# Research Papers — 2026-09 · bundle page 116 of 266 > Full-text markdown of papers #5751–5800 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/116 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/115.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/117.md) ### Identifying Representational Biases in Datasets Using PCA: A Max-Disparity Partition Framework Authors: Arjun KM, Shashi Jain Published: 2026-09-21 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.24556v1 Principal Component Analysis (PCA) minimises aggregate reconstruction error, which can inadvertently represent majority subgroups with substantially higher fidelity than minority subgroups. Fairness-aware extensions of PCA correct this disparity but require group labels as input. We address the logically prior question: given only a data matrix, which binary partition of the data suffers the greatest representational disparity under a shared PCA projection? We formalise this as the max-disparity partition problem and propose a greedy local-search algorithm, grounded in the Fiduccia-Mattheyses bipartitioning framework, that discovers the disparity-maximising partition without any predefined group labels. Two benchmark algorithms, a fixed-projection sorting baseline and a simulated-annealing variant, confirm that the greedy solution is empirically near-optimal. Having identified the partition, we attribute the disparity to specific features via PCA loading scores and association rule mining, enabling a practitioner to assess whether the disadvantaged group corresponds to a human-meaningful minority. On the Predict Students' Dropout and Academic Success dataset, representational disparity is driven predominantly by institutional and programmatic proxies for socioeconomic disadvantage, with gender emerging as a secondary but consistent contributor within the disadvantaged group. The discovered partition is then passed directly to Fair PCA, completing a detect-explain-mitigate pipeline. --- ### The Endless Exam: Mathematical Constructions from Today's Models toward Superintelligence Authors: Muhan Zhang Published: 2026-09-21 Categories: cs.AI, math.HO arXiv: https://arxiv.org/abs/2609.24555v2 We introduce the Endless Exam, a benchmark spanning fourteen parameterised families of mathematical construction problems, with verifiable scores that distinguish progress before and beyond published mathematical frontiers. Each submitted object is checked automatically for validity and assigned a relative quality score against a published frontier or construction baseline, without capping improvements at 1. The benchmark draws long-term challenges from open mathematical problems and generates larger instances by varying their parameters. Compact certificates allow large constructions to be verified without listing every element. Across nine models evaluated on 69 distinct instances, continuous quality scores distinguish performance even though none of the 30 published-frontier references is surpassed. Size-quality curves show how construction quality changes as problem size increases. We release the generators, verifiers, references, model responses and analysis to support continued measurement before and beyond human frontiers. --- ### Toward a Unified Mathematics of Concepts Authors: Chen Shani Published: 2026-09-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.24554v1 Concepts are commonly defined as abstract, compact representations of knowledge and treated as basic units of intelligent behavior. Yet, cognition, psychology, and AI lack a shared mathematical language for them. Modern systems represent concepts as vectors, distributions, symbols, graphs, and other structures, but these formalisms are typically treated as competing rather than as solutions to a common problem. We propose an operation-based view that evaluates mathematical frameworks by the conceptual operations they support, identifying thirteen operations (including similarity, composition, generalization, and grounding) that recur across cognition, psychology, and AI. We show that ten frameworks embody distinct commitments to concepts as self-contained content, relational structure, or evolving process, and that these commitments determine which operations each supports naturally. For example, vector-based models facilitate graded similarity and generalization but struggle with explicit composition, whereas symbolic models support composition but offer but generalize poorly. No single framework we examined naturally supports all operations without extension. We test this account empirically using categorization as a case study, operationalizing nine theories on the same items against human judgments. Despite addressing the same conceptual question, the theories produce different procedures and results, demonstrating that mathematical commitment shapes what a theory can explain. We call for hybrid formalisms that treat content, relation, and process as jointly primary. --- ### Incentive Noise and Structural Prior Infusion for Multi-modal Object Re-Identification Authors: Weixiang Zhou, Yuhao Wang, Xingguo Xu, Weizhen Zhou, Zhixun