# Research Papers — 2026-08 · bundle page 206 of 240 > Full-text markdown of papers #10251–10300 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/206 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/205.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/207.md) ### SIGNPOST-Bench: Benchmarking Text-Vision Conflict Resolution in Multimodal Large Language Models Authors: Sirun Li, Minghao Liu, Ling Dai, Yong Li, Haoxin Lyu, Junting Zhou, Fan Zhang Published: 2026-08-04 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2608.04244v1 Multimodal large language models (MLLMs) make grounded predictions in real-world scenes by combining visual and textual cues, yet existing benchmarks rarely reveal how they arbitrate between these evidence sources when they conflict. We introduce SIGNPOST-Bench, a controlled counterfactual benchmark for evaluating text-vision conflict resolution. Each source image is transformed into a counterfactual quintuplet of Original, Blank, Similar, Random, and Adversarial variants. Synthetic, localized scene-text interventions are designed to preserve non-textual content, enabling paired measurements of changes in localization performance and directed shifts toward geographic targets introduced by conflicting text. SIGNPOST-Bench contains 5,111 counterfactual groups and 25,555 image variants from four datasets. We evaluate 20 MLLMs from seven providers. Compared with Original images, Adversarial variants raise median localization error from 282 km to 1,347 km, a 4.8-fold increase. Among geocodable adversarial samples, 6.5-20.1% of predictions lie less than 50 km from the injected target across models, and every evaluated model exhibits a positive mean paired reduction in target distance from Blank to Adversarial. Compatible, unrelated, and conflicting text replacements produce distinct effects on model predictions, while clean-input localization performance does not fully predict robustness to conflicting text. These results establish visual geolocation as a continuous diagnostic of scene-text arbitration and provide a controlled framework for evaluating how MLLMs resolve conflicting multimodal evidence. --- ### Attention-based representations for multi-task computation Authors: Daniel Hsu, Mingyue Xu Published: 2026-08-04 Categories: cs.LG, cs.AI, cs.CC arXiv: https://arxiv.org/abs/2608.04243v1 Multi-head attention layers produce vector representations that support multiple downstream tasks. We establish bounds on the number of heads required in two simple and concrete multi-task scenarios. In the first scenario, a vector representation is sought so that linear predictors can compute both the smallest and largest numbers in a given list. In this case, it is known two attention heads with small embedding dimension and bit precision level suffice. We prove that a single attention head requires exponentially higher embedding dimension or precision level. In the second scenario, a vector representation is sought so that a polynomial threshold function can compute the XOR of a given string of $n$ bits. This scenario is analogous to the first one for $n=2$, since XOR is readily computed by a linear function using a vector representation that encodes both the AND and the OR of the two bits. We observe that $n$-bit XOR requires the product of the number of heads and the polynomial degree to be at least $n$, and we construct multi-head attention layers that match this lower bound. These results generalize to arbitrary (symmetric) Boolean functions, where the bound is given in terms of the threshold degree. --- ### Hallucinations on the Board: Tool-Augmented Evaluation of LLM Chess Commentary Authors: S. Ashwin Hebbar, Peiyao Sheng, Sewoong Oh, Pramod Viswanath Published: 2026-08-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.04240v1 Superhuman game engines in domains like chess have made expert-level evaluations easily accessible, yet they communicate what is true without the natural-language explanations that make such expertise educationally useful to experts and non-experts alike. Large language models could, in principle, bridge this gap, but they frequently hallucinate due to limited domain-specific knowledge, and standard reference-based or LLM-as-a-judge frameworks cannot reliably detect these errors. In this work, we present ACT-Eval, an evaluation framework that decomposes chess commentary into atomic claims and routes them to engine-supported tools and expert-annotated gold references to assess factual correctness, conceptual coverage, and move-quality judgment. We release a benchmark of 325 position--move pairs spanning pedagogical, tournament, and critical positions, including 125 positions with expert-verified gold atoms and a five-class error taxonomy. Evaluating leading proprietary and open-weight models, we find that factual hallucinations remain pervasive in chess commentary: GPT-5.4 without tools produces incorrect sub-claims 22.0% of the time, while smaller open-weight models exceed 40%. Although tool augmentation substantially improves factual correctness and move-quality assessment, coverage of expert strategic and tactical ideas remains limited across all models. Human calibration shows that ACT-Eval's factual judgments fall within the observed range of inter-human agreement, while its coverage scores correlate strongly with human assessments of strategic completeness. --- ### Physics-informed reduced-order modelling with equivariant spectral submanifolds Authors: Georg Maierhofer Published: 2026-08-04 Categories: cs.LG, math.DS, math.NA arXiv: https://arxiv.org/abs/2608.04239v1 Spectral submanifold (SSM) reduction has emerged as a mathematically principled route to reliable nonlinear reduced-order models, capturing dynamics beyond the reach of linear techniques such as Dynamic Mode Decomposition (DMD). The computation of SSMs, however, remains computationally expensive, particularly for high-dimensional systems. In this work, we introduce equivariant spectral submanifold (eSSM) reduction, a novel extension of the SSM framework that explicitly incorporates symmetries of the full-order model into the reduction process. We establish the mathematical foundations of this approach by showing that SSMs are naturally equivariant submanifolds and that the associated charts and reduced dynamics inherit the appropriate induced group actions. Building on this framework, we develop a novel equivariant SSM reduction algorithm that exploits these symmetries to achieve substantially faster computations while also improving model robustness. We demonstrate the advantages of this approach on several benchmark problems including a test from the Common Task Framework for Science. --- ### Multimodal Alignment Through Joint Kernel Entropic Gromov--Wasserstein Optimal Transport Authors: Yixuan Florence Wu, Yilun Zhu, Naichen Shi Published: 2026-08-04 Categories: math.ST, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2608.04234v1 We study the problem of aligning data from multiple modalities into a shared representation space, focusing on settings where strong pretrained unimodal encoders are available but cross-modal paired data are scarce. We propose a structure-preserving alignment framework, joint kernel entropic Gromov--Wasserstein Optimal Transport (JK-EGW), which maps multiple modalities into a common latent space by minimizing a quadratic optimal transport objective. JK-EGW leverages fine-grained similarity relationships within and across modalities to construct a global affinity kernel instead of relying on raw feature-space distances. Our framework naturally provides explicit control over the geometry and distribution of the latent embedding. On the theory side, we establish parametric sample complexity rate of $n^{-1/2}$, matching the corresponding rates for standard, entropic and Gromov--Wasserstein optimal transport. On the algorithmic side, we derive a scalable alternating procedure to solve JK-EGW with entropic optimal transport (EOT) updates through a low-rank kernel approximation and a variational lifting. This lifting scheme effectively relieves the burden of a quadratic objective, and allowing us to take the advantage of existing EOT solvers. Empirically, we focus on post-hoc alignment of embeddings from pretrained encoders in data-scarce regimes, and show that our proposed method achieves improved multimodal retrieval performance compared to existing alignment baselines. --- ### Interoceptive Attention as Dynamic Homeostatic Prioritization in a Foraging Agent Authors: St John Grimbly, Nicolas Kuske, Evert A. Boonstra, Bruce A. Bassett, Charel van Hoof, Rowan Hodson, Benjamin Rosman, Ryan Smith, Mark Solms, Jonathan P. Shock Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.04232v1 Biological systems must regulate competing needs under limited perceptual bandwidth, where sharpening one estimate costs the capacity to sharpen the others. Any fixed-budget system therefore has to decide where to allocate its perceptual precision. We study this in a foraging agent that must keep several bodily needs satisfied to survive, modelled with active inference. At each step it reads its own body-state beliefs, identifies the most-needed channel, and reallocates a fixed budget of interoceptive precision toward it, so that the same precision-shaped likelihood feeds both belief update and planning. In AffectWorld, a four-channel foraging gridworld, this selective allocation more than doubles learning-phase survival at matched budget against a uniform-precision agent ($0.414$ vs $0.199$ across 11 layouts, $n{=}32$ seeds each, paired cluster-bootstrap $p \leq 10^{-4}$). Two further results sharpen the mechanism. The benefit runs through planning as well as perception, since denying the shaped likelihood to the planner alone removes about half of it. It is also need-aligned, since aiming precision at the least-needed channel does worse than spreading it evenly. The attended channel additionally learns its own dynamics about twice as fast, and stays ahead even at matched observation count, a behavioural trace of the same precision routing, visible in learning speed, not survival. --- ### Transferable Dual-Stream Representations for Mesoscale-Preserving Sea Surface Temperature Downscaling Authors: Parth Doshi, Priyanka Aravindan, Vaishnav Vaidheeswaran, Md Mahbub Alam, Gabriel Spadon Published: 2026-08-04 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2608.04230v1 Deep learning models for scientific spatio-temporal downscaling often minimize reconstruction error while failing to preserve physically meaningful multi-scale structure. For sea surface temperature prediction, this can yield outputs that are numerically plausible yet overly smooth, missing mesoscale variability critical to regional ocean dynamics. Existing methods often focus on pixel-wise objectives or single-context conditioning, which limits their ability to preserve spectral fidelity and generalize across regions. To address this, we propose EddyFlow, a representation learning framework for kilometer-scale sea surface temperature downscaling that balances predictive accuracy, scale-dependent structure, and regional generalization. EddyFlow is trained on the Gulf of St.