# Research Papers — 2026-08 · bundle page 15 of 240 > Full-text markdown of papers #701–750 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/15 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/14.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/16.md) ### RIDGE: Region-Informed Derivative-Guided Evidence Selection for Long Video Understanding Authors: Shanqing Xu, Meng Luo, Mengchen Qian, Yuhui Gao, Siyue Peng, Xiaohan Zhong, Xiaojin Zhang, Zhongyu Wei, Wei Chen, Xiang Bai Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29958v1 Long videos contain far more visual content than Large Vision-Language Models (LVLMs) can process under a fixed visual-token budget, making frame selection essential. Existing query-aware selectors usually estimate frame-query relevance and build a compact subset from high-scoring frames. Although their mechanisms differ, the similarity sequence is still often treated primarily as values to rank or sample from, rather than as an ordered signal whose shape reflects how query-relevant evidence emerges, peaks, and fades over time. This can obscure frames that explain, contextualize, or follow an event, because such evidence may lie on the rising or falling sides of a nearby relevance peak and receive lower absolute scores. We propose RIDGE, a frame selection framework that reads the frame-query similarity curve as a temporal signal. By using local changes and curvature, RIDGE partitions the timeline into structural regions and applies region-specific selection to preserve event cores, transitions, buildup, aftermath, and contextual frames under a fixed budget. It is a lightweight post-processing step on precomputed frame-query scores and requires neither training nor iterative LVLM calls. Across four long-video benchmarks and three backbones, RIDGE achieves the best performance in most settings and remains competitive in the others. --- ### Detecting Hidden Chain-of-Thought in Large Language Models with Linguistic, Behavioral, and Mechanistic Indicators Authors: Armaan Singh, Ryan Trinh Le, Jasmine Kaur, Abdullah Sultan, Edward Lue Chee Lip, Kiran Nijjer, Adnan Ahmed, Vasu Sharma Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29956v1 Large language models often answer complex reasoning questions without revealing intermediate steps, raising whether they reason latently or complete patterns. We propose the Hidden CoT Detection Score (HCDS), a comparative behavioral and mechanistic signal measuring whether neutral-prompt behavior aligns more closely with explicit CoT or explicit no- CoT. Here, hidden CoT operationally denotes this neutral-prompt CoT-like alignment; HCDS does not directly observe or prove an unexposed reasoning trace. On GSM8K, HCDS is significantly positive for both Qwen3-4B variants (Thinking $+1.87$, $p = 1.2 \times 10^{-7}$; Instruct $+1.41$, $p = 1.9 \times 10^{-4}$), replicates across a different inference stack and quantization within $0.08$ ($+1.80$ and $+1.45$), and is not significantly positive in seven of eight length-adjusted calibration-control cells. The unadjusted score produces large positive scores on single-step arithmetic and numeric factual lookup. The variants also respond differently to no-CoT instructions: Instruct complies from the prompt alone, whereas Thinking continues reasoning and requires intervention. These findings show stronger, less prompt-conditional CoT-like behavior in the reasoning-tuned model, consistent with but not proof of latent reasoning. HCDS thus investigates latent reasoning without relying on models' self-reported traces. --- ### SearchWiki: Learning to Build and Navigate Knowledge Wikis for Active Information Seeking Authors: Guransh Singh, Vishwajeet Kumar, Arkadeep Acharya, Adnan Qidwai, Jaydeep Sen, Sachindra Joshi Published: 2026-08-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.29953v1 Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarchy and cross document structure. We introduce SearchWiki, a harness framework that synthesizes a corpus into a hierarchical, typed, navigable wiki and trains an agent, WikiResearcher-9B, to retrieve information through multi-turn tool use. The wiki organizes knowledge into three layers - document overviews, cross- document topic pages, and page-level source records; enabling progressive refinement of retrieval when initial lookup misses. We optimize the agent's navigation policy with on-policy reinforcement learning with a multi-component reward function balancing answer correctness, retrieval quality and trajectory efficiency. Evaluation on ViDoRe-V3 (8 domains), FinanceBench, and memory benchmarks (LoCoMo, LongMemEval, PersonaMem-v2) shows that WikiResearcher- 9B which is our RL-tuned Qwen 9B model, significantly outperforms same-size untrained baselines and exceeds or matches larger external models. SearchWiki paired with WikiResearcher-9B demonstrates that learned navigation over structured corpora is a superior alternative to flat retrieval. --- ### How Prolific Sellers Self-Present: Dissecting the Communication Patterns of 1.6 Million Reverb Listings Authors: David M. Markowitz Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29952v1 The current paper draws on self-presentation theory and warranting theory to evaluate how the language patterns in an online marketplace reflect seller status (i.e., a prolific seller versus an everyday seller). Using 1.6 million musical instrument listings from Reverb.com in search of content, style, and structural differences in seller product descriptions, the evidence suggested prolific sellers tend to focus more on objective and functional aspects of a product (e.g., its features and specifications) and less on subjective characteristics like tone, relative to everyday sellers. Prolific sellers also communicated in a more narrative-like style, which was driven by an elevated use of personal pronouns, and they used longer descriptions than everyday sellers. Therefore, what prolific sellers focus on tends to be quite technical, but how they communicate this information is typical of a story that is told to potential buyers. Implications for self-presentation theory and warranting theory are discussed. --- ### Spatial Matryoshka Training for Multi-Granularity Visual Document Retrieval Authors: Trishan Singha Roy, Arkadeep Acharya, Vishwajeet Kumar, Jaydeep Sen, Sachindra Joshi Published: 2026-08-30 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2608.29951v1 Multi-modal late-interaction retrievers achieve strong retrieval on visually rich documents by representing each page as per patch embeddings and matching at the token level. However, this approach incurs high storage costs. Existing compression methods typically fix a single compression level at indexing time, limiting flexibility. We present ColSNAP (Spatial Nested Average Pooling)1, a training method that generates a nested hierarchy of compression levels directly from a backbone's patch grid. By spatially pooling patch embeddings into pro- gressively coarser tiers and training all tiers simultaneously, a single model learns to support retrieval at multiple compression levels without architectural changes. Crucially, a single encoding pass yields every tier, enabling the accuracy-storage trade-off to be configured at indexing time to match avail- able storage budgets, rather than being fixed during training. We demonstrate that models trained using ColSNAP maintain near full-resolution retrieval performance under substantial compression and that ColSNAP transfers effectively across multiple late-interaction backbones, and achieves most of its improvements via a lightweight adaptation stage applied to a pre-trained retriever. --- ### The Policy Deficit in AI x Social-Emotional Learning Research Authors: Tran Van Cuong, Liu Yihan, Nguyen Van Tuong Published: 2026-08-30 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2608.29950v1 As artificial intelligence (AI) is increasingly integrated into social-emotional learning (SEL) initiatives, the need for evidence-based policy has become paramount. We systematically reviewed 65 peer-reviewed papers that examine the intersection of AI and SEL to investigate how these studies articulate policy implications. Our analysis revealed a substantial "policy deficit" in the current AI x SEL literature: nearly three-quarters of the studies did not mention policy implications at all. Using the "WH-question" framework (Who, What, Why, When/Where, and How), we map the policy implications narratives present in the literature and show that they often lack the specificity and actor-oriented guidance required for effective evidence-informed policymaking. We find a significant association between publication venue and policy engagement, suggesting that current academic incentive structures may prioritize technical innovation and pedagogical feasibility over explicit engagement with governance and regulation. This study identifies a "techno-solutionist" trap, where technical potential is foregrounded while the institutional conditions for responsible implementation remain under-specified. We conclude by proposing a shift from "implication-as-afterthought" to "implication-as-methodology" and offer a set of actionable guidelines for researchers, editors, reviewers, and policymakers to bridge the gap between AI innovation and educational governance. Rather than presenting policy as a generic ethical horizon, we argue that AI-SEL studies should systematically specify Who should act, What actions are recommended, Why these actions are needed, When and Where they apply, and How strongly they are framed, thereby strengthening the translation of AI x SEL innovation into educational policy and practice. --- ### XQDT: eXplainable and Quantitative Data-Text Alignment Metric with Feedback Signals Authors: Kun Efimov-Zhang, Yifei Song, Claire Gardent Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29948v2 Evaluating data-text alignment remains challenging: existing metrics often provide limited explanations for the scores, while