Su, Jinshan Pan, Cong Wang Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24539v1 Multi-modal object Re-Identification (ReID) benefits from complementary information across heterogeneous imaging modalities. To further enrich semantic representation, text descriptions have recently been incorporated as an additional modality. However, recent vision-language approaches often treat text descriptions as clean, deterministic signals and overlook their inherent noise, including modality-mismatched phrases and semantically ambiguous expressions. Moreover, prevailing methods lack explicit mechanisms to reconcile fine-grained structural discrepancies between modalities, even after high-level semantic alignment. To address these challenges, we propose a novel framework centered on Positive-Incentive Noise (π-noise) and structured prompt modulation. First, the Semantic Cross-Modal Modulator harnesses task-aware π-noise, sampled from a distribution conditioned on both visual and text inputs, to perturb global tokens and enable semantics-guided cross-modal compensation. Second, the Structure-Aware Prompt Adapter injects learnable geometric priors via prompts to enhance spatial consistency. Third, the Context-Aware Sparse Fusion module distills structural context to guide adaptive fusion while shielding identity features from noisy local details. Experiments on three multi-modal ReID benchmarks demonstrate the effectiveness and robustness of our approach. The code is available at https://github.com/zw-absin/INSPI. --- ### QLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein Annotation Authors: Demian Pavlyshenko, Bohdan Pavlyshenko Published: 2026-09-21 Categories: cs.CL, cs.AI, cs.NE, q-bio.QM arXiv: https://arxiv.org/abs/2609.24538v1 Functional annotation of newly sequenced proteins remains a bottleneck in molecular biology: the number of sequences in public repositories grows far faster than the capacity for manual curation. Most computational approaches consider annotation as multi-label classification over a fixed ontology, which constrains predictions to a predefined label set. In this work we study the the protein annotation as a sequence-to-text generation problem. We fine-tune the 3B-parameter Ministral 3 base model with QLoRA (4-bit NF4 quantization with low-rank adapters) on sequence annotation pairs. We assess predictions with an LLM-as-expert protocol: a GPT model prompted as a senior molecular-biology curator scores organism identification as binary and function annotation quality. We conclude that QLoRA-fine-tuned compact LLMs can generate curator-style annotations with genuine biological value for a substantial subset of proteins. We also discuss future directions in data quality, model scaling, and evidence grounding that are needed to make the approach sufficiently reliable for practical use. --- ### MIRAGE: Full-Body Bystander Privacy for Smart Glasses with Consent-Based Restoration Authors: Muhammad Umair, Muhammad Danial Maqbool, Fatima Arshad Cheema, Kapal Dev, Muhammad Hamad Alizai, Muhammad Ali Siddiqi, Naveed Anwar Bhatti Published: 2026-09-21 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2609.24537v1 Video recording on smart glasses exposes more than faces. Continuous capture reveals full-body biometric signatures, including gait, posture, and silhouette, that enable person re-identification (ReID) even after conventional face sanitization. We present MIRAGE, a three-tier architecture for privacy-preserving smart glasses that enforces full-body privacy, supports synthetic full-body replacement, and retains encrypted recovery material for consent-based restoration. We implement MIRAGE on a Raspberry Pi~5 (a CPU-only proxy for smart-glasses compute), companion phones, and a cloud generative backend. Compared to prior systems, MIRAGE achieves 0.948 AP and 0.976 AR while accurately detecting the complete visible body. Its bounding box masking reduces learned silhouette-based ReID to essentially random guessing, with 10.86% Rank-1 accuracy compared with an 11.12% measured chance level. Even against an adaptive adversary retrained on MIRAGE's sanitized pose signals, Rank-1 gait identification drops from 90.25% to 26.20%, removing 72.5% of the adversary's identification advantage. --- ### Dynamic Thermal Gaussians: Multimodal 4D Gaussian Splatting Authors: Rongfeng Lu, Lifeng Lin, Xiaobao Wei, Quan Chen, Ming Lu, Yitian Xue, Yaoqi Sun, Yuhan Gao, Anke Xue, Chenggang Yan Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24531v1 Thermography plays a vital role in military and broader thermal analysis applications. Recent progress in 3D thermal reconstruction has extended temperature analysis from 2D to 3D space, yet most existing works assume static temperature distributions, neglecting the temporal dynamics of heat transfer in real-world environments. To address this limitation, we propose the first dynamic RGB-Thermal reconstruction framework for complex scenes. Our method jointly models RGB appearance, thermal observations, and scene geometry as they change over time. Specifically, we introduce a multimodal dynamic scene representation that anchors