~Lawrence and evaluated in zero-shot and few-shot settings on the Bay of Fundy and the Gulf of Mexico. EddyFlow demonstrates that physics-informed representation learning reduces zero-shot RMSE by 21%, achieves up to 85.6% skill relative to persistence on unseen domains, and maintains near-ideal spectral fidelity with a PSD ratio of $\approx 1.00$. --- ### Random features for Grassmannian kernel approximation with bounded rank-one projections Authors: Rémi Delogne, Laurent Jacques Published: 2026-08-04 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2608.04227v1 We propose a family of random feature maps for scalable kernel machines on low-dimensional subspaces, ie on the Grassmannian manifold. Such representations are useful when data classes or clusters are well described by the span of a few samples. Classical Grassmannian kernels, including the projection and Binet-Cauchy kernels, require full Gram matrices, which leads to prohibitive computational and memory costs for large high-dimensional subspace datasets. We address this limitation using random features based on rank-one projections of subspace projection matrices followed by bounded non-linear transforms, either periodic or binary, to control the resulting distributions. We show that inner products in the random feature space approximate well-defined rotation-invariant Grassmannian kernels that depend only on the principal angles between subspaces. When the number of features is sufficiently large relative to the intrinsic subspace dimension, the approximation holds uniformly over all fixed-dimensional subspaces with high probability. For periodic transforms, the approximated kernel has a closed-form expression with tunable behaviour between inverse Binet-Cauchy and Gaussian-type regimes. Binary transforms yield compact one-bit subspace features, although no closed-form kernel is known. Structured rank-one projections based on randomised fast Fourier transforms further reduce computation without sacrificing practical accuracy. Experiments on synthetic data and ETH-80 classification tasks show that these features accurately preserve Grassmannian geometry while reducing computation, memory, and storage. Rank-one embeddings therefore provide a practical and scalable alternative to classical Grassmannian kernels. --- ### OmniVR: Audio-Video Conditional Generation for Archival Footage Restoration Authors: Xin Lu, Zihao Fan, Jie Huang, Mingchen Zhong, Hexin Zhang, Xueyang Fu, Zheng-Jun Zha Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.04224v2 Archival footage often suffers from coupled visual and acoustic degradations, yet most restoration systems process the two modalities separately. To address this problem, we present OmniVR, the first systematic framework for joint audio-video restoration, covering data construction, model adaptation, efficient inference, and evaluation. We construct a high-quality audio-video corpus with detailed captions and use a joint degradation pipeline to produce aligned clean and degraded pairs. Using these pairs, we adapt a pretrained text-to-audio-video model (T2AV) by introducing degraded audio-video conditions (TAV2AV), then progressively replace sample captions with a fixed restoration prompt while retaining caption/null rehearsal. The resulting AV2AV model requires no user-provided text. Under a compatible residual-learning model, we prove that this condition-annealing schedule reduces gradient variance and expected restoration risk relative to direct fixed-prompt adaptation at the same training budget. For efficient deployment, OmniVR-Flash combines reduced-resolution video conditioning, MeanFlow-based one-step distillation, and Turbo VAE, achieving approximately 38 fps at 1K and 18 fps at 2K on a single B200 GPU. We further introduce OmniVRBench to evaluate four complementary dimensions: visual quality, audio quality, temporal consistency, and audio-visual synchrony. OmniVR achieves state-of-the-art results on public benchmarks and OmniVRBench. Data, code, and model weights will be released. Project Page: https://xin1u.github.io/OminiVR_PAGE/ --- ### OmniVR: Joint Video-Audio Conditional Generation for Restoring Degraded Historical Films Authors: Xin Lu, Zihao Fan, Mingchen Zhong, Jie Huang, Xueyang Fu, Zheng-Jun Zha Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.04224v1 Historical films suffer from co-occurring visual and audio degradations---blur, noise, flicker, hiss, clipping, and dropout---yet existing methods restore each modality independently, leaving quality gaps and cross-modal inconsistency. We present OmniVR, the first joint audio-video generative restoration model. Built upon a 22B-parameter audio-video generation backbone, OmniVR formulates restoration as conditional generation within a unified multimodal DiT: the low-quality video and audio are encoded as latent conditions, combined with a fixed restoration prompt, and jointly denoised to recover visual structure, temporal motion, and acoustic detail under one coordinated objective. Three key designs enable this adaptation: (1) a joint audio-video degradation pipeline that simulates real old-film characteristics from Internet-collected data; (2) an architecture-preserving text-to-audio-video (T2AV) to audio-video-to-audio-video (AV2AV) transition with prompt annealing that maximally retains the generative prior; and (3) first-frame image-to-video (I2V) anchoring with loss reweighting and waveform supervision for long-video extrapolation and audio fidelity. We also propose OmniVRBench, the first benchmark that evaluates audio-video restoration across visual quality, audio quality, temporal consistency, and audio-visual synchrony on 200 real historical clips. OmniVR surpasses all prior methods on all six visual metrics, achieves the best audio quality, and produces natural colorization---the first method to jointly address all three aspects. Code and weights will be publicly released. Project Page: https://xin1u.github.io/OminiVR_PAGE/ --- ### TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning Authors: Yilong Dai, Yiming Sun, Yiheng Chen, Shengyu Chen, Peyman Givi, Xiaowei Jia, Runlong Yu Published: 2026-08-04 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2608.04222v1 Turbulence is a central testbed for machine learning on physical dynamics because its governing laws are known exactly. However, most existing studies remain in 2D, while 3D turbulence has fundamentally different physics and is far more costly to simulate. Existing 3D resources also typically provide only one realization per configuration, making it difficult to distinguish learning the dynamics from fitting the statistics of a single flow. In this paper, we introduce TIDE (Turbulent Incompressible DNS Ensembles), a 256^3 DNS corpus and benchmark for 3D incompressible turbulence, with 15 configurations on eight controlled axes, independent ensembles, pressure fields, and equation-level verification. The benchmark includes five tasks, standardized learned baselines, controlled generalization splits, and physical-fidelity metrics alongside pointwise error. Across the main forecasting configurations, current learned models barely outperform persistence and still make about twice the error of a spectral solver given the true equations. Moreover, lower pointwise error can coincide with severely distorted small-scale dynamics, showing that accuracy alone does not ensure physical fidelity. Generalization results further show that most regime shifts reflect limited training coverage, whereas forced-to-decay transfer exposes a missing conditioning variable: operators trained under forcing continue to predict driven evolution when the external drive is removed. Closing these accuracy, fidelity, and conditioning gaps is the central open problem made measurable by TIDE. --- ### A Unified Model for Cross-Domain Clone Detection via Model Merging Authors: Palash R. Roy, Banani Roy, Kevin A. Schneider, Chanchal K. Roy Published: 2026-08-04 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.04215v1 The growing diversity of code clone types, from syntactic copies to cross-language semantic clones to AI-generated duplicates, has created a fragmentation crisis in clone detection. Current deep learning detectors are domain specialists that degrade significantly outside their training distribution, with F1 drops exceeding 70% across domains. Deploying multiple specialized models is impractical, yet training a single cross-domain detector requires simultaneous access to all training data. To address this, we investigate model merging, a family of post-hoc techniques that operate solely on trained checkpoints. We evaluate parameter merging with five task-vector methods, architecture merging via greedy layer stitching, and cross-tokenizer alignment across four code models, three benchmarks, and twelve configurations. Same-base TIES merging creates effective cross-domain detectors, validated across two model families and three random seeds, reaching 0.865 combined F1 on UniXcoder, 93% of multi-task performance without any training data at the merging step. WUDI achieves the highest in-distribution combined F1 at 0.899, but TIES generalizes better to unseen AI-generated clones, making it our recommended method. Cross-base merging yields only marginal and high-variance gains across all five methods, indicating that task vector compatibility through a shared pre-trained base is the binding factor for effective merging. Merged detectors also outperform zero-shot code LLMs on GPTCloneBench at lower inference cost and generalize up to 4x better than multi-task training to unseen AI-generated clones, suggesting a trade-off between in-domain performance and OOD robustness. This work provides one of the first systematic empirical studies of model merging for software engineering and a practical recipe for building cross-domain clone detectors. --- ### Attention-Only White-Box Transformer via LeJEPA-Based Self-Supervised Pretraining Authors: Yang Bai, Linyuan Wang, Haoyang Jiang, Nuolin Sun, Libin Hou, Bin Yan Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.04213v1 Existing studies on self-supervised learning for white-box networks typically decouple the derivation of white-box networks via optimization algorithms from self-supervised learning paradigms. In this work, we instead revisit the two components from a joint perspective. The LeJEPA-based self-supervised framework