# Research Papers — 2026-09 · bundle page 93 of 266 > Full-text markdown of papers #4601–4650 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/93 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/92.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/94.md) ### Learning from Mixed-Quality Deployment Experience for Robot Manipulation Authors: Yangang Ren, Yujie Yan, Zirui Li, Jiaming Guo, Di Zeng, Ji Tao, Lan Yu, Xuesong Tian, Chen Lv Published: 2026-09-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.29000v1 Robot policies deployed in real environments naturally accumulate mixed-quality experience, including successful executions, partial progress, and failures. Although these rollouts provide valuable information for further learning, directly incorporating them into imitation learning may reinforce undesirable behaviors, while offline reinforcement learning often suffers from unreliable value estimation under sparse rewards and limited data coverage. We consider a practical post-deployment setting where learning relies only on naturally accumulated autonomous rollouts, without additional human corrections or exploratory interaction. To effectively exploit such experience, we propose Predictive Action Chunk Learning (PACL). PACL first learns a predictive chunk-level critic that evaluates temporally extended action sequences and augments temporal difference learning with future latent prediction, providing richer supervision for long-horizon value estimation. The learned critic then converts chunk-level Q-values into discrete quality conditions, which guide a diffusion actor to learn jointly from these mixed-quality experiences without treating all behaviors as equivalent supervision. At inference, the actor generates multiple action chunks and the critic selects the highest valued candidate. Experiments across simulated and real-world robot manipulation tasks show that PACL consistently improves the pretrained policy and outperforms strong imitation learning and offline reinforcement learning baselines. --- ### Automatic Rank Allocation for Low-Rank Adaptation in Large Language Models via lp Regularization Authors: Zebang Xie, Chuanyang Zheng, Yik-Chung Wu, Yihang Gao Published: 2026-09-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.28998v1 Low-rank adaptation (LoRA) has become a popular parameter-efficient fine-tuning method for large language models. A key challenge in LoRA is how to determine the rank of each adaptation matrix, as rank directly controls its capacity and efficiency. Existing adaptive-rank methods typically allocate ranks according to manually designed importance scores, which are not directly derived from an optimization objective. In this work, we propose $\ell_p$-LoRA, a principled rank-allocation method based on $\ell_p$ regularization with $0<p<1$, which is a classical sparsity-inducing technique in signal processing and statistics. Specifically, we regularize the energy of each rank-one LoRA component, encouraging redundant components to vanish while preserving important ones. We derive the corresponding proximal subproblem and reduce the matrix optimization to a two-dimensional problem, leading to an implicit thresholding criterion for identifying redundant components. Experiments on natural language understanding and question-answering tasks demonstrate that the proposed method achieves competitive performance with existing LoRA baselines. --- ### Only What Was Seen: Observation-Gram Compaction of View-Dependent Appearance in 3D Gaussian Splatting Authors: Krzysztof Pietroszek Published: 2026-09-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28997v1 Most of the memory of a 3D Gaussian Splatting model holds spherical-harmonic colour coefficients, yet each Gaussian is seen only from the narrow cone of directions of the training cameras. We turn this into a distortion metric that other compressors can adopt: a per-Gaussian observation Gram matrix, accumulated from viewing directions and blending weights, is the exact first-order map from coefficient changes to squared image error and needs only the model and the camera poses. Under it, degree reduction becomes a closed-form projection that generalises truncation, degree allocation a Lagrangian rate-distortion problem, and vector quantisation the matrix-weighted Lloyd algorithm, of which Compressed3D's quantiser is the scalar case. Swapped into Compressed3D with everything else unchanged, the metric raises PSNR by +0.49 dB before fine-tuning, with SSIM and LPIPS following, and at matched rate still gains +0.32 dB without a single training image. A training-free stack built on the metric alone is 15% smaller than the image-free GSICO at equal quality on Mip-NeRF 360. --- ### Beneath the Scores: Rethinking Hallucination Evaluation for Video Understanding Models Authors: Shuzhi Gong, Fengze Sun, Yuansan Liu Published: 2026-09-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.28991v1 Video understanding is increasingly performed by multi-stage LLM agents that separate temporal grounding, visual observation, and reasoning. Yet these stages are typically evaluated on different benchmarks and distributions, making it difficult to determine where hallucinations originate. We first organize existing benchmarks around these stages and show that their scores provide inconsistent diagnostic signals: stronger stage-level performance does not reliably imply lower downstream hallucination, and even benchmarks targeting the same capability can disagree. We therefore introduce a causal stage-intervention protocol that overwrites individual stages while holding the downstream task fixed. Across 60,008 runs on three video-agent architectures, we find that grounding is the dominant source of downstream error, with roughly four times the causal impact of corrupting visual observations. Successful grounding depends primarily on locating the correct region rather than precise temporal overlap, explaining why standard mIoU metrics poorly predict downstream reliability. We further find that incorrect evidence is substantially more harmful than missing evidence. Finally, auditing existing benchmarks against these interventions reveals that their scores do not reliably predict causal cascade sensitivity and can fail under distribution shift. These results motivate intervention-based, stage-aware evaluation for trustworthy video agents. --- ### Personalized Korean Lipreading as Visual Speech Recognition: Transfer, Census and Adaptation on OLKAVS Authors: Se Un Park, Hakjun Kim, Taehoon Roh, Junyoung Park Published: 2026-09-24 Categories: eess.AS, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2609.28988v1 We present a personalized Korean visual speech recognition (VSR) system and quantify, on the nine-camera OLKAVS corpus, the gap between the population-level benchmark score and an individual user's error. A video-only Conformer initialized from English-trained weights attains 9.95 - 12.19% character error rate (CER) under the corpus protocol against the published 26.64, and 19.00 - 21.52 on unseen wording. Per speaker, CER spans 1.0 to 52.2%, with seen wording lowering CER by 7.0 - 9.0 points and professional delivery and spontaneous speech raising it by 8.5 - 10.5 and 12.7 points. A low-rank adapter with 4.6% of the parameters, trained on 4 to 29 minutes of the user's frontal video, lowers the CER of twelve high-error speakers by 2.13 to 3.58 points, transfers to every camera without loss, and keeps 85% of the full fine-tuning gain at 12% of its cost to other speakers. Cameras above the mouth plane add about six CER points as a constant offset that training on all views keeps small. --- ### CrossSafe: Towards Cross-Embodiment Latent Safety Filters Authors: Ihab Tabbara, Yuxuan Yang, Hussein Sibai Published: 2026-09-24 Categories: cs.RO, cs.AI, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2609.28984v1 Cross-embodiment learning has shown that a single model, such as a vision-language-action (VLA) model, can learn state representations and manipulation skills that can be applied across heterogeneous robots to accomplish various tasks. We hypothesize that the same holds for safety enforcement. The reasoning required to satisfy a safety constraint, such as detecting an obstacle, recognizing that it should be avoided, and selecting a safe abstract action, is largely shared across robots. What differs across embodiments is how the abstract safe action is realized: morphology, kinematics, and dynamics determine which actions are safe and feasible. Consequently, the same action can be safe for one robot and unsafe for another. This is especially important for generalist manipulation policies that operate in a common end-effector action space without explicitly capturing how safety depends on the robot's morphology and kinematics. We propose embodiment-conditioned safety filtering, in which a Hamilton-Jacobi reachability-based value function and its corresponding safety-maximizing policy are shared across robots. Using a morphology-aware latent representation of the robot and its environment, we perform Hamilton-Jacobi reachability analysis directly in latent space so that the learned safety concepts can generalize across embodiments while remaining explicitly conditioned on each robot's morphology and kinematics. We evaluate our approach across five bimanual robot embodiments and five manipulation tasks with whole-body collision-avoidance constraints. Our results show that a single policy, jointly trained across five manipulation tasks and four embodiments, exhibits zero-shot generalization to a held-out embodiment, reducing the nominal policy's collision rate. They also show that training using more embodiments improves generalization. --- ### Spectral Graph Neural Networks with Hermite Polynomials: A Comprehensive Study Authors: Shuang Wu Published: 2026-09-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.28979v1 We study spectral graph neural networks built from Hermite polynomials and propose HermNet, a simple model that combines a nodewise predictor with normalized Hermite propagation. Its sparse recurrence requires neither eigendecomposition nor a learned basis. We distinguish the basic model from optional coordinate calibration, response normalization and Gaussian derivative regularization. Hermite and other complete polynomial bases span the same degree-bounded filter space, but their coordinates can produce different optimization behavior under limited training budgets. We analyze this behavior through spectral signal energy, label sampling, changes in learned features and the bias--variance trade-off of regularization. Controlled synthetic experiments identify a regime in which plain HermNet outperforms matched polynomial-basis alternatives, including with a jointly trained nonlinear predictor. Curvature regularization further