency of Large Language Model (LLM) serving is fundamentally limited by the sequential nature of autoregressive decoding. Speculative Decoding (SD) mitigates this by using a lightweight draft model to speculate future tokens, which are then validated by the LLM in a single parallel forward pass. To further boost efficiency, multi-candidate schemes propose diverse candidate sets to increase the likelihood of token acceptance. However, we show that these schemes are bottlenecked by Residual Drift: a phenomenon where the rejection of initial candidates causes the residual target distribution to diverge from the draft model's predictions. This shift renders subsequent candidates ineffective and forces the system into expensive resampling. To resolve this, we propose ResiSpec, a framework that strategically reforms the proposal distribution during verification to anchor the residual target mass within the draft model's high-confidence regions. By mathematically re-aligning the verification process without compromising output exactness, ResiSpec prevents candidate obsolescence and achieves up to 1.92$\times$ speedup over state-of-the-art multi-candidate methods. Code is available at https://github.com/Czzzk/Resispec. --- ### Multilevel Fair Allocation under Additive Preferences Authors: Maxime Lucet, Nawal Benabbou, Aurélie Beynier, Nicolas Maudet Published: 2026-08-25 Categories: cs.GT, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.24400v1 We study multilevel fair resource allocation with tree-structured hierarchical relations among agents. At each level, the problem can be viewed locally as allocating an agent's bundle to its children, the overall allocation being a trace of this process iterated down to the leaves. Assuming that internal nodes' utilities are the utilitarian welfare of their children, and the leaves have classical additive utilities over items, we first propose multilevel adaptations of usual envy-based fairness notions (e.g., WEF1). We present three adaptations and show that the choice among them is not neutral. We prove that, under identical preferences, the three adapted envy-based notions coincide, and that the Multilevel extension of Weighted Round Robin (Chakraborty et al., 2021) (MWRR) guarantees them. We then show that under general preferences, MWRR may guarantee some notions while failing others. Finally, through experiments, we show that MWRR may still perform well even for adaptations it does not formally guarantee. --- ### Equivariant Covariance Tensors: Guaranteed SPD Uncertainty for Tensor-Valued Geometric Learning Authors: Ruihan Liu, Yu Ji, Jianbo Yu, Shifu Yan, Qingchao Jiang Published: 2026-08-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.24386v1 Tensor-valued prediction is fundamental to geometric deep learning, yet uncertainty quantification (UQ) for such outputs remains an open challenge. While E(3)-equivariant neural networks excel at point estimates, they lack rigorous confidence measures. We focus on symmetric rank-2 tensor prediction, where the target has six Kelvin--Mandel coordinates and full uncertainty is represented by a $6\times6$ covariance matrix. We introduce a framework for E(3)-equivariant UQ, modeling the full predictive distribution where both mean and covariance preserve rotational symmetry. Our approach decomposes the covariance into irreducible representations $\mathrm{Sym}^2(ρ_c) \cong 2\times(l=0) \oplus 2\times(l=2) \oplus 1\times(l=4)$. By mapping from the flat Lie algebra $\mathfrak{sym}(6)$ to the curved SPD manifold via matrix exponentiation, we strictly ensure positive-definite covariances while maintaining exact equivariance. Furthermore, we formulate a Log-Euclidean Equivariant Scoring Objective (LE-ESO)---a robust surrogate loss based on the Multivariate Laplace distribution---providing robustness to heavy-tailed errors and stable optimization. Validation on ModelNet40 inertia tensors and Materials Project dielectric tensors demonstrates that our method achieves competitive performance and provides physically consistent, symmetry-preserving uncertainty estimates with useful risk and OOD sensitivity. --- ### Markerless Pose Estimation for Resistance Training Technique Assessment Authors: Joseph Turner, Jeff Clark, Nawid Keshtmand Published: 2026-08-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.24384v1 Resistance training can be a high risk activity, and safe form is essential to avoiding injury. Laboratory-based movement analysis provides quantitive technique assessment, yet is not easily accessible. Markerless pose estimation infers body landmarks from images or video without physical markers and could offer a feasible alternative for technique assessment. We present a pose estimation framework to evaluate resistance-training technique from ordinary video footage. Using BlazePose, anatomical landmarks were extracted from squat, bench press, and deadlift videos and converted into joint-angle trajectories, with the squat serving as the primary case study. Trajectories were assessed against a defined reference repetition using root mean square error (RMSE). Results show that the framework recovers meaningful kinematic patterns for the squat and deadlift, enabling quantitative comparison between repetitions and identification of technique variability within a set. Performance depended strongly on camera orientation and visual occlusion, with non-sagittal views distorting 2D joint-angle estimates. The findings demonstrate that markerless pose estimation can support accessible biomechanical assessment outside laboratory environments. --- ### When Does Self-Supervised Pretraining Help Tabular Models? A Study of Label Scarcity and Missing Data Authors: Sahand Mazrouei Published: 2026-08-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.24381v1 Self-supervised learning (SSL) has emerged as a promising approach for tabular data, yet its efficacy under extreme label scarcity and test-time missingness remains under-explored. In this paper, we evaluate a mask-and-recover SSL pretraining objective against training from scratch and classical baselines across 14 diverse classification tasks. First, while SSL outperforms training from scratch on average and remains competitive with state-of-the-art tree ensembles (achieving ~0.8954 AUC vs. Random Forest's 0.9015 at 10% labels), the SSL-vs-scratch gains exhibit high inter-task variance and lack significance (p = 0.626 at both 5% and 10% labels). Second, contrary to the hypothesis that missing-value imputation objectives universally benefit datasets with native missingness, SSL yields the most reliable improvements on clean datasets, while frequently degrading performance on datasets with high inherent missingness. Third, despite this training variance, SSL-pretrained models achieve a higher average AUC than scratch-trained models under both test-time missingness completely at random (MCAR) injection (+0.0245 AUC, positive on 11 of 14 tasks) and structured missingness shifts (MNAR, +0.0418 AUC, positive on 8 of 14 tasks), though neither difference remains statistically significant after Holm-Bonferroni correction for multiple comparisons (adjusted p = 0.118 and p = 0.518, respectively). Fourth, comparing our mask-and-recover objective against three established tabular SSL baselines (VIME, SCARF, SubTab) under an identical encoder architecture, we find no significant difference from any of them (adjusted p = 0.459, p = 1.000, p = 1.000), indicating our findings reflect general properties of tabular SSL rather than idiosyncrasies of one particular pretext task. --- ### Bridging Adversarial and Collaborative Learning for AI-Generated Image Quality Assessment Authors: Baoliang Chen, Qing Lin, Sijie Mai Published: 2026-08-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.24372v1 AI-generated image quality assessment (AIGIQA) requires jointly reasoning about perceptual fidelity and prompt alignment, two quality dimensions that are often treated as independent in existing AIGIQA models. However, by re-examining human ratings, we uncover a previously overlooked phenomenon: the two dimensions are interdependent and exhibit both competitive and cooperative interactions during human rating. This observation suggests that a unified model should neither collapse the two dimensions nor rigidly separate them, but rather adaptively negotiate their interplay. Motivated by this insight, we introduce an interaction-aware learning framework that models perception-alignment relations through adversarial and collaborative inference pathways. Instead of designing a rigid dual-branch architecture, our method employs a gated interaction module that dynamically routes features according to the inferred relationship between the two dimensions. Task-aware prompts further modulate the gating behaviour, enabling the model to switch between competition and cooperation when necessary. Experiments across multiple AIGIQA benchmarks demonstrate that our approach not only achieves state-of-the-art accuracy but also yields interpretable interaction patterns, offering a more faithful approximation of human judgment. The codes are available at https://github.com/LQAMEI/ACL-IQA. --- ### Do Recipes Have Personas? Characterizing and Generating Creator Style in Attributed Procedural Graphs Authors: Lei Jiang Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.24369v1 While large language models (LLMs) possess vast zero-shot procedural knowledge, their tendency to produce homogenized logic often obscures the unique, idiosyncratic execution processes of individual human creators. In this paper, we investigate the computational discovery of procedural personas from unstructured data. To achieve this, we introduce ViralRecipesTrans, a new dataset of