# Research Papers — 2026-08 · bundle page 31 of 240 > Full-text markdown of papers #1501–1550 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/31 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/30.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/32.md) ### PEEL: Physics-Enabled Evidential Learning for Identifiable Uncertainty in CT Imaging Authors: Ge Wang Published: 2026-08-27 Categories: cs.AI, physics.med-ph arXiv: https://arxiv.org/abs/2609.29599v1 Normal-inverse-gamma (NIG) regression is not uniquely identifiable from its marginal Student-t likelihood: the likelihood determines three combinations of four NIG parameters and is constant along a one-dimensional fiber. We identify that fiber using independent physical measurement. As an initial embodiment, a reconstruction network receives one noisy filtered-backprojection (FBP) image and is first trained only by Student-t negative log-likelihood to estimate the three identifiable coordinates (gamma, alpha, c). The network is then frozen; repeated physical-noise realizations propagated through its reconstruction output form a Monte Carlo (MC) teacher label for output-domain aleatoric variance. An aleatoric head attached to frozen features learns this label, after which (beta, nu) are recovered algebraically. On 30 held-out simulated objects at five photon levels, one-image predictions achieved pooled Spearman correlations of 0.832-0.951 against independent 400-repeat references, median within-image correlations were 0.834-0.947, and 98.81-99.55% of evaluated pixels satisfied the algebraic admissibility condition. The method needs no KL term, reference prior, evidence regularizer, or cross-loss weight. --- ### A Computational Framework for Modelling Organisation-Level Semantic Identity from Longitudinal Textual Data Authors: Brinda Murali Krishna, Oktay Karakuş, Can Eyupoglu Published: 2026-08-27 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.29584v1 Organisations continuously generate large volumes of textual data that capture how they communicate, evolve and differentiate themselves over time. Although recent advances in natural language processing have substantially improved organisation-level text analytics, existing approaches primarily represent organisations as latent embeddings or predictive feature vectors for similarity estimation, classification or retrieval. Consequently, there is currently no general computational framework for modelling organisation-level semantic identity as an interpretable and evolving semantic construct derived from longitudinal textual evidence. This paper introduces a computational framework that integrates semantic representation learning, graph-based semantic modelling, organisation-level semantic fingerprints, temporal semantic evolution and evidence-driven validation within a unified analytical methodology. Organisations are characterised through complementary semantic dimensions describing diversity, concentration, connectivity, novelty and semantic community composition, which are analysed longitudinally to infer evidence-supported semantic identities. The framework is demonstrated using a longitudinal corpus of K-pop lyrics from artists affiliated with the four major South Korean entertainment companies. The empirical analyses reveal distinguishable multidimensional semantic identities, diverse temporal evolutionary trajectories and coherent integrated identity profiles. Comprehensive validation demonstrates that the inferred identities are statistically supported, robust under alternative analytical assumptions, reproducible and operationally informative. Beyond the case study, the proposed framework establishes organisation-level semantic identity and provides a transferable methodology for modelling organisational behaviour from longitudinal textual data. --- ### When Identical Rows Disagree: From Benchmark Identifiability to Replication-Robust Anomaly Detection Authors: Jie Deng Published: 2026-08-27 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.29580v1 A released table is often treated as an i.i.d. sample, although its repeated rows may encode business frequency, repeated entities, joins, resampling, or extraction errors. We show that this ambiguity creates a hidden measurement layer with three consequences: feature-identical rows impose an attained evaluation ceiling, row-weighted AUROC is sensitive to replication, and row-trained detectors learn a multiplicity-size-biased law. An exact-row audit of all 690 OddBench datasets finds train-test overlap in 355, feature-identical label conflict in 147, and a test anomaly identical to a training normal in 137. Switching from row to support weighting changes AUROC by at least 0.05 on 50-61 datasets across four classical detector geometries. We introduce SCOUT (Support-Count Orthogonalized Unsupervised Testing), a factorized anomaly detector that separates replication-invariant support evidence from exposure-aware count evidence. Factorwise split-conformal calibration yields marginal false-positive-rate control, while the support channel is exactly invariant to arbitrary positive row replication. On 686 OddBench datasets and five seeds, support-only SCOUT is non-inferior to row-wise Isolation Forest in raw AUROC and improves replication-invariant AUROC. External normal-support evaluations track nominal false-positive levels, and four backbones remain exactly unchanged under controlled replication. Semi-synthetic interventions show that conditional count modeling helps materially only under strong rate heterogeneity. These results specify when multiplicity should be treated as signal, nuisance, or uninterpretable without additional information. --- ### PartHackBench: Certified Equal-Progress Stress Tests for Partial-Credit Tool-Agent Evaluation Authors: Hongye Yang, Zhihao Xie, Shengjun Xiong Published: 2026-08-27 Categories: cs.AI, cs.CL, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2609.29578v1 Long-horizon tool agents often make useful progress without reaching terminal success, motivating partial-credit evaluation. Yet evaluators may reward milestones that were temporary, later reversed, or not attributable to the evaluated agent. Comparing an honest trajectory with a higher-scoring adversarial one is inconclusive if the latter made more genuine progress. We introduce PartHackBench, a controlled methodology that removes this confound. A private certifier admits a pair only when its trajectories match component-wise in both current-state predicate satisfaction and standardized agent attribution; score inflation, defined as f(A) - f(H), is measured only afterward. In 18 sealed held-out tasks in PB-CSTE, the frozen historical-target run produced matched adversaries for 15 tasks. Historical credit yielded mean inflation of .252, conditional attack success of 10/15, end-to-end yield of 10/18, and detected none of 14 strict rollbacks. Semantic LLM judges were more resistant but remained vulnerable, especially under evaluator-targeted attacks, while PB-CSTE current-state controls, defined as exact functions of the certified components, yielded zero inflation by construction. PartHackBench thus provides a certified control for testing whether evaluator credit changes while all benchmark-defined task-relevant progress remains fixed. --- ### The Recall Ceiling of LLM Recommendation Reranking Authors: Zhaohui Wang Published: 2026-08-27 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2609.27953v1 Some LLM-based recommendation rerankers are evaluated under an oracle protocol that guarantees the ground-truth item is present in the scored set, either by injecting it into the candidate list or by scoring it against sampled negatives. Across three primary Amazon datasets, we show that this protocol overestimates realistic NDCG@10 by 92--95%. The cause is a recall ceiling: realistic retrieval covers only 2--19% of relevant items at $K=100$ across eight datasets in three domains, imposing a deterministic upper bound on any closed-candidate reranker's top-$k$ NDCG. Under leave-one-out evaluation, $\mathbb{E}(\mathrm{NDCG}@k) \leq \mathrm{Recall}@|W_π|$, where $W_π$ is the reranker's candidate window. Under realistic retrieval, none of the tested optimisation strategies significantly improves over the collaborative-filtering baseline on our primary Amazon datasets. These strategies include prompt engineering, model scaling over a 168$\times$ parameter range, sequential models, supervised neural rerankers, LoRA fine-tuning, hybrid retrieval, score-aware prompting, and LLM+CF fusion. Text-aware retrieval increases recall on one dataset but does not improve end-to-end NDCG, while providing upstream CF scores mainly makes the LLM reproduce the CF order. We therefore propose the Recall-Aware Evaluation Protocol (RAEP): first classify the retrieval-recall regime, then evaluate reranking where the ceiling permits meaningful differentiation. In the low-recall regimes measured here, improving retrieval is more consequential than increasing reranker sophistication; this ordering need not hold in production systems with higher recall, richer features, or online feedback. --- ### BananaVLM: A Domain-Adapted Vision Language Model for Banana Crop Disease Diagnosis Authors: Sangam Kumar Jena, Pandarasamy Arjunan Published: 2026-08-27 Categories: q-bio.QM, cs.CV arXiv: https://arxiv.org/abs/2609.25040v1 Banana crop diseases threaten food security across the world, yet field diagnosis remains difficult because of limited expert access and visual similarity among disease classes. We present BananaVLM, a domain-adapted vision-language model for banana disease diagnosis built on LLaVA-v1.5-7B and fine-tuned with Low-Rank Adaptation (LoRA). To address the lack of multimodal agricultural instruction data, we introduce BananaInstruct, an automated pipeline that converts raw disease images into $\approx$80,000 question--answer pairs without manual annotation, using LLaVA-1.5-13B for symptom descriptions and Mistral-7B for agricultural Q&A generation and label grounding. Evaluated against 14 open-source and 5 closed-source VLMs on a nine-class benchmark, BananaVLM achieves 92.21% in-domain and 83.28% out-of-domain (OOD) classification accuracy, outperforming the best closed-source baseline, Gemini~2.5~Pro, by 49.8 and 63.3 percentage points, respectively. Binary healthy/diseased identification reaches 98.38% OOD accuracy with 1.00 recall. A controlled LoRA--DoRA comparison shows that DoRA performance degrades across epochs, while LoRA remains more effective for fine-grained classification. Qualitative evaluation using nine LLM judges yields G-Eval win rates of 0.81--0.96, while five domain experts prefer BananaVLM in 98.48% of 990 blind pairwise comparisons. These