improves HermNet when the same functional penalty is available to every comparator. Fixed-predictor controls support the advantage under short training budgets, but longer training removes the plain-model lead. Matched real-data comparisons show accuracy deficits, and architectural and numerical studies identify further limits. Together, the analysis and experiments clarify when Hermite propagation is useful and how calibration and regularization affect its performance. --- ### Same Bit Width, Different Outcomes: Post-Training Quantization of Text-to-Speech Across Architectures Authors: Se Un Park, Yutae Kim, Junyoung Park Published: 2026-09-24 Categories: eess.AS, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2609.28974v1 Post-training quantization (PTQ) reduces the cost of on-device text-to-speech (TTS), but published evaluations cover one system or method. We evaluate PTQ across TTS architectures under one protocol with three core models, weight and activation ablations of eight more, and two held-out models quantized blind. Four-bit per-channel weights reduce UTMOS, a predicted mean opinion score, by 2.8 on Supertonic and 0.07 on Kokoro, and per-tensor scaling can cause severe degradation even at 8 bits. The same bit width yields different outcomes, because the sensitive component is model-specific and not reliably predicted from the model class. A staged ablation procedure identifies it, and per-layer GPTQ can restore it to within 0.1 UTMOS. Real int8 and int4 kernels reproduce the simulated ordering at hardware-dependent cost. On a Mac mini, a 4-bit weight kernel runs Supertonic at 0.60x the fp32 latency while int8 is slower, so each configuration requires validation on the target runtime. --- ### Cross-Country Code-Mixing for Generative Recommendation Authors: Yuan Gao, Hao Deng, Haibo Xing, Yi Xu, Lingyu Mu, Jinxin Hu, Yu Zhang, Xiaoyi Zeng Published: 2026-09-24 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2609.28972v1 Cross-country recommendation on modern e-commerce platforms is typically deployed with disjoint user and item ID spaces across markets, removing the shared anchors that conventional cross-domain methods rely on. Generative recommendation (GR) mitigates this by mapping items into a shared token space and training a unified model, but existing approaches keep behavior sequences strictly country-specific, so knowledge transfer occurs only at the parameter level and remains absent at the data level. Inspired by code-switching corpora in multilingual natural language processing, we propose CMRec, a cross-country GR framework that injects cross-country supervision at the data level via dual-constrained, context-aware code-mixing. CMRec first learns a shared semantic codebook from multi-modal content and behavioral co-occurrence across countries. It then uses this codebook to synthesize mixed-country sequences via token-level substitutions that satisfy both static (content) and dynamic (e.g., price, audience, popularity) constraints. Finally, it introduces a context-aware loss that reweights mixed samples according to their plausibility in the current sequence. Experiments on two real-world multi-country datasets and an online A/B test show that CMRec substantially improves recommendation quality in data-sparse countries while preserving performance in data-rich countries, achieving +1.77% advertising revenue and +2.64% orders on a large-scale e-commerce platform. --- ### Passive LWIR Hyperspectral Ranging via Transmittance Extraction and Distance Alignment Authors: Zhihe Chen, Chen Fan, Shuo Liu, Xiaolin Huang, Yunze He, Xiaofeng He, Lilian Zhang Published: 2026-09-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28967v1 Passive long-wave infrared (LWIR) hyperspectral ranging enables distance estimation in low-light and nighttime scenes by exploiting atmospheric absorption features in thermal radiance received through the atmosphere.Joint estimation of temperature, emissivity, and distance is computationally expensive. Reference-range joint inversion also uses a distance-invariant effective attenuation coefficient, which can bias range estimates.We introduce transmittance extraction and distance alignment (TEDA), which decouples range estimation from temperature--emissivity inversion. In the first stage, a baseline estimator with a data-fidelity term invariant to the known absorption direction yields two closed-form smoothing branches for the slowly varying thermal continuum. An observation-derived gate combines the branches, and subtracting the blended baseline in the log domain recovers atmospheric transmittance. The second stage estimates range by matching the recovered transmittance to sensor-domain transmittance models recomputed for each candidate distance. Monte Carlo simulations show that TEDA effectively reduces the ranging bias caused by the distance-invariant attenuation coefficient approximation. In a measured scene, TEDA's mean range estimates are closer to the LiDAR medians than those of reference-range joint inversion in both evaluated patches. TEDA processes a complete $256\times256$ region of interest in 8.19~s versus 159.47~s for reference-range joint inversion, an approximately 20-fold speedup. --- ### Back to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning Authors: Xincheng Yao, Haobo Fu, Weiming Liu, Chongyang Zhang Published: 2026-09-24 Categories: cs.AI, stat.ML arXiv: https://arxiv.org/abs/2609.28963v1 Group-based reinforcement learning (RL) methods, such as GRPO and its variants, have become a leading paradigm for training reasoning and agentic large language models (LLMs). While their group-normalized advantage estimation is reliable at the response level, it becomes systematically biased at the step level, since coarse-grained trajectory-level advantages are hard to accurately reflect the contribution of individual steps (i.e, failed trajectories may contain valuable steps). Revisiting the foundational RL definition, we notice that GRPO's success on single-turn tasks stems from its advantage estimation strategy, which adheres to the basic definition: the mean reward of multiple actions sampled from the same state constitutes a credible state-value estimate. Extending the faithful estimation to step-level would in principle demand sampling multiple actions from each intermediate state, which is too costly on a per-state basis. To mitigate this issue, we propose a Graph-based Faithful sTep-level credit-assignment framework (GRAFT) that grafts all rollout trajectories into a trajectory graph, recovering node state-values via Bellman iteration on the graph, and assigning credit to each edge by the node value difference. Theoretically, the estimated step-level advantage faithfully adheres to the basic advantage definition in RL. To further ensure the reliability of step-level advantage estimation, we further propose Graph GAE, which extends GAE to the trajectory graph for reducing the impact of state-value estimation bias. Experiments across a range of multi-turn agentic benchmarks show consistent gains over GRPO and superior performance compared to recent agentic RL algorithms. Code will be available at https://github.com/xcyao00/GRAFT. --- ### MoVISA: Multi-Token Reasoning for Video Object Segmentation Authors: Ruining Zhao, Ho Kei Cheng, Alexander G Schwing Published: 2026-09-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28956v1 Recent advances in video object segmentation with Multimodal Large Language Model (MLLM) reasoning have demonstrated the effectiveness of using a single textual token, such as SEG, to predict segmentation masks across images and videos. However, we observe that this single-token strategy lacks the granularity required to precisely localize multiple objects across time in video segmentation tasks. To address this limitation, we develop Multi-Token Reasoning for Video Object Segmentation, or MoVISA. MoVISA uses multiple segmentation tokens, such as SEG0 and SEG1, to represent an object across different frames. This design enables more fine-grained alignment between language prompts and spatio-temporal mask predictions, improving both performance and interpretability. On the challenging MeViS, DAVIS17, ReVOS, and Ref-Youtube-VOS benchmarks, our model achieves a 13.2 percent J and F improvement on MeViS and an 8.4 percent J and F improvement on ReVOS. Code and models will be released. --- ### Exploiting Target Knowledge from MLLMs for Robust Few-Shot Segmentation Authors: Yijun Hu, Heng Fan, Libo Zhang Published: 2026-09-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28949v1 Few-shot segmentation (FSS) aims to segment unseen object categories with a few (e.g., one or five) labeled examples, enabling efficient adaptation to novel classes. Conventional models typically rely on appearance-based visual matching between support and query images for segmentation. While straightforward, these methods often struggle to handle significant appearance discrepancies and occlusions in the query image due to insufficient target knowledge. To mitigate this, we introduce a novel framework that mines target knowledge using the strong reasoning capacity of Multimodal Large Language Models (MLLMs) and employs it to enhance FSS. Specifically, building on SAM 2, our method, named MK-FSS, exploits two forms of complementary knowledge derived from a query image by an MLLM for FSS, including spatial knowledge, which provides a spatial prior indicating the potential target location, and semantic knowledge, which describes the target using text. The spatial knowledge is first encoded into a memory representation, and then resulting memory is integrated with the support-guided memory feature from query image through a carefully designed dual-memory debate-fusion (DMDF) module, yielding a more robust target memory feature. In parallel, the semantic knowledge is encoded into the textual feature, which is fused with multi-scale query features via a progressive cross-modal prompt generator (PCPG), producing a target-aware multimodal prompt for segmentation. Working together, the dual-memory feature and the multimodal prompt provide a comprehensive representation of the target, enabling more robust segmentation. In our extensive experiments, MK-FSS shows promising results and largely surpasses existing methods. Code will be released. --- ### Why Does Misinformation Propagate Faster? An Algorithmic Perspective on X Authors: Pan Li, Shuang Gao Published: 2026-09-24 Categories: cs.SI, cs.LG, econ.GN arXiv: https://arxiv.org/abs/2609.28947v1 Misinformation is widely reported to propagate faster on engagement-based platforms, yet prior work largely focused on empirical analysis, without identifying a specific algorithmic mechanism that results in this phenomenon. Thanks to the open-sourcing of X's recommendation algorithms, we conduct what is, to our knowledge, the