procedurally aligned execution flow graphs extracted from popular culinary video transcripts and explicitly mapped to specific creators. We formulate procedural stylometry as a graph learning and process discovery task, revealing a fundamental duality: while traditional lexical classifiers overfit via semantic leakage, discrete topological metrics successfully capture the rigid physical constraints of a creator's workflow. Building upon this characterization, we extend our framework into a novel generative task--predicting a creator's exact structural execution graph for unseen dishes. We expose a fundamental dichotomy in style generation between global macro-planning and local structural execution. Our results demonstrate that few-shot LLMs dominate semantic assignment but suffer from persistent macro-planning deficits, whereas our structured two-stage model achieves superior topological control via rigid Markovian priors. Together, an ensemble approach to procedural generation combines the strengths from both sides, dynamically synthesizing global semantic reasoning with localized topological footprints to automate the discovery and generation of personalized workflows. --- ### From State to Action: OODA-Tool for Reliable Multi-Turn Tool Use Authors: Rongfeng Guo, Yinxuan Huang, Yusen Wu, Maoqing Zhong, Yunlu Chen, Meng Tang, Teng Long, Vincent Tao Hu Published: 2026-08-25 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.24368v2 Reliable multi-turn tool use requires an agent to preserve an evolving task state and ensure that each action remains consistent with it. However, direct function-calling and ReAct-style policies learn state tracking and action generation within the same autoregressive trajectory. This coupling creates state-action competition: the pressure to produce the next call can overwrite or ignore information accumulated earlier in the interaction. Inspired by Boyd's Observe-Orient-Decide-Act cycle, we introduce OODA-Tool, a typed closed-loop policy designed to mitigate this competition by separating state preservation from action realization. Rather than generating an action directly from the interaction history, OODA-Tool routes each decision through controller-checked intermediate states, ensuring that the final output remains grounded in the current task state. Specifically, Observe reconstructs the task state, Orient determines whether execution is warranted, Decide forms an admissible action structure, and Act realizes the external output. We evaluate OODA-Tool against direct function-calling and ReAct policies using Qwen3 models ranging from 0.6B to 14B across multi-turn, multi-tool, and incomplete-information settings. OODA-Tool consistently improves task success across model sizes, with larger gains on smaller models and on tasks whose actions depend strongly on information accumulated across turns and prior tool results. Controlled variants, stage-level ablations, and transfer evaluations further demonstrate the robustness of these improvements. --- ### Variance-Guided Spatial Attention Fusion for Robust End-to-End Driving under Asymmetric Sensor Degradation Authors: Weizhi Tao, Zengwang Jin, Xiao Wang, Hailong Huang Published: 2026-08-25 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2608.24366v1 End-to-end multimodal driving has progressed rapidly by fusing camera and LiDAR streams. Existing pipelines remain fragile under asymmetric sensor degradation, where either an entire modality or only a localized region is corrupted while other regions remain useful. The key difficulty is not simply to add an uncertainty head, but to obtain dense reliability supervision, calibrate this reliability against physical fault severity, and use it before unreliable features bias the planner. We propose Variance-Guided Spatial Attention Fusion (VG-SAF), in which dense heteroscedastic reliability estimates act as interpretable spatial gates. The framework couples three components. First, a physically grounded augmentor simulates representative camera and LiDAR failures and emits a continuous spatial mask, providing dense supervision without additional annotation. Second, modality-specific experts predict per-pixel reliability scales through cross-branch dense distillation in log space, enforcing a monotone severity-to-scale response. Third, calibrated reliability maps drive a hybrid attention mechanism that suppresses unreliable cells with a local spatial gate and arbitrates between modalities through a cross-modal trust softmax. A Laplace uncertainty head emits a systemic waypoint uncertainty scale that signals severe or combined sensor degradation, including severities outside the training ranges. On the CARLA Longest6 benchmark, VG-SAF consistently improves closed-loop robustness over the baselines across camera-only, LiDAR-only, and joint degradation regimes, as measured by driving score, route completion, and infraction score. --- ### MaST: Motion-aware Sparse Pipeline for Lightweight Object Tracking Authors: Qingmao Wei, Fagui Liu, Dengke Zhang, Qingze He, Quan Tang Published: 2026-08-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.24365v1 Transformer-based object trackers are renowned for their strong performance, yet dense token processing often leads to prohibitive computational cost, limiting real-time deployment on edge devices. While recent works explore token pruning to reduce computation, they often stop short of an end-to-end sparse pipeline, as early-layer token scores can be noisy without a motion prior, and many trackers ultimately fall back to dense reshaping to feed the dense prediction head that partially negates the savings. We introduce Motion-aware Sparse Tracker (MaST), a sparse tracking framework that makes sparsity effective from tokens to boxes. First, MaST injects a lightweight motion prior to refine cross-attention-based importance scores, enabling earlier and more stable token reduction in the search region. Second, we introduce a natively sparse prediction head that operates directly on the retained unstructured tokens with a score-first, regress-once design, eliminating dense padding/reshaping and reducing redundant computation. Extensive experiments on multiple benchmarks demonstrate that MaST establishes new state of the art among lightweight trackers, where MaST-tiny attains 63.8 AUC on LaSOT and 80.1 SUC on TrackingNet, surpassing the prior best AsymTrack-S by +1.0 AUC and +2.2 SUC while running at 152 FPS on Jetson Nano, nearly twice as fast as AsymTrack-S at 88 FPS. Code is available at https://github.com/TsingWei/MaST. --- ### B-MIM: Biased Masked Image Modeling for Generalizable Segmentation of Fine-Grained Anatomical Structures Authors: Sebastián González, Karen Sanchez, José M. Saavedra, Marcelo Pizarro, Bernard Ghanem Published: 2026-08-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.24364v1 Self-supervised pretraining enables transferable representations for medical imaging, yet most CT encoders remain biased toward coarse semantic understanding, limiting their sensitivity to fine-grained anatomical structures such as vessels or small tumors. In this paper, we introduce Biased Masked Image Modeling (B-MIM), a modification of the iBOT objective that stochastically reduces global semantic alignment to prioritize local patch reconstruction. This bias encourages the encoder to capture high-frequency morphological details and structural continuity. We curate a multi-institutional CT abdominal dataset of 9,955 filtered studies from 17 public sources and pretrain a 3D Swin Transformer backbone using B-MIM. Across inter-dataset experiments on liver vessel segmentation, the proposed encoder improves topological fidelity (clDice) and achieves competitive Dice scores in tumor segmentation, compared to fully fine-tuned baselines, despite updating only a fraction of the parameters. Our results suggest that reducing global semantic pressure during pretraining enhances generalization to intricate anatomical structures. --- ### Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems Authors: Yarden Bakish, Amir Dudai, Roy Ganz, Oren Nuriel, Elad Ben Avraham, Mor Shpigel Nacson, Ron Litman Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.24361v1 Multi-agent LLM systems are increasingly deployed in real-world applications, where failures can be costly and difficult to localize. Despite growing efforts to automate failure attribution, diagnosing failed runs still largely relies on human engineers. Yet engineers rarely debug complex systems by reading raw logs end to end. Instead, observability tools organize traces around components, actions, and dependencies to support targeted navigation. We hypothesize that modern LLMs can benefit from the same paradigm. To test this hypothesis, we introduce Adaptive Influence Graphs (AIGs), a two-stage agentic framework that first transforms a failed trace into a structured graph and then navigates it to identify the critical error. Across multiple models, we show that richer trace representations consistently improve failure attribution, with adaptive graph construction and agent-directed traversal yielding the strongest results. AIGs establish a new state of the art on Who&When, the standard benchmark for multi-agent failure attribution. This affirms our hypothesis that attribution depends not only on the diagnosing model, but also on how the trace is represented and explored. --- ### Words, Spaces and Generative AI: Layers of language in contemporary architecture Authors: Anca-Simona Horvath Published: 2026-08-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.24360v1 Language can be considered a design material in architecture, and in the context of text-to-X generative AI models becoming a common tool for architectural practice, looking