both the color and thermal modalities to a shared geometric substrate, ensuring their consistency under spatiotemporal deformations. We further design multimodal embeddings to enhance the motion expressiveness for each modality, and propose a multimodal routing mechanism that retains a unified set of shared multimodal Gaussians as the geometric backbone while adaptively spawning modality-specific Gaussians to strengthen the representational capacity in detail-rich regions of each individual modality. In addition, we contribute a novel benchmark dataset featuring high-frequency temperature variations to facilitate the evaluation of 4D reconstruction. Extensive experiments demonstrate that our method achieves high-fidelity spatiotemporal reconstruction of both appearance and temperature. Our code and dataset are available at: https://github.com/LinLif1869/DTG. --- ### Beyond Point Prediction: Artificial Representative Trees with Uncertainty Authors: Lea L. Mairhöfer, Silke Szymczak, Björn-Hergen Laabs, Tuwe Löfström-Cavallin Published: 2026-09-21 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2609.24528v1 Random forests (RFs) predict well but are opaque, whereas single decision trees are interpretable but unstable. Artificial representative trees (ARTs) were developed as interpretable surrogate models for RFs, but their use as standalone prediction models with uncertainty quantification has not been systematically investigated. We combine ARTs with leaf-wise Mondrian conformal predictive systems (CPS), enabling a single tree to provide continuous predictions, prediction intervals, and probabilities of exceeding arbitrary thresholds. We compared ARTs with CPS against decision trees with CPS and separate regression and probability trees across five simulation scenarios, 21 benchmark datasets, and a cross-sectional NHANES example data set. Repeated cross-validation assessed predictive performance, interpretability, and stability. ARTs with CPS yield compact, structurally stable trees with substantially more reproducible split-variable selection than decision trees across benchmark datasets and NHANES. Decision trees showed slightly better predictive performance and narrower prediction intervals, while coverage was broadly comparable. CPS-based trees generally achieved lower and less variable Brier scores than multi-model approaches. Combining ARTs with CPS therefore provides a single, interpretable, and stable model for continuous predictions and calibrated probabilities, balancing predictive performance with reproducibility and transparency in settings where stability and interpretability are essential. --- ### ME-VLM: A Unified VLM for Embodied Cognition and Agent Coordination Authors: Foundation Model, Li Auto Inc Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24526v2 Physical AI requires models to ground visual and linguistic understanding in real-world environments while accounting for environmental constraints and execution feedback. We introduce MachEmbodied-VLM (ME-VLM), a unified vision-language model with two variants, 4B and 35B-A3B, that brings together embodied cognition and multimodal agent capabilities. Our work emphasizes physical perception and spatiotemporal reasoning, together with planning, interaction, and outcome assessment in both digital and physical environments. We construct training data spanning embodied and multimodal agent tasks, including execution observations and feedback to support outcome assessment and decision refinement. The training pipeline comprises embodied capability injection, separate reinforcement learning of embodied and multimodal-agent experts, and multi-teacher on-policy distillation that consolidates their complementary capabilities into a single model. Experiments show competitive performance on both embodied and agent benchmarks, as well as on autonomous-driving and embodied-navigation tasks. For edge deployment, visual token compression, W4A8 quantization, and hardware-software co-optimization enable on-device inference of the 4B variant on the M100, reducing prefill latency from 400 ms to 188 ms. Project Page: https://machembodied.com/ME-Brain/ME-VLM.html Code Repository: https://github.com/MachEmbodied/ME-VLM --- ### Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma by Integrating Multimodal Ultrasound and Clinical Data: A Multicenter Study Authors: Jun Cheng, Yuanyuan Kong, Qing Huang, Xiaotong Tan, Licong Dong, Yulong Han, Wufeng Xue, Ruobing Huang, Dong Ni, Qi Yang, Jie Yu, Ping Liang Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24524v1 Background: Microvascular invasion (MVI) predicts recurrence and survival in hepatocellular carcinoma (HCC) but requires postoperative histopathology for diagnosis. We developed and validated a model integrating multimodal ultrasound and clinical data for preoperative MVI prediction. Methods: This multicenter study included 489 patients with HCC from eight centers. All patients had B-mode ultrasound (BUS), color Doppler flow imaging (CDFI), dynamic contrast-enhanced ultrasound (DCE-US), and clinical information. Data from seven centers (n = 421) were used for model