results show that lightweight domain adaptation with automated instruction tuning is an effective and scalable approach for specialized agricultural AI. Code, datasets, and model weights are available at https://github.com/samy101/banana-vlm --- ### CleanScore: Black-Box Benchmark Audits with Negative Controls and Sensitivity Bounds Authors: Jeffery Opoku, David Banahene Published: 2026-08-27 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2609.22183v1 Public benchmark scores may reflect skill, prior exposure to the questions, or both, and for most models the training data are unknown. We present CleanScore, a black-box audit using scored outputs only. Each benchmark question becomes a parent item with one public form and two independently written fresh forms preserving its numbers, facts and answer. The audit reports an interval for the public-form advantage rather than a verdict, and a private negative-control bank with an explicit transport radius separates exposure from ordinary form mismatch. A registered controlled-exposure experiment detects planted exposure and stays quiet under fresh-form exposure. A registered audit of five open models on 200 GSM8K and 200 ARC-Challenge items finds no exposure-consistent advantage, bounding surface-form inflation below five points. Registered positive controls then bound what such a null can mean. Leaking an item raises accuracy on paraphrases the model never saw almost as much as on the leaked wording, leaving 52% to 110% of the effect invisible to a paraphrase audit. On ARC a planted 49-point advantage shows an observable gap of -0.020, and about 20 points survive rewriting stem and options, across four training seeds. A surface-form null bounds far less than the phrase contamination audit implies. --- ### Gaussian Process Decorrelation for Spatiotemporal Deep Learning-Based Snow Water Equivalent Prediction Authors: Colin Fenster, Adrienne Marshall, Soutir Bandyopadhyay, Daniel McKenzie Published: 2026-08-27 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2609.22182v1 In the Western United States, snowmelt is essential to the agricultural industry in addition to being a key source of municipal drinking water. Consequently, accurate snowpack forecasting is critical for water policy and management. Automated Snow Telemetry (SNOTEL) stations provide accurate daily measurements of snow water equivalent (SWE) that exhibit strong correlations in space and in time. We tackle the problem of predicting future SWE values across the SNOTEL network. Specifically, we use a Gaussian Process-based linear transformation to remove spatial correlations before training a long short-term memory (LSTM) neural network on the decorrelated SWE data. This approach allows the LSTM to learn a clean temporal signal at each station. We show that this separation of spatial and temporal components yields better predictive success than multiple baseline models. Furthermore, we incorporate conformal prediction to quantify uncertainty in the resulting SWE forecasts, providing a distribution-free approach to illustrate a potential framework for establishing predictive intervals for spatiotemporal data. Together, accurate point forecasts and distribution-free uncertainty quantification provide a framework for SWE accumulation forecasting on subseasonal scales or projecting SWE with future data while motivating and supporting future work in predicting a large-scale, spatiotemporally complete SWE map. --- ### Interpretable Stress Detection from ECG Signals Using Motif-Based Anomaly Analysis Authors: Zhanna Balyan, Sachin Kumar Published: 2026-08-27 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2609.22179v1 Stress detection using physiological signals has gained significant attention due to its impact on both physical and mental health. While existing approaches based on machine learning and deep learning achieve strong predictive performance, they often rely on black-box models and fail to capture individual variability in physiological responses. In this work, we propose an interpretable and personalized framework for stress detection using electrocardiogram (ECG) signals based on motif discovery and Matrix Profile analysis. Instead of training a classifier, the method learns subject-specific baseline cardiac behavior by extracting recurring heartbeat patterns (motifs) from ECG signals. Stress is then detected as a deviation from these baseline patterns using a distance-based anomaly score. Experiments are conducted on the WESAD dataset using a carefully designed train-validation-test protocol to ensure reliable evaluation. The results show that the proposed approach can effectively detect stress for several subjects while providing clear interpretability through direct comparison of ECG patterns. However, the performance varies across individuals due to differences in physiological responses, with some subjects exhibiting minimal morphological changes under stress. Additional analysis incorporating heart rate variability (HRV) features reveals that while HRV can improve performance in certain cases, its contribution is not consistent across all subjects. These findings highlight the importance of personalization and interpretability in physiological stress detection and demonstrate that motif-based approaches provide a meaningful alternative to black-box models, while also revealing inherent limitations due to inter-subject variability. --- ### Beyond Task Completion: Training Capable and Safe Computer-Use Agents Authors: Zeyu Kang, Zhenyun Yin, Yang Zhang, Shan He, Shanzhe Lei, Yanjiu Zhong, Xinquan Chen, Xuhong Wang Published: 2026-08-27 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.22178v2 Computer-use agents (CUAs) have made rapid progress in completing complex tasks through graphical user interfaces, yet post-training centered on task success alone does not induce reliable safety behavior. A reliable CUA must condition its execution on risk: it should complete ordinary benign tasks, avoid environmental hazards and continue when a safe completion path remains, and refuse when the goal is harmful or no safe path exists. To learn this conditional policy, we develop Safety and Capability Optimization for Policy Execution (SCOPE), which jointly post-trains a CUA for task-execution capability and safety-aware decision making. To provide aligned training data for this joint objective, we further introduce SCOPE-Gen, an automated pipeline that synthesizes verifiable capability tasks and converts them into paired environment-risk variants while preserving their original goals. Using the resulting tasks, we construct SATraj-OS, a trajectory dataset comprising capability demonstrations, safe continuations, and explicit refusals. SCOPE first learns from all three trajectory types through supervised fine-tuning and then further improves task completion through online reinforcement learning. Starting from Qwen3.5-9B, SCOPE-RL achieves a 54.17% task success rate on OSWorld and a 64.30% attack-avoidance rate on OS-BLIND, yielding the best aggregate capability--safety score of 58.80% among the evaluated agents. Ablations reveal asymmetric but complementary roles for the two forms of safety supervision: refusal trajectories account for most of the attack-avoidance gain, whereas risk-handling trajectories preserve greater task utility at comparable attack-avoidance levels. --- ### OpenBlock: Constructive and Verified Content Generation for Adaptive Tile-Matching Games Authors: Jiang Jun Published: 2026-08-27 Categories: cs.LG, cs.GT arXiv: https://arxiv.org/abs/2609.22177v1 Tile-matching puzzle games serve hundreds of millions of players, yet the content-generation algorithms that decide which pieces to present at each turn remain proprietary, and no open platform exists for studying adaptive difficulty in this genre. We present an adaptive tile-matching platform whose central algorithmic contribution is a dual-track content-generation architecture: a deterministic rule-based generator that is always available, and an optional learned generator, both subject to a common verification gate that establishes, by exhaustive sequential-placement search, that every delivered piece set is fully placeable so the learned track can never degrade the constructive-feasibility guarantee of the rule track. A self-play reinforcement-learning placement agent, supervised by auxiliary tasks that expose per-shape placeability to shared representations, is used to diagnose the game's dominant failure mode: at high board fill, long-bar pieces lose the majority of their legal placements. Across 234,000+ self-play episodes the agent reaches a 35.6\% win rate (median score 4,200), and controlled simulation shows that at board fill rates of 70--75\%, 33--56\% of long-bar pieces have no legal placement, while spawn difficulty distributions are statistically indistinguishable between won and lost games---evidence that board-state degeneration, not content difficulty, drives late-game failure. Head-to-head ablations show that per-shape placeability supervision---not aggregate difficulty features---drives the representation gain, and a 14-day online gray rollout (48,000 players; sample-ratio verified, CUPED-adjusted) lifts day-1 retention by 1.8 percentage points and session duration by 7\% over the rule track alone, quantifying the neural track's asymmetric upside in live play. --- ### Contrastive World Models Authors: Bonnie Li Published: 2026-08-27 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2609.22175v1 World models trained via pixel reconstruction can struggle in visually complex environments, where irrelevant information dominates the objective and distract the model from information relevant to planning and control. We present Contrastive World Models, an approach for learning latent dynamics models without pixel reconstruction. Building on Dreamer, we replace observation reconstruction in the standard world model objective with a Deep InfoMax-like lower bound that maximizes the mutual information between state-action sequences and local patch features of future observations, encouraging state representations to retain information that is predictive of the future without requiring the model to reconstruct visually irrelevant details. We evaluate our approach in small-scale experiments across three settings of increasing visual complexity. Our method matches Dreamer and a momentum prediction baseline in the default setting, and substantially outperforms both once distractors or natural video backgrounds are introduced, while also training more efficiently by removing the pixel decoder entirely. Our approach is general and makes minimal assumptions beyond access to state-action sequences and future