more closely at language is more important now than in the past. After describing some of the important developments in linguistics starting from Wittgenstein, and including the work of Chomsky, Lakoff, conceptual and generative metaphors as proposed by Schön, this chapter connects them to contemporary architectural design and generative text-to-X tools. The chapter builds on the idea that three main forms of language intertwine in architectural design done using generative AI, namely (I) discourse (or natural language which can contain professional terminology specific to our field), (II) programming languages (which are artificial languages sitting at the basis of all computational systems), and (III) annotations (as language elements attached to pieces of data). It concludes by outlining a research agenda for connecting generative metaphors to generative AI: (a) conducting corpus linguistics studies on architectural texts (using quantitative tools such as topic modelling, and qualitative tools such as discourse analysis); (b) bringing communication theory and information studies closer to architectural research and (c) taking into account that different (natural) languages come with different affordances meaning generative and conceptual metaphors differ in relation to this. --- ### The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents Authors: Roy Ganz, Mor Shpigel Nacson, Adi Kalyanpur, Ron Litman Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.24358v1 Coding agents perform long-running tasks spanning dozens of model calls, tool uses, and code edits. As these runs unfold, users face a practical cost-quality trade-off: escalating to a stronger model when a cheaper one struggles, or downshifting once the hard reasoning is complete. Each switch requires the receiver to continue a non-native trajectory produced by another model. We study how this handoff affects quality and cost, and how varying the trajectory information inherited by the receiver changes the outcome. Using pairs of low-cost, low-capability (LC) and high-cost, high-capability (HC) models from the Claude and GPT families, we vary handoff direction, timing, and interface, comparing full-trajectory transfer, compaction, and trajectory removal while preserving the repository state. Across both model families, full-trajectory escalation recovers less than half of the LC-to-HC quality gap while incurring a substantial cost premium. We term this cost-quality penalty the handoff tax. By contrast, downshift offers a favorable cost-quality point. Interestingly, the preferred interface also reverses with direction: reducing LC-model trajectory information improves escalation quality, whereas removing the HC-model trajectory reduces downshift quality. --- ### Not All Tokens Are Equal: Region-Aware Consistency Repair of Backdoors in MLLMs Authors: Jiali Wei, Ming Fan, Mingkun Zhang, Haoyu Wang, Jun Sun, Guoheng Sun, Xiaoning Ren, Haijun Wang, Ting Liu Published: 2026-08-25 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.24354v1 MLLMs are increasingly deployed in user-facing applications, yet they inherit backdoor risks from the pipelines used to construct them: triggers may reside in images, texts, or both. Existing model-level backdoor removal methods, largely designed for conventional classifiers, show limited effectiveness on MLLMs, while MLLM-specific defenses mainly operate at inference time, filtering suspicious inputs without removing the backdoor embedded in the model. To address this gap and eliminate latent backdoors from MLLMs at their source, we present RACER, a model-level repair framework motivated by a key observation: backdoors induce abnormal layer-to-layer evolution in internal representations, which we term the layer-wise inconsistency anomaly. Importantly, this anomaly is modality-dependent, concentrating primarily in the token region encoding the trigger features that the backdoor model actually relies on. RACER therefore decomposes the fused representation into visual and textual token regions, normalizes their layer-wise inconsistency separately, and recomposes them using modality-aware weights over a deep-layer window, yielding a region-aware inconsistency objective that better captures localized backdoor-induced anomalies. Through a min-max optimization, this objective drives worst-case perturbation synthesis and adversarial fine-tuning against the resulting perturbation to repair the model, suppressing the deep representational directional shifts on which backdoor behaviors rely. RACER requires only 100 clean samples and no knowledge of the trigger, attack objective, or even whether the input model contains a backdoor. Evaluations on three open-source MLLMs across 36 backdoor settings spanning image, text, and multimodal triggers show that RACER reduces the average ASR to 1.1%, reaching 0% in 32 settings, while preserving clean-task utility on both backdoor and clean models. --- ### FARCA: Fact-Aligned Reliability-Aware Credit Assignment for Reinforcement Learning with Factual Supervision Authors: Qiming Xie, Wenjie Zheng, Xiangqing Shen, Rui Xia Published: 2026-08-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.24350v1 To reduce the hallucination risk caused by outcome-driven rewards in large language models trained through reinforcement learning with verifiable rewards, existing mitigation approaches introduce process-level factual supervision. However, due to coarse-grained aggregation of factual signals and the lack of reliability assessment for these signals, they create a mismatch between fact verification and policy updates. We term this noisy factual credit assignment and decompose it into two aspects: credit localization ambiguity and credit reliability ambiguity. To address these issues, we propose FARCA (Fact-Aligned Reliability-Aware Credit Assignment), a policy optimization framework that transforms factual supervision into localized, reliability-weighted token-level training signals. FARCA achieves fine-grained credit localization by aligning the granularity of fact verification with that of policy updates. It further introduces counterfactual evidence attribution, which uses the dependence of a factual judgment on key evidence as an empirical proxy for verification reliability to compute reliability weights. These weights modulate factual rewards and local policy advantages, reducing the influence of potentially unreliable signals on policy optimization. Experiments across different models and multiple factual reasoning benchmarks show that FARCA significantly improves model factuality while preserving general reasoning capabilities. --- ### Metadata-Aware Adaptation of a Generative Foundation Model for Conditional CMR Synthesis Authors: Marc Rodríguez, Grzegorz Skorupko, Nay Aung, Steffen E Petersen, Karim Lekadir, Polyxeni Gkontra Published: 2026-08-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.24342v1 Synthetic image generation is a promising strategy to address data scarcity and the underrepresentation of clinically important phenotypes in medical imaging, yet generating images that faithfully reflect meaningful patient characteristics remains challenging. In this work, we investigate metadata-conditioned cardiac magnetic resonance (CMR) synthesis using a pretrained latent diffusion model, encoding structured clinical metadata and slice position as textual prompts to guide CMR generation. To improve metadata adherence and address the imbalance of clinical attributes, we integrate three strategies: Metadata-Free Classifier-Free Guidance (CFG), Contrastive Batching, and Inverse-Frequency Sampling. The framework was fine-tuned and evaluated on 59,058 short-axis CMR from the UK Biobank using paired image similarity, distributional fidelity, and subgroup-level analyses. The combined approach achieved a Fréchet Inception Distance (FID) of 37.47, improving by 57.04\% over the same model fine-tuned without these strategies and by 28.68\% over a previous text-conditioned CMR diffusion baseline requiring cardiac geometry as additional input, while relying solely on patient metadata. This distributional gain, driven mainly by Metadata-Free CFG, came with a modest reduction in paired similarity, suggesting that the model prioritizes population-level realism over exact image reproduction. Subgroup analyses demonstrated improved alignment across demographic and acquisition-related metadata, with disease-specific conditioning being the most challenging task. These findings demonstrate the potential of generative foundation models for clinically meaningful CMR synthesis while highlighting the need for more effective metadata-aware conditioning strategies. Our code is available at https://github.com/rodriguezmarc/conditional-cmr. --- ### Mind the Student: Behavioral and Contextual Cues for Automated Engagement Prediction in Online Learning Authors: Alperen Kantarci, Visvanathan Ramesh, Gemma Roig Published: 2026-08-25 Categories: cs.CV, cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2608.24340v1 The prediction of student engagement from the online tutoring videos is difficult because engagement is a multidimensional construct comprising distinct behavioral, emotional, and cognitive states. A reliable prediction requires bringing together different types of behavioral signals as well as expressive cues. Through our analysis of the CASED dataset, it is clear that engagement prediction gets even harder due to the high inter-person variability as well as the subjectivity of the engagement annotation. To tackle these challenges, we develop a multimodal framework that integrates the implicit spatiotemporal features extracted from pretrained video, audio, and image encoders along with structured behavioral modalities