assumes an isotropic Gaussian distribution as the optimal embedding distribution for downstream tasks, which is conceptually equivalent to the expansion term $R(Z)$ in the sparse rate reduction objective guiding white-box Transformer optimization. Building on this observation, we use the LeJEPA self-supervised paradigm to optimize $R(Z)$, and derive the remaining terms $R^{c}(Z\mid U_{(K)})+λ\lVert Z\rVert_{0}$ via the alternating direction method of multipliers (ADMM) into an attention-only Transformer that dispenses with the ISTA structure or MLP layers of the original design. Experimental results demonstrate that our attention-only white-box Transformer achieves classification accuracies of $88.88\%$ on CIFAR-10 and $63.54\%$ on CIFAR-100 at the Base scale under the LeJEPA self-supervised paradigm, while the original white-box Transformer CRATE achieves classification accuracies of $89.18\%$ on CIFAR-10 and $63.56\%$ on CIFAR-100. Our model achieves competitive performance while reducing the parameter count by roughly $31\%$. Beyond the white-box setting, we further investigate standard ViTs and find that replacing all MLP blocks with ReLU activations under knowledge distillation removes approximately 66\% of the parameters while preserving competitive accuracy, motivating further investigation into the potential redundancy of MLP modules in standard ViT architectures. --- ### PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images Authors: Ruiqi Wang, Yiming Qian, Fenggen Yu, Yuxuan Lu, Dakuo Wang, Hao Zhang, Jing Huang Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.04210v1 Pose-agnostic Anomaly Detection (PAD) remains challenging as anomalies can appear under arbitrary viewpoints, requiring methods to handle significant pose variations. Existing approaches rely on complex 3D reconstruction, which are computationally expensive and require extensive multi-view data. We propose PADFormer, a novel image-space approach that leverages Vision Transformer (ViT) to directly reconstruct anomaly-free versions of query images while preserving pose information. Our key insight is to adapt cross-view masked reconstruction for anomaly detection through training exclusively on normal data, combined with dynamic patch selection and spatial alignment mechanisms that enable effective learning from sparse reference views under significant pose variations. During inference, we perform multiple forward passes with different masking patterns to generate an ensemble of anomaly-free reconstructions, ensuring comprehensive coverage of the query image. Anomalies are detected by comparing these reconstructions with the query image. PADFormer achieves state-of-the-art results on the PAD benchmark while maintaining comparable performance on classic few-shot anomaly detection (FSAD) tasks, demonstrating superior efficiency and generalization without requiring 3D reconstruction. --- ### From Non-Convex Self-Concordant Regularization to Scalable Quasi-Newton Training of PINNs Authors: Chenhao Si, Kang An, Shiqian Ma, Ming Yan Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.04206v2 Physics-informed neural networks (PINNs) often require high-accuracy quasi-Newton refinement to obtain reliable partial differential equation solutions, but their residual objectives can exhibit indefinite, nearly singular, and poorly scaled local curvature. Regularized quasi-Newton methods provide established mechanisms for stabilizing secant models, while self-concordant methods provide local-metric rules for curvature-dependent step selection. Building on these two lines of work, we propose SCORE, a self-concordance-inspired quasi-Newton method with decrement-coupled shifted secant geometry for PINN training. Its distinguishing mechanism is that a single quasi-Newton decrement computed from the learned inverse metric jointly determines a strong-Wolfe-tested candidate step and an adaptive shift used to define the next secant geometry. The shifted displacement represents the action of an averaged shifted metric along the accepted step, while requiring neither Hessian construction nor Hessian-vector products. Under a local spectral-equivalence condition, we show that the quasi-Newton decrement and candidate step remain comparable to their counterparts in a positive shifted metric, and recover the normalized self-concordant rule in the matched-metric case. Strong Wolfe acceptance, fallback line search, and standard curvature safeguards provide globalization without modifying the underlying PINN objective. Experiments on the viscous Burgers, Kuramoto--Sivashinsky, Korteweg--de Vries, and complex Ginzburg--Landau equations show that SCORE attains lower final errors than the tested BFGS and self-scaled Broyden baselines. The Burgers ablation further indicates that shifted curvature stabilization and decrement-based step selection make complementary contributions to high-accuracy refinement. --- ### From Non-Convex Self-Concordant Regularization to Scalable Quasi-Newton Training of PINNs Authors: Chenhao Si, Kang An, Shiqian Ma, Ming Yan Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.04206v1 Physics-informed neural networks (PINNs) often require high-accuracy quasi-Newton refinement to obtain reliable partial differential equation solutions, but their residual objectives can exhibit indefinite, nearly singular, and poorly scaled local curvature. Regularized quasi-Newton methods provide established mechanisms for stabilizing secant models, while self-concordant methods provide local-metric rules for curvature-dependent step selection. Building on these two lines of work, we propose SCORE, a self-concordance-inspired quasi-Newton method with decrement-coupled shifted secant geometry for PINN training. Its distinguishing mechanism is that a single quasi-Newton decrement computed from the learned inverse metric jointly determines a strong-Wolfe-tested candidate step and an adaptive shift used to define the next secant geometry. The shifted displacement represents the action of an averaged shifted metric along the accepted step, while requiring neither Hessian construction nor Hessian-vector products. Under a local spectral-equivalence condition, we show that the quasi-Newton decrement and candidate step remain comparable to their counterparts in a positive shifted metric, and recover the normalized self-concordant rule in the matched-metric case. Strong Wolfe acceptance, fallback line search, and standard curvature safeguards provide globalization without modifying the underlying PINN objective. Experiments on the viscous Burgers, Kuramoto--Sivashinsky, Korteweg--de Vries, and complex Ginzburg--Landau equations show that SCORE attains lower final errors than the tested BFGS and self-scaled Broyden baselines. The Burgers ablation further indicates that shifted curvature stabilization and decrement-based step selection make complementary contributions to high-accuracy refinement. --- ### MatrAIx: Simulating the World with 8.3 Billion Persona Agents Authors: Xiaomin Li, Yuexing Hao, Jianheng Hou, Jintao Huang, Qianfeng Wen, Shirley Huang, Yifan Liu, Xiaoyi Liu, Yilan Fan, Yijun Wang, Koutian Wu, Ruoqi Gao et al. Published: 2026-08-04 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.04205v1 Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and interactive behavior. We therefore introduce MatrAIx, a population-scale simulated-user evaluation infrastructure for testing AI systems and digital products with heterogeneous users. MatrAIx has three core components: First, Persona 8B contains 8.3 billion persona records represented by 1,290 categorical dimensions. Records are either sampled from a dependency graph that preserves correlated attributes or derived from human-authored profiles. We release a quality-filtered coreset of approximately 1 million personas, comprising 599,847 human-grounded and 400,000 synthetic records. Second, the MatrAIx Playground provides four environments in which diverse users evaluate and interact with digital products: Survey, AI Chatbot, Web, and App. Third, MatrAIx provides 1,010 application tasks spanning more than 25 domains, including Commerce, Software, Finance, and Healthcare. We conducted 18,189 evaluation trials across eight representative tasks. Persona agents were powered by three LLMs: Claude Opus 4.8, GPT 5.5, and Claude Haiku 4.5. The resulting feedback captures how decisions and preferences vary across persona backgrounds, including hesitation after a price increase, willingness to continue after an AI assistant fails, and latency tolerance. We conducted two main validation studies: First, a 400-trial controlled study evaluated persona adherence across ten behavioral attributes and all four environments. The declared behavior was expressed or correctly suppressed in 366 trials (91.5%). Second, human and LLM judges evaluated the extraction quality of human-grounded personas. Overall, MatrAIx provides an end-to-end infrastructure for evaluating AI systems and digital products with diverse simulated human users. --- ### Unscented KalmanNet: Structure-Preserving Deep Learning with Calibrated Posterior Uncertainty under Incomplete Physics and Unknown Noise Authors: Minhyeok Ko, Abdollah Shafieezadeh Published: 2026-08-04 Categories: cs.LG, eess.SP, math.NA arXiv: https://arxiv.org/abs/2608.04201v2 Nonlinear state estimation requires sequentially fusing model-based predictions with noisy measurements. Under imperfect dynamics and unknown, time-varying noise statistics, this fusion can degrade in both accuracy and statistical consistency. Existing learning-aided filters largely treat accuracy and uncertainty estimation separately, limiting their ability to correct model-mismatch-induced bias while retaining an explicit, calibrated posterior covariance. This paper introduces Unscented KalmanNet (UKN), a model-based deep learning architecture that extends the Unscented Kalman Filter (UKF) with learned mechanisms for these two sources of filtering error while preserving explicit posterior covariance propagation. NoiseNet learns time-varying process and measurement covariances as bounded multiplicative corrections to baseline covariances, guaranteeing positive definiteness, while GainNet learns a bounded residual correction to the analytical UKF gain to compensate for model-mismatch-induced bias. A calibration-aware training objective couples state error with posterior covariance and innovation consistency terms through adaptive weighting, jointly optimizing accuracy and calibration. UKN is benchmarked against UKF, KalmanNet, and Bayesian KalmanNet on three synthetic systems and real-flight UZH-FPV data. It achieves the lowest state-estimation error in all four examples and reduces RMSE by 26.4-49.7% compared with UKF in the synthetic cases. Leave-one-sequence-out cross-validation over 11 