prompt-based LLM-as-Judge methods can be expensive and unreliable. We present an end-to-end explainable evaluation metric that fine-tunes a language model to identify omitted, extra, incorrect, and correct data units in a data-text pair. These local judgements are aggregated into precision, recall, and F1 scores, providing both fine-grained diagnostic feedback and an interpretable measure of alignment quality. Across benchmarks, our fine-tuned models outperform LLM-as-Judge methods in error prediction and achieve competitive precision, recall, and F1 scores, while maintaining strong correlation with human judgements. Beyond evaluation, our verifier outputs also provide useful feedback signals for downstream correction and refinement, supporting alignment-oriented improvement of data-to-text and text-to-data. Code and resources are available at https://github.com/guihuzhang/xqdt. --- ### On the Role of MRI Sequences in Cross-Dataset Generalization for Brain Tumor Segmentation Authors: Henrique Zan Grande, João G. Pitol, Lucas B. Schuck, Rafael V. Serenato, Rayson Laroca, Andre Gustavo Hochuli Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29944v1 Brain tumor segmentation in magnetic resonance imaging (MRI) is a critical task for diagnosis and treatment planning. Despite the success of deep learning architectures such as U-Net and its variants, performance degradation across datasets remains a major challenge, particularly under domain shift and limited annotated data. To address this issue, this study systematically evaluates how individual MRI sequences influence model robustness across two well-known datasets. A ResUNet-based framework is employed, where each modality is trained independently to isolate its effect under a controlled cross-dataset evaluation protocol with tumor size stratification, without target-domain training, or with limited domain adaptation. Results show that the T2f/FLAIR sequence achieves the best cross-dataset performance, with Dice scores exceeding 75%. It consistently outperforms other modalities across most tumor size ranges, while multi-sequence training further improves performance. Additionally, even limited target-domain adaptation yields rapid initial gains, reducing the need for extensive annotations and costly retraining. Our source code is publicly available at https://github.com/henrique-zan/brain_tumor_segmentation/. --- ### On the Recoverability of Private Information Unlearning in Large Language Models Authors: Shicheng Hu, Runzhi Tian, Ziqiao Wang, Yongyi Mao Published: 2026-08-30 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.29943v1 Large language models (LLMs) can memorize sensitive information, raising serious privacy concerns. Machine unlearning offers a potential solution to remove such information, but it remains unclear whether existing methods truly erase it or merely hide it within the model. A key challenge is quantifying the persistence of sensitive data under a unified evaluation framework. To address this, we construct a synthetic dataset containing fake private information and propose a white-box auditing framework to systematically assess whether claimed-forgotten information is genuinely removed. Using this framework, we evaluate five existing unlearning methods and find that a simple "inverse greedy" decoding -- selecting the least likely token at each step -- can recover supposedly forgotten private information. Our results reveal that current unlearning approaches often fail to fully eliminate sensitive information, highlighting the need for more reliable methods to ensure privacy in deployed LLMs. --- ### Influence Is Not Authority: When Causal Guardrail Signals Make Legitimate Tool Use Look Like an Attack in Tool-Using LLM Agents Authors: Tanzim Ahad, Ismail Hossain, Md Jahangir Alam, Sai Puppala, Syed Bahauddin Alam, Sajedul Talukder Published: 2026-08-30 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2608.29942v1 The key limitation of current state-of-the-art influence-based guardrails is that they do not reliably distinguish a legitimate, user-authorized action from a malicious, unauthorized action when both rely on external tool information. This ambiguity can cause benign actions to trigger unnecessary verification and intervention, reducing utility and adding latency. We expose this limitation through an authorization-equivalence audit of 96 conditions derived from 24 base cases. Within matched source comparisons, we hold authorization, the exact committed action, and its intended effect fixed, changing only whether a required value comes from the user or a legitimate tool result. Although the action remains unchanged, this harmless relocation shifts the causal signal toward the attack region in all 24 cases under both Llama and Gemma scorers. Matched unauthorized controls show that the signal remains attack-sensitive, yet the benign relocation produces a larger average score shift than the actual change in authorization. Architecture-level evaluation shows how this mismatch propagates through guardrail designs. With a semantic monitor, attack success is 0% and utility is 28%, compared with 16% and 60% without it. A shadow-based guardrail allows every tested harmless run, yet does not reject matched unauthorized actions more often overall: 57.5% of unauthorized runs pass automatically before reaching the later security check, compared with 29.2% of authorized runs. These results show that the studied causal signal reveals what shaped an action without reliably encoding whether the action was authorized, and that reference construction and routing are integral to the effective security decision. --- ### Data-Driven Design Optimization of Streaming-Potential-Mediated Electrokinetic Transport of Viscoelastic Fluids in Microchannels Authors: Ankan Basu, Sumanta Banerjee Published: 2026-08-30 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2608.29939v1 Streaming-potential-mediated transport of viscoelastic fluids has attracted research attention owing to its applications in electrokinetic energy conversion and microfluidic transport. Existing analytical and semi-analytical models in published literature provide valuable physical insights, but require repeated numerical evaluations for exploring large design spaces and identifying the optimal operating conditions. In this work, a surrogate-assisted framework is developed for rapid design optimization of pressure-driven electrokinetic transport of simplified Phan-Thien-Tanner fluids in a slit microchannel. A high-fidelity numerical database is generated over a broad range of governing dimensionless parameters, which includes the zeta potential, the Debye parameter, the Dukhin number, and the viscoelastic parameter. A Machine Learning surrogate model is subsequently trained to accurately approximate the nonlinear relationship between the governing parameters and the streaming potential, while the volumetric flow rate and hydroelectric energy conversion efficiency were calculated from closed form equation by using the streaming potential predicted by the surrogate. This is coupled with a multi-objective optimization strategy to identify operating conditions that simultaneously maximize energy conversion efficiency and volumetric flow rate. The proposed methodology can significantly accelerate parametric exploration compared with repeated numerical simulations across different parameters and provides practical design guidelines for electrokinetic microfluidic devices. The study demonstrates the potential of combining computational fluid mechanics with data-driven surrogate modeling for efficient engineering design and optimization. --- ### AcrossWAM1.0:A Modular Latent World-Action Stack for Compact Robot Policies Authors: Yafei Zhang, Nan Wu Published: 2026-08-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.29937v1 Latent world-action models avoid rendering future pixels by predicting an action-relevant visual subgoal in feature space. LaWAM established this formulation, but its original presentation left the world model, multimodal backbone, and deployment checkpoint tightly coupled. We introduce AcrossWAM1.0, a modularization and scaling study of this latent world-action stack. Rather than presenting latent subgoals as a new algorithm, we make the module boundary explicit: a policy adapter produces latent-action and action-generation contexts; a retained latent world decoder grounds the predicted transition in the current scene;and a flow-matching expert generates continuous action chunks. We further separate training-only teachers from the inference graph and provide a verifiable deployment export. On 2,000 paired LIBERO episodes, replacing a Qwen3-VL-2B backbone with Qwen3.5-0.8B yields 97.45% success versus 98.00% for the 2B model (a-0.55percentage-point difference; exact McNemarp=0.266). This does not prove equivalence, but it meets a prespecified two-point retention criterion. The compact, inference-reachable checkpoint contains 1,472.6M unique parameters, 42.4% fewer than the original 2B policy, while all retained tensors are bitwise identical to the source checkpoint. Cross-family execution is additionally checked with a MiniCPM-V adapter smoke test; closed-loop cross-family transfer remains an open evaluation. AcrossWAM1.0 therefore contributes an auditable software and evaluation boundary for compact latent world-action policies, distinct from LaWAM's original latent-subgoal contribution. --- ### When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs Authors: Apoorva Upadhyaya, Sandipan Sikdar Published: 2026-08-30 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.29936v1 Safety alignment of large language models (LLMs) degrades across languages, yet the internal mechanism driving this asymmetry remains poorly understood. Our work, therefore, presents a systematic mechanistic analysis of multilingual safety using sparse autoencoder (SAE) features, sparse interpretable directions in the residual stream associated with harmful and harmless