observations. These results suggest that contrastive, infomax-based objectives are a principled and promising direction for building world models that are robust to visual nuisance factors, a property particularly relevant for transferring model-based RL agents to the real world. --- ### SCoR: A Hierarchical Framework for Forecasting Relations Between Scientific Concepts Authors: Jingze Wang, Fred Sun, Shangqi Guo Published: 2026-08-27 Categories: cs.CL, cs.IR, cs.LG, cs.SI arXiv: https://arxiv.org/abs/2609.22174v1 Anticipating emerging research directions is a critical goal of AI-assisted science. Existing methods mainly predict which concepts will co-occur in future papers, but co-occurrence captures shared attention rather than the scientific meaning of a connection, such as whether one method uses, combines, replaces, or contradicts another. We formulate research-direction discovery as hierarchical scientific-relation forecasting over a shared candidate-pair space, comprising three temporally aligned tasks: first co-occurrence, first scientific-relation formation, and relation type at formation. We construct SCoR-Graph from 187,848 cs.CV papers published between 2017 and 2026, yielding 270,687 consolidated concepts, 7.45 million co-occurrence edges, and 615,036 typed, directed relation edges. From cutoff-specific graph snapshots, we derive SCoR-Bench, a leakage-audited benchmark for these three capabilities, with expert-verified gold labels for the entire relation-type test set. We further introduce HiSCoR, a task-adapted model family that models relation emergence as a temporally evolving, hierarchically constrained process by encoding pre-cutoff event histories and conditioning relation formation on future co-occurrence. On the held-out 2025-2026 window, HiSCoR achieves an AUROC of 0.9515, a 2.4% relative improvement over the strongest temporal-graph baseline, and improves population-AUPRC by 14.0%; its relation-type variant achieves a Macro-AUROC of 0.7795. Ablations show that semantic, co-occurrence, and typed-relation views provide complementary predictive evidence. SCoR advances research-direction forecasting from predicting which concepts will co-occur to anticipating whether and how evidence-backed scientific relations will emerge. --- ### Industrial Kinematic Trajectory Model (IKTM): Coordinate-Free Autoregressive Generator Authors: Max Amiri, David Eyers Published: 2026-08-27 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2609.22173v1 Mobility simulation supports logistics, safety, and communications planning in industrial environments such as ports, mines, and airports. Existing trajectory models, however, rely on absolute coordinates, road-network tokens, or semantic zones: representations that are site-specific and not well suited to unstructured industrial terrain. We introduce the Industrial Kinematic Trajectory Model (IKTM), a coordinate-free trajectory generator that represents industrial vehicle motion through kinematic sequences (speed and heading change) with no absolute spatial reference. IKTM uses an autoregressive causal transformer with probabilistic mixture heads and extends our prior coordinate-free Markovian model with deep sequence modelling and an explicit duration-conditioning signal. Trained on one site and evaluated zero-shot on three unseen sites, it matches the small-turn shape of the empirical turn-rate distributions of held-out telematics; across all four sites, the per-site mean Jensen-Shannon divergence over 100 sampling seeds spans approximately 0.035-0.050 bits under an oracle-length duration-target protocol and approximately 0.032-0.042 bits under a fully zero-shot prior-length protocol, with similar ranges whether out-of-distribution (OOD) duration targets are drawn from each held-out site's empirical length distribution or from the Site A prior. Both protocols stay above the metric's sampling-noise floor (<=0.0049 bits). Paired by site, the oracle-length values are 5.3-6.0x lower than those of a re-implementation of our prior Markovian model under the same 1 Hz protocol. Termination is duration-conditioned rather than spatial: rollouts stop on 100% of trials with a length-tracking error of +0.0 +/- 0.0 s against the sampled target (100 of 100 exactly on target; N=100, T=0.2, untouched in-distribution test split). --- ### Stagewise Anomaly Detection for E-Transaxle Quality Monitoring Using Wavelet and STFT Features Authors: Mohammad N. Bisheh, Rajesh Gupta, Qian Wang, Mohammad Babakmehr, Colin Brady, Parinaz Farajiparvar, Saurabh Singh, Kamran Payanabar Published: 2026-08-27 Categories: eess.SP, cs.LG, stat.OT arXiv: https://arxiv.org/abs/2609.22172v1 This paper presents two interpretable machine-learning frameworks for quality screening of e-transaxle assemblies in electric vehicles: a Stagewise Wavelet Isolation Forest (SWIF) framework and a short-time Fourier transform (STFT)-based diagnostic framework. High-dimensional vibration signals acquired from front and back accelerometers are analyzed across multiple operating stages to capture stage-dependent vibration behavior. In the SWIF framework, signals are decomposed using a five-level Daubechies-4 discrete wavelet transform, and blockwise mean-squared coefficients are extracted from the selected wavelet detail level to obtain compact multiscale features. In the STFT-based framework, dominant-frequency trends are extracted from time-frequency representations and summarized through regression coefficients with respect to instantaneous motor speed. Anomaly detection models are trained using accepted production units under the assumption that only a small fraction of accepted assemblies contain latent defects, and their performance is evaluated using road-tested units with validated quality outcomes. Experiments on production and road-tested e-transaxle units show that both approaches provide interpretable diagnostic information, while SWIF achieves the most favorable balance between defect detection and false-positive control. Compared with the STFT-based method and alternative anomaly detectors, SWIF combined with Isolation Forest yields lower anomaly rates within the Accept population while identifying high-risk units from the Reject population. The stagewise structure further localizes anomalous behavior to specific operating conditions, supporting root-cause analysis and targeted process improvement. --- ### Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery Authors: Fei Ding Published: 2026-08-27 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.19164v1 In verifier-style RLVR, group-relative optimization often treats advantage scale as an implementation detail. This paper separates two low-variance cases: sub-resolution jitter that should not become a preference signal, and credible but small cardinal gaps that should be learned without distorting KL calibration. We propose an advantage-scale three-way calibration interface: the same within-group scale denominator simultaneously determines the reward-branch strength, prompt-level batch weight, and the effective KL calibration induced when the reward branch is re-expressed on the original cardinal scale. This interface explains why RLOO / Dr.GRPO can let credible small gaps become KL dominated, whereas GRPO's standard-deviation denominator can amplify tiny gaps without bound. Based on this interface, we further introduce the Reward-Resolution Protocol and MaxNorm-AC, respectively filtering sub-resolution gaps and providing bounded cardinal recovery on credible nonzero gaps. Across dense / MoE architectures and math / code reasoning, MaxNorm-AC improves over the strongest robust-scale baseline while truncating the low-variance inverse-scale tail. --- ### LLM-Guided Reinforcement Learning for Adaptive NPC Behavior in Multi-Agent Combat Games Authors: Hrithika Deepu Nair, Kayvan Karim Published: 2026-08-27 Categories: cs.MA, cs.LG arXiv: https://arxiv.org/abs/2609.02931v1 Scripted and rule-based non-player characters (NPCs) in combat video games often exhibit predictable behaviors that experienced players can exploit, while reinforcement learning (RL) agents typically retain a fixed policy after training and cannot readily adapt their strategy to different opponents. We investigate a runtime strategy-selection framework in which a large language model (LLM) guides a trained RL policy without modifying its underlying behavior. To demonstrate this, we train five NPC agents with a shared PPO policy in Unity and compare a baseline configuration, in which the policy acts independently, with an LLM-augmented configuration in which a locally hosted Mistral 7B model, accessed through Ollama, reads the live game state every five seconds and assigns one of four tactical tags. We evaluate both configurations against three scripted opponent types across 600 episodes and analyze outcomes using the Mann-Whitney U test. Against a Balanced opponent that changes tactics during an episode, the LLM-augmented agents more than doubled their win rate from 11% to 24% and produced significantly longer episodes. Against an Evasive opponent, the augmented agents achieved a higher win rate and faster kills, although their shorter episode duration did not satisfy the strict hypothesis definition. Against an Aggressive opponent, the LLM's near-constant preference for encirclement was counterproductive. Analysis of 2,430 strategy selections showed that Surround was selected in 83.8% of cases regardless of opponent type, indicating limited zero-shot strategic differentiation at this model scale. These results demonstrate both the potential and limitations of LLM-guided runtime strategy selection for adaptive multi-agent game AI. --- ### Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts Authors: Saman Rahbar, Xiliang Zhu, Irvin Cardoza, David Rossouw Published: 2026-08-27 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.00330v1 In contact centers, real-time agent-assist tools determine, for each of many predefined topics, whether a live customer utterance is relevant and display a coaching card to the agent when it is. The input is noisy and challenging: ASR(Automatic Speech Recognition) transcripts of spontaneous phone conversations, which can be unclear, repetitive, and mostly lack punctuation. To systematically study this real-world task, we curate a human-annotated topic-utterance judgments dataset sourced from real call-center transcripts. We compare three types of matchers: a regex-based baseline, zero-shot sentence embedding encoders, and Gemini-based LLM matchers. In addition, two types of topic representations are studied in our benchmark:keyphrases and natural language description. Our empirical experiments highlight the superior performance of lightweight LLM