flights shows 22.4% and 34.3% reductions in mean position and velocity RMSE, respectively. UKN also yields the lowest fold-to-fold variability, with dimension-normalized NEES and empirical coverage closest to nominal values among covariance-reporting filters. These results show that structured learned adaptation improves estimation accuracy while retaining calibrated uncertainty. --- ### Unscented KalmanNet: a hybrid deep learning filter with calibrated posterior covariance for nonlinear state estimation Authors: Minhyeok Ko, Abdollah Shafieezadeh Published: 2026-08-04 Categories: cs.LG, eess.SP, math.NA arXiv: https://arxiv.org/abs/2608.04201v1 State estimation for nonlinear dynamical systems is commonly performed with the Unscented Kalman filter (UKF), which propagates the state moments through deterministic sigma points and reports a posterior covariance at every step. In practice, however, unknown and time-varying noise statistics and model mismatch degrade both estimation accuracy and covariance calibration. Existing learned filters improve accuracy but are largely built on the extended Kalman filter and either forgo an explicit covariance or learn uncertainty without correcting mismatch-induced gain bias. This paper introduces the Unscented KalmanNet (UKN), a hybrid recursive estimator that augments the UKF with two structurally distinct learned components while preserving its explicit sigma-point covariance recursion. NoiseNet predicts time-varying process and measurement covariances as bounded multiplicative corrections to fixed baselines, guaranteeing positive definiteness, while GainNet applies a bounded residual correction to the analytical gain. A calibration-aware training objective combines state error with covariance- and innovation-consistency terms through adaptive weights, jointly optimizing accuracy and calibration. UKN is benchmarked against UKF, KalmanNet, and Bayesian KalmanNet on three synthetic systems and UZH-FPV real-flight data. It achieves the lowest aggregate state-estimation error in all four examples and reduces RMSE by $26.4$-$49.7\%$ compared to UKF in the synthetic cases. Leave-one-sequence-out cross-validation over 11 flights shows $22.4\%$ and $34.3\%$ reductions in mean position and velocity RMSE, respectively. UKN also yields the lowest fold-to-fold variability, with normalized NEES and empirical coverage closest to nominal values among the other filters. --- ### From Financial Sentiment Classification to Return Predictability: A QLoRA Benchmark of Large Language Models Authors: Fusheng Luo Published: 2026-08-04 Categories: q-fin.MF, cs.LG arXiv: https://arxiv.org/abs/2608.04200v1 Financial sentiment classifiers are commonly evaluated against human labels, but strong linguistic performance does not necessarily imply economically useful return predictability. This study separates these questions through two experiments. First, we construct a unified three-class benchmark from five financial text datasets and compare TF--IDF Naive Bayes, off-the-shelf FinBERT and Financial-RoBERTa encoders, zero-shot Qwen2.5-7B, and QLoRA-adapted Qwen2.5-7B, LLaMA3-8B, and Mistral-7B models. Mistral-7B achieves the best test accuracy (0.8840) and macro-F1 (0.8771), while QLoRA raises Qwen2.5's macro-F1 from 0.7274 to 0.8615. An inverse-frequency class-weighted loss does not improve Qwen2.5. Second, we evaluate economic validity on a temporally separate 2019 Benzinga sample containing 10,637 unique headlines and 13,115 headline--stock observations for a fixed S\&P~100 universe. Model probabilities are converted into continuous sentiment scores, aggregated by stock and signal date, and aligned with next-session returns over one-, two-, three-, and five-day horizons. All seven downstream models produce positive but small mean rank information coefficients at the one-day horizon; the largest is 0.0143 for FinBERT. None of the 28 model--horizon tests remains significant after Newey--West inference and false-discovery-rate correction. Portfolio results likewise fail to establish a robust advantage for the best-performing classifiers. The findings show that QLoRA is effective for financial sentiment adaptation, while also documenting a clear gap between classification accuracy and tradable cross-sectional signals. --- ### SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation Authors: Nie Lin, Takehiko Ohkawa, Sijin Chen, Ruoshi Wen, Zhuohang Li, Liqun Huang, Zhengming Zhu, Yiming Bao, Yunfei Li, Minjie Cai, Xiao Ma, Wei Xu et al. Published: 2026-08-04 Categories: cs.RO, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.04196v1 Recent years have witnessed an explosive trend of scaling ego-centric human videos for robot manipulation, yet it remains unclear which data actually benefits dexterous manipulation. We present SiMDex, a similarity-based data mining framework that casts human data selection for VLA post-training in dexterous manipulation as a recommendation problem. For each robot demonstration, SiMDex employs a three-layer recall-ranking-re-ranking pipeline to extract task-relevant subsets from a pool of ~32M egocentric human samples, operating in a morphology-agnostic action space that requires no changes to VLA architecture or training. Against a strong baseline trained with an equal amount of randomly sampled human data, SiMDex uses only ~1.49M mined samples (<5% of the pool) yet improves the overall success rate from 47.7% to 61.1%, showing that selective curation outperforms indiscriminate data mixing. --- ### Patients-like-me: A Variational LM--GNN Framework for Explainable Clinical Prediction Authors: Xinyu Wang, Yixuan Li, Hanwei Wu, Qincheng Lu, Chi-Kuang Yeh, Xiao-Wen Chang, Ziyang Song Published: 2026-08-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.04193v1 Language models (LMs) offer strong textual representations for electronic health records (EHRs), but they encode patient sequences in isolation and provide limited explainability. Graph neural networks (GNNs) complement LMs by incorporating inter-patient relationships and enabling reference-patient attribution, yet they rely on high-quality patient representations. We propose Patients-like-me (PLM), a unified LM--GNN framework that integrates local patient semantics with global cohort structure. To train PLM efficiently, we introduce a Variational Expectation-Maximization algorithm that alternates LM and GNN updates under a supervised variational objective. Extensive experiments on MIMIC-III and MIMIC-IV show that PLM consistently outperforms state-of-the-art methods, with improvements generalizing across encoder-only and decoder-only LM backbones. These gains are achieved with only modest additional computational overhead. PLM also provides reference-patient explanations by retrieving influential similar patients, while edge-masking experiments confirm that the highest-ranked references have the greatest impact on model predictions. --- ### Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills Authors: Peichun Hua, Haoxuan Xu, Mengyuan Li Published: 2026-08-04 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.04192v2 Closed source agent skills may encode proprietary instructions, scripts, constants, and data. Providers may offer their capabilities as services while keeping the underlying packages hidden. Prior work focuses on prompt injection attacks that directly disclose these artifacts, and existing defenses accordingly aim to prevent such leakage. However, preventing file disclosure does not prevent users from recovering the functionality those files implement. This raises a fundamental question: can a user reconstruct a skill's functionality through ordinary use while its files remain hidden? We study behavioral skill reconstruction (BSR), in which an attacker uses valid task requests and observed responses to build a functional clone of a hidden skill. We introduce SkillClone, a black-box attack that clones a target skill by forming an interface hypothesis from its public advertisement, issuing structured benign probes, synthesizing an executable replica, and iteratively repairing it through differential validation against the victim skill. Across 30 skills spanning rules, tables, procedures, and algorithms, SkillClone achieves exact or partial recovery on held-out inputs for several targets. Iterative requerying closes gaps missed by single-round reconstruction. Because SkillClone uses only legitimate interactions, disclosure-focused defenses provide limited coverage, and less detailed skill descriptions offer limited protection. These results show that file secrecy alone does not ensure functional secrecy. Defenses must also limit cumulative information leakage from ordinary use. --- ### Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills Authors: Peichun Hua, Haoxuan Xu, Mengyuan Li Published: 2026-08-04 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.04192v1 Closed source agent skills may encode proprietary instructions, scripts, constants, and data. Providers may offer their capabilities as services while keeping the underlying packages hidden. Prior work focuses on prompt injection attacks that directly disclose these artifacts, and existing defenses accordingly aim to prevent such leakage. However, preventing file disclosure does not prevent users from recovering the functionality those files implement. This raises a fundamental question: can a user reconstruct a skill's functionality through ordinary use while its files remain hidden? We study behavioral skill reconstruction (BSR), in which an attacker uses valid task requests and observed responses to build a functional clone of a hidden skill. We introduce SkillClone, a black-box attack that clones a target skill by forming an interface hypothesis from its public advertisement, issuing structured benign probes, synthesizing an executable replica, and iteratively repairing it through differential validation against the victim skill. Across 30 skills spanning rules, tables, procedures, and algorithms, SkillClone achieves exact or partial recovery on held-out inputs for several targets. Iterative requerying closes gaps missed by single-round reconstruction. Because SkillClone uses only legitimate interactions, disclosure-focused defenses provide limited coverage, and less detailed skill descriptions offer limited protection. These results show that file secrecy alone does not ensure functional secrecy. Defenses must also limit cumulative information leakage from ordinary use. --- ### Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models Authors: Mario Leiva, Yue Ma, Qinru Qiu, Gerardo Simari, Paulo Shakarian Published: 2026-08-04 Categories: cs.AI, cs.CV, cs.LG, cs.LO arXiv: https://arxiv.org/abs/2608.04190v1 Deploying pre-trained perception models in novel environments degrades their accuracy under