development with five-fold cross-validation; data from the remaining center (n = 68) formed an independent external validation cohort. The proposed multimodal information fusion network used modality-specific encoders, a hemodynamic temporal change module for bidirectional DCE-US perfusion changes, and a representation consistency learning module to align heterogeneous ultrasound representations before Transformer-based fusion. Results: In external validation, DCE-US achieved the highest single-modality area under the receiver operating characteristic curve (AUC; 0.8545+/-0.0198), versus clinical information (0.6715+/-0.0156), CDFI (0.6435+/-0.0344), and BUS (0.6087+/-0.0417). Pixel-difference sampling and the proposed temporal module outperformed alternative sampling and video representation methods. The full model achieved the best performance, with an AUC of 0.8953+/-0.0180, accuracy of 81.18%+/-2.83%, sensitivity of 86.40%+/-6.69%, and specificity of 78.14%+/-6.28. Conclusions: Integrating multimodal ultrasound and clinical information enabled promising preoperative MVI prediction in HCC. DCE-US was the main source of predictive information, while BUS, CDFI, and clinical information provided complementary value. The proposed framework may support preoperative risk stratification and individualized clinical decision-making. --- ### Not All Task Vectors Need Equal Rank: Energy-Proportional Allocation for Model Merging Authors: Hyunjoong Cho, Jinhyeok Jang Published: 2026-09-21 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.24517v1 Model merging aims to combine multiple fine-tuned models derived from a common pretrained model into a single multi-task model without additional joint training. Recent spectral merging methods improve over simple weight averaging by exploiting low-rank structures of task-specific updates, but they commonly assign the same rank capacity to every task. This uniform allocation ignores that task vectors can have heterogeneous spectral complexity, causing the shared merging space to be used suboptimally. In this paper, we propose Spectral Energy-proportional Rank Allocation (SERA), a simple task-adaptive strategy that allocates ranks according to the singular-value energy structure of each task vector. By assigning richer spectral capacity to complex or isolated tasks and fewer directions to compact tasks, SERA extends SVD-based model merging from uniform-capacity merging to task-dependent capacity allocation. Experiments under standard vision model merging protocols show that SERA improves multi-task merging performance while preserving the same total rank budget as existing spectral merging methods. Further analysis demonstrates that task-level spectral concentration is closely related to the per-task effect of adaptive rank allocation, providing insight into when and why SERA is effective. --- ### LLJ Cards: Best practices for the Use of LLMs as Judges Authors: Khaoula Chehbouni, Melina Medjdoub, Florian Carichon, Golnoosh Farnadi, Jackie Chi Kit Cheung Published: 2026-09-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.24516v1 In recent years, large language models (LLMs) have emerged as a popular alternative for evaluation. Often referred to as LLMs as judges (LLJs), these systems have been widely adopted by researchers and practitioners across a broad range of measurement tasks, driven by their strong performance, scalability, and cost-effectiveness relative to human judgment. However, a growing body of work has shown that the use of LLJs raise concerns about their validity and reliability as evaluators. Existing efforts to address these challenges have largely focused on developing bias-mitigation techniques and refining prompting strategies. While these approaches represent an important step forward, they primarily offer technical fixes and leave a more fundamental challenge unaddressed: the lack of standardized, transparent, and reproducible evaluation practices. In this paper, we introduce LLJ Cards, a framework that synthesizes best practices from measurement theory, natural language generation, and machine learning literature into practical guidelines for LLJ-based evaluations. While LLJs offer a promising path toward scalable evaluation, their effective use requires grounding in rigorous evaluation principles to ensure validity, reliability, and reproducibility. LLJ Cards addresses this need by providing a structured framework for applying these principles in the design and reporting of automated evaluations. --- ### Beyond Predictable Paths: Redefining AI Security Incident Reporting for Agents Authors: Anastasia Pustozerova, Eugene Bagdasarian, Luca Beurer-Kellner, Battista Biggio, Nico Ebert, David Filip, Marc Fischer, Heather Frase, David Hofer, Juliane Hoffmann, Daphne Ippolito, Somesh Jha et al. Published: 2026-09-21 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.24515v1 AI agents are being deployed rapidly, accompanied by a growing number of AI-specific attacks and corresponding incidents. As incident reporting becomes increasingly important for legal compliance, governance, accountability, and security; current