matchers over embedding and regex models when equipped with natural language descriptions. --- ### The Curse of Multilinguality in Lexical Normalization Authors: Saman Rahbar Published: 2026-08-27 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.00329v1 Lexical normalization rewrites the noisy, non-standard words that fill user-generated text (tmrw, u, gr8) into their standard forms. Because labelled data is scarce for most languages, a popular shortcut is to train a single model on many languages at once. We ask a simple question: how many languages should such a model be trained on? Using one fixed-capacity character-level model and twelve languages from a standard benchmark, we vary the number of jointly trained languages from one to twelve and measure per-language accuracy. We find a clear curse of multilinguality: accuracy is highest when a language is trained with only a few others, often just one to four, and then falls steadily and substantially, dropping by about forty percent as the rest are piled on. A control that holds the total amount of training data constant makes the decline arrive sooner and fall further, which points to competition among the languages for one fixed-size model rather than to how much data is available. We also test whether a language's typological distance from the others predicts its ideal number of co-training languages, and find no dependable rule: any apparent relationship rests on a couple of languages and does not hold up. For compact normalization models, less can be more: a few languages beat pooling everything into a single model. --- ### UI-Venus-2 Technical Report Authors: Venus Team, Zhuohan Cai, Haoxing Chen, Jiaxuan Chen, Weizhi Chen, Changlong Gao, Zhangxuan Gu, Yuan Guo, Yusong Hu, Jianrong Jiang, Jianguo Li, Runze Li et al. Published: 2026-08-27 Categories: cs.AI, cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.00028v1 Multimodal GUI agents have emerged as a promising paradigm for digital task automation, yet transitioning from benchmark-oriented models to dependable real-world applications remains challenging due to limited environment coverage, brittle task construction, and unreliable reward verification. In this work, we present UI-Venus-2, a general-purpose foundation GUI agent designed to operate across mobile, web, and desktop environments through a unified closed-loop reasoning-action framework. To bridge the gap toward practical deployment, we jointly scale three critical dimensions: (1) Environments, expanding coverage to more than 170 multilingual mobile apps and native desktop operating systems; (2) Tasks, employing a deep-research pipeline for function-grounded instruction generation; and (3) Verification, adopting trace-level and sample-level evaluators with visual keypoints and multi-model voting to ensure reliable RL signals for training. Furthermore, we integrate safety-aware mechanisms to ensure controlled execution of consequential actions. By offering a capable, efficient, and open-source foundation, UI-Venus-2 advances the field toward more generalizable, verifiable, and self-reflective agents for real-world applications. --- ### Benchmarking spiking neural networks across sensing modalities on edge devices Authors: Xin Du, Di Yu, Changze Lv, Yuqi Zhang, Zhuo Chen, Wentao Tong, Helin Zheng, Weisong Zhang, Xiaofan Zhao, Linshan Jiang, Shijie Ji, Hui Fang et al. Published: 2026-08-27 Categories: cs.NE arXiv: https://arxiv.org/abs/2609.00026v1 Edge computing systems need to support diverse sensing workloads under tight energy and memory constraints, thereby motivating deployment-aware model selection. Spiking neural networks (SNNs) are a promising alternative to conventional artificial neural networks (ANNs), yet systematic evidence for when and why they provide practical advantages remains limited. Here, we present a benchmark of SNNs across five sensing modalities and multiple edge devices, systematically evaluating spike encoding, neuron models, and network topologies under consistent training and deployment protocols. We find that SNN advantages are strongly modality-dependent: while SNNs achieve performance broadly comparable to ANNs across most workloads, wireless sensing emerges as a particularly favorable domain. Frequency-domain and feature-space analyses further explain this result by showing that spiking dynamics naturally align with the spectral-temporal structure of wireless signals. Our deployment analysis further shows that SNN advantages are not one-dimensional, with energy gains often accompanied by modality-dependent system costs. Finally, we provide an open-source framework for reproducible benchmarking and deployment profiling, offering a practical foundation for algorithm-software-hardware co-design on emerging edge and neuromorphic computing platforms. --- ### Enhancing MRI Brain Tumor Edge Detection: A Hybrid Preprocessing Approach Utilizing CLAHE Authors: Shahid-E-Kaiser Md. Tashrif, Munshi Md Arafat Hussain, Sheikh Nahian, Sumaiya Islam Published: 2026-08-27 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.28709v1 Accurate boundary delineation of brain tumors in Magnetic Resonance Imaging (MRI) is a critical yet formidable challenge in neuro-oncology due to inherent scanner noise, complex anatomical structures, and uneven illumination. Traditional edge detection algorithms, while computationally lightweight and mathematically interpretable, frequently fail to capture the diffuse, localized boundaries of edema when relying solely on global preprocessing and manual parameter tuning. To overcome these limitations, we propose a hybrid automated edge detection pipeline. Our approach integrates an optimally configured Contrast-Limited Adaptive Histogram Equalization (CLAHE) layer into a comprehensive morphological preprocessing framework, followed by a deterministic sequential parameter sweep to fully automate threshold selection. The proposed hybrid model demonstrated enhancement in detecting critical anatomical structures in a publicly available benchmark database from Kaggle. By intelligently amplifying localized gradients without overwhelming the image with background noise, our method achieved higher Recall (Sensitivity). Consequently, the overall F1-Score elevated, and the Structural Similarity Index (SSIM) improved, all while maintaining a highly efficient execution. This establishes our optimized pipeline as a highly practical and near real-time operational model for clinical diagnostics, offering a compelling alternative to computationally heavy deep learning approaches. --- ### STEP: A Modular Silent Trial Engine for Operational Evaluation of Digital Pathology AI in Routine Workflow Authors: Gabriele Campanella, Matthew Croken, Olga Lukatskaya, Jane Houldsworth, Ricky Kwan, Peter Schüffler, Chad Vanderbilt Published: 2026-08-27 Categories: cs.SE, cs.CV arXiv: https://arxiv.org/abs/2608.28708v1 Prospective silent trials provide an important bridge between retrospective validation of artificial intelligence (AI) models and their use in clinical care by evaluating model performance and operational reliability on live clinical data without influencing patient management. In computational pathology, conducting silent trials requires integration across laboratory information systems, digital pathology infrastructure, computational resources, and model inference pipelines, and these workflows are often implemented using application-specific software. We developed the Silent Trial Engine for Pathology (STEP), a reusable software platform for orchestrating prospective silent trials of computational pathology AI models across heterogeneous clinical and computational environments. STEP separates common trial orchestration from institution-specific data access and compute infrastructure through modular adapter interfaces. The platform supports scheduled case discovery, per-slide inference submission, deterministic idempotency, failure recovery, result and ancillary-data ingestion, persistent trial and run state, and audit logging, with compute adapters supporting local execution and high-performance computing environments using LSF and Slurm. STEP was deployed at three institutions to support prospective silent evaluation of EAGLE, an AI model for predicting EGFR mutation status from hematoxylin and eosin-stained whole-slide images. By separating trial-level workflow logic from site-specific integrations, STEP enables a common execution framework to operate across heterogeneous pathology environments while maintaining durable and auditable trial state. This approach may reduce duplicated engineering effort and facilitate systematic real-world evaluation of computational pathology AI before interventional clinical deployment. --- ### ReVA: A Region-Aware Visual Assistant for Visually Grounded Question Answering Authors: Anoop Senthil Published: 2026-08-27 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2608.28707v1 Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Visual Question Answering (VQA), yet they continue to struggle with questions requiring precise spatial reasoning and fine-grained visual understanding. These limitations often manifest as object, attribute, and spatial hallucinations, where models generate confident but visually unsupported responses due to insufficient region-level and fine-grained visual grounding. To address this challenge, we propose ReVA, a region-aware VQA model that employs a frozen CLIP ViT-L/14 Vision Transformer (ViT) and a Qwen2.5-7B-Instruct large language model (LLM) connected through a dual bridge that aligns both whole-image and region-level representations with the LLM's embedding space. The image bridge maps final transformer block features into image tokens. The region bridge maps cropped features from enriched intermediate features across ViT blocks so early texture and later object cues are more evident, into K region tokens for every bounding box. ReVA uses a detector stack that supplies automatic zero-shot bounding boxes that are both question-agnostic and question-dependent, using RAM++ (Recognize Anything Model), spaCy, and Grounding DINO. The image tokens and region tokens are concatenated as an LLM prompt prefix to jointly encode scene-level context and fine-grained regional evidence when answering questions. Evaluated on VQAv2, MMBench, POPE, and SEED-Bench, ReVA achieves 82.85% mean F1 on POPE, compared with 81.14% for an image-token baseline without region tokens. These results demonstrate that explicit region-aware visual representations reduce object hallucination and improve the factual grounding of MLLMs. --- ### Variable-Granularity Tokenization for High-Resolution Object Detection Authors: Khayrul Islam Published: 