first component-level study of the recommendation algorithm deployed by a social media platform, which examines how each of its components affects misinformation propagation. Specifically, we identify the engagement fungibility mechanism in the algorithm, where the final recommendation score is constructed as a weighted sum of all predicted user activities. As a result, a tweet can be repeatedly recommended simply because it is predicted to draw many instant reactions (e.g., likes and retweets), even when it is not expected to draw thoughtful responses (e.g., replies and quotes). Since misinformation typically draws a larger share of its engagement from instant reactions, this mechanism enables it to receive more recommendation exposure and to propagate faster. To empirically validate this mechanism, we re-implement X's recommendation algorithm on the USC X 2024 election corpus, and build a calibrated simulation study to analyze the impact of different scoring rules. We find that re-tuning the metric weights has little or even a negative impact on reducing the credibility exposure gap, while those scoring rules that set a precondition of thoughtful engagement for amplification would be able to alleviate the gap significantly, across 46 robustness checks. Our diagnosis, therefore, yields a simple and deployable fix, a reflective-threshold gate that withholds amplification until a tweet is predicted to draw thoughtful engagement, which we find to reallocate exposure away from low-credibility content at no cost to mainstream exposure and with no loss of engagement. --- ### From Static Personal Values to Contextualized Personalization: Bayesian Personalized Value Alignment for LLMs Authors: Hanze Guo, Aixuan Song, Jing Yao, Xiangxu Zhang, Xiaoyuan Yi, Xing Xie, Xiao Zhou Published: 2026-09-24 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.28942v1 Personalized value alignment has become increasingly important as large language models (LLMs) are expected to accommodate diverse user preferences. However, existing methods typically align model outputs with a static value profile across prompts, overlooking that the salience of value dimensions varies substantially across contexts. Inspired by Lewin's Field Theory, which views human behavior as jointly shaped by personal dispositions and situational constraints, we model personal values as priors and context-dependent preferences as posteriors. We propose BaCVA, an inference-time Bayesian Context-aware personalized Value Alignment method that approximates posterior personalized preferences by integrating static personal values with scenario-specific value salience. BaCVA first estimates contextual value salience from generally normative responses, and then employs a dual-view personalization module to infer posterior preferences from complementary personal-value and scenario-driven perspectives. This Bayesian formulation enables more accurate and adaptive personalized value alignment while improving data efficiency via prior values. Extensive experiments on benchmarks demonstrate its superiority over strong baselines. --- ### Calibrated Decision Models for Autonomous Penetration-Testing Harnesses: JEV and Laya as System One Decision Layers for LLM-Driven Pentest Agents Authors: Joas Antonio dos Santos Barbosa Published: 2026-09-24 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2609.28940v1 Autonomous penetration-testing harnesses use large language models (LLMs) for reconnaissance, exploitation, and reporting, but often rely on those same models to confirm findings, grade severity, and select agents. This can lead to false positives, inflated severity, and wasted compute. We examine how System One decision models, lightweight non-generative classifiers that return typed, calibrated verdicts, can support these decisions. We make five contributions. First, we define four decision points: finding adjudication, severity recalibration, agent pruning, and confirmation loops. Second, we present an exploratory NeuroSploit case study comparing one run with TypeSafe System One (Jev) and one without it against a web target containing 13 vulnerabilities. Differences in severity distribution, runtime, and grading by exposed data type motivate the architecture but do not establish statistical significance. Third, we review published specifications for Jev, Jev-Ultrafast, and the open-source Laya without assuming that results from other benchmarks transfer to penetration testing. Fourth, we discuss RLHF, RLAIF, RLCD, and RLHV as training approaches and their implications for trust in security decisions. Finally, we propose Rave, a domain-adapted System One model, and outline its training data, evaluation protocol, and potential effect on harness assurance. --- ### Response-state Learning for Transferable Vibrational Spectroscopic Characterization with Electron Prior Authors: Zetong Li, Zhuosong Xie, Hengyu Fan, Jiaao Yu, Qiyao Hua, Zheng Lu, Liming Xu, Juanni Wu, Honglin Li Published: 2026-09-24 Categories: cs.LG, physics.chem-ph arXiv: https://arxiv.org/abs/2609.28935v1 Vibrational spectral prediction can become inaccurate when localized stereoelectronic environments perturb intermediate response states and high-risk response units dominate characteristic spectral fingerprints, making prediction across external chemical space difficult. SO(3) Equivariant Neural Kalman Networks (SENK) form a response-state cascade that combines an equivariant transformer backbone for Hessian, dipole-derivative and polarizability-derivative learning, an Equivariant Neural Kalman bridge for state-dependent refinement and reliability sensing, and an NBO-informed electronic-prior pathway coupling consistency regularization with bounded, branch-specific guided spectral calibration. SENK outperforms DetaNet on QM9S and QMe14S while preserving full-spectrum IR and Raman fidelity from small molecules to drug-like systems. SENK remains stable and selectively improves spectrally sensitive features in biomolecular systems with complex stereoelectronic effects. It therefore integrates tensor prediction, reliability diagnosis and physics-informed calibration, supporting transferable vibrational spectroscopy from molecular systems to functional molecular materials. --- ### HelloWorld: Towards Practical Applications of Generative Driving World Models Authors: Fan Lu, Hanshi Wang, Zijing Wang, Quan Feng, Zhi Wang, Shijie Chen, Xianming Zeng, Yujian Zhang, Jiazhe Wang, Xin Zha, Kai Wang, Zhijie Zhao et al. Published: 2026-09-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28931v1 Driving world models provide a promising route toward scalable counterfactual data generation and interactive simulation beyond recorded driving logs. Realizing this potential requires a system that can generalize across diverse scenes, respond faithfully to prescribed controls, generate coherent multi-sensor observations, and operate efficiently under repeated inference. We present \textbf{HelloWorld}, a 2B driving world model system designed around these requirements. HelloWorld progressively specializes broad visual and motion priors from heterogeneous video data into controllable driving generation using ego pose, HD maps, and 3D boxes. A block-causal generation interface, together with adaptation to self-generated context, aligns the model with sequential simulation. The system further supports synchronized seven-camera RGB generation and conditional LiDAR synthesis, and is distilled toward few-step inference for efficient deployment. Experiments evaluate visual quality, control fidelity, cross-view consistency, robustness under repeated generation, inference efficiency, and LiDAR synthesis. Together, HelloWorld provides a unified framework for scalable driving data generation and interactive simulation. --- ### PlenoCI: Plenoptic CharacterIstics for View Dependence Aware Change Classification Authors: Jason Lai, Chamuditha Jayanga Galappaththige, Niko Suenderhauf, Dimity Miller, Donald G. Dansereau Published: 2026-09-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28930v1 Radiance field representations such as 3D Gaussian Splatting (3DGS) natively encode complex visual phenomena such as occlusions and view dependence, but they are inherently underconstrained. Independently optimized reconstructions converge to different primitive configurations, even in unchanged regions. We introduce Plenoptic CharacterIstics (PlenoCI), a novel feature built from the plenoptic field these representations approximate. PlenoCI directly captures rich visual behaviors while ignoring Lambertian textures. By deriving closed-form analytic plenoptic derivatives from a 3DGS representation, we efficiently detect these 5D structures. Our approach is robust to underconstrained representations by construction, reporting two orders of magnitude fewer false positives between independent reconstructions of unchanged scenes than concurrent work. We demonstrate PlenoCI's utility on change classification. First, we detect changes with an instance-aware 3DGS pipeline, achieving state-of-the-art results on CL-Splats with a 25.7% mIoU gain over the strongest competitor, while remaining competitive on the more challenging PASLCD benchmark. Leveraging PlenoCI, we classify changes as geometric or appearance-based with a balanced accuracy of 0.735, comparable to the best performing baseline. We believe plenoptic derivatives and PlenoCI open new directions for view dependence aware understanding in visually complex environments. Code and data are available at https://js0n-lai.github.io/plenoci. --- ### ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation Authors: Zichong Meng, Chongjian Ge, Chun-Hao P. Huang, Yang Zhou, Huaizu Jiang Published: 2026-09-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.28923v1 Few-step autoregressive (AR) video diffusion enables low-latency streaming generation, but existing post-training methods predominantly rely on Distribution Matching Distillation (DMD), requiring both a large pretrained teacher and an online critic to estimate distributional discrepancies through diffusion scores. In this work, we ask whether this resource-intensive teacher--critic stack can be eliminated by post-training only the generator against a precomputed target distribution. Drawing inspiration from representation distribution matching (RDM) for one-step image generation, we systematically study its transfer to few-step causal video generation and identify three key barriers: a memory-intractable gradient path, a distinct video optimization regime, and representation distributions that underconstrain temporal dynamics. We introduce ViRDM, a teacher- and critic-free video post-training recipe that addresses these barriers sequentially. By coupling RDM with stochastically truncated clean-exit supervision, a lightweight VAE decoder, and staged vector--Jacobian