like head pose, gaze, facial action units, emotion, and wavelet-based audio features. We integrate these modalities via a Perceiver IO latent bottleneck. Moreover, student and instructor personalities are modeled as variational posteriors over learnable embeddings to enable partial pooling across participants. We employ evidential regression and spectral-normalized Gaussian process classification heads for uncertainty-aware prediction to further improve robustness and calibration. Benchmark on the CASED challenge test set shows that all participating methods converge near random-chance performance, revealing the difficulty of the dataset. In this highly ambiguous regime, our framework achieves competitive performance while uniquely offering well-calibrated uncertainty metrics, demonstrating that reliable risk-quantification is an essential prerequisite for deploying engagement models in real-world educational tools. --- ### Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning Authors: Sophia Xiao Pu, Yumo Xu, Sailik Sengupta, Millennium Bismay, Ruixue Lian, James Gung, Yi-an Lai, Arshit Gupta Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.24338v1 Inference-time decoding methods improve LLM reasoning by exploring multiple candidate trajectories, yet treat each trajectory as atomic: either retaining it whole or discarding it irreversibly. This wastes computation on partially promising candidates whose high-quality prefixes are abandoned alongside degraded suffixes. We introduce Selective Regenerative Decoding (SRD), which routes each candidate to discard, keep, or refine only the degraded portion of the suffix while preserving the useful prefix of borderline candidates, without requiring a larger target model. Under mild assumptions, SRD achieves a provable 1.28-to-1.36-fold gain in sample efficiency over rejection sampling with strictly higher expected trajectory quality, with the gain growing as the candidate pool grows. Across MATH500, GPQA Diamond, HotpotQA, and AlpacaEval with multiple generation-reward model pairs, SRD matches Best-of-N accuracy with substantially fewer generated tokens and outperforms speculative rejection in low-compute regimes. By enabling segment-level intervention rather than whole-trajectory selection, SRD opens a previously underexplored region of the accuracy-compute tradeoff for inference-time reasoning. --- ### SteerCheck: Attribution Specificity and Alignment Leakage in Activation-Steering Audits Authors: Daming Luo, Christy Liang, Junyu Xuan Published: 2026-08-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.24335v1 Activation steering can change behaviour without establishing that the effect is specific to the intended concept. We introduce SteerCheck, a preregistered attribution audit that matches off-target KL and separates mean, protected-tail, polarity, transfer, and semantic claims. Exact replay of 960 Qwen3-14B interventions reveals complementary limits of common controls: isotropic directions occupy a narrow near-orthogonal region, whereas sign-randomized same-construction directions often retain substantial target alignment. Effect is strongly associated with signed cosine within the sign-randomized family ($ρ=.94$); $25.3\%$ of its draws exceed cosine $.5$, and every draw exceeding the observed mean effect has cosine above $.80$. This alignment leakage does not by itself invalidate a conditional randomization test; it limits what the comparator can distinguish and motivates reporting exchangeability assumptions, a construction diagnostic $A$, and the empirical cosine distribution. The primary Qwen complete gate remains negative because the protected tail fails all families. On independent data, continuous margin transfers only in Qwen and accuracy transfers in no selected cell. Prospectively registered language controls pass the complete gate in Qwen and DeepSeek, while a passing DeepSeek detox comparator rules out categorical separation; all nominal passes are sensitive to $Γ=1.10$. Frozen three-rater open-generation evaluation supports factual correction in DeepSeek but not Qwen; the automatic judge fails calibration (macro-F1 $.562$), so null-wide semantic results remain descriptive. SteerCheck makes these conditional and mixed conclusions auditable. --- ### SeMoCo: A Semantic-First Motion Codec for Motion Language Modeling Authors: Tianlv Huang, Hetian Guo, Ziyi Cai, Song Wang, Yanping Zhang, Zipei Fan, Xuan Song, Guangming Wu, Xin Zheng Published: 2026-08-25 Categories: cs.CV, cs.CL, cs.GR arXiv: https://arxiv.org/abs/2608.24334v2 Discrete motion representations have substantially advanced autoregressive text-to-motion generation. However, most motion tokenizers are optimized for reconstruction and do not explicitly allocate capacity according to semantic role. Action-level meaning and fine-grained kinematic detail must therefore be encoded through the same reconstruction-driven hierarchy. We introduce SeMoCo, a semantic-first motion codec, together with a dual-axis motion generator for language-conditioned motion generation. Each motion token contains one semantic token and a residual sequence of kinematic tokens. The generator models semantic progression across time and autoregressively refines the residual entries. We also construct $Ω$-MotionVerse, a large-scale, multi-source human-motion dataset unified under the SOMA representation. Across the reported comparisons, SeMoCo achieves the best reconstruction accuracy among the compared codecs, while strong text-to-motion results demonstrate the effectiveness of its motion tokens for downstream generation. --- ### A Structural FHMM for Interpretable Disease Trajectories in T2DM Authors: Alessandro Mari, Ekaterina Krymova, Guillaume Obozinski, Maria Luisa Marques de Sa Faquetti, Adrian Martinez de la Torre, Andrea Burden Published: 2026-08-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.24328v1 In this work, we propose a structural variant of the Factorial Hidden Markov Model (FHMM) for the analysis of disease trajectories in patients with Type 2 diabetes mellitus (T2DM). The model represents a patient's latent health state as a combination of multiple independent, simultaneously evolving components, associated with comorbidities and lab results. This structured latent representation facilitates the identification of clinically meaningful patient states and clustering of common disease trajectories. We evaluate the proposed approach using The IQVIA Medical Research Data incorporating data from THIN, a Cegedim database of anonymized electronic health records (EHR), identifying patients with a first-ever prescription for a non-insulin antidiabetic drug (NIAD) between January 2006 and December 2019. The model identifies multiple clinically coherent latent components corresponding to known patterns of diabetes-related complications and reveals heterogeneous progression pathways, including distinct microvascular-dominant and multi-organ trajectories associated with elevated comorbidity burden and mortality. These results demonstrate that the proposed framework captures meaningful longitudinal structure in EHR data and provides interpretable insights into the evolution of T2DM and its comorbidities. --- ### Speech-to-SOAP: End-to-End Summarization of Medical Dialogues: KIT@BeTraC 2026 Authors: Enes Yavuz Ugan, Fabian Retkowski, Yuka Ko, Thai-Binh Nguyen, Maike Züfle, Jan Niehues, Alexander Waibel Published: 2026-08-25 Categories: cs.CL, eess.AS arXiv: https://arxiv.org/abs/2608.24327v2 With the advent of Large Language Models and its instruction following capabilities a promising application is the task of summarization. Within this domain of task the extractive sub-task of clinical protocolling has emerged as a topic of particular interest as it can significantly reduce the downtime and protocolling burden of health-care workers thus enabling them to focus on their core work helping humans. A further step towards automation is the direct generation of clinical notes from speech without intermediate transcripts, reducing processing time while preserving information such as coughing or other paralinguistic cues that may be lost in transcript-based systems. To this end, we present KIT's submission to this years BeTraC challenge in the lightweight track. Our main contribution is a scalable data augmentation pipeline that unifies heterogeneous medical dialogue datasets through synthetic speech generation and automatically generated SOAP supervision, enabling robust adaptation of a speech foundation model for end-to-end speech-to-SOAP generation. --- ### SonarLLM: A Native Sonar--Optical Multimodal Large Language Model for Underwater Perception Authors: Cong Su, longxuan ma, Ling Dong, Guofeng Tang, Weijie Yin, Haohui Chen, Zhengtao Yu Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.24325v1 Reliable underwater perception requires complementary sensing under variable visibility. Optical cameras capture appearance and semantics but degrade rapidly with turbidity, whereas imaging sonar preserves geometry while exhibiting distinct range-azimuth structure and acoustic artifacts. Existing MLLMs, built primarily on optical encoders, are therefore ill-suited to model sonar or adaptively exploit sonar-optical complementarity. We propose SonarLLM, a sonar-optical MLLM that treats sonar as a native perceptual modality. It combines a sonar-specific encoder, modality-specific physics-aware feature enhancement, and reliability-aware hierarchical fusion to align acoustic structure with optical semantics and dynamically adjust their contributions as sensing quality changes. We also introduce SonarBench, a paired benchmark that spans four tasks: recognition, counting, visual question answering, and captioning; and, across the benchmark, three