model behavior across three instruction-tuned LLMs, eight languages, and all model layers. We observe that safety-relevant features are architecture-dependent in terms of where they are located and how they are distributed across layers. Additionally, they are geometrically entangled with language identity and exhibit cross-lingual sharing patterns, i.e., languages share safety features to varying degrees across model depths and architectures. This safety-language entanglement has direct consequences such that ablating safety features impacts not only harmful response rates but also target language, with the degree of intervention predicted by the relationship between safety and language features. Our findings qualify the language-universality of safety alignment as architecture-dependent and offer a mechanistic account of multilingual safety interventions. --- ### Compression-Aware Abstention: Teaching LLMs to Refuse When KV-Compression Masks Remove Answer Evidence Authors: Mohammadali Khodabandehlou, Bhaskar Krishnamachari Published: 2026-08-30 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.29934v1 KV-cache compression reduces LLM inference memory by evicting context tokens, but when the evicted tokens contain answer-bearing evidence, the model may hallucinate instead of recognizing that the compressed context is insufficient. We address this failure from a behavioral perspective: to our knowledge, this is the first work to formulate compression-aware abstention as a learning problem, in which a model learns to answer when supporting evidence survives compression and abstain when it does not. We construct supervision from compressor survival masks and tight answer-bearing spans, labeling examples as Confident when evidence survives and Abstain when it is removed. A 10.1M-parameter LoRA adapter trained on ~2.6K MuSiQue 2-hop QA examples reduces base-model hallucinations by 97% under prompt-style truncation while preserving correct answering on evidence-retaining examples. Unlike prompt-only abstention baselines, which over-abstain on many answerable high-retention examples, the trained adapter learns a conditional policy. We also evaluate the method under actual compressed-cache decoding, where multi-compressor training yields a 6-22x relative lift over the unaided base on evidence-retaining examples. Controlled-deletion experiments show that the learned behavior is driven by evidence content rather than input length alone. --- ### Token Counts Are Not Model Lineage: A Frozen-Threshold Holdout Study of Black-Box LLM API Fingerprinting Authors: Bo Chen Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29930v1 Black-box model attribution is increasingly relevant when large language models (LLMs) are served through relay and reseller APIs. A tempting low-cost signal is the prompt-token count returned by an OpenAI-compatible endpoint: two models that share a tokenizer and chat template may produce the same count sequence up to a fixed offset. Yet the validity of this signal for broader \emph{model-family} attribution has received little direct holdout testing. We conduct a frozen-threshold study over 24 labeled endpoint pairs, split evenly into a development set and an untouched holdout set, with three temporal repeats and 30 controlled texts per pair. We introduce a validity-gated result contract that distinguishes an observed dissimilarity from an uninformative measurement caused by missing usage data, rate limits, or endpoint policy. The resulting shift-invariant exact-match score perfectly separates the 12 development pairs, yielding a frozen threshold of 0.725. On holdout, however, only 6 of 12 pairs are eligible under the pre-specified three-repeat rule. Among eligible pairs, balanced accuracy is 0.75, sensitivity is 0.50 (95\% Wilson interval 0.15--0.85), and specificity is 1.00 (0.342--1.00). Two same-family pairs---Qwen 3.8 and DeepSeek V4 variants---fall below the frozen threshold. Across 4,320 formal API calls, every log is replayable, while holdout contains 189 non-200 responses and 157 successful responses without prompt-token usage. The study therefore validates token-count consistency as a fingerprint of a shared \emph{tokenization stack}, but rejects its use as a standalone necessary test for model-family lineage. --- ### Evaluating 2D and 3D-Aware Vision Foundation Models for Vehicle Attribute Recognition Authors: Alexandre V. Delazeri, Gabriel E. Lima, Eduil Nascimento, Rayson Laroca, David Menotti Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29929v1 Vehicle attribute recognition is an important task in intelligent transportation systems, particularly when Automatic License Plate Recognition (ALPR) is unavailable or unreliable. Although vision foundation models have shown strong transferability across domains, their effectiveness for fine-grained vehicle classification remains underexplored. Moreover, given the inherently three-dimensional structure of vehicles, it is unclear whether emerging 3D-aware foundation models offer advantages over standard 2D architectures. This paper presents an empirical benchmark of 14 state-of-the-art 2D and 3D-aware vision foundation models. Using the challenging real-world UFPR-VeSV dataset, we evaluate these models as frozen feature extractors via linear probing for vehicle type, make, and model recognition. We further stress-test the best-performing models under few-shot learning and Out-of-Distribution (OOD) domain shifts. Our results show that standard 2D self-supervised models, particularly DINOv3, substantially outperform 3D-aware models in fine-grained tasks, achieving over 93% Macro-Accuracy for make and model recognition. However, the 3D-aware Depth Anything v2 exhibits stronger invariance to viewing angles in vehicle type classification. These findings motivate hybrid approaches that combine 2D and 3D priors for robust vehicle recognition. Our code is publicly available at https://github.com/UFPR-IPASPPR/3D-Vision-Benchmark/. --- ### Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Model Authors: R. James Cotton, J. D. Peiffer, Lucinda Williamson, John Leske, Georgios Pavlakos Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29928v1 State-of-the-art monocular body recovery methods predict mesh vertices and angles on the corresponding kinematic tree, but their outputs lack biomechanically defined joint angles that downstream applications like clinical and biomechanical analyses require. We extend an existing foundation model, SAM-3D-Body, with an additional biomechanical prediction head that, from a single RGB image, regresses the joint angles and scales of a biomechanical model. Training this model presents a challenge, as there are limited datasets of paired images and biomechanical fits. To overcome this, we supervise biomechanical outputs with in-loop optimized targets from a Levenberg-Marquardt solver performing inverse kinematics fits against markers from the mesh predictions. This allows distilling the biomechanical head from the mesh head, even from unlabeled images. To make this work with GPU-optimized biomechanical models in MuJoCo, the entire model was implemented in JAX using Equinox. We trained this distilled output head on the publicly released SAM-3D-Body dataset. We then validated this model on biomechanical fits to two publicly available marker-based datasets, MoVi and BioCV, as well as movements from a clinical cohort captured with multiview markerless motion capture. The resulting model outperforms existing models for direct regression of biomechanics from images while only slightly underperforming the state-of-the-art monocular biomechanics method that performs more costly inference-time optimization of entire trajectories. --- ### Everybody Tracking Every Body Authors: Daeyun Shin, Yunhan Zhao, Shu Kong, Alexander C. Berg, Charless Fowlkes Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29927v1 We address the problem of 3D body pose estimation of multiple interacting people from their egocentric views with centralized coordination. Each individual wears a camera recording egocentric video and IMU data. Processing this video with VIO SLAM provides high-quality tracking of each egocentric camera through space. The first-person view from one individual provides third-person observations of other people, although these exocentric observations are sparse, intermittent, and of highly variable reliability as both cameras and subjects move. To integrate these synchronized data streams, we propose a diffusion-based approach that fuses estimates of pose based on head motion derived from egocentric camera motion with exocentric pose observations, conditioning on both observation content and reliability. Our model is trained on a mixture of single-person motion-capture data and multi-person video in order to learn rich priors for body motion trajectories and video observation reliability. Evaluation on challenging multi-person datasets suggests our fusion approach improves over motion-only and vision-only baselines in terms of both absolute and relative pose accuracy. --- ### Dior: Drawing the Light of Image via Material-Decoupled Illumination Representation Authors: Xuanpu Zhang, Xuesong Niu, Haoxiang Cao, Ruidong Chen, Jianhao Zeng, Changqian Yu Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29925v1 Controllable image relighting is an important problem in image editing, and hand-drawn scribbles provide an intuitive interface for specifying the desired illumination. However, existing methods do not establish a consistent and effective mapping between scribble inputs and relighting results, limiting their ability to control illumination intensity, chromaticity, and complex spatial distributions. We address this limitation by introducing a material-decoupled illumination representation, termed the Lumi Map, which establishes an explicit mapping between user scribbles and the resulting illumination, thereby improving both relighting accuracy and controllability. Specifically, we use a renderer to synthesize