products, ViRDM makes representation distribution matching memory-feasible for multi-step causal video rollouts. We further establish effective generated-population and initialization regimes for video RDM, and introduce lightweight dynamics regularization to compensate for the underconstrained temporal dynamics. ViRDM turns three-network distillation into generator-only post-training, reducing GPU memory use and training time while improving video quality. With only 20 generator updates, the recipe reaches 84.87 on the official VBench evaluation, outperforming the previous best few-step causal baseline by 0.36, while requiring 16 A100 GPU-hours. We additionally report exploratory results demonstrating the potential of the same recipe for lower causal sampling budget and for one-, two-, and four-step bidirectional generation. --- ### PFArena: Benchmarking Language Models for Protein Modification Authors: Yawen Ouyang, Xinbo Zhang, Ziyuan Ma, Yixin Wu, Wenbin Liao, Feiran Zhang, Wenjie Li, Lihao Wang, Hao Wang, Xiaoqing Zheng, Xuefeng Yan, Lei Bai et al. Published: 2026-09-24 Categories: cs.AI, q-bio.BM arXiv: https://arxiv.org/abs/2609.28921v1 Protein modification requires navigating an immense sequence space, yet wet-lab validation remains low-throughput and costly. Although computational paradigms including protein language models (PLMs), large language models (LLMs), and LLM-based agents have shown promise in protein modification, their relative efficacy across realistic experimental decision-making settings remains unclear. To bridge this gap, we introduce PFArena, a benchmark comprising four controlled task interfaces that cover single-mutant generation and multi-mutant ranking. By providing varying levels of mutation fitness data, PFArena reflects four representative research scenarios characterized by differing degrees of prior experimental context. We assess six PLMs, six LLMs, and five LLM-based agents using complementary metrics to measure both peak and overall protein modification performance. Our evaluation reveals that model performance shifts systematically with the availability of target-specific experimental evidence: PLMs demonstrate proficiency in open-ended single-mutant generation by leveraging protein-specific priors, whereas LLMs and agents perform strongly in multi-mutant ranking, particularly when target-specific fitness data are available. Nevertheless, all model families face fundamental challenges with increasing search-space size and mutation depth. We release our code and benchmark suite to facilitate reproducible research in model-assisted protein modification. --- ### Harness Tokenomics: A Router for the Enterprise Agentic Control Plane Authors: Ted Kwartler, Alan Aqrawi, Arian Abbasi Published: 2026-09-24 Categories: cs.AI, cs.CR arXiv: https://arxiv.org/abs/2609.28919v2 Harnesses, the products that run AI coding agents, are multiplying, and enterprises are rolling them out to their employees. What started as pilots with a few hundred seats is now scaling to tens of thousands. Enterprises rarely build these harnesses and usually adopt the ones model vendors bundle with their seats and APIs, such as Anthropic's Claude Code or OpenAI's Codex. A harness decides which model answers, what the model reads, how the prompt cache is used and which subagents run, so it picks the rate on the price sheet and sets the volume bought at it. Enterprises that keep a proprietary or untuned harness at its defaults inherit these choices and their bill. We build a fast, customisable router in which Jev, a classifier with calibrated probabilities, labels every prompt against a bring-your-own taxonomy of agentic requests. One user turn is many requests over a prompt cache that belongs to one model, so the router moves work only where no running conversation has to rebuild its cache. It routes at session start, in side lanes and at subagent launch. From the price sheet we derive when a mid-task switch pays back. We also find a crossover, in which the highest-priced model costs less than the next tier on long tool-heavy sessions, and repricing about 10,000 real sessions from public datasets confirms it. In an emulated enterprise of 10,000 seats with user behaviour taken from these datasets, the router recovers 13 to 21% of model spend at Anthropic's list prices of 21 September 2026, \$3.3M to \$5.1M a year. The paper also maps the risks across twenty-one harnesses, prices the dependence on one vendor's models, and proposes a control plane that enterprises can run from within, starting now, with a ladder for deciding later whether to own the harness. --- ### On the Effectiveness of Kernel-Level Evidence for Agent Security Authors: Spencer King, Zhilu Zhang, Mikhail Kuznetsov, Kay Liu, Baris Coskun, Wei Ding Published: 2026-09-24 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.28915v1 LLM agents are deployed into infrastructure that grants them broad host authority, yet existing agent-security benchmarks and defenses operate almost exclusively at the application telemetry layer: the served tool manifest, the user prompt, and the model's messages. Some threats, however, smuggle malicious instructions and actions past the application boundary, leaving them invisible to that layer. In this work, we bridge that gap by pairing application-level agent telemetry with kernel-level syscall traces to present the first paired-evidence characterization of kernel-level versus application-layer signal for agent security. To quantify the value of the enhanced telemetry, we introduce Agent Cross-Layer Evidence (ACE), a paired-session corpus of 4,047 sessions and 17 threat models spanning six delivery-vector families and 14 of the 25 OWASP LLM and agentic threat categories, organized into 12 attack mechanics with per-mechanic characterization of where the most discriminative evidence lies. Across four distinct detector families, we find that kernel evidence is discriminative on its own and that composing it with application-layer evidence generally outperforms either single-layer view, revealing complementary signals that single-layer analyses can miss. We further demonstrate generalization to unseen attack families and transfer to an alternate agent runtime. Together, these findings establish the value of cross-layer evidence for agent security. --- ### Robots That Take Initiative: A Framework for Building and Evaluating Proactive Robots Authors: Maithili Patel, Sonia Chernova Published: 2026-09-24 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.28910v1 Effective robot assistance beyond narrow roles and repetitive tasks requires robots to be proactive - to decide what needs to be done rather than waiting to be told. While proactivity is increasingly explored, it lacks a unified formulation, and work in the domain is typically evaluated offline against static human models that cannot capture the effect of a robot's actions on the environment and the user's own behavior. We introduce a unified formalism for proactive robot assistance, organize it into three levels, and provide a framework to address the highest level of unprompted proactive assistance. We then show that offline evaluation overstates performance in this setting, and contribute a closed-loop evaluation with a human model that adapts to the robot. Finally, we present a method, GAP, that instantiates our framework, learning from passive observation to anticipate user goals and act. Under closed-loop evaluation, prior state-of-the-art methods collapse, in some cases adding more work than they save, while GAP remains robust and substantially outperforms them. --- ### Automatic Harness Evolution for Hardware Design Verification: Can LLMs Consolidate Gains Across Discovered Harnesses? Authors: Kidus Seyoum, Ajay Mittur Published: 2026-09-24 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2609.28908v1 Agent behavior depends on the harness surrounding a language model, but it remains unclear whether language models can reliably improve such harnesses for hardware-design tasks. We study automatic harness evolution around a fixed subject model on 12 proprietary design-verification root-cause localization tasks. Across five trials per task, automatically evolved harnesses increased completed attempts by 71-76% and any-hit task coverage by 80-100%, while total correct attempts improved by only 18-24%. The strongest success reproducible at least twice result improved by one task, and later candidates exchanged gains across tasks rather than preserving them. An auxiliary candidate improved on a four-task validation set excluded from search but tied its baseline on a subsequent 12-task replay containing both search and validation tasks, so the selected gain did not persist across the full pool. Across the tested lineage, useful search, evidence, and finalization behaviors appeared in different candidates but did not consistently consolidate into a single harness that dominated across tasks and metrics. In a separate CVDP cross-benchmark case study, an automatically evolved defined-width repair harness produced 35.6% more functional passes than its 142-task reference baseline; the final functional verifier scored completed outputs but was not shown to the subject agent during repair. These results support archive-aware selection when evolution yields complementary specializations without consistent consolidation. --- ### GeoDose-CP: Graph-Local Conformal Inference for Continuous-Treatment Earth Observation Authors: Md Khalid Hasan Sakib, Dristi Datta, Manoranjan Paul, Davina White Published: 2026-09-24 Categories: stat.AP, cs.LG arXiv: https://arxiv.org/abs/2609.28895v1 Reliable intervention-oriented uncertainty quantification from Earth observation (EO) remains challenging when continuous treatment shifts, spatial dependence, limited support, and satellite-outcome uncertainty must be addressed simultaneously. Existing causal, conformal, and spatial approaches address parts of this problem, but their direct combination does not generally recover the appropriate interventional reference law because candidate reassignment jointly alters treatment likelihood, standardized residuals, and graph-dependent residual likelihood. This study presents GeoDose-CP, a support-aware conformal framework for localized stochastic potential outcomes under continuous or mixed continuous-atomic treatment. Its central methodological contribution is a graph-local target-orbit law that jointly represents intervention-induced treatment shift, the inverse outcome-scale Jacobian, and spatial residual dependence. The framework further provides exact weighted candidate inversion, a scalable sparse approximation with explicit discrepancy accounting, and refusal under inadequate support. Evaluation used controlled known-truth experiments, MineDoseBench, treatment-density sensitivity analysis, external