distributional shift, and assembling them alone does not recover it: combiners such as majority voting trade recall for precision and are brittle to coordinated failures. Prior metacognitive methods learn logical rules that flag a model's errors, but rely on hand-authored domain-knowledge cues (object-size priors, segmentation masks) that do not transfer to genuinely novel scenes. We show that this metacognitive layer can be learned without any domain knowledge by exploiting vector-space geometry: per-model Label Vector Pools (LVP), built from each model's own training embeddings, yield error-detection rules from the geometry of detections relative to training-determined prototypes, reaching parity with domain-knowledge rules to within $0.002$ every F1 on test set. Because the approach remains neurosymbolic, these geometric rules share a single logical framework and can still be complemented by domain knowledge when available. We frame the fusion of multiple imperfect ViT-based detectors as a consistency-based abduction problem solved at test time by an exact Integer Program (IP) and a polynomial-time heuristic. On an aerial-imagery benchmark of 15 weather-shifted test sets and six ViT detectors, our domain-knowledge-free layer matches the strongest majority-vote variant on clean data (within $0.005$ F1) and, unlike every majority-vote baseline, retains its performance under a coordinated label-flipping attack: at a $90\%$ flip rate it averages $0.42$ F1 versus $0.35$ for MV-Plurality (a $22\%$ relative gain) and attains the highest F1 on \emph{every} test set once the flip rate exceeds $0.4$ --- ### Large Language Models for Low-Resource Languages: A Conceptual Framework for an Electronic Explanatory Dictionary of the Tajik Language Authors: Mullosharaf K. Arabov, Saidali M. Pirzoda, Behruz A. Sultonov Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.04186v3 This paper presents a conceptual framework for developing an electronic explanatory dictionary of the Tajik language using large language models (LLMs). The relevance of the work stems from the absence of a comprehensive digital lexicographic resource for Tajik that is comparable in functionality to dictionaries for high-resource languages, and from the limited adaptation of modern natural language processing technologies to low-resource language systems. Based on a systematic survey of existing linguistic, statistical, and corpus resources, we propose a dictionary architecture that integrates modules for morphological analysis, lemmatization, semantic clustering, and dictionary entry generation using LLMs. The choice of subword tokenization is justified by the agglutinative nature of Tajik morphology and its high morphological variability, along with a parameter-efficient fine-tuning (PEFT) strategy suitable for limited annotated data. The novelty of the work lies in proposing the first holistic conceptual architecture of an explanatory dictionary for Tajik that unifies classical lexicographic methods, language statistics, and generative capabilities of LLMs into a single system. The practical significance of the study is the formation of a methodological foundation for developing a full-featured electronic dictionary that can serve both as a lexicographic tool and as a core resource for machine translation, automatic summarization, sentiment analysis, and other applied NLP tasks. The paper is intended for specialists in computational linguistics, lexicography, and developers of natural language processing systems working with low-resource languages. --- ### Large Language Models for Low-Resource Languages: A Conceptual Framework for an Electronic Explanatory Dictionary of the Tajik Language Authors: Mullosharaf K. Arabov, S. S. Pirov, B. Sultonov Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.04186v2 This paper presents a conceptual framework for developing an electronic explanatory dictionary of the Tajik language using large language models (LLMs). The relevance of the work stems from the absence of a comprehensive digital lexicographic resource for Tajik that is comparable in functionality to dictionaries for high-resource languages, and from the limited adaptation of modern natural language processing technologies to low-resource language systems. Based on a systematic survey of existing linguistic, statistical, and corpus resources, we propose a dictionary architecture that integrates modules for morphological analysis, lemmatization, semantic clustering, and dictionary entry generation using LLMs. The choice of subword tokenization is justified by the agglutinative nature of Tajik morphology and its high morphological variability, along with a parameter-efficient fine-tuning (PEFT) strategy suitable for limited annotated data. The novelty of the work lies in proposing the first holistic conceptual architecture of an explanatory dictionary for Tajik that unifies classical lexicographic methods, language statistics, and generative capabilities of LLMs into a single system. The practical significance of the study is the formation of a methodological foundation for developing a full-featured electronic dictionary that can serve both as a lexicographic tool and as a core resource for machine translation, automatic summarization, sentiment analysis, and other applied NLP tasks. The paper is intended for specialists in computational linguistics, lexicography, and developers of natural language processing systems working with low-resource languages. --- ### Test, then Route: How Language Models Execute In-Context Conditional Rules Across Models and Languages Authors: Luxshan Thavarasa, Sivasuthan Sukumar Published: 2026-08-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.04183v1 When a language model follows an in-context conditional rule such as "if P(x) then A else B," does it assemble a runtime circuit with one module that tests the predicate and another that routes the answer? We probe this with activation patching under a four-donor design whose two swapped-rule donors make the condition and the answer word disagree, so each layer reveals which of the two it carries. Across three open models from two families and six languages sharing one fixed item bank, a mid-stack residual band carries the predicate's truth value: patching it reroutes the answer with predicate-outcome flip near 1.0 and mapping flip near 0.0, meeting a strict pre-specified isolation criterion in 17 of 18 cells, and the same localization holds across five predicate families. The router shows the opposite profile. A learned subspace flips A and B near-perfectly within the trained pair yet transfers to a new pair at approximately 0 in every model, while in Gemma-3-4B (the only model probed cross-lingually) it transfers at approximately 0.98 to the same pair in other languages. Under every probe we ran, the router direction is token-bound and non-transferable (largely answer-readout in Gemma, pair-specific in Qwen) rather than an abstract routing module. Test is modular; under these probes, route is not. --- ### A Comparative Study of Feature Selection Methods for EHR Diagnosis Codes in Opioid Use Disorder Prediction Authors: Zihan Ding, Yinan Liu, Tengfei Ma, Rachel Wong, Xia Zhao, Richard N. Rosenthal, Fusheng Wang Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.04180v2 Feature selection is a critical step in electronic health record (EHR)-based predictive modeling, where input variables are often high-dimensional, sparse, noisy, and redundant. Large feature sets not only increase computational burden and overfitting risk, but also make model interpretation difficult, leading to limited usefulness in clinical settings. In this study, we focus on diagnosis-related features and compare five feature selection paradigms for opioid use disorder (OUD) prediction: recurrence enrichment, NTK-motivated early gradient sensitivity, LightGBM-SHAP, Elastic Net, and large language model (LLM)-guided semantic selection. We use a unified preprocessing and evaluation framework and assess each method by downstream predictive performance, resampling stability, and representation of infrequent diagnosis codes. Our results demonstrate that performance improves with larger feature budgets with diminishing returns beyond a moderate size. NTK sensitivity provides the best overall balance of accuracy and stability, and LLM-guided selection contributes complementary clinically meaningful signals despite lower standalone performance. --- ### A Comparative Study of Feature Selection Methods for EHR Diagnosis Codes in Opioid Use Disorder Prediction Authors: Zihan Ding, Yinan Liu, Tengfei Ma, Rachel Wong, George Leibowitz, Benjamin Littenberg, Xia Zheng, Richard N. Rosenthal, Fusheng Wang Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.04180v1 Feature selection is a critical step in electronic health record (EHR)-based predictive modeling, where input variables are often high-dimensional, sparse, noisy, and redundant. Large feature sets not only increase computational burden and overfitting risk, but also make model interpretation difficult, leading to limited usefulness in clinical settings. In this study, we focus on diagnosis-related features and compare five feature selection paradigms for opioid use disorder (OUD) prediction: recurrence enrichment, NTK-motivated early gradient sensitivity, LightGBM-SHAP, Elastic Net, and large language model (LLM)-guided semantic selection. We use a unified preprocessing and evaluation framework and assess each method by downstream predictive performance, resampling stability, and representation of infrequent diagnosis codes. Our results demonstrate that performance improves with larger feature budgets with diminishing returns beyond a moderate size. NTK sensitivity provides the best overall balance of accuracy and stability, and LLM-guided selection contributes complementary clinically meaningful signals despite lower standalone performance. --- ### TriCLE: Tri-Modal Vision-Language Reasoning for Edge-Deployed Fine-Grained Clustering Authors: Kishor Datta Gupta, Md. Mahfuzur Rahman, Fahad Rahman, Ahmed Rafi Hasan, Faysal Mehrab Chowdhury, Mohd Ariful Haque, Roy George Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.04175v1 Edge platforms used for aerial observation must interpret aircraft imagery under limited memory, limited compute, and intermittent connectivity. This setting is difficult for standard RGB-only recognition models and general-purpose vision-language models, especially when calibrated thermal and LiDAR aircraft data are unavailable. We present TriCLE, an application-oriented tri-modal vision-language system for aircraft taxonomic grouping under edge constraints. From a single RGB aircraft image, TriCLE generates a structure-preserving FLIR-style thermal view and a pseudo-LiDAR depth projection, then