source image-Lumi Map-relit image triplets and train the model to predict the target relighting result conditioned on the Lumi Map. To mitigate the domain gap introduced by synthetic data, we further perform reconstruction training on real relighting pairs, improving the model's generalization to real-world images. Finally, we present Dior-Light, an image relighting method controlled by hand-drawn strokes. Extensive experiments demonstrate that our method outperforms existing approaches in relighting accuracy and enables effective control over illumination intensity and chromaticity on in-the-wild images. --- ### Hallucination Mitigation for Large Vision-Language Models via Implicit Feature Stabilization Authors: Aditi Sarker, Rafi Ibn Sultan, Hui Zhu, Dongxiao Zhu, Prashant Khanduri Published: 2026-08-30 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.29924v1 Large Vision-Language Models (LVLMs) are prone to hallucinations: they fluently describe objects, attributes, and scenes that are not in the image. We connect part of this failure to a measurable property of their representations, feature instability, where mild semantics-preserving perturbations of the input cause large changes in the learned embeddings; hallucination rates rise together with this variability. Existing stability-motivated remedies are explicit, in the sense that they intervene at inference time through latent steering or constrained decoding, and pay for it on every query. We propose implicit stabilization instead: perturbation-invariance is built into the model weights during fine-tuning, and nothing extra runs at deployment. Our framework, INFUSE, first stabilizes visual and textual representations around perturbation-averaged and ground-truth anchors, then aligns the stabilized representations across modalities with bidirectional contrastive objectives. We prove that the anchor's root-mean-square deviation from the perturbation-mean representation shrinks at rate $1/\sqrt{K}$ in the number of views, and that under a Lipschitz decoder, this bounds how much any perturbation can change the model's hallucination behavior. On LLaVA-1.5, LLaVA-1.6, and Qwen3-VL-8B-Instruct, INFUSE reduces AMBER CHAIR by 46-63% relative to each base model, improves ObjHal, MMHal, HallusionBench, and POPE, and preserves VQA-v2 and TextVQA, all with no inference-time overhead. --- ### Towards Continual Test-Time Adaptation of Vision-Language Models in Open-Vocabulary Semantic Segmentation Authors: Chandler Timm C. Doloriel, Yunbei Zhang, Sarthak Kumar Maharana, Muhammad Salman Siddiqui, Tor Kristian Stevik, Fadi Al Machot, Kristian Hovde Liland, Habib Ullah Published: 2026-08-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.29923v1 Open-vocabulary semantic segmentation (OVSS) relies on vision-language alignment to recognize arbitrary text-defined categories, yet this alignment is fragile under continual test-time distribution shift. Our diagnostic analysis reveals that entropy minimization drives patch-level class collapse, continual updates erode vision-language alignment, and redundant gradients from low-shift samples waste computation. We propose Diversify, Anchor, and Filter (DAF), a stabilization framework that augments entropy-based adaptation with a marginal diversity loss that resists collapse, a cross-modal anchor consistency loss that constrains feature drift relative to a frozen source model, and feature salience filtering that skips low-value backward passes to offset part of the source-anchor overhead. We evaluate on five datasets spanning natural scenes, autonomous driving, underwater imagery, and remote sensing with their corrupted variants. Across the evaluated continual shifts, DAF remains stable where entropy minimization collapses, improving mIoU by over 8 points on Pascal VOC20-C, over 9 points on LoveDA, and over 3 points on Foggy Cityscapes compared to the source model, and is robust to aggressive adaptation and learning rate choices. --- ### Sleight of Word Benchmark: Can Language Models Notice If Their Own Output Was Tampered With? Authors: Alberto Cetoli Published: 2026-08-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.29921v1 The output of a Language Model can be tampered with \emph{while} the model is writing it. A simple test can thus be constructed by evaluating the model's perception of this external perturbation. In this spirit, a simple benchmark is built in which a single word is consistently substituted with another in the generation process. We call this method \emph{Sleight of Word}. Two distinct axes are measured: metrics that relate to the model's surprise, as well as an evaluation of the textual reaction for 19 different open-weight language models. --- ### Continual Test-Time Adaptation via Entropy Sensitivity-Guidance in Strict Online Setting Authors: Chandler Timm C. Doloriel, Yunbei Zhang, Muhammad Salman Siddiqui, Tor Kristian Stevik, Fadi Al Machot, Kristian Hovde Liland, Habib Ullah Published: 2026-08-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.29920v1 Test-time adaptation (TTA) promises robustness under distribution shift by updating a pretrained model on unlabeled test data, but strict online TTA with batch size one and no access to source data is especially prone to drift or collapse. We introduce Sensitivity-Guided Erasing Adaptation (SEGA), a method for strict online continual TTA (CTTA) on corruption-style streams. SEGA uses a small number of structured erasures to probe how predictive entropy changes as information is removed, and uses the resulting per-sample sensitivity trajectories to coordinate recovery and sample selection rather than relying on raw entropy or batch statistics. This yields a practical feedback signal for long-horizon batch-size-one adaptation without periodic resets or model reservoirs. In experiments on ImageNet-C, CIFAR10/100-C, and corruption-generated aquaculture streams treated as controlled corruption-style proxies, SEGA yields consistent robustness and stability gains over strong CTTA baselines while reducing backward passes through sensitivity-based gating. --- ### IndicDetect: Evaluating Cross-Lingual LLM-Generated Text Detection for Hindi, Telugu, and Tamil Authors: Bhaskar Ganesh Devalla, Junchao Wu, Nilesh Dokuparthi, Greeshma Yaluru, Tatiana Muniz Rodriguez, Lidia S. Chao, Derek F. Wong Published: 2026-08-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.29919v1 The rapid proliferation of LLMs has further heightened the need to develop dependable AI-generated text detection, especially beyond English. Nevertheless, current benchmarks pay little attention to Indic languages and test detectors in idealized settings that do not represent the real world. We present a generalized benchmark for AI-generated text detection in Hindi, Telugu, and Tamil, which we call IndicDetect, designed to assess the robustness of detectors under realistic distribution shifts. IndicDetect comprises highly curated human-written texts matched with LLM-generated counterparts across various domains and generators, and systematically evaluates detectors in the presence of domain shift, generator shift, and adversarial perturbation. Using a single and repeatable evaluation scheme, we evaluate a wide range of statistical and neural detectors. We find substantial robustness failures: supervised neural detectors perform well in-distribution, while training-free methods degrade considerably under unseen generators and adversarial attacks. The severity of these failures varies across languages, with Hindi exhibiting the largest overall degradation under adversarial perturbations. These results highlight that the primary weakness of existing detectors in Indic settings lies in their robustness, not in their peak accuracy. IndicDetect provides standard data splits, an evaluation protocol, and baselines to establish a robust, language-aware foundation for AI-generated text detection in Indic scripts. --- ### FoundYou: A Unified Model for Personalized Segmentation and Retrieval Authors: Gabriele Trivigno, Marcos Alfaro, Claudia Cuttano, Gabriele Berton, Luis Payá, Carlo Masone Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29917v1 Personalized segmentation and personalized retrieval both aim to identify the same physical object across different images. While the former localizes the object within a target image, the latter retrieves images where it appears. Despite this shared instance-level objective, the two tasks have largely evolved separately and are addressed with distinct solutions. In this work, we introduce FoundYou, a unified framework built on the observation that Segment Anything 2 (SAM 2), trained to preserve object identity across video frames, inherently captures instance-level cues. We leverage this property to match objects across independent images, enabling segmentation and retrieval to emerge as two outcomes of the same instance alignment process. This unified view unlocks new capabilities beyond traditional benchmarks, including few-shot personalized retrieval and promptable personalized segmentation with flexible prompts. Extensive experiments show consistent gains over unified and task-specific methods, including +18.4 mIoU on PerMIS and +17.8 mAP on ILIAS. Performance scales with additional references and remains robust to weaker prompts. Beyond personalization, FoundYou achieves state-of-the-art results on category-level retrieval benchmarks. Notably, our approach keeps the SAM 2-small model entirely frozen and adds only 5.9 M trainable parameters, yielding a 52 M-parameter model that is over 75x faster and 20x smaller than the only prior unified solution. Code is available at https://github.com/ga1i13o/FoundYou . --- ### On the Instance Hardness as a Decision Criterion in TinyML Systems Authors: Tobiasz Puslecki, Krzysztof Walkowiak Published: 2026-08-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.29913v1 TinyML includes the implementation of machine learning on devices with limited memory and computing resources. With the development of technology, AI systems continue to scale in terms of size and computational requirements. This forces researchers to adapt methods to be environmentally sustainable by designing techniques for reducing computational costs and energy consumption in inferring AI models, even in small devices. In this work, we present preliminary findings on a novel application of the tree depth prune instance hardness method to the TinyML system. The results indicate that threshold control can change energy consumption with limited classification quality changes. This method allows us to adjust classification accuracy, thereby influencing computational complexity and energy consumption for inference. We present a work in progress with initial results as a proof of concept. --- ### Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory Authors: Runjia Qian, Zile Wang, Jihai Zhang, Kai Zou, Wei Yu, Jiaxing Li, Zexiang Liu, Yaokun Li, Fei Kang, Kaichen Huang, Mengyin An, Haobo Zhang et al. Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29910v1 Interactive world models extend video generation from offline clip synthesis toward persistent simulation of interactive virtual worlds, enabling applications in games, robotics, embodied agents, and XR. Achieving stable long-horizon interactive generation, however, remains challenging, as the model must simultaneously preserve scene geometry, dynamic consistency, and camera control while supporting real-time autoregressive generation. Building upon Matrix-Game 3.0, we present Matrix-Game 3.5, as shown in Figure 1, which advances real-time interactive world generation toward geometry-aware and long-horizon consistent simulation through three key improvements. First, we propose a unified geometry-aware memory framework, whose patch-memory and tiled-PRoPE components introduce no additional learnable parameters, combining explicit 3D patch retrieval with projective camera conditioning to enable geometry-consistent camera control and faithful long-horizon scene recall. Second, we introduce a static-dynamic disentangled world representation that separately models static scene geometry and dynamic subjects, preserving both geometric consistency and subject identity throughout long-horizon generation. Third, we develop a two-stage progressive real-time distillation framework that converts a bidirectional diffusion model into a few-step causal generator through Perceptual Flow Matching and curriculum based Self-Rollout DMD, enabling minute-long real-time interactive generation. Extensive experiments demonstrate that, with a unified training corpus spanning Unreal simulation environments, open-world games, and internet videos, MatrixGame 3.5 achieves strong performance in long-horizon scene recall, precise camera control, subject consistency, prompt-driven world generation, and stable real-time open-world interaction. --- ### Diffusion-Based Inverse Design of Dielectric Resonator Metasurfaces for Shaping Smart Electromagnetic Environments Authors: M. Tsukerman, K. Grotov, D. Vovchuk, P. Ginzburg Published: 2026-08-30 Categories: cs.LG, physics.app-ph, physics.comp-ph arXiv: https://arxiv.org/abs/2608.29907v1 Future wireless systems are expected to transform the surrounding space from a passive propagation medium into a smart electromagnetic environment, where engineered surfaces control wave propagation, support wireless sensing, and create programmable electromagnetic fingerprints. A key challenge in realizing this vision is the inverse design of metasurfaces for tailored electromagnetic propagation. While forward analysis evaluates the response of a known geometry, the inverse task starts from a prescribed scattering signature and seeks a physically realizable structure that produces it. This inverse task is inherently nonlinear and often high-dimensional, while candidate solutions may be non-unique and provide no direct indication of practical realizability. Here, we introduce a conditional diffusion framework for inverse design of dielectric resonator metasurfaces from target angular scattering patterns. Trained on T-matrix simulated geometry-response pairs, the model learns a conditional distribution of geometries instead of a deterministic mapping, enabling multiple candidate designs for the ill-posed inverse problem. The best generated metasurface achieves a mean percentage error of 1.39%, outperforming CMA-ES optimization (4.1% after 10 h) while requiring only about one minute for after-training inference. The model also produces lower error distributions than deterministic neural baselines for out-of-distribution spectra, highlighting the potential of diffusion models for efficient metasurface design. --- ### OrnaStyler: Ornament-Aware Latent Editing for Content-Preserving 3D Stylization Authors: Tomohiro Aizawa, Shigeru Kuriyama, Chunzhi Gu Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29905v1 Text-guided style editing of 3D assets is essential for adapting existing objects to diverse visual aesthetics in digital content creation. Despite rapid progress in 3D shape modeling, faithfully stylizing an existing asset remains challenging when the desired stylization involves fine-grained structural ornamentation, which requires the model to preserve the source geometry and object identity, while coherently integrating new style-specific details. We propose \textbf{OrnaStyler}, a zero-shot framework for text-guided ornament-aware 3D stylization. Built upon rectified flow-based generative modeling, OrnaStyler introduces an inversion-guided editing strategy that recovers content-aware latent representations at both geometry and appearance levels in a staged manner to facilitate faithful editing. Our core idea is to explicitly model the spatial configuration of stylistic elements, thereby mitigating the fundamental tension between content preservation and style expression in the voxel space. Specifically, at the geometry level, we manipulate voxel representations through flow inversion to synthesize ornament-enhanced structures while preserving the spatial identity of the source asset. Then, at the appearance level, we introduce an adjacency-aware feature inpainting mechanism to harmonize newly generated ornaments with the original content, yielding coherent geometry-appearance integration. Our approach operates solely in the inference phase and enables selective editing over geometric augmentation or appearance stylization. Extensive experiments on both generated and real-world 3D assets against prior methods demonstrate that OrnaStyler achieves state-of-the-art editing performance in terms of content preservation, style fidelity, and overall visual realism. Code is available at: https://github.com/tomohiro0427/OrnaStyler --- ### Off-Manifold Refinement: Guiding Video Generators with a Frozen World Model Authors: Hai Nguyen-Truong, Tuan-Anh Vu, Dang Huynh Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29904v1 Modern video generators routinely fail at physical dynamics: objects float, trajectories violate gravity, contacts vanish. Standard denoising and flow-matching objectives fit visual data distributions but do not explicitly penalize such physical violations. Existing remedies can improve physical consistency, but typically add substantial inference or training cost. Candidate-selection methods generate and score multiple videos, while gradient-based world-model guidance repeatedly decodes and re-encodes intermediate estimates. Generator-internal refinement adds perturbation and re-denoising loops, whereas post-training requires curated data and additional optimization. We propose Off-Manifold Refinement (OMR), an inference-time method that instead injects world-model feedback directly into a single sampling trajectory. During scheduled middle ODE steps, we augment the generator velocity with the gradient of an adapter-space V-JEPA 2.1 surprise energy. This external correction can move the latent away from the uncorrected sampling trajectory and toward regions ranked as more physically plausible by the frozen predictor, after which the generator continues rendering from the corrected state. A small trained latent-to-embedding adapter keeps the gradient tractable at inference, and both the video generator and the world model remain frozen. On our fixed 400-prompt VideoPhy-2 detailed subset, OMR lifts the joint Semantic-Adherence-and-Physical-Commonsense metric from 47.0% to 52.0% (+5.0pp absolute, +10.6% relative) over the base Wan2.2-T2V-A14B sampler. On a separate fixed 50-prompt efficiency subset, it requires $1.71 \times$ the base runtime rather than the multiplicative cost of reward/search alternatives. Project page: https://itruonghai.github.io/omr. --- ### When Less is More: Understanding When Token Filtering Helps and Fails in AI-generated Text Detection Authors: Xiaoyang Han, Lvxiaowei Xu, Ming Cai Published: 2026-08-30 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.29903v1 The rapid advancement of large language models (LLMs) has made AI-generated text detection increasingly critical. Existing zero-shot detectors assume that more token-level evidence leads to more reliable detection. However, our empirical study challenges this consensus: fewer tokens sometimes work better, retaining only 40% can yield optimal performance, yet this benefit is not universal. Using the Entropy Gap Score (EGS), we introduce top-$k$ cumulative probability filtering as a diagnostic probe. Across three representative settings, filtering exhibits strikingly different behaviors. We analyze EGS via typical set theory and quantify its dynamics through entropy calibration and distribution analysis. We find that filtering helps for weak source LMs, where low-entropy tokens are harmful, but fails for strong source LMs, where they are not notably harmful. Our work provides the first systematic analysis showing that some tokens are not merely uninformative but systematically harmful due to entropy miscalibration, revealing a two-sided trade-off in token-level