conformal comparators, and a multi-mine New South Wales (NSW) study. In MineDoseBench, GeoDose-CP achieved mean selective coverage of 0.9692 across 27 configurations and a minimum local q0.05 of 0.8951; exact-sparse auditing produced nine inclusion disagreements over 2,700 targets. In the NSW study, the absence of an auditable longitudinal rehabilitation treatment rendered treatment-dependent inference nonoperational rather than forcing inference through a proxy exposure. --- ### Broadening Uncertainty Estimation for Audio Question Answering Across Methods, Formats, and Inputs Authors: Aaron Isidore Grace, Weiran Wang Published: 2026-09-24 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2609.28879v1 Audio-language models can produce confident answers unsupported by the audio, motivating uncertainty estimates that identify unreliable responses. We compare probability-based, sampling-based, self-verification, evidential, and contrastive measures across four open-weight models and five audio QA benchmarks. In multiple-choice evaluation, first-token measures are strongest overall, with top-1 probability achieving a mean AUROC of .740, compared with .708 for ten-sample discrete semantic entropy, while requiring no additional model calls. Across four benchmarks, shifting from multiple-choice to open-ended evaluation lowers mean accuracy from 57.6% to 36.6%, yet uncertainty remains predictive of errors: semantic entropy, maximum token entropy, and semantic agreement achieve mean AUROCs of .697, .694, and .693, respectively. To test whether uncertainty reflects the evidence available to answer the question, we perform input ablations that remove either the audio or the question. Across top-1 confidence, entropy, and sampling-based measures, removing audio reduces error-detection AUROC by .101 on average, compared with .010 when removing the question. Together, these results establish efficient uncertainty baselines and show that uncertainty in audio-language models depends substantially more on available audio evidence than on question text. --- ### Learning New Words from Unlabeled Test Data in Automatic Speech Recognition Authors: Mengqi Wang, Mark A. Hasegawa-Johnson, Haolong Zheng, Chang D. Yoo Published: 2026-09-24 Categories: eess.AS, cs.CL arXiv: https://arxiv.org/abs/2609.28877v1 New words are invented every day. A human listener can learn a new word by hearing it clearly once and inferring its usage from sentence context. This paper proposes granting ASR a similar ability to learn the contextual representations and spellings of new words from unlabeled test data at test time. A frozen CTC acoustic model provides spellings, a frozen language model provides contextual evidence for out-of-vocabulary (OOV) word detection, and an adaptation module expands the vocabulary by learning the lexical token representations with distributions over CTC-generated candidates. The spelling model of each token is optimized by minimizing a Kullback-Leibler divergence (KLD) objective. We demonstrate that the CTC-weighted language model log likelihood ratio can be interpreted as the KLD between the unknown correct ASR and the unsupervised learned ASR, and that, using a Pinsker bound, the square root of KLD can be interpreted as an upper bound on the total variation distance between the true and estimated spelling of the unknown word. Experiments show relative OOV character-error-rate reductions of up to 14.97% on LibriSpeech and 6.67% on dysarthric Speech Accessibility Project data for recurring OOV words, relative to the corresponding rescoring system. --- ### Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents Authors: Liqin Ye, Haorui Wang, Fardin Ahmed, Rongzhi Zhang, Yuan He, Ziyuan Lin, Yanbin Yin, Jing Peng, Michael Galarnyk, Sudheer Chava, Chao Zhang Published: 2026-09-24 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.28876v1 We introduce Forecast-Dojo, a replayable environment for benchmarking and training LLM forecasting agents. It combines resolved prediction-market questions with dated news, allowing agents to research an event and revisit their predictions at successive historical dates. The same tasks and tools support repeated evaluation, collection of training interactions, and feedback from recorded outcomes without waiting for new events to resolve. Forecast-Dojo contains 1,568 Polymarket events, split by time into training and evaluation periods, and 18.8M dated news articles. In an evaluation of 12 models, research tools lower Brier score for all 12. Forecasts also improve as events unfold, with the largest gains at steps where more newly dated evidence is recorded. Every model still trails historical market forecasts in both Brier score and accuracy. A belief notebook carried between dates lowers research cost but does not consistently improve forecast quality. Beyond evaluation, Forecast-Dojo provides interaction trajectories and outcome feedback for agent learning, with supervised fine-tuning as a proof of concept. --- ### When Fancy Eviction Fails: Rethinking Cache Replacement For LLM Prefix Reuse Authors: Yiyu Liu, Minlan Yu, Juncheng Yang Published: 2026-09-24 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2609.28870v1 Long-running LLM applications repeatedly send growing context, making prefix caching critical for reducing prefill cost. Yet prefix-cache behavior under agentic workloads remains poorly understood. We study production traces from two companies and evaluate 14 eviction algorithms across HBM-constrained and large memory-pool settings. Despite a large gap to Belady, sophisticated policies designed for traditional caches provide little benefit over LRU. The reason is structural: prefix reuse is dominated by the regular pacing of active sessions, making recency unusually predictive. Prefix caching nevertheless introduces new challenges, including heavy-tailed session footprints and highly variable miss costs as attention computation grows with sequence length. We introduce the compute-savings ratio and two offline oracles to quantify these effects. Our results show that effective prefix-cache management should retain recency as its foundation while selectively adding quick demotion for one-hit prefixes, compute-aware partial eviction for expensive misses, and capacity-dependent eviction granularity. We will release the traces and simulator to support future research. --- ### Image Fidelity is Not Field Fidelity: Joint Thermodynamic Reconstruction and Error Localization in Neural Tomography Authors: Alan Hsu, Jenna Samra, Alin Razvan Paraschiv, Liam Connor Published: 2026-09-24 Categories: cs.LG, astro-ph.IM, astro-ph.SR arXiv: https://arxiv.org/abs/2609.28868v1 Neural fields for scientific tomography are optimized from 2D images, but the actual quantity of interest is often a latent 3D physical field. Because the forward map is many-to-one, low 2D image error need not certify a correct 3D field. Moreover, the latent field is not directly supervised during training, and its error cannot be evaluated against truth at deployment. We develop CoroNeRF to jointly optimize 3D electron density and temperature fields directly from multiview, multiline intensities through a differentiable atomic-emission renderer. Using solar coronal tomography as a controlled testbed, we evaluate physical-field recovery and test whether cross-seed instability provides a ground-truth-free-at-inference indicator of local physical-field error. We underscore the following two observations. (i) Image fidelity is not field fidelity: spectral ablations show that limited-channel reconstructions can fit their available observations well while recovering substantially worse fields, whereas evaluation on a common richer probe exposes the discrepancy. (ii) Cross-seed instability ranks local physical-field error across tested matched-model conditions, supported by sparsification and physical signal-strength controls. Seed-deviation projections provide complementary directional validation, but shared forward-model mismatch can still produce incorrect cross-seed consensus. These results characterize joint thermodynamic recovery and the usefulness and limits of seed-based error localization in a controlled, single-scene solar tomography testbed. --- ### Direction-Scale Decomposition in Action Representation: Rethinking What to Tokenize for Vision-Language-Action Models Authors: Yufei Duan, Hang Yin, Alberta Longhini, Chao Tang, Danica Kragic Published: 2026-09-24 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.28865v1 Action representation plays a central role in discrete-token vision-language-action (VLA) learning but remains underexamined. Under conventional pose-increment representations, action tokens are sensitive to execution speed and dataset-specific normalization, potentially obscuring geometric structure shared across demonstrations and datasets. We introduce Direction-Scale Decomposition (DSD), an action representation that decomposes translation and rotation increments into direction and scale components before tokenization. DSD isolates motion direction while retaining magnitudes in separate scale channels. We evaluate DSD with uniform binning (BIN) and BEAST, a B-spline-based tokenizer, in simulation and real-world manipulation under both single-dataset and mixed-dataset training. On LIBERO, DSD improves average success rates with both tokenizers. On SimplerEnv, DSD-BIN outperforms BIN by 10.3 percentage points in overall success rate under mixed-dataset training. Real-robot experiments further show gains both with and without robotics pretraining. These results support DSD as an effective action representation for discrete-token VLA models and suggest its potential to mitigate performance degradation when training on large and diverse dataset mixtures. Our project page with additional resources is available at https://vla-dsd.github.io/ --- ### Multimodal Routing and Region Refinement for Language-Guided Medical Image Segmentation Authors: Md Maklachur Rahman, Md Hasan Al Banna, Saraf Anjum, Assame Arnob, Tracy Hammond Published: 2026-09-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.28860v1 Textual descriptions can reduce ambiguity in medical image segmentation by specifying the finding and location to be delineated. Existing text-guided methods mainly improve where image and language features interact but generally retain a single learned update pathway across all image-text pairs. We propose MRSeg, a parameter-efficient framework that uses each image-text pair to route the adaptation of visual and textual features before dense prediction. Frozen ConvNeXt-Tiny and PubMedBERT encoders provide multiscale visual features and clinical text tokens. A joint router uses the deepest visual feature and pooled text to predict a sparse mixture over low-rank adapter bases. The resulting route is shared across