frameworks must be adapted to the unique characteristics of AI agents. In this paper, two editorial authors compare AI systems and AI agents and, drawing on input from 23 experts in academia and industry, identify the information required for reporting incidents where the security of AI agents is harmed. %involving AI agents. Potential reporting elements include, for example, agent memory and memory accesses, actual and potential levels of autonomy, and tool usage. Based on these findings, we identify several open research questions, including how to efficiently record incidents and how to determine whether vulnerabilities and incidents generalize. Expert feedback also highlighted potential reporting weaknesses, such as risks of data leakage and attacks targeting the reporting infrastructure itself, creating additional research needs. Lastly, we summarize privacy requirements and outline research directions for the secure and trustworthy deployment of AI agents. --- ### 0.5%>100%: Bidirectional Reciprocal Learning for Referring Image Segmentation Authors: Xiaoqiang Lu, Licheng Jiao, Lingling Li, Yuting Yang, Long Sun, Wenping Ma, Xu Liu, Fang Liu Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24510v2 Recent advances in vision foundation models (VFMs) have shown remarkable capabilities across diverse unimodal visual tasks. However, adapting VFMs to referring image segmentation (RIS) typically necessitates precise vision-language alignment via full fine-tuning, incurring substantial computational overhead and risking catastrophic forgetting. While existing parameter-efficient fine-tuning (PEFT) methods enable safe knowledge transfer with minimal training costs, they predominantly operate independently within individual modalities or focus exclusively on unidirectional guidance from language to vision, overlooking progressive cross-modal interaction and visual feedback for textual refinement. To address these limitations, we propose $\textbf{B}$idirectional $\textbf{R}$eciprocal $\textbf{L}$earning ($\textbf{BRL}$), a novel adapter-based PEFT framework that facilitates hierarchical, bidirectional information flow within both token-mixing and channel-mixing layers of frozen foundation models. Specifically, BRL introduces two complementary lightweight modules. The Reciprocal Attention Adapter (RAA) performs cross-modal query-key exchanges at the token level, enabling visual and linguistic tokens to mutually attend to each other for fine-grained spatial grounding. The Reciprocal Gate Adapter (RGA) generates cross-modal gating signals at the channel level, allowing global semantic context from one modality to adaptively recalibrate channel activations of the other. Extensive experiments on RefCOCO, RefCOCO+, and RefCOCOg benchmarks demonstrate the superiority of BRL over prior RIS methods, achieving state-of-the-art performance while requiring less than 0.5% backbone parameter updates. Code and models will be released at https://github.com/xiaoqiang-lu/BRL. --- ### On Emergent Capabilities and Model Merging Authors: Luca Zhou, Emanuele Rodolà Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.24504v1 Fine-tuned checkpoints and adapters now fill public repositories, and the most common operation applied to these artifacts is model merging: arithmetic on their weights that assembles capabilities cheaply. We ask what this operation does to emergent capabilities: behaviors an artifact carries that were never an explicit training target. Studying two independent testbeds (activation oracles and emergent-misaligned models) across three model families, we find that the answer is threefold. First, merging preserves an emergent capability that both parents carry: merging two misaligned checkpoints retains most of their broad misalignment across the whole mixing range. Second, merging cannot create an emergent capability that is superadditive in its parents: no weighted merge of two single-task oracles reaches the jointly-trained oracle's auditing ability. Third, when only one parent carries the capability, merging dilutes it faster than the trained capability that accompanies it: the gap is significant in most settings. In short, emergent behaviors of an artifact do not compose the way its trained capability does. --- ### Tensor Completion using Subspace Information Authors: Jingyang Li, Michael K. Ng Published: 2026-09-21 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2609.24501v1 Tensor completion has attracted significant attention in both applications and theoretical research. Under standard uniform sampling, existing polynomial-time guarantees generally require more observations than the number of degree of freedom, motivating the study of a possible statistical-to-computational gap in highly missing regimes. Fortunately, in many practical scenarios, side information is available, which can provide valuable insights to mitigate these challenges. In this paper, we introduce an algorithm called Tensor Completion using Subspace Information (TCSI) that incorporates side information through an estimated subspace. Our approach first extracts the subspace from the available