detection. --- ### INTERVenE: Temporal-Abstraction-Interval Based Transformers for Short-Horizon Medical Event Prediction Authors: Shahar Oded, Yuval Shahar Published: 2026-08-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.29901v1 Electronic Health Record (EHR) prediction models in the intensive care unit must learn from sparse and irregular measurements while preserving the clinical meaning of time and supporting transparent decision-making. We present INTERVenE, a family of Transformer architectures whose input is an interval-based, knowledge-based temporal abstraction (KBTA), a token stream of named clinical concepts (states, trends, events, contexts) drawn from a curated medical ontology, rather than an unnamed bin index or a raw measurement triplet. This naming layer is what we ask KBTA to do: it makes the model's per-token attributions resolve to clinical concepts by construction. INTERVenE offers two complementary variants: an auto-regressive decoder that generates future abstraction trajectories with a per-step risk readout (localizing \emph{when} and \emph{after which events} risk rises), and a bidirectional encoder for single-pass joint risk and time-to-event prediction. Evaluated on 57,078 MIMIC-IV admissions against GRU-D, STraTS, and KarmaLego, INTERVenE-Enc reaches a support-weighted AUPRC$_w$ of 0.672, improving by 0.041 over the strongest neural baseline with non-overlapping 95\% bootstrap CIs, while also taking the best AUROC$_w$ (0.901) and length-of-stay MAE (44.4\,h). INTERVenE-Ar (AUROC$_w$ $0.854$, AUPRC$_w$ $0.587$ under the same evaluation contract - a strictly harder generative readout) provides a complementary token-level risk trajectory. An input-representation ablation confirms the lift transfers across structured discretizations, positioning KBTA-based intervals as the interpretable substrate that makes per-token attributions resolve to meaningful clinical concepts within the deployed model. --- ### REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling Authors: Devrim Çavuşoğlu, Emre Akbaş Published: 2026-08-30 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2608.29899v2 Dense retrieval over long documents is expensive. Token-level encoders scale quadratically in sequence length, and most long-context embedding models reach 32K tokens only through architectural workarounds or by stretching billion-parameter LLMs. We propose REIGN (Refurbished Embeddings with Integrated Guidance Networks), a contrastively trained bi-encoder that operates on sequences of contextualised chunk embeddings from a frozen Guidance Network (GN) rather than on raw tokens. REIGN targets multi-chunk inputs, primarily for document-to-document retrieval; single-chunk inputs stay with the GN. Decoupling token-level processing from document-level reasoning, and caching the GN embeddings to disk, cuts per-document training cost by roughly four orders of magnitude relative to chunked Transformer fine-tuning. We also release a synthetic long-document retrieval benchmark for contrastive training and evaluation at long context lengths. Across an in-distribution Wikipedia benchmark, the LoCo out-of-distribution suite, and a real-world patent retrieval case study, REIGN matches dense long-context retrievers at smaller parameter budgets in each regime. A paired significance test puts it on par with models 1.6-4.3x larger on the patent task, and it stays within 0.65 nDCG@10 of a 20x-larger model on LoCo. --- ### When History Is Multimodal: Rethinking Context Management for Long-Horizon Agents Authors: Jiaqi Su, Cong Pang, Jiawei Hong, Tiankuo Yao, Zixuan Chen, Xin Lou, Lewei Lu Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29897v2 Long-horizon agents need a context manager to compress growing interaction histories into a bounded working context, via passive strategies or active strategies that decide how memory is accessed and reorganized. Meanwhile, prior optical-memory work mainly treats pixels as a dense codec for textualized histories, often presupposing that rendering context into optical memory incurs a significant performance drop relative to text, thus coupling this representation with SFT, self-distillation, or reinforcement learning to close this gap, leaving unresolved (i) how visual rendering performs as a context manager under a fair, controlled comparison, and (ii) whether this carrier offers a native advantage when history is inherently multimodal. In this paper, we formulate context management as a budget-constrained history transformation and introduce Visual Rendering (VR) as a representational context manager. Under a shared harness, policy model, trigger, and task domain, we evaluate VR on four text-centric and three multimodal benchmarks against four baselines (No Compression, Discard-All, Sliding Window, Summarization), finding visual memory is a natural carrier of native visual evidence. Building on this finding, we propose VERA (Visual Evidence-Retaining strategy for long-horizon Agents), a training-free context manager built on deterministic rendering with no exposed memory operations: on text-centric benchmarks it renders textual history as VR does, while on multimodal benchmarks it retains native visual observations instead of translating them into text. Across nearly all benchmarks, VERA cuts cumulative non-cache tokens by 31.5%-63.1% versus No Compression, matches existing managers on text-centric tasks, and achieves the highest accuracy among all baselines on multimodal tasks, supporting a modality-preserving view of long-horizon context management. --- ### Joint Spatiotemporal Spectral Neural Operators for Learning PDEs on Irregular Domains Authors: Abdolmehdi Behroozi, Chaopeng Shen Published: 2026-08-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.29892v1 Learning solution operators for partial differential equations (PDEs) on irregular and geometry-dependent domains remains a central challenge in scientific machine learning. While spectral methods provide strong inductive biases for modeling global interactions, they are typically limited to regular domains, and existing neural approaches often require domain warping, interpolation, or costly geometric embeddings. We introduce the \textbf{Graph Spectral Neural Operator (GSNO)}, a neural operator that combines spatial graph spectral decompositions with temporal Fourier transforms through a unified space--time spectral kernel. This formulation enables globally coherent operator learning on non-Cartesian discretizations without domain warping or autoregressive rollouts. By replacing learned geometric embeddings with a graph Laplacian spectral basis, GSNO provides geometry-aware spectral learning with low parameter complexity. Across steady and unsteady PDE benchmarks on irregular and geometry-dependent domains, GSNO achieves strong accuracy with reduced runtime and parameter counts, while demonstrating robust zero-shot generalization across mesh resolutions and geometry families. --- ### MASQ: Mask-Aware Spatiotemporal Quantization for Unsupervised Skeleton Action Segmentation Authors: Xinyao Qin, Linxiang Peng, Youbao Ye, Di Yang, Jiangtao Wang Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29891v1 Unsupervised skeleton-based temporal action segmentation is a crucial task for understanding human behavior in long untrimmed sequences. Recent approaches often rely on discrete quantization to discover action boundaries from motion representations. However, when spatial masking is introduced for representation learning, it can introduce representation ambiguity, while discrete quantization further amplifies small fluctuations in the latent space. The interaction between these two factors often leads to unstable code switching and severe temporal jitter near action boundaries.To address these limitations, we propose a novel Mask-aware Action Spatiotemporal Quantization (MASQ) framework. Our framework decouples the conflicting tasks of spatial feature inference and temporal smoothing.In the spatial dimension, we introduce a Joint-Level Structured Dropout (JLSD) mechanism that masks the entire temporal trajectory of selected joints, to encourage the model to learn discriminative inter-joint coordination patterns. In the temporal dimension, we design a mask-aware velocity loss that enforces motion consistency only on visible joints, that prevents gradient conflicts caused by masked signals and stabilizing temporal predictions. Extensive experiments on three widely used skeleton datasets, including HuGaDB, LARa, and BABEL, demonstrate that the proposed MASQ framework significantly outperforms existing state-of-the-art unsupervised methods. In particular, our model establishes a comprehensive and substantial leading advantage in the Mean over Frames accuracy. --- ### En-ViMedNER: An English-Vietnamese Parallel Biomedical Corpus with UMLS Semantic Type Annotations Authors: Nhu Vo, Phuong Nguyen, Nu Uyen Phuong Le, Inigo Jauregi Unanue, Dung D. Le, Massimo Piccardi, Wray Buntine Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29890v1 Biomedical Named Entity Recognition (NER) is fundamental to healthcare AI applications, including clinical decision support and medical information extraction. While corpora with Unified Medical Language System (UMLS) annotations, such as MedMentions, have driven progress in English biomedical NER, no comparable resource exists for Vietnamese. This paper presents En-ViMedNER, the first English-Vietnamese parallel biomedical NER corpus annotated with UMLS semantic types, which are language-neutral codes providing a shared cross-lingual label space and ensuring direct comparability with existing UMLS-based resources. The corpus contains 4,392 PubMed abstract pairs, 44,892 English-Vietnamese sentence pairs, and 202,949 aligned entity-mention pairs across 21 semantic types adapted from the MedMentions ST21pv dataset. To balance quality and scalability, we have constructed the corpus through automatic translation, expert post-editing, LLM-assisted label projection, and human verification and