fuses the aligned views with task instructions in a compact Qwen3-VL backbone. The model is aligned to an expert aircraft taxonomy based on propulsion, airframe family, size, design era, and configuration, so its outputs reflect engineering-relevant similarity rather than only surface appearance. We evaluate supervised fine-tuning, rotation-preserving SFT, and three policy-alignment strategies: GRPO, GSPO, and DAPO. Sequence-level GSPO gives the strongest validation performance, reaching 88.33\% validation accuracy and 0.91 weighted F1 on valid aircraft outputs. On a held-out aircraft test partition, GSPO achieves 78.00\% accuracy and 0.793 weighted F1 while preserving 94.00\% parseable output formatting. After 4-bit quantization and attention-memory optimization, the aligned 4B model fits an 8GB deployment target and processes each tri-modal triplet in 1.48 seconds. These results support TriCLE as a practical prototype for interpretable, edge-feasible aircraft grouping, while emphasizing the need for further validation on real aligned thermal and LiDAR sensor streams. --- ### TS2TabPFN: Time Series Classification and Extrinsic Regression through Feature Extraction and a Tabular Foundation Model Authors: Gabriel da Costa Merlin, Diego Furtado Silva Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.04174v1 Time series data are ubiquitous in practical applications, where classification (TSC) and extrinsic regression (TSER) have emerged as essential tasks for obtaining value from temporal sequences. While the literature has seen significant progress through feature-based and deep learning models, existing methods often focus either on the quality of feature extraction or on the intrinsic predictive power of complex architectures applied to raw data. This division creates a gap between the control offered by feature engineering and the automated performance of end-to-end models. This paper proposes TS2TabPFN, a framework that bridges this gap by integrating explicit feature extraction with TabPFN 2.5, a cutting-edge foundation model for tabular data, to leverage its predictive capabilities. Our extensive experimental evaluation demonstrates that TS2TabPFN significantly outperforms state-of-the-art models in TSER tasks with statistical significance, providing a robust and efficient alternative for TSC and surpassing most of the currently best-performing algorithms. These results suggest that combining foundation models with structured features overcomes single-paradigm limitations, establishing a new time series state-of-the-art. --- ### Understanding Fault Tolerance of Adversarially Robust Pruned Models Authors: Manali Dangarikar, Cory Merkel Published: 2026-08-04 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2608.04173v1 Deep neural networks (DNNs) deployed on resource-constrained neuromorphic hardware face three concurrent challenges: the need for model compression through pruning, vulnerability to adversarial input perturbations, and susceptibility to hardware-induced weight faults such as stuck-at-zero errors. While each of these factors has been studied in isolation, their combined effects on model reliability have received little attention. This paper presents an empirical investigation of how pruning, adversarial training, and hardware fault injection interact to affect the robustness of convolutional neural networks. Using a compact three-layer CNN trained on MNIST, we conduct three experiments: (1) comparing the fault tolerance of naturally and adversarially trained models under simultaneous hardware faults and adversarial attacks, (2) evaluating how pruning affects adversarial robustness, and (3) characterizing the joint accuracy surface across fault rates, adversarial perturbation magnitudes, and pruning levels. Our results show that adversarial training improves robustness against input perturbations but increases sensitivity to stuck-at-zero weight faults. Contrary to intuition, pruning did not significantly increase fault sensitivity, and varying the pruning level had little effect across fault rates and attack strengths. These results highlight the need to jointly consider adversarial robustness and hardware reliability. --- ### Visualizing Graph-to-Answer Mechanism Recovery in Materials-Science Hypothesis Generation Authors: Shashwat Sourav, Subhadeep Pal, Markus J. Buehler, Sanjay Das, Fiona Y. Wang, Dominik Soos, Tirthankar Ghosal Published: 2026-08-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.04170v1 AI co-scientists can generate fluent materials-science hypotheses, but fluency does not show that an answer preserves a scientifically meaningful mechanism. We present a graph-to-answer mechanism-tracing case study for Graph-PRefLexOR-8B, a Qwen3-8B model adapted to expose distinct stages for brainstorming, graph construction, pattern extraction, and synthesis. We organize semantic backtracking, graph corruption, activation-based recovery measurements, and layer-by-token-region grids into a visual diagnostic workflow for inspecting this pathway. Across 100 open-ended materials-science questions, final answers remain closest to the model's own structured stages, especially synthesis. Under graph corruption, a full sweep over 37 residual-stream checkpoints, the embedding output and 36 transformer blocks, shows little mechanism recovery in the earlier transition region at layers 7--10, recovery instead concentrates in late synthesis and answer-start regions around layers 30 and 36. The workflow is intended to help scientists and model developers identify where a generated hypothesis loses or regains mechanism support before it is passed to downstream experimental planning. --- ### Mind the Cap: Output-Budget Regimes Change the Measured Multilingual Reasoning Gap Authors: Ankit Goyal, Jaideep Ray Published: 2026-08-04 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.04160v1 Multilingual evaluations report accuracy at a single output-token cap, but languages need different numbers of tokens to express the same content, so the cap is a hidden experimental variable. We test whether the native-vs-translate gap on MGSM (German, Thai, Swahili) is a token-budget artifact for Qwen3-8B and Llama-3.1-8B-Instruct under four prompting strategies. The measured gap swings by up to 57 points across budgets, length normalization moves it by up to 38.9 points where the cap binds, and at tight caps normalization can reverse which strategy scores higher. We prospectively froze the sweep's three Qwen peaks and its near-zero value at 1024 and evaluated them on 540,000 independently hard-capped decodes: a second frozen family of six Holm-corrected tests rejects every null. The frozen test at $B^*=1024$ still fails to reject because native accuracy has already saturated there; above saturation, the residual difference is a strategy-performance gap, not an identified reasoning deficit. The same truncation channel prices a cost-ordered adaptation ladder: a cross-fitted Thai vocabulary extension closes 0.0 points of the gap at the frozen budget and 4.9 points where 19% of traces still truncate. A third frozen family varies only the announced budget at a fixed enforced cap; announcing 128 rather than 2048 tokens moves Thai native accuracy by 5.1 points, so accuracy is not a function of the enforced cap alone. A correct-emission timing identity computed from one long-cap run matches the three pre-specified MGSM peaks to 0.65 points and, in an exploratory Qwen-only analysis of three further benchmarks, tracks held-out items to 0.92 points, locating the peak exactly in five of seven cells. Treat the output cap as an independent variable and report accuracy across the budget regime, not at a single budget. --- ### MINT: Tensor Decomposition on Stacked Recurrence Matrices for Time Series Data Mining Authors: Kaamil Kaka, Audrey Der, Evangelos E. Papalexakis, Zachary Zimmerman, Vikram Jayaram Published: 2026-08-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.04157v1 Recurrence plots are a time series data mining primitive applied to a variety of domains (e.g. star light curves, sound waveforms, CCT telemetry). This work proposes tensorized self-similarity matrices as a primitive for univariate time series datasets ($N\times n$) of $N$ time series of length $n$ with a subsequence window of length $m$, and whose tensor-based nature is naturally extensible to multivariate datasets. The proposed method to compute this primitive computes dot plots of size $N \times (n-m+1) \times (n-m+ 1)$ from these datasets, where the subsequent tensor is mined using tensor decomposition methods to mine for co-clustered patterns. We demonstrate our results in mass rapid transit, electricity demand, wind turbine, and car traffic data, finding the MINT pipeline effectively co-clusters cross-sensor patterns in highly regular datasets containing motifs at regular intervals. --- ### BrainBench: Benchmarking Large Language Models for Comprehensive EEG Understanding Authors: Yangxuan Zhou, Yuning Chen, Chen Wu, Jiquan Wang, Shijian Li, Gang Pan, Sha Zhao Published: 2026-08-04 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.04156v2 Electroencephalography (EEG) analysis extends beyond assigning predefined labels to recordings; it requires workflows connecting natural-language instructions, signal processing, quantitative evidence, and scientific interpretation. We term this capability \emph{comprehensive EEG understanding}. Existing evaluations, however, primarily target isolated decoding tasks or system-specific demonstrations, leaving the competence of large language models (LLMs) insufficiently quantified. We introduce \benchmarkname{}, a unified benchmark for comprehensive, instruction-conditioned EEG understanding. It comprises four subsets---Foundational Analysis, Sleep Assessment, Neurocognitive Assessment, and Physiological Integration---covering 17 datasets, \numcases{} tasks, and over \numinstances{} real-data instances. Given an instruction and EEG recordings with optional physiological signals, a system must perform the analysis and produce a scientifically grounded report and, when required, artifacts. Outputs are assessed through numerical, categorical, set, sequence, semantic, and artifact validation. We evaluate \nummodels{} representative LLMs across more than 100K executions under two paradigms: autonomous code execution with CodeAct and structured agentic analysis with BrainAgent. Results vary substantially across models, subsets, difficulty levels, and execution paradigms, showing that EEG competence depends on the model and its operationalization. \benchmarkname{} provides a reproducible testbed for advancing LLM-based EEG understanding. The code and benchmark will be released soon, with evaluation results continuously updated. --- ### BrainBench: Benchmarking Large Language Models