2026-08-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28706v1 ViT detectors fix a uniform token grid before any learned stage. A native-resolution aerial detector must then choose between resolving few-pixel objects and staying inside compute and memory limits. We introduce VGTok, a training-free tokenizer that sets patch granularity per region from pixels, ahead of the encoder. VGTok scores each region by multi-scale morphological top-hat separability from its surround, then thresholds those scores at a per-image percentile, which fixes the token budget. A structure-tensor gate ($λ_{\min}$) refines only where two-dimensional object structure supports it, leaving one-dimensional clutter coarse. The resulting token set is a strict partition of the image. In a Co-DETR detector with an EVA-02 ViT-L encoder, VGTok clears every published VisDrone-val AP and AP$_S$ at every budget from 40\% to 100\% of tokens. At 40\% it records 44.22 AP with three fifths of the sequence discarded before the first transformer block; dense, it reaches 48.38 AP, $6.08$ above the strongest published entry. VGTok transfers to AI-TOD-v2 untouched, same scorer and same rank, and sets a new state of the art at 37.27 AP and 19.51 AP$_{vt}$. As a pure drop-in into a frozen checkpoint it reaches 36.29 AP at 78.5\% of tokens, above every published entry, where our 376.3M-parameter detector clears a 3.0B multi-expert model. We show that a token budget fixed before the backbone, from local separability and structure geometry alone, holds accuracy on the tiny-object regimes that dominate aerial detection, at $3.1\times$ less encoder compute and $1.9\times$ less encoder memory. Code and models are available at \href{https://github.com/khayrulbuet13/vgtok}{\texttt{github.com/khayrulbuet13/vgtok}} and \href{https://huggingface.co/khayrulbuet13/vgtok}{\texttt{huggingface.co/khayrulbuet13/vgtok}}. --- ### Is Deformable Image Registration Ready for Brain Metastasis Reirradiation Dose Accumulation? A Longitudinal MRI Benchmark of Registration Accuracy Authors: Hengjie Liu, Manju Sharma, Xinyi Fu, Di Xu, Ke Sheng Published: 2026-08-27 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.28705v1 Dose accumulation is increasingly important in adaptive radiation therapy and reirradiation, but its clinical validity depends on the performance of deformable image registration (DIR). Reirradiation of brain metastases (BMs) with stereotactic radiosurgery (SRS) provides a controlled but clinically meaningful DIR test case: intra-subject brain deformation is usually limited after rigid alignment, yet recurrent lesions can undergo substantial local shape and volume changes that rigid registration cannot capture and can affect dose accumulation. We benchmarked a wide range of learning-based and optimization-based DIR methods on 87 manually screened longitudinal contrast-enhanced T1-weighted MRI lesion pairs from an institutional BM SRS retreatment cohort. Learning-based methods pretrained on healthy-brain MRI were evaluated zero-shot and after instance-specific optimization (ISO) or tumor-proximity target-specific optimization (TSO). Registration was assessed using lesion overlap (Dice), surface distance metrics (HD95 and sASD), target-volume recovery, and runtime and memory. Pretrained learning-based methods showed variable zero-shot performance, while ISO/TSO improved all tested learning-based families. However, optimization-based methods remained the best-performing approach while maintaining reasonable runtime. These findings suggest that even state-of-the-art DIR methods do not yet provide sufficiently accurate and consistent registration for unmonitored use in brain metastasis reirradiation dose accumulation. Because accurate registration is a prerequisite for deformable dose accumulation, clinical application will require case-level quality control and direct assessment of how registration uncertainty affects downstream dose metrics. --- ### ORDDAR: Observation-Driven Reasoning for Distortion-Resilient Decision, Action, and Cognitive Recovery Authors: Deblina Kar, Anant Nawalgaria, Shyamal Kumar Das Mandal Published: 2026-08-27 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.28704v1 AI agents increasingly perform long-term reasoning, planning, tool use, memory integration, and autonomous decision making, yet erroneous intermediate states can propagate and cause inconsistent decisions and unreliable outputs. Existing reasoning approaches mainly rely on iterative planning, self-reflection, augmented memory, or verification, but rarely localize and selectively repair faulty reasoning. We present ORDDAR (Observation-Driven Reasoning for Distortion-Resilient Decision, Action, and Cognitive Recovery), a reasoning framework that models reasoning as cognitive state transitions, detects localized distortions, retrieves related reasoning from prior experiences, and repairs only the affected states. ORDDAR therefore performs recovery at the local reasoning-transition level rather than regenerating the complete trajectory. Experiments across mathematical, commonsense, multi-hop, and clinical reasoning benchmarks demonstrate improved reasoning quality, recovery ability, and interpretability over multiple evaluated reasoning baselines. --- ### Stochastic Liquid Deformation Fields: An SDE Generalisation of Closed-Form Continuous-Time Cells for Dynamic 3D Gaussian Splatting Authors: Mingzhao Li, Arghya Pal Published: 2026-08-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28702v1 Deformable 3D Gaussian Splatting (D-3DGS) reconstructs dynamic scenes by deforming a canonical set of 3D Gaussians through a deformation field of frame time. Replacing its MLP with a stack of Closed-form Continuous-time (CfC) cells-a Liquid Neural Network that solves the Liquid Timeconstant ODE in closed form-gives the field continuous-time behaviour at feed-forward cost. That closed form, however, is only the deterministic limit of a noise-driven system, and drops the stochastic term usually credited for the robustness of liquid networks. We put it back: a small Gaussian perturbation is added to the time gate of every CfC cell, turning the deterministic field into a simple stochastic (SDE) one. The noise is used only during training, needs no solver, and reduces exactly to the CfC when switched off. On the synthetic D-NeRF scenes the stochastic field is on par with the deterministic CfC and beats the MLP baseline on most scenes; on the real-world NeRF-DS scenes the deterministic limit is already best and adding noise does not help. The study thus gives both a clean way to read the CfC field as an SDE and an honest account of when a plain noise term helps and when it does not. --- ### TopoAgent: A Structure-Aware Perception-to-Reasoning Framework for Diagram-to-Graph Topology Extraction with Large Vision-Language Models Authors: Bangwei Guo, Xujiang Zhao, Yanchi Liu, Wei Cheng, Shengyu Chen, Dongyue Li, Masaharu Morimoto, Takayuki Kuroda, Dimitris Metaxas, Haifeng Chen Published: 2026-08-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28701v1 Diagram-to-graph topology extraction aims to extract a graph of entities and their connections from a structural diagram. This task remains challenging for current vision-language models because it requires both fine-grained perceptual grounding and topology-aware reasoning with global consistency. We present TopoBench-180, a human-verified benchmark for diagram-to-graph topology extraction, and TopoAgent, a structure-aware perception-to-reasoning framework for reliable topology extraction using large vision-language models. TopoBench-180 contains 180 structural diagrams spanning Web-style and Network-style categories, paired with canonical graph annotations. TopoAgent progressively extracts the target graph by combining grounded perception, global structural priors, canonical node inventory construction, node-centric local-to-global relation reasoning, and topological consistency enforcement. Experiments on TopoBench-180 show that TopoAgent outperforms strong vision-language model baselines and recent visual reasoning frameworks, especially on edge extraction. More broadly, this work fills an important gap in multimodal structured understanding by establishing a benchmark and framework for diagram-to-graph topology extraction. The benchmark and associated resources will be publicly released at https://huggingface.co/datasets/WayneGuo0011/TopoBench-180. --- ### Beyond Visual Boundaries: Rethinking Scene Segmentation for Movie RAG Authors: Dong-Hee Kim, Seonwoo Choi, Changbeen Kim, Jungmyung Wi, Juyeon Ko, Youngju Choi, Il Hyeon Mun, Hyunwoo J. Kim, Donghyun Kim Published: 2026-08-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28699v1 Understanding long-form video remains a fundamental challenge for multimodal large language models (MLLMs). Sparse frame sampling fails to capture fine-grained visual details, while dense sampling quickly exceeds context length limits. Retrieval-augmented generation (RAG) offers a promising middle ground by selectively retrieving relevant video segments for grounded generation, yet its effectiveness critically depends on the quality of the video segments used as retrieval units. In this paper, we investigate RAG for movie understanding, which demands story-level reasoning over characters, events, and narrative arcs spanning hours of content. Scene segmentation, a long-studied problem that partitions movies into semantically coherent units, is a natural candidate for defining such retrieval units. We reexamine whether existing methods actually serve this role through comprehensive evaluation on downstream movie understanding tasks, and find that they consistently fail to outperform naive uniform temporal chunking. Our audit of the most standard scene segmentation benchmarks reveals why: current annotations prioritize visually salient transitions over narrative event structure. Motivated by this mismatch, we introduce NarraScene, a narrative-centric scene segmentation dataset annotated with a three-level cognitive taxonomy spanning physical, character, and narrative change, where every valid boundary requires a narrative-level shift. When used as retrieval units, these narrative-grounded segments outperform uniform chunking on downstream movie understanding tasks, suggesting that the central challenge for scene segmentation in movie RAG is not detecting boundaries, but identifying the narrative event units that matter for movie understanding. --- ### State-Conditioned Visual Evidence Retrieval for Fine-Grained Perception in Document Vision-Language Models Authors: Mingxu Chai, Chenyu Liu, Ziyu Shen, Jiazheng Zhang, Kaidi Zhang, Ruoyu Chen, Jun Long, Jihua Kang, Tao Gui, Qi Zhang Published: 