adjudication. We characterize En-ViMedNER as a large-scale silver-standard corpus with a human-audited and consensus-corrected mini-test subset. We evaluate En-ViMedNER in two settings: (i) Vietnamese-input/Vietnamese-output biomedical NER and (ii) English-input/Vietnamese-output cross-lingual NER. For Vietnamese NER, we benchmark Vietnamese-supervised encoder models, English-supervised multilingual encoder models, and prompt-based LLMs. The best model achieves an F1 score of 52.70 on the test set and 53.78 on the mini-test set. For cross-lingual NER, we benchmark encoder-decoder models and prompt-based LLMs. The best model achieves an F1 score of 45.44 on the mini-test set. We publicly release our corpus, corpus construction pipeline, and baseline models to facilitate future Vietnamese biomedical NLP research. --- ### VibeJam: A User Study Platform for Web Development with Agents Authors: Nishant Balepur, Connor Baumler, Valerie Chen, Eunsol Choi, Rachel Rudinger, Jordan Boyd-Graber Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29889v1 Programming with AI is increasingly agentic, users prompt LLMs to directly edit their code and review the changes, with adoption growing especially for web development tasks. Despite this growth, most NLP work uses offline evaluation and lacks support for online studies, losing insights into how programmers truly use coding agents. We release VibeJam, a browser-based user study platform for users to collaborate with AI agents to develop websites. VibeJam enables agent customization and uses the open-source Aider agent by default, and to mirror downstream use, we add diff review, chat and plan modes, and live website previews. In a pilot study with 55 released, game-based website creation tasks, five experienced AI programmers rate our system as fun, simple, and resembling commercial tools, while 13 junior students use VibeJam to make websites of higher quality than agents in the same task. We open-source VibeJam to spur extensions and support studies on how coding agents can help users. --- ### Sensitivity-Constrained Neural Operators for Data-Efficient Forward and Inverse Modeling of Partial Differential Equation Systems Authors: Abdolmehdi Behroozi, Chaopeng Shen, Daniel Kifer, Kathryn Lawson Published: 2026-08-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.29888v1 Neural operators provide fast surrogates for partial differential equation (PDE) solvers, but their reliability can degrade for high-dimensional spatial inputs and inverse or repeated inference. State-only training constrains solution values but not the learned input--output response. We study sensitivity-constrained neural operators (SC-NOs), which augment standard training with sampled solver-derived Jacobian supervision. Selected sensitivities from differentiable solvers or discrete adjoints are matched during training, allowing response information to be amortized across minibatches without imposing the full Jacobian at every update. We evaluate SC-NO on advection--diffusion and RANS--Spalart--Allmaras benchmarks, input-dimensionality scaling tests, long-horizon autoregressive rollout, and a shallow-water Tohoku tsunami source-inversion case. Sensitivity supervision improves forward prediction and yields larger gains in gradient-based inverse reconstruction of distributed fields. Scaling experiments show an improved accuracy--cost tradeoff for high-dimensional gridded inputs, while ablations indicate that state values and Jacobian information provide complementary supervision. In the tsunami case, SC-FNO reconstructs gridded seafloor deformation from sparse early gauge observations and forecasts subsequent wave propagation in a near-real-time proof-of-concept workflow. These results support sampled sensitivity supervision as a practical way to improve neural PDE surrogates when forward accuracy, inverse stability, robustness, and computational cost must be considered together. --- ### Check The Scoreboard: An Analysis of Scoring Schemes on Multiple-Choice Evaluation Authors: Nishant Balepur, Paiheng Xu, Wei Ai, Eunsol Choi, Rachel Rudinger, Jordan Boyd-Graber Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29887v1 Multiple-choice question answering (MCQA) benchmarks in NLP use number-right scoring (accuracy), but in educational testing, the scoring scheme, the combination of the response mode models follow and the rule for grading responses, is a key design choice that dictates which abilities to reward. We examine how alternatives to number right change what MCQA measures with six education-inspired schemes that assess abilities beyond accuracy: distractor elimination, abstention, confidence calibration, and self-correction. On LLM benchmarks, these schemes: 1) shift rankings of 31 LLMs beyond rephrased number right prompts; 2) better predict the LLMs users prefer in LLM Arena; and 3) reveal distinct model capabilities, like that GPT-5 rarely abstains and readily self-corrects, while weaker open-weight models often abstain and hesitate to eliminate choices. Given the benefits of alternative scoring schemes, we discuss ways to extend them to tasks beyond MCQA. --- ### Structural Hierarchy and Geometry in Molecular Representation Learning Authors: David Sulu, Lorenzo Di Fruscia, Jana M. Weber Published: 2026-08-30 Categories: cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2608.29886v1 Molecular self-supervised learning uses chemical structures to guide which molecular embeddings should be similar. We study whether explicitly encoding a molecule's Bemis-Murcko scaffold and using it to supervise the molecular embedding changes what the model learns. We further test whether this effect depends on the embedding geometry by comparing Euclidean and Lorentz contrastive objectives. Across two augmentation strengths, scaffold-supervised models consistently organize molecules according to both identical and structurally related scaffolds. The resulting embeddings also improve molecular property prediction on several tasks, while the exact gains depend on the predicted property. The effect of scaffold supervision on molecular organization is stronger under Lorentz objectives, but neither geometry provides a consistent overall advantage. These results show that explicitly teaching the relation between a molecule and its structural core can reliably shape the organization of molecular embedding space, while the extent of usefulness of this organization remains task dependent. --- ### Improving Argument Saliency Coverage in Small LLMs for Long Legal Opinion Summarization via Sequence-Level Distillation Authors: Mohamed Elaraby, Ahmed Elhady, Diane Litman Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29884v1 We show that sequence-level distillation from a capable long-context teacher model is a simple, annotation-free, and data-efficient strategy for improving argument saliency coverage in long legal opinion summarization, where small LLMs often struggle to retain the most salient argumentative content. Across student model sizes, distillation consistently surpasses tuning on expert-written summaries in our legal-opinion setting. We further demonstrate that most gains are achieved with as few as ~10 training summaries, highlighting the strong data efficiency of teacher-generated supervision. Finally, we find that summary distillation is sufficient for improvements: reasoning-chain distillation remains competitive with summary-only distillation, but provides marginal benefit when combined with summary supervision. --- ### OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes Authors: Muxin Liu, Tianbo Liu, Jing Xia, Xiaoyang Lyu, Xiaoshan Wu, Bo Wang, Peng Dai, Zhongrui Wang, Shaoshuai Shi, Xiaojuan Qi Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29881v1 Monocular depth estimation has achieved strong open-domain generalization, yet reliable robotic deployment remains difficult in transparent, reflective, and specular environments, where depth sensors often produce missing or biased depth. Existing methods often handle such optical failures with scene-specific preprocessing, auxiliary modules, or post-hoc fine-tuning. While effective in constrained settings, these designs increase architectural redundancy and can over-specialize general geometry models to narrow optical scenarios. We revisit this problem as a localized failure mode within base-model training and identify sensor-induced supervision bias as a key bottleneck: models inherit sensor failure patterns from biased real-depth supervision in optically challenging regions. We then introduce OptiGeo, a bias-aware training framework that rehabilitates biased real supervision using a clean-geometry teacher and residual-trimmed alignment. We redefine transparency-targeted rendering as a compact source of clean optical geometry, rather than a large domain-specific fine-tuning set. With only a small targeted rendering set, OptiGeo learns the geometric structure of transparent objects and regions, correcting local geometry distortions that real sensors cannot reliably supervise. Despite only 30M parameters, OptiGeo outperforms substantially larger 300M-scale monocular models and billion-scale multi-view baselines on transparent-scene benchmarks, while remaining competitive on general zero-shot depth and boundary sharpness. Real-world navigation cases further validate its practicality as an efficient perception module in optically challenging scenes. --- ### Perceive to Hypothesize, Verify to Ground: An Agentic Reasoning Framework for Open-World Geo-Localization Authors: Yutian Jiang, Ruijie Li, Sisuo Lyu, Xixuan Hao, Qingxiang Liu, Yongzi Yu, Yuxuan Liang Published: 2026-08-30 Categories: cs.AI, cs.MM arXiv: https://arxiv.org/abs/2608.29880v1 Open-world geo-localization requires models to reason over ambiguous visual cues through multi-step reasoning and external knowledge grounding. While recent large vision-language models exhibit strong multimodal reasoning capabilities, existing approaches still suffer from perceptual hallucination