input settings: sonar-only, optical-only, and fusion. By fixing the scene and sonar observation while varying optical degradation, SonarBench enables controlled measurement of cross-modal complementarity. SonarLLM achieves 72.0% macro accuracy across sonar-only recognition, counting, and VQA, outperforming the strongest baseline by 34.4 percentage points, and 68.7% under fusion, exceeding the best baseline by 25.1 points. For recognition and counting, the fusion-over-optical gain grows from 6.0 to 36.0 points as turbidity increases, indicating the increasing complementary value of sonar under controlled optical degradation. Together, these results show that robust heterogeneous perception depends not only on adding sonar, but on representing and weighting it according to its sensing characteristics. --- ### Can a Dynamic Internal Field Govern a Transformer's Cognition? Certifiability, not Superiority, in Homeostatic Compute Control Authors: Francisco M. Arrabal-Campos, Ignacio Fernandez, Francisco G. Montoya, Alfredo Alcayde Published: 2026-08-25 Categories: cs.AI, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2608.24319v1 An intelligent system does not merely reason: it governs its own reasoning - how much to compute, when to stop, which module to activate. Can that role be played by a dynamic internal field - a low-dimensional homeostatic state with explicit physics and certified stability - that modulates cognition without performing it? Ours is a field on the module graph governed by a family of PDEs on the graph Laplacian, advancing with an adaptive-depth reasoner. We certify the stability of the integrator of the whole family - an integrator certificate, not a closed-loop one. New, and proved here: a discrete Schur-Cohn criterion for Verlet with velocity coupling, necessary and sufficient per latent root, with no commutation hypothesis. The answer is threefold: substance no, structure only in part, certifiability yes. The type of the field's physics is irrelevant for accuracy: wave, diffusion, gated mixtures and a 2D Navier-Stokes substrate tie. A twenty-seed preregistered deconfounding campaign bounds the structural claim: at equalized caps the second-order effect is strong in one family (+0.087 (+0.042, +0.132), t=4.0) but is not detected in the other (+0.014 (-0.013, +0.040), n.s.), so part of the original contrast was capacity, not order; and a matched-interface GRU is indistinguishable in the first and nominally exceeds the field in the second (-0.035 (-0.067, -0.002)). What distinguishes the field is not capability but that its one-step operator admits an exact runtime stability check - a difference of kind, not of existence: learned recurrences carry certificates too, sufficient and conservative ones. A kill-gate with a positive control finds no evidence for the field as evidence accumulator (Delta AUC +0.0007 (-0.0065, +0.0079) vs a 0.03 threshold). A dynamic internal field is a viable, certifiable compute governor, but not an enhancer of cognition: it modulates, it does not think. --- ### Benchmarking LLM Judges for Voice-Agent Evaluation: Reliability, Calibration, and Human Oversight Authors: Anupam Purwar, Shashank Singh, Kritika Srivastava Published: 2026-08-25 Categories: cs.AI, cs.ET arXiv: https://arxiv.org/abs/2608.24314v2 Evaluating conversational voice agents at scale re- quires reliable assessment methods that capture both observ- able interaction quality and the contextual judgment typically provided by human evaluators. We investigate LLM-as-a-Judge evaluation by comparing human judgments with GPT-4.1 and GPT-5 on telecom and retail voice-agent conversations, across conversational quality and safety dimensions. The same interac- tions are scored under three evaluation configurations, p0, p1, and p2, to test whether automated judgments are sensitive to the evaluation setup and whether observed patterns generalize across configurations and judge models. Beyond aggregate agreement, we examine metric-level correlations, evaluator consistency, and systematic human-LLM disagreement to identify which conver- sational attributes can be judged reliably by automation and which remain sensitive to interpretation and context. Effective voice-agent evaluation is also shaped by pipeline-level factors such as speech generation, streaming, and error propagation across ASR, reasoning, and tool-calling stages, motivating our focus on comparing how human and LLM judges score the same interactions end to end. Our results show that LLM- based evaluation can serve as an effective component of large- scale voice-agent assessment, but that its reliability is metric- and configuration-dependent rather than uniform. This pro- vides an empirical framework for identifying which metrics suit automated evaluation and supports hybrid pipelines in which LLM judges handle scalable assessment while human evaluators remain engaged for metrics that demand contextual interpretation and higher-confidence judgment. --- ### OPDSearch+: On-Policy Distillation with RL Refinement for Search-Augmented Reasoning Authors: Qinglin Ye, Zhiyuan Gu, Jingjie Xia, Yiheng Zhang, Kaiyan Zhao, Shunchao Zheng, Yuhang Mu, Wenchao Du, Yiming Wang Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.24310v1 Search-augmented reasoning remains difficult for small language models. On-policy distillation (OPD) from trained teachers offers a promising direction, but suffers from two issues: (1) high-quality multi-turn search trajectories depend on dynamic retriever responses, making SFT data prohibitively expensive to collect at scale; (2) task-specifically trained teachers incur substantial training cost, while directly applying OPD with an off-the-shelf teacher without task-specific fine-tuning constrains the student to the teacher's performance ceiling and suffers from severe training instability. We propose OPDSearch+, the first distillation paradigm that requires no teacher fine-tuning for search-augmented reasoning. We investigate the role of a frozen off-the-shelf instruct model as the teacher in on-policy distillation, and reveal a key insight: the teacher reshapes the student's policy distribution so that subsequent RL converges to a superior solution that RL alone cannot reach. In stage one, the student interacts with a live search engine and is distilled via a per-position forward KL objective, transferring reasoning decomposition and evidence integration skills without any task-specific teacher training. In stage two, RL refines the distilled student from a richer behavioral foundation, achieving performance that RL alone cannot reach from scratch. Across seven QA benchmarks, OPDSearch+ with a 3B model consistently outperforms all prior 3B RL baselines, achieving gains of 13.1% on HotpotQA and 8.5% on 2WikiMultihopQA. --- ### Who is the Agent to Blame? Localizing Faithfulness and Citation Mistakes in Agentic Deep Research Authors: Eran Hirsch, David Wan, Han Wang, Elias Stengel-Eskin, Mohit Bansal, Ido Dagan Published: 2026-08-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.24306v1 Deep research (DR) systems produce long-form cited reports by orchestrating multiple agents that search and synthesize information from the web. Citations are the primary mechanism for evaluating the faithfulness of these reports, yet current DR systems exhibit poor citation recall. Moreover, improving citation recall is challenging because DR systems are complex multi-agent architectures where information passes through agents like a telephone game, and both content and citations can get corrupted along the way. We propose an evaluation method that pinpoints which agent introduced each error by locally testing agent invocations for faithfulness and verifiability relative to their own inputs. Furthermore, we propose a four-type taxonomy to categorize the discovered errors: hallucination, uncited input reliance, uncited output, or insufficient citations. Applying our method to three top-ranked open-source DR systems, we obtain actionable diagnostics. Almost every agent makes a lot of mistakes with the exception being those that summarize a single document. We find that the dominant error type varies systematically across agents, where the orchestrator mistakes are mostly citation-related. We find that 84.7% of final-report errors in AI-Q originate at the orchestrator, roughly 31% of them hallucinations and the rest citation mistakes. Guided by these insights, we demonstrate that two simple interventions raise citation recall by 5% without degrading output quality. --- ### SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infilling Authors: Shahed Masoudian, Markus Frohmann, Emmanouil Karystinaios, Navid Rekabsaz, Markus Schedl Published: 2026-08-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.24304v1 Recent controllable text generation (CTG) for sentiment control has largely focused on decoder-based large language models, making causal attention the dominant paradigm. While effective for fluent generation, these models still struggle to satisfy complex constraints and follow fine-grained sentiment signals specified by users. Existing sentiment-aware CTG methods typically simplify the problem by treating sentiment either as a coarse categorical label (e.g., positive or negative) or as a single fine-grained control signal applied to an entire document. Consequently, more challenging settings such as sentence-level sentiment control within long-form text remain underexplored. To address these limitations, we introduce SenseShift , an encoder-based framework for fine-grained sentence-level CTG. Unlike standard decoder architectures, SenseShift leverages bidirectional attention, quantized sentiment signals, and iterative mask infilling to generate local sentences