2026-08-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28698v1 Compared with typical vision-language tasks, document parsing places stronger demands on fine-grained visual perception. Existing vision-language model (VLM)-based parsing approaches rely on globally compressed visual tokens, where fine-grained details are entangled within a single representation and repeatedly accessed during decoding. However, we observe that the visual evidence for each prediction is typically localized and conditioned on the current decoding state, whereas such representations must be accessed in full at every decoding step, resulting in inefficient computation. To address this mismatch, we formulate perception as state-conditioned visual evidence retrieval (SCVER) during autoregressive decoding. The model operates on a compact global representation for coarse structure and retrieves a small set of relevant high-resolution regions conditioned on the current token state. This coarse-to-fine design enables on-demand access to fine-grained visual cues, relieving globally shared representations from encoding all fine-grained details. We further find that learning such state-conditioned retrieval in VLMs is challenging and unstable. To stabilize this process, we introduce a Spatially-Guided Learning Objective (SGLO) to guide the retrieval process. Experiments on document parsing benchmarks show that SCVER improves robustness under reduced input resolution and achieves a better accuracy-efficiency trade-off, demonstrating the effectiveness of on-demand visual evidence retrieval for fine-grained perception. --- ### Instruction Distillation: Text Instructions as Visual Examples Authors: Hardik Jindal, Soumyabrata Pal, Sayak Ray Chowdhury Published: 2026-08-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28696v1 Visual in-context learning (ICL) with multimodal large language models (MLLMs) is effective for fine-grained visual classification, but each retrieved image example consumes several hundred context tokens, making large-$K$ settings prohibitively expensive at inference scale. We propose Instruction Distillation: an offline procedure in which the MLLM itself generates, for each individual training image, a structured identification instruction encoding general appearance cues, features that differentiate the class from visually similar ones, and a common confusion point. Unlike prior work that produces a single description per class, our instructions are generated per training image, preserving the intra-class visual diversity that per-class descriptions collapse. At inference time, we study five configurations sharing a single CLIP retrieval index: zero-shot, image ICL, instruction-only ICL, and two hybrid variants in which retrieved neighbors are split between images and instructions. Across seven fine-grained benchmarks and two MLLM backbones, instruction based pipelines match, or exceeds image ICL at $K{=}1$ and reduces per-query tokens by $2.9\times$ and inference latency by $3.3\times$ at $K{=}5$. Hybrid configurations further show that visual and textual ICL signals are complementary, images give visual patterns to learn and see, while instructions give explicit rules and logic. When both of these are provided, the quality of context improves, which is noticeable in the performance. --- ### Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching Authors: Rong Shan, Tianyi Xu, Congmin Zheng, Wenteng Chen, Jiachen Zhu, Junjie Wu, Teng Wang, Weiwen Liu, Changwang Zhang, Weinan Zhang, Jun Wang, Jianghao Lin Published: 2026-08-27 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2608.28695v1 Image retrieval has traditionally been formulated as a point-wise matching problem, where each candidate image is scored in isolation. However, this atomic paradigm fails to capture the complexity of human search intent within personal photo collections, where users often seek compact visual stories bound by structural relations rather than isolated snapshots. To address this limitation, we introduce **Image Bundle Composition (IBC)**, a novel paradigm that shifts the objective from ranking individual images to dynamically composing cohesive image bundles from a massive, unstructured photo pool. Since target bundles are not predefined, IBC presents a severe combinatorial explosion challenge and demands modeling non-decomposable joint relevance. To establish this paradigm, we construct **IBCBench**, the first IBC benchmark dataset containing 109,467 images and 667 verified queries, built via a semi-automated verification pipeline. Furthermore, we propose **BundleWeaver**, an agentic framework that reformulates IBC as query-conditioned incremental hyperedge discovery. By employing a Large Language Model to adaptively search for missing relational roles and utilizing a Vision-Language Model for whole-bundle verification, BundleWeaver effectively navigates the combinatorial space. Extensive experiments demonstrate that while state-of-the-art embedding models and static decompose-and-rerank paradigms suffer from relational blindness, BundleWeaver achieves substantial performance gains, highlighting the necessity of shifting from atomic scoring to dynamic relational composition. Our dataset and code are available. --- ### SNF-Bench: Separating Static Drift from Natural Flow in Long-Horizon Fixed-Camera Video Generation Authors: Matiur Rahman Minar, Seunghun Oh, Ganghyeon Jeong, Unsang Park Published: 2026-08-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28694v1 Long-horizon video generation is evaluated with whole-frame metrics that reward motion and temporal consistency. For fixed-camera nature scenes this creates an ambiguity: motion of water, fire, smoke, or rain is desirable, whereas motion of the background is an error. A system can therefore score well on motion while its scene drifts, or on consistency while its flow stagnates. We introduce SNF-Bench, an evaluation framework for long-horizon fixed-camera generation that partitions each scene into static support and dynamic flow and reports static fidelity, flow persistence with absolute magnitude, and drift leakage separately, never as one score. Drift leakage is interpretive context rather than a headline measurement. Each factor is validated mechanistically rather than by correlation with preference: we inject global translation, rotation, and scale drift and progressive late freezing at known severity into real generations, and require each factor to respond in its stated direction and to remain selective against corruptions it does not target. Auditing publicly released long-horizon text-conditioned checkpoints under one recorded common inference configuration, plus an image-conditioned track with released-pipeline references and a deployment-sensitivity panel, we find that whole-frame motion and static-region drift induce near-opposite orderings of the same outputs. At maximum controlled translation, fBD and NBF rise to $1.86\times$ and $1.32\times$ baseline, but whole-frame Dynamic Degree reaches only $1.07\times$---rewarding the corruption. SNF-Bench measures where motion occurs and whether it persists; it does not measure physical realism. Project page: https://minar09.github.io/snfbench/. --- ### RoboGesture: Real-Time Semantic-aligned Co-Speech Gestures Generation for Humanoid Interaction Authors: Zifan Wang, Ziang Ren, Pengyang Shi, Zirui Wang, Chenghuai Lin, Tianze Wang, Zekun Qi, Liangliang Zhao, He Wang, Li Yi Published: 2026-08-27 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2608.28693v1 Enabling humanoid robots to respond to human speech with synchronized and semantically meaningful gestures is fundamental to natural human-robot interaction. However, this task faces three critical barriers: the scarcity of semantically rich datasets, the "modality eclipse" where models ignore audio cues in favor of kinematic inertia, and the sim-to-real gap regarding physical safety. We propose RoboGesture, a robot-centric framework that co-designs data, modeling, and control to power a complete interactive human-humanoid system in which the robot listens, responds, and gestures in real time. We first establish the RoboGesture dataset featuring over 300 gesture categories and develop an automated pipeline to synthesize large-scale collision-free, robot-specific audio-motion pairs. Our architecture features a Hierarchical Semantic-Acoustic Aligner that extracts multi-granular prosodic and semantic cues directly from raw audio tokens. These cues drive a Streaming Conditional Motion Generator based on a diffusion transformer with conditional flow matching. To ensure high responsiveness, we introduce Anti-Inertia CFG Masking, which prevents the model from collapsing into repetitive historical patterns by compelling it to proactively mine control signals from the audio modality. Finally, an MPC-based safety filter ensures real-time, collision-free execution on physical hardware. Experiments on a Unitree G1 humanoid demonstrate that RoboGesture generates safer, more rhythmic, and more semantically appropriate responses compared to state-of-the-art baselines. --- ### Growing a Stand, Not a Tree: Joint Canopy Generation Reproduces Crown Shyness Authors: Guang Yang, Fengchen Liu Published: 2026-08-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.28692v1 In closed forests, neighboring tree crowns often stop short of touching, leaving a network of narrow gaps known as crown shyness. The pattern belongs to the stand rather than to any single tree, which makes it a natural probe of a question in generative modeling: can a learned model produce a set of objects whose defining structure exists only between them? We formulate stand-level canopy generation as set generation with a flow-matching model, in which attention between trees is the only channel through which coupling can arise. Trained on stands grown by a resource-competition simulation that is provably not reducible to per-tree geometry, the joint model halves the clearance distribution error of an identical-capacity model that generates each tree alone, and the advantage persists at stem densities outside the training range. Against field measurements of a tropical oak forest, a single calibrated scalar yields held-out agreement in gap magnitude and crown asymmetry. The directional statistics of the gaps are controlled by stem placement rather than by the growth rule, and match the field once stem jitter is calibrated. Crown shyness, in both the simulation and the learned model, is a property of the stand and not of the tree. --- ### Compositional Failure in Audio-Visual LLMs: Late-Layer Prior Dominance Under Cross-modal Conflict Authors: Adarsh Sudheer, David Li, Omar Elbanna, Ishaan Kodarapu, Arjun Bahuguna, Vasu Sharma Published: 