for Comprehensive EEG Understanding Authors: Yangxuan Zhou, Sha Zhao, Yuning Chen, Chen Wu, Jiquan Wang, Shijian Li, Gang Pan Published: 2026-08-04 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.04156v1 Electroencephalography (EEG) analysis extends beyond assigning predefined labels to recordings; it requires workflows connecting natural-language instructions, signal processing, quantitative evidence, and scientific interpretation. We term this capability \emph{comprehensive EEG understanding}. Existing evaluations, however, primarily target isolated decoding tasks or system-specific demonstrations, leaving the competence of large language models (LLMs) insufficiently quantified. We introduce \benchmarkname{}, a unified benchmark for comprehensive, instruction-conditioned EEG understanding. It comprises four subsets---Foundational Analysis, Sleep Assessment, Neurocognitive Assessment, and Physiological Integration---covering 17 datasets, \numcases{} tasks, and over \numinstances{} real-data instances. Given an instruction and EEG recordings with optional physiological signals, a system must perform the analysis and produce a scientifically grounded report and, when required, artifacts. Outputs are assessed through numerical, categorical, set, sequence, semantic, and artifact validation. We evaluate \nummodels{} representative LLMs across more than 100K executions under two paradigms: autonomous code execution with CodeAct and structured agentic analysis with BrainAgent. Results vary substantially across models, subsets, difficulty levels, and execution paradigms, showing that EEG competence depends on the model and its operationalization. \benchmarkname{} provides a reproducible testbed for advancing LLM-based EEG understanding. The code and benchmark will be released soon, with evaluation results continuously updated. --- ### TRNet: Learning with Topographic Priors for VHR Paddy Rice Mapping Authors: Kaiwen Xiao, Chunlong Fu, Liping Zheng, Yanfeng Su, Yuanhao Xi Published: 2026-08-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.04154v3 Mapping paddy rice from very high resolution (VHR) imagery in mountainous and hilly regions remains challenging because terrain variations alter optical appearance and increase confusion with visually similar vegetation. To address this issue, we propose TRNet for multimodal paddy rice segmentation using 0.5 m GaoJing 1 red green blue (RGB) imagery, a 5 m TanDEM X digital elevation model (DEM), and derived slope information. TRNet employs separate visual and terrain encoders to preserve modality specific representations. At an early encoder stage, the proposed Topographic Energy Spectral Rectification (TESR) performs terrain conditioned low frequency modulation and asymmetric high frequency regulation to suppress steep slope clutter while selectively enhancing rice related cues on compatible low slope regions. The Topography Guided Paddy Structure Decoder (TPSD) further integrates semantic, rice background boundary, and interior cues with coarse topographic context to refine structural predictions. Experiments are conducted on an Area A internal test set and a geographically held out Area B with steeper terrain and lower rice prevalence. TRNet achieves Rice IoU scores of 85.10% and 80.68% on Areas A and B, outperforming the original Dual Encoder U Net by 9.15 and 18.83 percentage points, respectively. Without any adaptation, evaluation on matched August 2024 imagery retains Rice IoU scores of 82.04% and 76.12%. Extensive ablation, slope stratified, and cross year seasonal analyses demonstrate that the improvements arise from effective frequency rectification and structure learning, which reduce steep terrain false positives and low slope rice omissions. These results demonstrate that coarse topography can serve as a stable contextual prior for robust VHR paddy rice mapping. --- ### TRNet: Topography-Guided Frequency Rectification and Structure-Aware Decoding for Multimodal Paddy Rice Segmentation Authors: Kaiwen Xiao, Chunlong Fu, Liping Zheng, Yanfeng Su Published: 2026-08-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.04154v1 Mapping paddy rice from very-high-resolution imagery in mountainous and hilly regions is difficult because terrain alters optical appearance and increases confusion with visually similar vegetation. We present TRNet for 0.5-m GaoJing-1 red--green--blue (RGB) imagery, a 5-m TanDEM-X digital elevation model (DEM), and derived slope. Separate visual and terrain encoders preserve modality-specific features. At an early encoder stage, Topographic Energy-Spectral Rectification applies terrain-conditioned low-frequency modulation and asymmetric high-frequency regulation to suppress steep-slope clutter and conditionally enhance compatible low-slope rice cues. The Topography-guided Paddy Structure Decoder combines semantic, rice--background boundary, and interior cues, using coarse terrain as context. Experiments used an Area A internal test set and held-out Area B, which had steeper terrain and lower rice prevalence. TRNet achieved rice intersection-over-union (IoU) values of 85.10\% and 80.68\%, exceeding the original Dual-Encoder U-Net by 9.15 and 18.83 percentage points, respectively. Ablation and slope-stratified results linked these gains to frequency rectification, structure learning, and fewer steep-terrain false positives. The results support coarse topography as a contextual prior for very-high-resolution paddy rice mapping. --- ### Sublogarithmic Swap Regret in Multiplayer General-Sum Games via Hybrid Regularization Authors: Taira Tsuchiya Published: 2026-08-04 Categories: cs.GT, cs.LG arXiv: https://arxiv.org/abs/2608.04149v1 Swap regret governs the rate at which uncoupled learning dynamics converge to correlated equilibria in multiplayer general-sum games. Under full-information feedback, the best previous guarantee when every player follows the same dynamics grows logarithmically in the horizon $T$. We construct uncoupled dynamics under which every player incurs only $O(nm^2\sqrt{\log m\log T})$ swap regret, where $n$ is the number of players and $m$ bounds the number of actions per player. To our knowledge, this is the first sublogarithmic individual guarantee in this setting, and it implies that the time-averaged product distribution of play is an $O(nm^2\sqrt{\log m\log T}/T)$-approximate correlated equilibrium. The key algorithmic choice is to combine the Blum--Mansour reduction with optimistic follow-the-regularized-leader using a hybrid regularizer that separately weights negative Shannon entropy and the log-barrier: the entropy controls the optimistic prediction error, whereas the log-barrier controls the transition-matrix movement through its Bregman divergence. A new sensitivity theorem for stationary distributions of Markov chains, which involves neither mixing parameters nor the smallest transition probability, transfers this control to the played strategies and yields a simpler analysis without local-norm or self-concordance arguments. The guarantee is preserved by an adversarially robust variant that additionally ensures $O(nm^2\sqrt{\log m\log T}+\sqrt{mT\log m})$ swap regret against arbitrary utility sequences, and by a horizon-free variant that requires no prior knowledge of $T$. --- ### AgentForge: An Immersive Role-Playing Platform for Learning Agentic Software Engineering Authors: Zihan Fang, Yueke Zhang, Yu Huang Published: 2026-08-04 Categories: cs.SE, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.04148v1 Agentic AI is increasingly used to coordinate planning, implementation, review, and testing in software development, yet it often offers limited transparency into its decisions and interactions. Many such systems also assume that users can effectively guide the AI's decisions and validate its outputs. This assumption poses a particular challenge for novices, who must simultaneously learn how agentic AI works, how to collaborate with it effectively, and how to evaluate its outputs critically. To address this challenge, we present \textit{AgentForge}, an immersive learning system in which novices take on one of four software-engineering roles: Task Planner, Patch Author, Code Reviewer, or Test Runner, within a multi-agent code-repair workflow. In each practice session, the novices perform their chosen role while AI agents perform the remaining three. Through role-based scaffolding and metacognitive support, AgentForge clarifies role-specific responsibilities, makes agent coordination and intermediate artifacts visible, and encourages novices to monitor and evaluate their decisions. In a study with 37 novice developers, participants achieved high task-completion rates with AI-agent support. However, interaction demands differed significantly across practices: the Code Reviewer practice required more interaction turns, reroutes, and completion time ($p_{\mathrm{adj}} = .004$) and was perceived as the most challenging. Participants nevertheless reported significant gains in their understanding of software repair and agent collaboration ($p_{\mathrm{adj}} < .001$). These findings suggest that AgentForge can help novices develop practical software-engineering skills while learning to collaborate with agentic AI more critically and effectively. --- ### LiNC: Lightweight Noise Correction via Per-Sample Trust and Gaussian Mixture Modeling Authors: Abhishek Moturu, Babak Taati, Anna Goldenberg Published: 2026-08-04 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.04147v1 Label noise is common in medical imaging datasets due to factors such as inter-rater variability, annotation errors, and ambiguous cases. This can severely undermine the reliability and clinical effectiveness of machine learning models trained using those datasets. To address this challenge, we introduce Lightweight Noise Correction (LiNC), which adds a single trainable trust parameter per training sample and learns when to use the observed label and when to defer to the model during a standard training loop. The key idea is to train using a convex combination of the observed label and the model's own predictive distribution, controlled by a per-sample trust parameter. We show that the gradient of this objective drives trust values in opposite directions for clean versus noisy samples in the early training phase, yielding separable trust distributions. We use a 3-component Gaussian Mixture Model over the trust values to separate them into clean, ambiguous, and noisy cases and then execute a short soft-correction phase on the noisy cases and a final hard correction phase. Experiments on ten 2D datasets from MedMNISTv2 under label noise of up to 50% show consistent gains in accuracy and strong mislabel detection. LiNC adds negligible asymptotic overhead: the training-time complexity remains dominated by the base