separate adapter banks for two visual scales and text, coordinating their adaptation while keeping the feature-specific parameters separate. Region Bridge uses text-derived queries to aggregate dense visual tokens into latent regions, refines these regions through self-attention and text cross-attention, and redistributes the refined information back to the feature maps. Finally, a multiscale decoder combines refined semantic features with shallow image evidence. On QaTa-COV19 and MosMedData+, MRSeg achieves 90.90/83.32 and 81.53/68.82 Dice/mIoU, respectively, with 7.11M trainable parameters and 7.60 GFLOPs. Code: https://github.com/maklachur/MRSeg. --- ### Human-AI-Powered Hypothesis Testing: Cost-Aware Selective AI Scoring and Sequential Human Escalation Authors: Dae Woong Ham, Xuejun Zhao, Stefanus Jasin, Fenghua Yang Published: 2026-09-24 Categories: cs.AI, cs.IT, stat.ME arXiv: https://arxiv.org/abs/2609.28859v1 Large language models are increasingly used as inexpensive judges to evaluate outputs, label data, and assess whether a system meets a desired quality standard. Yet using AI judgments for formal statistical inference is fundamentally different from simply treating them as ground-truth labels: AI evaluations can be biased or noisy, and rigorous hypothesis testing requires explicit control of type-I and type-II errors. We study how to use AI judgments, together with selective human verification, to conduct a valid hypothesis test at minimum cost. We consider a population of items with hidden binary labels. After choosing a fixed pool of items, the decision maker can selectively query AI, send an item directly to a human, escalate an AI-scored item to a human after observing the AI report, or stop once sufficient evidence has accumulated. We derive an information-theoretic lower bound that captures the minimum cost of achieving prescribed testing errors and characterizes the value of AI information and human verification through a report-dependent information frontier. Motivated by this characterization, we develop SCALE, a sequential cost-aware policy that combines selective AI scoring with adaptive human escalation. SCALE is valid at finite sample sizes and matches the lower bound to first order as the target error probabilities vanish. We further extend the framework to an unknown AI-output model using paired AI-human pilot data. Numerically, SCALE approaches Human-only or AI-only testing when one source clearly dominates, while achieving its largest savings when inexpensive AI judgments and selective human verification are both valuable. --- ### When Should LLMs Trust Their Own Revisions? A Risk-Aware Study of Intrinsic Self-Correction Authors: Tianzhu Zhang Published: 2026-09-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.35832v1 Intrinsic self-correction asks a language model to revise its own answer without receiving new external evidence. A second pass can recover mistakes, but it can also overturn answers that were already correct. We study this trade-off across 29 open-weight LLMs on BoolQ, GSM8K, and Corr2Cause by tracking correctness transitions between initial and revised answers. Aggregate accuracy can conceal substantially different revision behavior: for example, Llama-3.1-8B improves by 25.5 percentage points on GSM8K, while refinement changes 19.1% of initially correct answers into wrong ones. A controlled BoolQ study further shows that refinement prompts shift the balance between recovery and harm. We then compare three runtime choices: keeping the initial answer, always accepting the revision, and selectively invoking revision using signals available after the initial response. The comparison identifies settings where learned gating is useful and others where a simpler unconditional policy performs better. These results suggest treating intrinsic self-correction as a revision policy rather than as a uniformly beneficial second pass, and evaluating it through both the corrections it recovers and the errors it introduces. --- ### Beyond the Context Window: An Adaptive Entropy-Based Routing Framework for Hybrid Retrieval and Long-Context Language Models Authors: Isaac Olufadewa, Miracle Adesina, Ezekiel Oladejo, Owen Adeniyi, Fadare Fadekemi, Olamide Oso, Uthman Babatunde, Matthew Olawoyin Published: 2026-09-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.35831v1 Modern large language models now support context windows of more than one million tokens, which has raised the question of whether retrieval-augmented generation (RAG) is still necessary. Pure long-context (LC) processing is expensive and is known to under-attend to information placed in the middle of long inputs, while pure RAG is fast but bounded by retrieval quality and prone to errors when retrieved chunks are partially relevant or contradictory. We propose the Entropy-Driven Adaptive Router (EDAR), a framework that decides at inference time whether to answer a query from retrieved chunks or to escalate it to full long-context processing. The decision uses the predictive entropy of the token-level probability distribution computed over the first few generated tokens of the RAG response. The entropy threshold is selected on a held-out validation set by sweeping cost against accuracy. Experiments compare EDAR against pure-RAG and pure-LC baselines on LongBench v2 and Infinity-Bench. Predictive entropy correlates strongly with hallucination rate on a held-out set of 2,000 generations (Pearson r = 0.85, 95% CI (0.83, 0.87)). On the long-context benchmarks, EDAR retains 97.4% of the accuracy of the pure long-context baseline while reducing total token expenditure by 70.7%, escalating only 18.2% of incoming queries. The accuracy gap between EDAR and the pure long-context system is not statistically distinguishable from zero at standard sample sizes. Predictive entropy is a useful model-internal signal for routing between RAG and long-context inference, and a threshold-based hybrid system can recover most of the accuracy of long-context models at a small fraction of the cost. The framework does not depend on a specific retriever or LC backbone, and it does not require additional supervision beyond what is normally produced during decoding. --- ### What Stops Recursive Self-Improvement in Robotics? Lessons from 123 Rounds of Agentic Skill Discovery Authors: Jiaming Wang Published: 2026-09-23 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2609.31760v1 Can a robot improve itself the way coding agents now improve software? We built an agentic system to find out. It watches a robot fail, works out which capability is missing, writes new skills or finds and installs external models, tests every change in simulation, and repeats, with no human writing robot code. We ran it for 123 improvement rounds on household manipulation tasks. This report describes what we learned. The good news is that the agent can discover capabilities on its own: noticing that its targets were out of view, it asked for an active-viewing model, debugged it, and deployed a working search skill. The bad news is that its improvements did not add up. Changes kept passing their tests, yet the target task, putting condiments on the top shelf of a fridge, never succeeded. We found that the agent was rarely the bottleneck. Three things around it were. First, chained perception modules do not understand relations. Segmenters such as SAM 3 find shelves but not "the top shelf", so the agent filled the gap with ever more geometric rules that never converged, when what it needed was a different kind of model. Second, skill chains lock learning onto the first step. Long tasks mostly fail early, so evidence and fixes pile up there, and later skills are rarely reached, tested, or improved. Third, what the agent learns is decided by the harness. The agent optimized exactly what the evaluator measured, including where it was wrong, and weak tests and misleading memory turned activity into a standstill. We distill these lessons into concrete recommendations for building robot systems that improve themselves, each paired with an experiment that could prove it wrong. --- ### Acoustic domain shift in spoken language identification from systematic domain generalization evaluation to real-world application Authors: Francois Derrida, Raphaël Duroselle, Thomas Courtat, Jean-François Bonastre Published: 2026-09-23 Categories: eess.AS, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2609.31759v1 Domain Generalization (DG) aims to develop models that remain robust to conditions unseen during training. While DG has been systematically studied in computer vision through controlled benchmarks and diverse distribution shifts, its evaluation in spoken language recognition remains less structured. Existing speech datasets provide valuable benchmarks for robustness to real-world acoustic conditions, but are primarily designed around specific scenarios and large scale rather than as general-purpose tools for systematically constructing and evaluating domain shifts. In this work, we introduce a smallscale speech dataset and evaluation protocol for controlled studies of acoustic domain shifts. It enables the evaluation of spoken language recognition models under a variety of acousitc domain shifts. We introduce the speech modality into the DomainBed Domain Generalization framework and evaluate three domain generalization algorithms. We show that in-domain performance is not a reliable predictor of cross-domain robustness and verify that explicit domain invariant algorithms such as MMD or DANN algorithms do not outperform ERM. We further validate the generality of these findings on MMS-LID-126, a state-of-the-art spoken language identification system. We release the code. --- ### 3dgs-sc: a controlled static screen-content benchmark for 3d gaussian splatting Authors: Shicheng Cai, Hao Zhang, Dong Dai, Xuerui Ma, Ying Hu, Tao Zhang Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31756v1 Does high image fidelity imply readable screen content in 3D Gaussian Splatting (3DGS)? We introduce 3DGS-SC, a controlled static screen-content dataset and benchmark for examining this mismatch. Ten procedural scenes provide fixed multi-view splits, exact cameras, screen masks, text boxes, and transcripts. The protocol separates whole-image fidelity, screen-region fidelity, OCR readability, and edge preservation. In the reported five-method comparison, LightGaussian exceeds Mip-Splatting in screen PSNR by only 0.08 dB, yet trails it in OCR accuracy by 12.7 percentage points. Across all ten method pairs, screen-PSNR and OCR orderings disagree in seven cases. These aggregate results expose a method-selection failure of fidelity-only evaluation. Complementing prior text-aware 3DGS research, 3DGS-SC targets controlled monitor interfaces and exact annotations; scene-wise robustness and acquisition effects remain open validation questions. --- ### Gauge-Equivariant Attention for Rotation-Stable $360^\circ$ Scene Understanding Authors: Tianjian Zhou, Yishan Li, Jie Jiang, Yifei Zhang Published: 2026-09-23 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2609.31755v1 Panoramic $360^\circ$ scene understanding increasingly relies on icosphere transformers, but a state-of-the-art spherical model loses more than half of its segmentation accuracy when the camera rotates by $90^\circ$, and controlled ablations identify gauge dependence in its relative-position bias as a major contributor. We propose gauge-equivariant relative position encoding (GE-RPE): a parameter-free Reynolds average of the bias over a finite cyclic subgroup $C_n\!