conditioned on target sentiment intensity. Empirical evaluations on story and review generation demonstrate that SenseShift achieves stronger sentiment controllability while maintaining text quality and robustness to out-of-domain generation compared to larger decoder-based baselines. --- ### Causal Analysis for Time Series Foundation Models Authors: Mathis Jander, Wouter van Heeswijk, Martijn Mes Published: 2026-08-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.24303v1 Transitioning from bespoke time series models towards time series foundation models changes the relationship of model and application from one-to-one to one-to-many. This shift introduces concentration risk as many, potentially high-risk, forecasting applications are exposed to the same biases and failure modes of a single time series foundation model. At the same time, this centralization allows for economies of scale in model development and validation. In this study we investigate how biases and failure modes of time series foundation models can be identified before deployment. We propose a causal analysis framework to investigate the ability of a time series foundation model to preserve time series patterns. To achieve this, we intervene on parameterized synthetic time series generators and measure the corresponding change in model output under ceteris paribus conditions. We apply our causal analysis framework to Chronos-2 and TimesFM-2.5 and test them across six distinct time series patterns. We find safe configurations for trend and harmonic oscillation patterns. The results also indicate a bias in both models towards overestimating persistence, sudden failures for both models against the regime switch pattern and failure for TimesFM-2.5 against the energy-release pattern. Our review of the original works for both models indicates that the findings might be explained by the data used for pretraining. We conclude our study with suggestions for further model development, recommendations for application-specific model selection, and a discussion of limitations and further research directions. --- ### VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models Authors: Guoyang Xu, Hao Chen Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.24302v2 Long-video understanding depends not only on the capability of a vision-language model (VLM), but also on how its limited context is constructed from a much longer video. Existing systems typically introduce hand-designed sampling, retrieval, memory, or agentic control strategies, making the context-construction program itself difficult to study as an independent optimization target. We introduce VideoHarness-RSI, a controlled framework that recursively searches executable context constructors around a frozen VLM while keeping the answering model and interface fixed. We study this baseline under complementary weak- and strong-initialization regimes. From a weak uniform constructor, recursive search progressively discovers more structured context-construction programs; from a stronger AKS harness, the same process further advances an already competitive hand-crafted frontier. The resulting harness retains its advantage under a matched cumulative visual-token control and transfers directly to additional long-video benchmarks without further search. Together, these results establish executable context construction as a distinct optimization layer and provide an auditable baseline for studying harness discovery, transfer, and efficiency around frozen VLMs. --- ### Contrastive Branch Policy Optimization Authors: Ying Wang, Changlin Qiu, Bang Lin, Linbo Jin, Wen Jiang, Zhe Sun, Jingli Yang Published: 2026-08-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.24300v1 Reinforcement learning with verifiable rewards (RLVR) enables language models to learn multi-turn interaction with external tools, yet its sparse outcome rewards provide no signal for identifying which intermediate decisions are responsible for success. Branch sampling induces local comparisons among alternative continuations, but existing methods tend to conflate two distinct problems: allocating a fixed rollout budget and translating branch outcomes into token-level credit. We introduce Contrastive Branch Policy Optimization (CBPO), which disentangles these two problems and assigns a dedicated mechanism to each. Generation entropy screens candidate branch positions across the entire response, while path-level and node-level decay distribute a fixed budget across trajectories and positions to prevent exploration from collapsing onto a few paths or adjacent tokens. A parent trajectory together with the branches that share an identical token prefix forms an exact-prefix group, and the reward variation within this controlled group defines the Contrastive Branch Value (CBV), an outcome-based estimate of local decision sensitivity that rescales continuation advantages without altering their sign. When multiple nodes are selected along the same trajectory, CBPO partitions it into non-overlapping credit segments, thereby avoiding duplicated gradients on shared tokens. Requiring only outcome rewards and no process-level annotation, CBPO provides a practical solution for fine-grained credit assignment in tool-integrated agent training. Extensive experiments on ten benchmarks, including five for mathematical reasoning and five for knowledge-intensive search, show that CBPO consistently outperforms state-of-the-art policy-optimization and branch-based methods, attaining the highest macro-average accuracy in both domains and across two model scales. --- ### Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation Authors: Yeonkyeong Lee, Hyunsung Go, Jongmin Kim, Sewoong Lim, Donghoon Lee Published: 2026-08-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.24293v2 Latent diffusion models have emerged as a dominant framework for high-fidelity image and video synthesis, operating in compact latent spaces with variational autoencoders (VAEs) to enhance computational efficiency without compromising visual quality. However, conventional VAEs are suboptimal for video data as they employ fixed compression ratios that cannot adapt to the varying complexity of spatio-temporal content. We present KATok (Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation), a transformer-based VAE that incorporates an adaptive token selector which is jointly learned with latent tokens. By evaluating each token's content-richness as keep-or-drop probability, the token selector effectively discards uninformative tokens, naturally allowing data-dependent compression. Applying adaptive tokenization to diffusion models may cause spatial misalignment, as token dropping can disturb the original spatio-temporal structure. To alleviate this issue, we propose two position-prediction strategies: cascaded and joint generation, to ensure spatial consistency. We empirically show that our model achieves strong reconstruction and generation quality at a state-of-the-art compression ratio. Further analysis on video data reveals that this improvement is primarily achieved by reducing spatio-temporal redundancy and removing uninformative tokens, as supported by both quantitative and qualitative results. --- ### ReproAgent: Contract-Guided Paper-to-Code Reproduction Authors: Xue Hu, Zewei Pan, Zhongyuan Wang, Zhou Liu, Zeli Su, Wentao Zhang Published: 2026-08-25 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.24291v1 Paper-to-code reproduction asks scientific AI agents to turn research papers into executable repositories that preserve the paper's method, protocol and artifacts. This is difficult because the specification is split: explicit paper content such as algorithms, metrics and artifacts is often lost across long agent trajectories, while implicit details such as framework defaults and conventions inherited from related work are absent from the paper. We introduce ReproAgent, a four-stage Prepare--Plan--Generate--Repair pipeline built around a persistent implementation contract with two channels: an implementation-requirement channel that turns paper snippets into code obligations, and a reference-evidence channel that retrieves content and structure evidence from related repositories. Both are bound to work packages, projected into file-level contracts, and consumed across generation and repair. On PaperBench Code-Dev, ReproAgent reaches the highest mean score among same-backbone scaffolds under both Claude-Sonnet-4.5 and Gemini-3-Flash. End-to-end channel ablations and per-paper cases support the contribution of both channels. Code and experimental artifacts are publicly available. --- ### CARE: Camera-Residual Reserves for First Sightings in Adaptive LiDAR Sensing Authors: Jiachen Gong, Yun Li, Ehsan Javanmardi, Wencan Mao, Manabu Tsukada Published: 2026-08-25 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2608.24282v1 Adaptive LiDAR scanning concentrates a limited sensing budget on regions of interest predicted from past object tracks, lowering data volume in autonomous driving while maintaining detection accuracy. However, existing scanning policies face three challenges. First, history-driven approaches depend on past tracks, so unseen objects are detected late or missed. Second, random or uniform sampling outside the predicted regions has no awareness of where new objects appear. Third, camera-guided alternatives spend budget on all camera detections, resampling objects already covered, costing recall in crowded scenes and range when budgets are scarce. This paper introduces the CAmera-REsidual reserve (CARE), a training-free allocation rule that reserves part of a fixed ray budget for the directions of current camera detections that the track forecasts cannot explain; the