network, with additional memory growing linearly with the size of the training set. --- ### Neighborhood-Aware Dual Biomedical Entity Linking Authors: Yicheng Tao, Jie Liu Published: 2026-08-04 Categories: cs.IR, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.04144v1 Biomedical entity linking grounds mentions in clinical and scientific text to entities in a curated knowledge base (KB) with ontological structure, which supports downstream applications such as literature-scale information extraction and patient-record normalization. The task has several challenges at once: the KB contains large numbers of entities, mentions are often ambiguous, and gold labels follow annotation conventions specific to each corpus. To address these challenges, we propose PILOT, a three-stage framework made up of neighborhood-aware retrieval, dual reranking, and score fusion. The retriever injects ontological structure from both the query and KB side, by reformulating mentions and pooling entity embeddings. The retrieved pool is then scored from two complementary views, one over surface forms and one over context, and fused together. PILOT achieves the state of the art on average across five widely-used benchmarks and remains efficient at inference. --- ### InvFlowFD: Reference-Free and Background-Set-Free Perceptual Music Quality Metric with Flow Matching Inversion Authors: Alon Ziv, Harel Pogoda, Yossi Adi Published: 2026-08-04 Categories: cs.SD, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.04142v1 Existing reference-free methods for evaluating music perceptual quality alleviate the need for paired noisy-clean data, but they still rely on a background set, which is used to compute aggregated statistics of clean audio samples. In this work, we propose a novel approach that eliminates this requirement, achieving background-set-free and reference-free quality estimation using only a pre-trained Flow Matching backbone. We demonstrate that unconditional Flow Matching inversion via simple Euler integration is sufficient to detect various artificial distortions and accurately rank music generation models against human perceptual judgments. We introduce InvFlowFD, which performs flow inversion and compares a group of inverted samples to the prior distribution. We evaluate our method against prior work, quantitatively and with a thorough human study. Results suggest that InvFlowFD is highly correlated with human perception of sound distortions, as well as generative models' quality, while being more flexible and less restrictive than existing metrics. --- ### RUTA: Principled Visual Token Allocation via Rate-Utility Optimization Authors: Jian Zou, Xiaoyu Xu, Zhihua Wang, Yilin Wang, Balu Adsumilli, Kede Ma Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.04132v1 High-resolution images and long videos provide vision-language models with rich context for multimodal reasoning and fine-grained perception, but the resulting long visual token sequences make large language model-side computation and memory costly. Existing visual token reducers often operate at prescribed rates, while recent methods adapt token counts across inputs using method-specific learned thresholds or importance predictors. We introduce RUTA, a principled Rate-Utility Token Allocation method that performs pre-LLM reduction by jointly learning which tokens to retain and how many to allocate to each image-query pair. RUTA constructs query-conditioned candidate tokens and predicts a retention probability for each candidate. During training, these probabilities parameterize independent Bernoulli gates, while their sum provides a differentiable training-time estimate of the token count for each pair. Retained tokens serve as anchors that aggregate information from non-retained tokens according to semantic affinity and spatial proximity. RUTA is optimized with a penalized rate-utility objective that balances downstream task loss against expected token usage. Averaged across five benchmarks and measured relative to each backbone's full-token baseline, RUTA uses only $2.0\%$ and $4.2\%$ of visual tokens while preserving $88.2\%$ and $94.4\%$ of task performance on LLaVA-NeXT-7B and Qwen3-VL-8B, respectively. --- ### Radar4D-VLM: Proposal-Grounded Temporal 4D Radar Reasoning Across Frozen Language Models Authors: Jiaju Han, Xuemeng Sun, Qike Zhang, Xiang Chen, Luwei Yang, Jiahuan Long, Yiwei Wei, Jiujiang Guo, Chengyin Hu Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.04130v1 Vision-language models for autonomous driving primarily rely on cameras and LiDAR, leaving 4D radar largely unexplored as a standalone perceptual modality despite its robustness to adverse visibility and direct measurement of radial velocity. We introduce Radar4D-VLM, a radar-only temporal vision-language model that reasons from ten consecutive 4D-radar point-cloud sweeps without camera or LiDAR input. Radar4D-VLM extracts geometrically grounded object proposals and organizes radar evidence into a compact hierarchy of object, scene, and kinematic tokens. A parameter-efficient projector maps these tokens into frozen language backbones, while auditable prediction heads jointly model object count, spatial distribution, motion state, collision risk, semantic category, and radial velocity. Radar4D-VLM combines proposal-grounded temporal object tokenization, global scene context, and explicit kinematic tokens within a unified frozen-backbone interface. On sequence-isolated K-Radar development validation, its Top-64 proposal recall reaches 98.13% at 4 m, exceeding fixed-lattice and uniform-random controls by 6.40 and 22.83 percentage points, respectively. We further evaluate 24 matched runs spanning eight frozen Qwen, Phi, Mistral, Llama, and Gemma backbones under an identical adaptation budget. The radar-token interface remains compatible across all five language-model families, while matched aligned, permuted, and no-language controls show sensor dependence but no stable direct-head gain from aligned language supervision. These results establish a reproducible foundation for radar-only multimodal scene and motion reasoning while separating interface compatibility from the benefit of language supervision. --- ### Teaching Foundation Models to Read mmWave: Pose-Guided Kinematic Representation for Human Behavior Understanding Authors: Duo Zhang, Zhehui Yin, Zhiyun Yao, Haotong Qin, Xusheng Zhang, Hongliu Yang, Jianyu Sun, Junzhe Wang, Zizhou Fan, Michele Magno, Daqing Zhang Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.04127v2 Large language model agents need to perceive human behavior in physical environments. Millimeter-wave (mmWave) radar provides a privacy-friendly and contactless sensing modality, but radar observations are difficult to align with language. Existing radar-language methods often rely on synthetic data or lack explicit supervision for human body structure and motion. We present mmMind, a radar-language model that uses synchronized 3D pose as training-only supervision. A spatio-temporal radar encoder is pretrained to capture body configuration and motion dynamics, after which the pose head is removed so that inference requires radar alone. The learned radar representations are then aligned with an LLM for behavior captioning and spatio-temporal question answering. We also introduce mmMind-Bench, a real-world mmWave-language benchmark containing 17.9 hours of recordings from 23 participants across seven indoor environments. Experiments on captioning, question answering, and unseen-action generalization show that mmMind consistently outperforms existing radar-language baselines, while ablations confirm the importance of pose-guided pretraining. --- ### Teaching Foundation Models to Read mmWave: Pose-Guided Kinematic Representation for Human Behavior Understanding Authors: Duo Zhang, Zhehui Yin, Zhiyun Yao, Haotong Qin, Xusheng Zhang, Hongliu Yang, Jianyu Sun, Junzhe Wang, Zizhou Fan, Michele Magno, Daqing Zhang Published: 2026-08-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.04127v1 Large language model agents need to perceive human behavior in physical environments. Millimeter-wave (mmWave) radar provides a privacy-friendly and contactless sensing modality, but radar observations are difficult to align with language. Existing radar-language methods often rely on synthetic data or lack explicit supervision for human body structure and motion. We present mmMind, a radar-language model that uses synchronized 3D pose as training-only supervision. A spatio-temporal radar encoder is pretrained to capture body configuration and motion dynamics, after which the pose head is removed so that inference requires radar alone. The learned radar representations are then aligned with an LLM for behavior captioning and spatio-temporal question answering. We also introduce mmMind-Bench, a real-world mmWave-language benchmark containing 17.9 hours of recordings from 23 participants across seven indoor environments. Experiments on captioning, question answering, and unseen-action generalization show that mmMind consistently outperforms existing radar-language baselines, while ablations confirm the importance of pose-guided pretraining. --- ### Perception Before Reasoning: Dynamic Latent Reasoning for Video Understanding and Question Answering Authors: Haotian Xia, Zilin Xiao, Junbo Zou, Vicente Ordonez, Hanjie Chen Published: 2026-08-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.04124v1 Video question answering requires models to ground language queries in visual evidence and, when necessary, reason over that evidence across time. Existing methods typically rely on long textual chain-of-thought rationales, even though many questions can be answered as soon as the relevant object, action, or frame is localized. We propose Dynamic Latent Reasoning (DyLaR), which first grounds a question in a short block of perception latents (continuous hidden states that encode query-relevant visual evidence), and then adaptively decides whether to append reasoning latents (continuous thoughts that reason over this evidence in latent space) before answering. DyLaR learns this behavior by grounding perception latents in verified visual evidence and distilling verified rationales into reasoning latents, followed by reinforcement learning that further refines when to reason. Across nine video benchmarks and four multimodal language model backbones, DyLaR improves average accuracy over same-backbone baselines while generating fewer than 20 tokens per query. On Qwen3-VL-4B, for example, DyLaR improves average accuracy over Qwen3-VL-4B-Thinking from 54.0 to 58.2 while reducing response length from 1,220.7 to 18.5 tokens per query. Ablations further show that grounded perception latents, rationale-supervised reasoning latents, and adaptive routing each improve accuracy. ---