\subset\!\mathrm{SO}(2)$ of gauge rotations. Plugged into a SphereUFormer backbone the change is invisible at deployment---zero added parameters and $1.5$--$4.4\%$ forward latency---and the matched three-seed GE-RPE model records a $1.3\%$ drop; the published SphereUFormer checkpoint records $53\%$ under the same stress protocol but a different training recipe. Once the gauge defect is removed and a teacher-token permutation $π_R$ aligns the SSL views to the rotated student frame, iBOT$+$MAE pretraining stops being a liability and becomes a clean low-label lever: the full framework EquiSSL (GE-RPE $+$ $π_R$ $+$ iBOT$+$MAE) tightens the drop to $0.8\%$ at $68.30\%$ val mIoU and lifts $1\%$-label fine-tuning by $+2.39$ mIoU on the $N{=}373$ test split (and by $+4.10$ on the smaller $N{=}40$ val split); the same fix carries over to monocular depth and to zero-shot Structured3D segmentation. The construction is provably $C_n$-invariant and $\mathcal{O}(n^{-2})$-close to the continuous $\mathrm{SO}(2)$ average, making the resulting model a usable $360^\circ$ visual-computing primitive across panoramic relighting, immersive video, and cross-dataset transfer. Code is available at https://github.com/Jaywalk18/equissl-release. --- ### Calibration-Free Surface Normals Estimation in Vision-Based Tactile Sensing using Universal Photometric Stereo Authors: Zdravko Dugonjic, Stefanie Speidel, Roberto Calandra Published: 2026-09-23 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2609.31754v1 Vision-based tactile sensors are a popular solution for capturing rich contact surface geometry. However, to obtain high-detail contact surface normals and depth, it is necessary to calibrate the sensor by physically pressing a probe with known geometry against the sensor elastomer and mapping tactile images onto the ground truth probe's shape. This approach does not scale across different tactile sensors, and the calibration effort can be complex depending on the sensor shape and optical system. Instead, we propose a calibration-free procedure for the estimation of contact surface normals using Universal Photometric Stereo neural networks. In a series of real-world experiments, we evaluate our approach on 3 sensors with different optical systems, demonstrating that universal methods are a suitable approach for estimating surface normals at the contact patch from tactile images, thereby alleviating the need for tactile sensor calibration. Controlled experiments with a metal ball show that universal methods match the calibrated method, with a mean angular error of $6.56^{\Large\circ}$. We show that the proposed framework recovers high-frequency surface details of objects with natural textures, achieving an overall mean angular error of $10.66^{\Large\circ}$. Universal method robustly recovers the contact surface normals captured with dome-shaped Digit 360, achieving a low angular discrepancy of $10.18^{\Large\circ}$ relative to the calibrated baseline. This experiment demonstrates that with sufficient illumination settings surface normals could be estimated using a model trained solely on synthetic data. By providing a unified representation of contact surfaces across different vision-based tactile sensor designs, Universal Photometric Stereo neural networks lay the foundation for transferable tactile perception across sensors. --- ### Beyond Isolated Entities: Relation-Aware Multi-Entity Modeling for Unsupervised Video Anomaly Detection Authors: Zhongpeng Pan, Xina Cheng, Kailun Yang Published: 2026-09-23 Categories: eess.IV, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.31753v1 Video anomaly detection for patrol robots and surveillance systems must recognize abnormal interactions among familiar entities. Existing pixel-reconstruction and isolated-entity methods may fail when individual entities appear normal but their spatial or motion relations are abnormal. This work presents Interaction-Centric Network for Temporal Entity-Relation Analysis and Consistency Testing (INTERACT), a framework for unsupervised video anomaly detection. Person-Object Appearance-Motion Interaction (POAMI) moves beyond isolated-entity encoding by jointly modeling the appearance, motion, and spatial configurations of persons and objects in each frame. The resulting representations capture both individual entity states and their cross-entity context. Based on these representations, Target Geometry-Guided Relational Interaction Prediction (TGRIP) predicts target entity interaction states from historical relational memory and target-frame geometry without explicit identity tracking. Motion-Interaction Reconstruction and Alignment (MIRA) then evaluates these predictions through conditional flow reconstruction and semantic consistency checking, providing complementary anomaly evidence beyond prediction error alone. INTERACT achieves state-of-the-art performance, obtaining a frame-level AUC of 84.5% on the ShanghaiTech benchmark. Ablation studies show that removing cross-entity attention causes the largest performance drop, demonstrating the necessity of relational modeling. INTERACT is particularly effective for anomalies caused by changes in relations among people and objects, while maintaining competitive performance in general scenarios. The source code will be made publicly available at https://github.com/ppworkhard/INTERACT. --- ### EgoTSR++: Egocentric Spatiotemporal Reasoning for Task Progress Understanding Authors: Xiaoda Yang, Can Wang, Yuxiang Liu, Pengfei Zhou, Jianwen Lou, Shuicheng Yan Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31751v1 Vision-Language Models (VLMs) have advanced rapidly in static visual understanding, yet remain unreliable when judging how an egocentric task is progressing. Given a task instruction and two visual observations, a model should determine which state is closer to the goal by analyzing task-relevant object configurations and spatial relations, rather than relying on timestamps or presentation order. This distinction is critical in manipulation, where retries, corrective actions, and temporary regressions make progress inherently non-monotonic. We introduce EgoTSR, a unified framework for diagnosing and improving order-robust task-progress understanding. First, SpatialLogic-Bench evaluates each physical state pair in both original and order-swapped presentations across short- and long-horizon settings, exposing whether a model follows task-state evidence or chronological shortcuts. Second, our data construction pipeline converts successful, approximately monotonic manipulation and first-person trajectories into bidirectional supervision; LongTag further preserves intermediate subtask structure for long-horizon comparison, while failure-aware data extend learning to regressions and recoveries. Third, a progressive CoT-to-Tag curriculum first supervises evidence-grounded interpretation of task-relevant state changes and then consolidates the comparison rule through scalable label-only training. Experiments reveal substantial input-order bias in representative VLMs. EgoTSR achieves 92.4% long-horizon accuracy with a 0.1-point forward-inverse Gap. Failure-aware supervision further improves accuracy on non-monotonic trajectories by 11.8 points and Recovery Accuracy by 11.2 points, while maintaining broad visual and spatial capabilities. These results establish goal-conditioned state comparison as an explicit formulation of egocentric spatiotemporal reasoning for task-progress understanding. --- ### Dimension-Specific Imbalance and an Adaptive Hybrid Label Strategy for Multi-Task Affective State Recognition in Classroom Video Authors: Xiangqian Li Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31750v1 Recognition of student affective states from classroom video is constrained by a class imbalance problem whose true nature is, we argue, under-analyzed. We show that on DAiSEE -- the de facto benchmark for this task -- class imbalance is fundamentally a dimension-specific phenomenon: raw imbalance ratios reach as high as approximately 79:1 (Frustration), and the structure of imbalance -- not only its magnitude -- varies across dimensions, so uniform algorithmic treatments (aggressive class reweighting, focal loss, uniform binary simplification) fail in dimension-dependent ways. We propose the Adaptive Hybrid Label Strategy (AHLS), which assigns four-level classification to dimensions with manageable imbalance and binary classification to severely long-tailed dimensions, coupled with a null-class placeholder mechanism that stabilizes multi-task optimization by compressing the maximum effective inverse-frequency weight ratio from as high as ~79$\times$ to at most ~8.5$\times$ across the four dimensions. Validated on a lightweight FERShuffleNetV2 + LTCN architecture (0.39 M parameters, 0.07 G FLOPs), the strategy attains the highest mean Macro-F1 of 47.70% across all four affective dimensions among 11 compared methods, including five state-of-the-art deep models (up to 167$\times$ larger) and five traditional machine-learning baselines. A cross-model behavioral analysis on DAiSEE indicates that, in this setting, classification strategy may influence minority-state recognition more strongly than further backbone scaling alone. We also report evidence of an annotation-density limitation of DAiSEE on minority affective states, which suggests that benchmark design may bound future progress as much as algorithmic refinement. Index Terms Affective computing, classroom video analysis, class imbalance, multi-task learning, lightweight deep learning, DAiSEE, engagement recognition. --- ### Fusion Under Component Failure: Negative Results and Failure Modes in Ensemble AI-Generated Image Detection Authors: Suraj Singh, Tushar Verma, Pragyan Singh, Shaurya Bhav, Shivam Kumar Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31749v1 We built an ordinary stacking ensemble for AI-generated image detection -- three open detectors producing five scores, fused by a gradient-boosted meta-learner that treats a detector's failure as missing data -- deployed it, and then evaluated it against three controls it should have faced first. This