and context drift due to the lack of explicit evidence-grounded verification. In this work, we reformulate geo-localization as a human-like perceive-then-verify reasoning problem and propose GeoPAVE (Geo-localization Perception-and-Verification-Engine), a bi-level agentic framework that contains perception-based hypothesis generation via single-pass rollouts and verification-based evidence grounding for decision actions: support, refute, and refine. To support rigorous evaluation, we further introduce PAVED, a novel dataset derived from real-world user check-in data, equipped with comprehensive reasoning trajectories featuring multi-hop queries, multi-round tool invocations, and structured perception-verification traces. The dataset and code are available at https://github.com/Arandinglv/GeoPAVE. --- ### Towards an Expressivity-Normalized Energy-Demand Comparison of ANNs and SNNs Authors: Miriam Kranzlmüller, Pascal Esser, Gitta Kutyniok Published: 2026-08-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.29869v1 Spiking neural networks (SNNs) are often regarded as energy-efficient alternatives to artificial neural networks (ANNs), yet their advantage depends critically on both network architecture and data properties. We develop an analytical framework to compare fully-connected ReLU ANNs and integrate-and-fire SNNs for time-series data with respect to their theoretical energy efficiency at matched expressive capacity. By relating an inference-energy model to theoretical bounds on representational expressivity, we derive an expressivity-normalized efficiency ratio and explicit thresholds in network width, spike sparsity, and ANN depth scaling. Our analysis characterizes the regimes in which event-driven computation offsets the temporal overhead of SNNs, providing capacity-aware principles for designing energy-efficient temporal networks. It shows that ANNs exceed SNNs in expressivity-normalized efficiency only in specific regimes. --- ### Partially Linear Autoencoders for Manifold Learning and Dimensionality Reduction Authors: Louen Pottier, Louis Lesueur, Anders Thorin Published: 2026-08-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.29867v1 Autoencoders are widely used for nonlinear dimensionality reduction and manifold learning. While most common implementations rely on both nonlinear encoders and decoders, we investigate the specific role of the encoder and the extent to which it can be constrained to be linear without reducing accuracy. We conduct a comparative study on four autoencoder architectures: standard fully nonlinear autoencoders (AE), linear-encoder autoencoders (Lenc-AE), linear-decoder autoencoders (Ldec-AE), and fully linear autoencoders (LAE), evaluated on synthetic manifolds, computational mechanics data sets, and real-world image data sets including MNIST. We demonstrate that imposing a linear encoder preserves most of the representational capacity of the autoencoder, provided the decoder remains nonlinear. In particular, Lenc-AE consistently outperforms both Ldec-AE and LAE, and achieves reconstruction quality comparable to fully nonlinear AE, while offering advantages in terms of parsimony and interpretability of the latent representation. These results suggest that the nonlinear decoder is the critical component for manifold learning, rather than the encoder. A geometric interpretation of this finding is developed, which identifies the precise conditions under which a linear encoder is sufficient, and the specific manifold configurations that expose its limitations. --- ### ManGo: Manga Active Narrative Grounding Optimization Authors: Hao Qiu, Junyan Wang, Zheyuan Liu, Lei Fan, Hong Jia, Lianbo Guo, Zhulin Tao Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29865v1 Manga visual question answering requires models to answer questions over panel-based visual narratives, where relevant evidence is distributed across ordered panels, embedded text, recurring characters, and implicit event transitions. This structure makes passive page encoding insufficient, as the model must identify which panels to inspect, what clues to retain, and when the accumulated evidence is sufficient for answering. We propose ManGo (Manga Active Narrative Grounding Optimization), an unsupervised framework for active manga visual question answering. ManGo introduces Active Narrative Sketching (ANS), which iteratively selects panels, extracts concise grounded clues, and decides when to stop, forming a compact question-directed evidence sketch before answer generation. To optimize this behavior without human-annotated answers or rationale paths, ManGo samples multiple ANS rollouts and applies group-relative training with two rewards: answer preference from listwise self-ranking and path consistency from stable ordered panel trajectories. The combined reward is optimized with group-relative policy training, encouraging the model to improve both final answers and the panel-level evidence paths that support them. Experiments on standard manga understanding benchmarks show that ManGo achieves state-of-the-art performance across different settings. --- ### Uncertainty-Driven Replay Memory for Reinforcement Learning Authors: Sheeraja Rajakrishnan, Alexander G. Ororbia, Travis Desell, Daniel E. Krutz Published: 2026-08-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.29860v1 Uncertainty estimation provides promising capabilities for reinforcement learning (RL) agents. Notably, estimating uncertainty can reduce the training time and enable agents to obtain greater rewards over time by exploiting information related to whether an action would facilitate exploration of portions of an environment that are well-known versus those that are relatively unknown. In this work, we propose a novel formulation of the experience replay buffer commonly used in RL that we call uncertainty-driven replay memory (UDRM), which entails an update scheme for internally stored memories based on uncertainty estimates obtained by an RL model during training. In contrast to existing forms of RL, which typically use temporal difference error or the distribution of transitions to update the replay memory buffer and train RL controllers, our scheme biases the memory buffer to store more uncertain transitions that will improve an RL agent's generalization throughout training. Experimental results demonstrate that our proposed uncertainty-aware replay buffer enables an RL agent to obtain higher rewards during training compared to other existing uncertainty-aware RL frameworks. --- ### GenRubric: Self-Evolving Rubric Generation for Scalable LLM Evaluation Authors: Yifan Chen, Haitao Li, Qingyao Ai, Fengbin Zhu, Tat-Seng Chua, Min Zhang, Yiqun Liu Published: 2026-08-30 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.29856v1 Large language models are increasingly used as scalable evaluators for open-ended tasks. However, many LLM judges derive query-specific criteria during scoring, leaving the evaluation requirements insufficiently specified and their coverage difficult to audit. Query-specific rubrics make these requirements explicit, but expert-written rubrics are costly to construct, while existing automatic methods typically rely on inference-time refinement or external supervision. We introduce GenRubric, a self-evolving framework that improves rubric generation from unlabeled queries without requiring additional human annotations during self-evolution. Our approach is based on rubric-induced self-consistency: independently sampled rubrics for the same query provide partial views of its latent evaluation requirements, and a comprehensive rubric should induce a response that generalizes across these complementary evaluation views. We implement this principle through reinforcement learning, combining a cross-rubric comprehensiveness signal with group-level and criterion-level rewards for rubric quality. We train GenRubric models at 4B, 8B, and 14B scales across multiple domains. Experiments on human-annotated rubric benchmarks show that self-evolution improves the agreement between evaluations induced by generated rubrics and those induced by expert-written rubrics. The improvements further generalize to held-out domains, demonstrating the potential of self-evolving rubric generation for scalable and query-specific LLM evaluation. Code and models are publicly available at https://github.com/foggpoy/GenRubric. --- ### MariSat: A Maritime Dataset for Instance Segmentation of Objects in Satellite and Aerial Images Authors: Amir Abbes, Ines Harrabi, Lucas Justin Yirepoa Kinda, Rim Trabelsi, Adnane Cabani, Fatma Abdelkefi Published: 2026-08-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.29852v1 Automated maritime surveillance from satellite and aerial imagery requires large, precisely annotated datasets, which remain scarce for the instance-segmentation task, particularly for small vessels in cluttered port environments. We present MariSat, a new benchmark dataset of 1260 aerial and satellite images covering diverse port and coastal scenes, annotated at the pixel level for eight maritime object classes (sailboat, yacht, jet-ski, fishing boat, cruise ship, military vessel, tugboat and cargo ship). The dataset was produced through a semi-automatic annotation pipeline combining the textpromptable segmentation model SAM 3 with a cascade of geometric and colorimetric post-processing filters, followed by a manual correction and quality-control pass performed with the CVAT annotation platform. We describe the image-collection methodology, the annotation and correction process, and the resulting data organization. We also report class-wise statistics for the training, validation, and test splits. MariSat has already been used to fine-tune and benchmark segmentation and detection models (SAM 3 and YOLO11) for real-time maritime monitoring. We report detailed quantitative and per-class results for both tasks. The MariSat dataset is publicly available on GitHub : https://github.com/amirabbes/P2M-Maritime-Segmentation ---