rest follows the base history policy, and unused reserve returns to a random floor. The paper makes three contributions. First, a leakage-free ray-budget evaluation on nuScenes (150 scenes, 4,148 events) measuring the first-sighting loss of history-driven scanning, with a strict-causal variant using the preceding keyframe. Second, CARE raises first-sighting recall by 5.2, 5.2, and 4.3 points at 10%, 20%, and 35% budgets over the history policy, with paired intervals excluding zero; the camera cue drives this gain, and the first-sighting versus overall trade-off is a budget-dependent Pareto choice. Third, a safety-bounded forgetting module that releases budget from receding or static tracks beyond a speed-dependent guard distance; at tight budgets, forgetting without the guard significantly harms near-field recall, so the guard is what keeps it safe. The pipeline runs end to end on a real vehicle and, in closed-loop simulation, detects an occluded pedestrian earlier and brakes more reliably than history-driven scanning. --- ### Example-based Robust Abnormality Detection with Minimal Annotations using Exemplar Med-DETR Authors: Sheethal Bhat, Bogdan Georgescu, Awais Mansoor, Mathias Zinnen, Pranjal Sahu, Florin C. Ghesu, Sasa Grbic, Andreas Maier Published: 2026-08-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.24281v1 Reducing annotation requirements remains a key challenge in developing robust medical object detectors. To address this, Vision-Language (VL) object detection methods leverage grounding text information to enable powerful zero-shot and few-shot object detectors in the natural image domain (1, 2, 3, 4). However, transferring these methods to the medical domain is challenging due to the absence of comparable quality and quantity of the grounding data. Regardless, significant contextual and non-imaging information exists in medical images that remains underutilized. Few-shot learning (FSL) techniques partially address this limitation but struggle to general ize to unseen medical findings and require extensive retraining when new findings are introduced (5, 6). To overcome these challenges, we extend our prior EM-DETR framework (7) and introduce a scalable FS detection approach designed for efficient abnormality detection in Chest X-Ray (CXR) images under minimal supervision. The proposed architecture incorporates exemplar-based feature generation and domain-aware contrastive optimization, enabling effective adaptation to novel disease findings without exhaustive retraining. Our method achieves near state-of-the-art (SOTA) detection performance using less than 10% of the annotated data, demonstrating its potential for practical, annotation-efficient clinical deployment across both proprietary and public CXR datasets. --- ### RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards Authors: Houcheng Jiang, Boxuan Zhang, Qiyong Zhong, Junfeng Fang, Xiang Wang, Xiangnan He Published: 2026-08-25 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.24275v2 Safeguarding language model agents requires assessing complete execution trajectories under context-dependent safety policies. Existing policy-aware safeguards mainly rely on prompting or supervised fine-tuning, limiting their ability to adapt to unseen trajectories and changing policy contexts. We propose RePolicy, an agent safeguard that learns safety-policy invocation through reinforcement learning. Given an agent trajectory and a dynamic policy library, RePolicy invokes the applicable policy and uses its content to produce a policy-grounded rationale and safety judgment. We construct PolicyTraj-20K to support supervised initialization, followed by GRPO with verifiable rewards and policy-context perturbation. Experiments across six agent safety benchmarks show that RePolicy achieves strong overall safety-detection performance and robust policy invocation under varying policy contexts. --- ### Eating for a Sustainable Planet: Personalized Sustainable Diet Recommendation via Constraint-Aware Decision-Making Modeling Authors: Ying Jin, Weiqing Min, Mingyu Huang, Shuqiang Jiang Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.24274v1 A sustainable diet represents a multi-dimensional synergy among four essential pillars: nutrition adequacy, economic affordability, cultural acceptability, and environmental respect. Despite the prevalence of population-level sustainability modeling, practical implementation relies on effective individual-level adoption. This transition is often hindered by inter-individual heterogeneity, posing a formidable challenge in aligning sustainable diet requirements with individual preferences. To address this issue, we propose a personalized sustainable diet recommendation model based on a constraint-aware decision-making mechanism, where sustainability is incorporated through learnable constraints rather than modeled as user preferences. To systematically evaluate the proposed approach, we construct a sustainable diet dataset named SusDiet with about 150k recipes, characterized by broad coverage of sustainability indicators. Experimental results on this dataset show that our method promotes more sustainable choices without compromising individual preference. This work establishes a framework for aligning individual dietary choices with planetary health, offering quantitative evidence to guide future sustainable diet interventions and policy-making for sustainable development. --- ### Matched Excess-Outranker Regularization for Candidate-Set Interference in Continual Knowledge Graph Embedding Authors: Hao Ren, Junbin Gao, Jiaojiao Jiang Published: 2026-08-25 Categories: cs.AI, cs.DB, cs.IR arXiv: https://arxiv.org/abs/2608.24273v2 Continual knowledge graph embedding updates entity and relation representations as a graph grows. Existing methods primarily address catastrophic forgetting, but entity admission also changes the candidate universe of every compatible query. A historical answer can therefore lose rank even when its score and its ordering among old entities are preserved. We formalize this effect as candidate-set interference and introduce Matched Excess-Outranker Regularization (MEOR), a host-level objective that compares smooth answer-relative newcomer pressure with score-blind, structurally matched old references. Its one-sided penalty acts only when newcomer competition exceeds the matched reference, preserving the host learner's signal for legitimate new entities. Across eight paired runs on ENTITY-ComplEx, MEOR improves historical current-universe mean reciprocal rank (MRR) by 0.0057 over replay and reduces candidate-set interference by 0.0055, with one-sided 95% lower bounds of 0.0052 and 0.0051, respectively. It satisfies the preservation criteria for old-universe ranking and newcomer acquisition and improves historical current-universe MRR over persistent calibration, matched maximum regularizer (MMR), and unmatched old regularizer (UOR). Direct ablations support each component of its reference construction and aggregation. Adding MEOR also improves historical ranking in all ten reported FBInc-S and FBInc-L host and backbone settings, with every paired 95% confidence interval excluding zero. These results establish candidate admission as a distinct source of continual rank loss and show that it can be controlled without replacing the underlying embedding architecture or continual learner. --- ### ROBE: Reversed-Order-Biased-Experts for Extracting Extreme Long-tail Events from Historical Texts Authors: Stella Verkijk, Piek Vossen Published: 2026-08-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.24268v2 This paper proposes methods to extract over 50 types of events from a Dutch historical corpus spanning the 17th and 18th centuries. The methods we propose aim to tackle a very challenging scenario in Machine Learning: extracting the long-tail of the long-tail. Historic data from before the 19th century is in itself a niche domain not covered in the pre-training of Large Language Models, and we aim to extract events only scarcely annotated in the training data available for this domain. We propose creating expert classifiers for subgroups of the events present in the training data. We make these groupings based on similar frequency in the training data or on semantic relatedness. Experts trained on underrepresented events are assigned higher priority when predicting to avoid being dominated by frequency biases. We refer to this new way of combining classifiers, specifically tailored to protect the long-tail, as ROBE: Reversed-Order-Biased-Experts. We also propose a controlled method to create domain-specific synthetic data.