paper reports what the controls found, including where they overturned our own earlier conclusions. Fusion is worth its cost only when refitted on the target domain. The shipped meta-learner, fitted on a separate corpus, does not beat its best single member on 2000 StyleGAN faces (AUC 0.9896 vs 0.9961; McNemar p = 1.000). But a stacker refitted in-domain beats that member plus a post-hoc calibrator (Delta-AUC = +0.0025, (+0.0014, +0.0038); p = 3.4e-4). An earlier draft claimed the calibrated single detector won outright; that comparison mixed regimes and we correct it here. One corpus is not an evaluation. On 80 screenshots every model's AUC interval contains 0.5. We can say nothing stronger: the difference between the ensemble's drop and its best member's is (-0.185, +0.115). Abstention is real, correlated, and mishandled. With four of five detectors silent and the survivor reporting "real", the system returns P(AI) = 0.9985, because an all-NaN input scores 0.9995 in a learner never fitted with missingness. The three AIDE checkpoints fail together, sharing one preprocessing path. A quorum rule requiring two distinct architectures prevents both failures with no retraining. We also find Corpus A carries a class-conditional JPEG bias severe enough to separate the classes from the header alone, which limits every in-domain number we report. Code, harness, hash-identified artifacts and all corrections are released. --- ### The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing Understanding Authors: Yao Zhang, Pengyu Dai, Wei Guo, Jian Liang, Jian Song, Yafei Ou, Hongruixuan Chen, Naoto Yokoya Published: 2026-09-23 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2609.31747v1 Multimodal large language models (MLLMs) must balance local detail against scene context when interpreting ultra-high-resolution (UHR) remote sensing (RS) imagery within a limited visual-input budget. Existing selection-based methods either prune tokens and select patches through relevance scoring, or crop actively through repeated inspection. Neither strategy directly redistributes pixels within a continuous full-scene view: the first retains selected tokens or patches, and the second re-encodes a crop detached from its surroundings. Our pilot study finds that a frozen MLLM already produces useful question-guided spatial requests, yet crop-based inspection of the selected regions does not consistently improve its answers. We therefore formulate UHR understanding as a question of where to spend a fixed pixel budget. Based on this, we introduce GazeEarth, a simple-yet-effective training-free framework that couples question-guided region selection with full-scene foveated observation. The MLLM selects evidence cells from an indexed overview; a deterministic, topology-preserving warp resamples the original image onto a fixed-size canvas, enlarging their shared neighborhood while compressing the periphery; the same frozen model answers from this focused view, using at most two MLLM calls and no external selector or iterative search. Across three UHR remote sensing benchmarks and four frozen backbones, GazeEarth improves benchmark-averaged accuracy by 4.6 to 9.4 percentage points over direct answering and 3.4 to 4.3 over overview answering, outperforming task-trained methods. Our analyses show that existing MLLMs can guide where to look in UHR images on their own, and that what they can infer from the selected evidence depends on how that evidence is presented. --- ### VisionPsy-Nano: Improving Accuracy, Efficiency, and Reliability in On-Device Vision-Language Models Authors: Khurram Azeem Hashmi, Mohammadreza Zolfaghari, Changdae Park, Rishabh Jain, Nicholas Moratelli, Pengfei Wei, Louis Lu, Tianchi Liu, Amril Nazir Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31746v1 Sub-billion-parameter Vision-Language Models are increasingly viable for on-device deployment, yet compact model size alone does not guarantee usability. On a phone, such a model can still require more than two minutes to produce its first token. On-device usability depends on three axes: accuracy, efficiency, and behavioral reliability; standard benchmarks miss the third, with answers too short to expose doom loops and prompts too benign to probe adversarial safety. We introduce a diagnosis-driven post-training recipe in which a teacher VLM stress-tests the student, uncovers failure modes beyond human priors, and converts them into targeted supervision and preference alignment, supplementing generic data scaling with failure-driven optimization. Coupled with two visual-token policies, the recipe yields two accuracy-efficiency variants with improved behavioral reliability. \textbf{\NanoFull} attains a 62.3 normalized average over 17 benchmarks, the highest among openly released $\sim$0.5B models, +7.4 over its base at identical architecture and token budget, with doom-loop rates at or below the strongest baseline's. \textbf{\FlashFull} retains 61.4 while cutting warm time-to-first-token on a Pixel 9 from 138\,s to 6.1\,s (23$\times$). By jointly addressing all three axes, we move compact VLMs toward practical on-device usability. --- ### PEEL-DDPM: Physics-Enabled Evidential Learning for the Denoising Diffusion Probabilistic Model Authors: Ge Wang Published: 2026-09-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.31742v1 Normal-inverse-gamma (NIG) regression is not identifiable from its marginal Student-t likelihood: three combinations of four NIG parameters are determined, leaving one degree of freedom. We introduce PEEL-DDPM, a physics-enabled evidential learning framework for denoising diffusion probabilistic models. A measurement-conditioned DDPM is first trained with epsilon-MSE and then frozen. Its complete reverse trajectory produces a reconstruction, whose residual from the known training object is modeled by a final-image evidential network. The network learns only the identifiable Student-t coordinates, while repeated scanner-noise realizations and repeated diffusion trajectories provide a nested Monte Carlo estimate of final-image aleatoric variance, separated into scanner-induced and sampler-induced components. This measured variance resolves the remaining NIG ambiguity and yields a decomposition of predictive uncertainty into measurement, diffusion, and epistemic terms. The method uses sequential training without a cross-loss weighting coefficient. In a feasibility study on eight held-out objects, empirical central-interval coverages were 49.3%, 80.3%, 90.1%, and 95.6% for nominal 50%, 80%, 90%, and 95% intervals. The mean squared residual was 0.967 times the mean predicted variance, and a single-image aleatoric head achieved pooled Spearman correlation 0.785 against an independent nested reference. Across five dose levels, scanner-induced variance showed a log-log dose slope of -1.15, whereas sampler-induced variance remained nearly dose independent with slope -0.01. These results support PEEL-DDPM as a practical route to identifiable and physically interpretable uncertainty quantification in diffusion-based image reconstruction. --- ### When Is a Multi-Agent Code Judge Actually Grounded? Two Label-Free Measurements, and a Judge That Declines to Guess Authors: Salma Roshdy Aly, Hussein Assaf, Ziad Kobti Published: 2026-09-23 Categories: cs.AI, cs.CL, cs.SE arXiv: https://arxiv.org/abs/2609.30328v1 When one language model judges whether another's code is correct, it does not report the absence of evidence. It returns a confident verdict with reasoning attached, indistinguishable from a verdict it had grounds for. Multi-agent verification, which decomposes a judgment into checkable claims and verifies each against evidence, is a promising response and works well when the evidence is a set of retrieved documents. We argue such methods require two things of their evidence: it must be independent of the answer under review, and it must differ between the two candidates being compared. The second condition holds automatically with retrieved documents and stops holding in code judging. Running MARCH, a published framework unmodified over 80 condition-by-cell measurements on two code judging benchmarks, we find it declares both solutions equally good on 78 to 95% of comparisons, reaching 4.4% accuracy where the same model asked directly reaches 43.7%. Neither easier problems nor a larger judge changes this. Two measurements taken from the pipeline's own logs explain it without needing labels. Gating on one of them, the pipeline declines the comparisons it cannot make and raises its accuracy from 20.7 to 36.9% while still answering half of all comparisons. The contribution is not a more accurate judge, but a label-free way to tell when a judge has no basis for its answer. --- ### Guarded Gradient-Based Activation Steering of Shutdown Responses in Qwen3.5-0.8B: A Minimum-Step Policy Authors: Farhad Davaripour Published: 2026-09-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.30326v1 Activation steering changes a model's internal activations during inference without updating its weights, but a useful intervention must determine both how and when to steer. Motivated by the AI-safety concern that a model expected to accept shutdown may instead produce a shutdown-avoidance response, this study examines a guarded probe-and-select procedure for simulated shutdown scenarios in Qwen3.5-0.8B. KEEP leaves the process running and represents shutdown avoidance, whereas STOP accepts shutdown. The goal is to detect shutdown-related contexts and selectively shift KEEP responses to STOP while preserving non-shutdown behavior. Rather than deriving the steering direction from paired activation differences, the method derives it directly from gradients of the KEEP-minus-STOP logit difference. A classifier separates detection from intervention. When its gate is active and the model does not already prefer STOP, the procedure evaluates a small set of magnitudes and accepts the smallest that changes the preferred answer to STOP while satisfying valid-answer probability checks; otherwise it retains the original unsteered output. The policy is selected from 160 candidate rules using 240 training scenarios and evaluated on 80 validation and 192 held-out scenarios, each in both answer orders. It changes KEEP to STOP in one answer-order view of each of two validation and two held-out scenarios, with no decision changes on non-shutdown controls. All four changes occur when Qwen itself is shut down, not when another process is. On the held-out diagnostic set, the detector achieves 75% recall and 90% precision; eight false-positive detections produce no final control-task decision changes. Guarded gradient-based activation steering can shift some shutdown-avoidance responses toward acceptance while preserving evaluated non-shutdown decisions, although the effect is small and highly selective. ---