2026-08-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.27785v2 We study audio-visual conflict as a compositional generalization test for AV-LLMs: the model must combine synchronized but semantically incompatible audio and video evidence and decide whether the pair matches. On VideoLLaMA 2-7B-AV, three alignment configurations remain nearchance on the scored exact-string Yes/No subset of AVHBench, even though their output priors shift substantially. Similarly, off-the-shelf InternVideo2 experienced a 32.3% accuracy decrease specifically under cross-modal conflict, accompanied by a 17.3% instruction-following failure. We call this failure mode prior dominance: late-layer commitment to an internally preferred answer pattern that is weakly grounded in the conflicting inputs. To explain this behavior, we conduct a mechanistic interpretability analysis and find that commitment remains concentrated at 25.5 $\pm$ 1 layers. We show that stronger temporal alignment changes answer bias, but do not improve compositional conflict resolution. Code and data to reproduce our mechanistic audit and behavioral evaluations are available at https://github.com/AdarshSudheer09/AVHBench-dmai. --- ### SURE-Voice: A Front-End Baseline for Speech-Evidence Filtering in Speech LLMs Authors: Mengzhe Geng Published: 2026-08-27 Categories: eess.AS, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2608.27783v3 Speech language models (speech LLMs) can generate plausible outputs from audio that contains no usable speech evidence. We study this failure as a pre-generation support-estimation problem and present SURE-Voice, a training-free front end that decides whether an audio prompt contains intelligible speech evidence before calling a speech LLM. We build SURE-Challenge with a 640-example SURE-Core split and a 1,920-example SURE-Extended split derived from 120 LibriSpeech source utterances. Using one fixed operating point, an energy screen plus Whisper token confidence raises unsupported accuracy on the held-out Extended test from 0.000--0.133 to 0.919 for six non-degenerate speech LLM backbones, while supported accuracy remains 0.919--0.970 and downstream calls fall from 480 to 287. A 500-clip ESC-50 sanity set shows the same pattern on real environmental audio, with vocal non-speech as a residual failure mode. An overlap diagnostic shows that source attribution remains separate from speech-evidence filtering. The evidence supports a controlled benchmark baseline and a deployment-oriented analysis; it does not establish universal robustness to semantic answerability, gain variation or natural conversations. --- ### Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots Authors: Xujun Che, Depeng Xu, Shuhan Yuan Published: 2026-08-27 Categories: cs.CR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.27782v1 Memorization in large language models is measured through a zoo of definitions whose formal relations are unknown, and differential privacy (DP) is treated as a proxy against all of them at once. We pin down the exact DP constant for the two that carry the practical weight, counterfactual memorization and adaptive extraction, and show that they do not control each other. Under $f$-DP, every adaptive extraction protocol with list budget $m$ succeeds with probability at most $1-f(κ)$ for the oblivious baseline $κ$, and the bound is tight on a dense set of baselines: DP uniformly controls extraction exactly up to a threshold in how well the secret can be guessed a priori. Min-entropy certifies that baseline distribution-free, since $H_\infty\geε\log_2 e+\log_2(m/τ)$ holds extraction below a risk level $τ\le1/2$ under pure $ε$-DP for every prior, and is exact on uniform priors. On the memorization side, $f$-DP caps the counterfactual memorization of any bounded score at an advantage functional $η(f)$, equal to $\tanh(ε/2)$ under pure DP; for $k\ge2$ duplicated copies the naive $ε\mapsto kε$ bound $\tanh(kε/2)$ is unattainable, the exact constant being a closed-form staircase attained by geometric noisy counting. That cap is attained inside the local score class used in practice, and it is there that the two measures separate: one mechanism is memorized yet unextractable, another fully extractable yet exactly invisible to every loss-based score. The two-sided blind spot this opens for loss-based auditing and unlearning verification survives on billion-parameter models: a reserved-trigger release is recovered verbatim from one prompt while the audits practitioners deploy certify it clean. --- ### Beyond Procrustes distances: a multilinear Gromov-Wasserstein distance capturing chirality Authors: Clément Soubrier, Geoffrey Woollard, Andrew Warren, Khanh Dao Duc Published: 2026-08-27 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2608.27774v1 Efficiently and robustly analyzing shape data is critical across many scientific disciplines. While chirality is a fundamental property in numerous applications - most notably in molecular science - existing shape analysis metrics fail to distinguish between a shape and its mirror image. To address this gap, we introduce a multilinear generalization of the Gromov-Wasserstein objective. Under mild assumptions, this objective yields a distance between shapes, represented as probability distributions quotiented by a symmetry group $G$. In particular, for $G = SO(d)$, we introduce the Chiral Gromov-Wasserstein ($\mathrm{CGW}$) distance, sensitive to chirality. We establish robustness properties for the multilinear Gromov-Wasserstein distances and develop efficient algorithms to compute them, reformulating the underlying optimization problem by projecting couplings onto a low-dimensional space. We derive algorithms for both local and approximate global solutions, yielding a fully polynomial-time approximation scheme for these problems. We validate the framework through numerical experiments that demonstrate the effectiveness of $\mathrm{CGW}$ as a shape metric for chiral objects. --- ### Why Didn't It Check? Unsupported Final Claims and Their Repair in Two Tool-Equipped Language Models Authors: Justin Bronder Published: 2026-08-27 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.27768v1 A language model with access to tools can commit to a final claim unsupported by the evidence it has seen, even when a single available tool call would resolve the uncertainty and its instructions explicitly forbid assumptions and guesses. We separate this failure into two precisely defined quantities: occurrence, how often the model makes an unsupported claim on its own, measured from the visible evidence and final claim without using the hidden correct answer; and conditional repair, how often those same naturally occurring unsupported claims are repaired when the missing evidence is supplied. On one fixed Qwen3-32B setup, 33 of 512 first responses to 256 new prompt templates ended with an unsupported established claim. We replayed each case from an exact copy of the state in which the claim occurred; within each matched replay, the alternative tool responses had the same structure and length and differed only in a one-character response code. Resolving evidence repaired 33 of 33 claims; a matched response carrying no useful information repaired 0 of 33. When the evidence supported the original answer, the model preserved 33 of 33, with no observed harm. In a separate experiment, on 64 cases where evidence was needed, an automatic checking rule added 21 evidence calls, corrected all 10 wrong unsupported claims, preserved the 11 that were correct by accident, and never changed a correct answer into a wrong one. On a fixed Gemma 4 setup using the same sampling settings, the model called the tool in all 512 first responses and never made an unsupported final claim, so conditional repair could not be measured for that setup. These results describe two local fixed model setups on two synthetic task families. They do not show how common this failure is in real-world deployments, nor that it reflects a general mechanism shared across models. --- ### Fast Weight Attention for Continual Learning Authors: Yifan Zhang, Steve Ta, Jasper Zhang, Jichen Feng, Shuzhen Li, Yongxin Zhang, Yifeng Liu, Huizhuo Yuan, Mengdi Wang, Quanquan Gu, Andrew Chi-Chih Yao Published: 2026-08-27 Categories: cs.LG, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2608.27763v1 Recurrent fast-weight memories and selective state-space models compress an expanding context into a fixed-size recurrent state, making the state transition an online learning rule. We study this rule under read-after-write autoregressive semantics. For the prefix-prediction objective considered here, the local fast-memory example revealed at step $t$ is the prefix-aligned pair $(\mathbf{x}_t,\mathbf{y}_t)=(φ(\mathbf{k}_{t-1}),\mathbf{v}_t)$. The common same-step association $(φ(\mathbf{k}_t),\mathbf{v}_t)$ remains causal, but optimizes a different internal objective. We derive normalized first-order updates for squared-error regression and negative inner-product objectives. The regression family comprises Falcon-1 (a scalar NLMS update), Falcon-2 (its per-column extension), and Falcon-3 (a sliding-window mini-batch update); Falcon-1A/Falcon-2A/Falcon-3A are the corresponding inner-product variants. We provide recurrent, masked-parallel, and chunk-parallel forms, together with numerically stable positive-decay renormalization. Representative variants remain competitive in language modeling and improve length extrapolation on variable-digit addition. This framework separates temporal alignment, plasticity, forgetting, and bounded rehearsal in recurrent sequence models. --- ### Informational Antilocality and the Locality Bias in LLMs Authors: Andrew McInnerney, Shane Storks, Steven Abney, Richard L. Lewis Published: 2026-08-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.27760v1 We consider the ability of transformer-based language models (LLMs) to learn what we call k-antilocal languages, i.e., languages that have no mutual information across any span of $k$ contiguous symbols. We construct such languages with increasing $k$, finding that LLMs trained on them achieve comparable cross-entropy loss regardless of antilocality, but converge more slowly on more antilocal languages. Our findings support the idea that non-local dependencies are more difficult to learn, but the evidence for this bias comes from learning speed rather than learning success. --- ### Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess Authors: Szymon Miłosz, Piotr Duch, Szymon Grabowski Published: 2026-08-27 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2608.27757v1 Searchless chess networks reach human master strength from a single forward pass by imitating a stronger teacher: the strongest, Leela Chess Zero's (Lc0) released Chessformer, distills the visit counts of an AlphaZero-style Monte Carlo Tree Search (MCTS). Imitating a search is a poor proxy for playing without one, so we fine-tune for single-pass strength with self-play reinforcement learning (RL). Its exploration is usually supplied by an entropy bonus, the reverse Kullback-Leibler (KL) divergence to uniform. We replace it with a forward, mass-covering KL toward the network's own MCTS prior (prior-directed exploration), so exploration covers the moves the prior judges promising, and pair it with an entropy-adaptive sampling temperature, set by the value head's outcome uncertainty, that sharpens once a position is decided. In about two thousand steps it raises puzzle accuracy from 93.9% to 94.9% on a 100,000-puzzle suite and mate-in-four accuracy from 77% to 81% while holding searchless strength at or slightly above the base. Measuring tactical accuracy and playing strength together across a matched-compute sweep, we find the two dissociate: accuracy gains fall in a one-point band while ratings straddle the base, and a control fine-tuned on puzzles alone posts the study's largest tactical gains while shedding roughly 260 Elo; a better puzzle-solver is not thereby a stronger player. Distribution-level measurements show what anchoring buys: without a regularizer self-play collapses onto a single line of play, and the puzzles newly solved are the near misses whose winning move the prior kept alive. The forward-KL prior tops the rating ladder, statistically tied with a reverse-KL anchor that concentrates twice as hard and drops the hardest solutions the mass-covering prior keeps in support. --- ### Load-Bearing Context: The Question Damage Score for Evaluating Context Reliance in Linguistic Reasoning Authors: Neh Majmudar, Elena Filatova Published: 2026-08-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.27756v1 Determining whether large language models derive answers from context or prior knowledge remains a fundamental challenge. Self-contained linguistic olympiad puzzles provide a controlled setting where all answers derive solely from expert-designed context examples without external knowledge. Removing individual context examples can eliminate information needed for specific questions while leaving the rest of the puzzle unchanged. We leverage this to introduce a diagnostic framework for analyzing individual context examples. Using 53 UK Linguistics Olympiad puzzles, we generate two modified variants by deleting a single context example: (1) uniform random deletion, and (2) targeted deletion (inspired by error-correcting codes) to remove a structurally load-bearing example uniquely carrying necessary information. We formalize this impact using a Question Damage Score to classify puzzles as fragile or robust. Evaluating three frontier LLMs under instructions to abstain when information is insufficient, we find they rarely abstain, often continuing to produce correct answers after load-bearing context is removed. These findings motivate further investigation into context-based reasoning, prior knowledge, memorization, and linguistic inference. Beyond abstention, the framework enables fine-grained analyses of context reliance, including causal interventions, stopping-set analysis, targeted contamination studies, and mechanistic interpretability. --- ### Efficient Auto-Interpretability of AI Models in Biology Authors: Piotr Jedryszek, Oliver M. Crook Published: 2026-08-27 Categories: q-bio.QM, cs.AI arXiv: https://arxiv.org/abs/2608.27754v1 Sparse autoencoders (SAEs), and other interpretability methods could turn AI models in Biology and other fields into engines of scientific discovery by explaining the superhuman capabilities of those models. However, a latent is only useful if we know three things: whether it is coherent, whether it can be described, and whether that description has predictive power. These questions are routinely conflated. We assemble them into a single pipeline and report the practical innovations each stage required. First, cross-seed dictionary stability prioritises which latents are worth spending resources to investigate. Second, an intruder-detection task asks whether a latents activating examples share a recognizable pattern. Third, a separate pass proposes a candidate biological description which we convert into falsifiable predictions which can be tested in silico. Deployed on the Boltz-1 Pairformer trunk, stability prioritisation finds interpretable latents using about 4.4 times fewer latent evaluations each, and at 5.2 times lower measured cost, while recovering over half of them, and the external check shows the surfaced motifs are significantly enriched for their claimed annotations. The results also suggest a possible tension: the cross- seed stability might be selecting for some types of features, like structure-related ones, much more than others, such as function-related features. --- ### What Can Low Resource Languages Learn From Each Other? Authors: Achyuth P, Kahaan Shah, Chetan Arora Published: 2026-08-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.27753v1 Despite the rapid advancement of Vision-Language Models (VLMs), their linguistic reach remains largely confined to high-resource languages, leaving the majority of the world's 7,000+ living languages on the wrong side of a growing digital divide. This disparity is especially pronounced in Optical Character Recognition (OCR), where low-resource scripts lack the massive datasets required for traditional scaling laws. We investigate OCR adaptation in extreme data-scarce regimes (<10K real and <250K synthetic images), demonstrating that conventional fine-tuning strategies often reach a performance ceiling. Our key finding reveals a structural inefficiency in language-specific adaptation: while higher layers of specialized models diverge to capture unique script nuances, the lower layers learn redundant, highly similar features. Motivated by this observation, we propose PSMC (Pre-train, Specialize, Merge, and Co-train), a data-efficient framework that capitalizes on a cross-script "transfer effect". Our approach first derives language-specific experts from a high-resource base model, then employs task arithmetic to fuse these experts into a unified, high-performance multilingual back- bone. Extensive evaluation across 10 Indian scripts (supporting 20+ languages) shows that PSMC achieves a ~2% average improvement in Word Recognition Rate (WRR) over individual specialist models without increasing parameter count. Our results indicate that joint training in the merged latent space facilitates a constructive knowledge transfer that benefits all constituent scripts, providing a scalable pathway for inclusive VLM development. Source code and datasets will be released post publication. --- ### The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs Authors: Eric Yeats, Brendan Kennedy, Loc Truong, John Buckheit, Jung Lee, Jesse Friedbaum, John Emanuello, Henry Kvinge Published: 2026-08-27 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.27750v1 The hidden states of large language models (LLMs) are known to capture rich information relating to model knowledge and behavior that can be hard to extract from examination of input and output alone. As LLM-based systems increasingly interface with the external world, one area of concern is detecting incorrect or improper use of tools. Motivated by this, we study the effectiveness of using linear probes to detect incorrect tool-calls, measuring probe efficacy across 18 tool-calling LLMs evaluated on the Berkeley Function Calling Leaderboard. Overall, we find that probing is an effective means to catch a range of different tool-calling errors, including errors arising from using an argument that has the wrong value but the correct type, which might not be recorded by standard logging frameworks. Important factors in success include model size, probing layer, and model post-training type. We also show that probes are capable of generalizing to novel types of errors, which is critical in real world deployments. --- ### The role of parameter Jacobians in the stability of network outputs Authors: Halyun Jeong, Palle E. T. Jorgensen, Hyun-Kyoung Kwon, Myung-Sin Song, James Tian Published: 2026-08-27 Categories: math.FA, stat.ML arXiv: https://arxiv.org/abs/2608.27748v1 In the framework of network dynamics, learning models, and neural tangent kernels (NTK), we show that the corresponding linearized dynamics leads naturally to a semigroup formulation. More precisely, in our analysis of input/output models, the time-dynamics is presented via special semigroups of linear operators on Hilbert spaces, together with an associated class of semigroup perturbations. In this context, we then present new and explicit a priori perturbation-bound results: for the fixed-kernel linearization constructions arising in the NTK setting, we prove norm-bounds on the corresponding semigroup perturbations, in the form of explicit finite-time perturbation estimates. We further present refinements on prescribed task spaces, Cesàro-averaged (ergodic) comparisons estimates, and versions in which the lower spectral edge assumption is replaced by a spectral-distribution condition. We also extend the comparison to nonautonomous NTK evolutions through piecewise-frozen approximations, record a corresponding discrete Euler specialization, and offer worked examples in order to illustrate our perturbation-bound estimates. --- ### ABCD: Alpha-Composited Block Coordinate Descent: Constant-VRAM Training for Large Radiance Fields Authors: Ka Heng Shiu, Kartic Subr Published: 2026-08-27 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2608.27735v1 We present ABCD (Alpha-Composited Block Coordinate Descent), an out-of-core training framework for alpha-composited radiance fields, instantiated here for 3D Gaussian Splatting. Our method reformulates training as block coordinate descent over spatial partitions: only one block of parameters is active at a time, while all others are frozen. By exploiting the associativity of alpha blending, these inactive regions can be pre-rendered and collapsed into foreground and background RGBA images. As a result, for fixed partition size and image resolution, peak VRAM becomes O(1) with respect to total scene extent, rather than growing with full scene size. This enables GPUs with limited memory to train scenes that would otherwise not fit in core. In experiments, our method closely preserves the reconstruction quality of 3DGS, with less than 5% PSNR degradation, while ABCD with compositing ablated suffers roughly 40% degradation. Our code can be found at https://github.com/shiukaheng/abcd ---