\ Our two implementations of ROBE outperform a simple fine-tuned encoder model with a .16 increase in precision and a .05 increase in recall respectively. The best model achieves a .11 increase in f1 for a group of long-tail classes in our niche data set. --- ### Real-World Knowledge-Guided Change Data Synthesis for Remote Sensing Authors: Yaoyi Qi, Xingxing Weng, Chao Pang, Yongkang Cui, Xiangyu Hao, Xiaokang Zhang, Guibo Zhu, Gui-Song Xia Published: 2026-08-25 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.24263v1 Change data synthesis provides a cost-effective solution for expanding training data and improving the performance of change detection models. However, existing synthesis methods typically rely on handcrafted rules to simulate changes, where limited coverage of class transitions restricts the diversity of synthesized data, while predefined transition designs limit their flexibility in accommodating varied change types. In this work, we introduce KnowChange, a knowledge-guided change data synthesis framework that leverages pretrained vision-language models as knowledge sources to reason about plausible change locations and class transitions from pre-change scenes and desired change types. By integrating knowledge-guided change simulation with generalizable synthesis models, KnowChange enables flexible synthesis of diverse change types within a unified framework. Extensive experiments demonstrate that KnowChange-generated data consistently outperforms existing synthetic datasets in both synthetic-to-real transfer and synthetic data augmentation, despite being generated at a compact scale. Further analyses show that the knowledge-guided change simulation can be seamlessly integrated into existing synthesis pipelines and enhance the downstream utility of synthesized data. --- ### Beyond Accuracy: A Dual-Judge Evaluation Protocol for Vision-Language Models in Legally Grounded Tasks Authors: Su Myat Noe, Ha Thanh Nguyen, May Myo Zin, Ken Satoh Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.24258v1 AI systems are increasingly evaluated for legally accountable settings, where correct outputs must also be justifiable against an applicable legal standard. Existing legal-AI benchmarks and LLM-as-judge protocols provide important infrastructure for measuring task performance and open-ended response quality. We contribute one additional evaluation signal: a dual-judge protocol that pairs a standard 0-10 quality judge with a strict binary semantic-equivalence judge against a human-curated reference. We study a controlled, visually grounded regulatory task - UK traffic-sign interpretation, whose meaning is a codified question with a known reference for every input - and measure not merely whether the two judges disagree (by construction they must) but how much and where. On 4,680 evaluations under seven visibility levels and two occlusion modes, the two judges are moderately associated (point-biserial r = 0.644), while revealing an asymmetric Type II pattern affecting 8.0% of all evaluations. Its distribution is instructive: the marginal rate peaks at high visibility (14.2% at v = 0.8) simply because high-scoring answers are common there, but conditioned on the answer already scoring above 7, the rate is highest under heavy occlusion (54-63% at v <= 0.3), so a high quality score is least trustworthy when the input is most degraded. We are explicit that the signal is a property of this judge and reference: a 49-row human check shows the 0-10 judge aligns closely with everyday-reader judgement (Pearson r = 0.81; r = 0.80 with the LLM accuracy sub-score), while the equivalence judge is fairly but one-directionally stricter. The protocol adds one LLM call per evaluation and surfaces a signal single-judge protocols do not report. We release the prompt template, occluded variants, and full evaluation results. --- ### SA-Bench: Evaluating Semantic Alignment in LLM-Based Paper Reproduction Authors: Xue Hu, Zewei Pan, Zeli Su, Zhou Liu, Wentao Zhang Published: 2026-08-25 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.24252v1 LLM agents can generate paper reproduction code, yet often produce scientifically unfaithful implementations. We define this failure mode as semantic drift, where generated code silently diverges from the paper's specifications. We introduce SemanticAlign-Bench(SA-Bench), a diagnostic benchmark covering 30 papers from ICLR, ICML and NeurIPS 2025. For each paper, we decompose its specifications into atomic and verifiable implementation claims, which we call Semantic Alignment Units (SAUs) and evaluate repositories along four diagnostic dimensions spanning numerical, methodological, protocol and ordering drift. In total, we construct 1,491 SAUs across five ML domains and evaluate 12 generator configurations (4 models $\times$ 3 scaffolds). Even the strongest configuration (Claude+PaperCoder) achieves a mean SAU score of only 0.301 out of 1.0, with an overall mean of 0.221 across 360 evaluations. A failure taxonomy reveals that agents attempt most requirements but implement them incorrectly, with implementation mismatch and stubs accounting for the majority of zero-scored claims. Our analysis further indicates that scaffolds optimized for executability provide limited leverage for scientific reproduction; narrowing the gap requires scaffolds that prioritize semantic specification verification. The benchmark, annotations and evaluation pipeline are publicly available. --- ### Validation of HRV Studio: A Transparent and Quality-Control-Aware Platform for Heart Rate Variability Analysis Authors: Cyrus Mexon Evrard Djindot, Faliang Liu, Sylvain Laborde, Yinjia Zhang, Jessie Chen, Ming Li, Congrong Wang, Weixiong Rao, Qinpei Zhao Published: 2026-08-25 Categories: physics.med-ph, cs.LG, cs.SE, q-bio.QM arXiv: https://arxiv.org/abs/2608.24241v1 Reproducibility of heart rate variability (HRV) analysis is limited by differences in preprocessing and computational conventions across software platforms. We developed HRV Studio, an open-source PyQt6-based desktop application integrating transparent HRV analysis with automated quality-control (QC) diagnostics. Validation included large-scale agreement with NeuroKit2, targeted Kubios benchmarking, spectral-method comparison, synthetic perturbation testing, recording-duration sensitivity analysis, and arrhythmia-focused QC stress testing. HRV Studio showed near-identical agreement for the widely used time-domain indices RMSSD and SDNN under matched conditions. In the primary five-minute NeuroKit2 comparison, frequency-domain median relative errors were 1.35% for LF, 0.18% for HF, and 1.41% for LF/HF, while VLF remained more convention-sensitive (37.79%). Nonlinear Poincaré indices also demonstrated high consistency. Sequence-harmonized Kubios benchmarking confirmed near-identical agreement for time-domain and nonlinear indices and strong agreement for most frequency-domain measures. Extended ten-minute analyses reproduced the same overall pattern with lower disagreement for some convention-sensitive spectral outputs. Synthetic and arrhythmia stress tests maintained 100% numerical stability while consistently triggering QC warnings. Overall, HRV Studio provides a transparent and reproducible platform for HRV research, with strong cross-platform consistency when NN sequences, preprocessing, and analytical conventions are harmonized. Stress-test results indicate computational robustness rather than clinical validation. --- ### STRIVE: Multi-Agent Structured Temporal Reasoning with Integrated Verification for Longitudinal Radiology Report Generation Authors: Junyeong Maeng, Eunsong Kang, Heung-Il Suk Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.24237v1 Longitudinal radiology report generation (LRRG) requires identifying both current findings and their changes relative to a prior study. Existing methods jointly model diagnosis, attribute estimation, temporal comparison, and language generation within implicit representations, which can cause task interference, obscure the evidence underlying each decision, and limit error traceability. They also model progression states as independent labels, ignoring their ordered structure and thus treating missed changes and direction reversals equally. We present STRIVE, Multi-Agent Structured Temporal Reasoning with Integrated Verification for LRRG, which decomposes clinical reasoning into specialized Diagnosis, Attribute, and Temporal Change Agents that produce explicit intermediate evidence. In particular, the Temporal Change Agent is further post-trained using Progression-Aware GRPO, a verifiable, shaped reward that assigns partial credit to direction-preserving errors while scoring direction reversals lowest. STRIVE performs verification at two stages: a deterministic Consistency Gate reconciles the agent outputs before report generation, and a Validation Agent checks whether the generated report is supported by the aggregated clinical evidence. On Longitudinal-MIMIC, STRIVE attains the best clinical efficacy among recent methods and more than doubles Longitudinal Change Concordance (LCC), a measure of temporal agreement with the reference report, over the strongest baseline. --- ### TRACE: An Evidence-Grounded Benchmark for Safety Evaluation of Large Reasoning Models Authors: Zhenyu Wu, Siyuan Chen, Changchun Yang, Jiaqi Dong, Min Zhou, Ali Almadan, Talal Hammad, Faisal Wahbo, Aminullah Tora, Mona Alshahrani, Xin Gao Published: 2026-08-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.24232v1 Large Reasoning Models (LRMs) generate intermediate reasoning traces that may contain unsafe content, even when their final responses appear safe. Guardrail models are designed to detect and block unsafe content, yet existing benchmarks for unsafe content detection focus primarily on prompts and final responses, leaving reasoning traces largely unexamined. Moreover, these benchmarks typically provide only binary safety labels, without evidence annotations that justify the judgments. To address these limitations, we introduce TRACE, an evidence-grounded safety evaluation benchmark that covers the entire LRM inference pipeline: prompts, reasoning traces, and final responses. TRACE includes prompts in two languages spanning nine risk categories and ten attack strategies. For each prompt, four LRMs generate reasoning traces and final responses, and we annotate the safety of each component and extract supporting evidence from the corresponding source text. Evaluating 18 guardrail models on TRACE reveals that safety judgment for reasoning traces is substantially more challenging than for prompts or final responses, and that current models struggle to accurately extract supporting evidence. These findings highlight the need for guardrail models that can reliably detect and precisely localize unsafe content across the LRM inference pipeline. ---