side information and then reformulates tensor completion as a matrix regression problem. We provide a theoretical analysis showing that, when accurate subspace information is available, the required sample complexity is reduced to nearly linear order in the uncoupled ambient dimensions, removing the coupled-mode dimension from the leading term. Leveraging the estimated subspace information, we obtain a less stringent sufficient signal-to-noise ratio requirement than those in several existing passive-uniform-sampling guarantees. Under additional mild conditions, we obtain a sharper statistical error bound. Our theoretical findings are supported by numerical simulations. We apply TCSI to the reconstruction of global Total Electron Content (TEC) maps and observe lower reconstruction errors than the compared methods in our experiments. --- ### CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention Authors: Xuezhi Xiang, Jiayao Liu, Heqi Xiang, Yuqi Hu, Yiming Chen, Shanjun Zhang Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24494v1 Accurate monocular depth estimation serves as a core enabler for single camera scene understanding. However, existing self-supervised monocular depth estimation methods generally suffer from the bottleneck of inefficient cross-scale information interaction and difficulty in balancing local and global spatial modeling. In this paper, we propose CMambaDepth, a self-supervised framework that achieves efficient multi-scale feature fusion and fine-grained contextual modeling via channel-wise selective state propagation. Specifically, Bidirectional Channel Mamba (Bi-CMamba) aligns encoder features across scales and enables bidirectional information exchange among ordered scale groups. Unidirectional Channel Mamba (Uni-CMamba) progressively aggregates decoder features and retains fine-grained scale groups through a group selection mechanism for subsequent fusion. Furthermore, a Hybrid Attention Module (HAM) is introduced to combine large-kernel local context and Manhattan self-attention for complementary spatial modeling. Experimental results demonstrate that our method achieves highly competitive performance. Specifically, our model achieves an AbsRel of 0.094 and an RMSE of 4.156 on KITTI, and an AbsRel of 0.140 on DDAD. In the zero-shot cross-dataset generalization test on NYUv2, it attains an AbsRel of 0.232, outperforming the baseline RA-Depth by 7.2%. --- ### Identity-Consistent Analysis of Long-Shot Windsurfing Video: A Domain-Specific Offline Tracking System Authors: Bertil Braun Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24492v1 Long-shot windsurfing video combines small targets, large camera pans, prolonged overlaps, and rapidly changing backgrounds. The desired output is not a generic MOT trace but a separate, stable rider-relative video for each surfer; one false identity merge can invalidate an otherwise useful result. We present an offline analysis system that detects surfers, forms conservative local tracklets, links them globally with camera-compensated motion and a foreground-masked sail-color descriptor, and uses two pose keypoints on the rig to drive a rider-relative virtual camera. The tracking stage is evaluated on 21 manually reconstructed development videos containing 41,004 retained observations. On this fixed-observation protocol, the production system achieves 0.957 pairwise precision, 0.918 recall, and 0.937 F1, compared with 0.792 F1 for OC-SORT and 0.828 for BoT-SORT. Compared with OC-SORT, it reduces fragmentation excess from 845 to 42, but nine of its 95 output tracks mix rider identities and these errors affect seven of the 21 videos. --- ### Lifted Bellman Linear Programming for Offline Reinforcement Learning Authors: Hyukjun Yang, Jongchan Park, Narim Jeong, Donghwan Lee Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.24489v2 Offline reinforcement learning (RL) typically trains a critic by minimizing a regression loss against bootstrapped value targets stabilized by target networks with exponential moving average (EMA) updates. Multi-step targets incorporate behavior-policy actions and therefore require off-policy correction. We instead impose in-sample Bellman optimality on the critic through inequality constraints. We formulate the Lifted Bellman Linear Program (LBLP), which lifts the linear programming characterization of Bellman optimality to the joint $(Q,V)$ space so that every constraint involves only state-action pairs in the dataset. Its unique minimizer is the in-sample optimal pair, and constraints along $K$-step segments of dataset trajectories leave this minimizer unchanged for any rollout policy and horizon. Under deterministic dynamics, this minimizer lies between the best dataset return and the optimal value. Relaxing the constraints into hinge penalties recovers the same solution above a finite penalty coefficient in the tabular case. Approximate Lifted Bellman Unconstrained Minimization (ALBUM) implements this relaxation with neural networks and detaches the $K$-step rollout targets by stop gradient. Its objective contains no squared regression onto bootstrapped targets, so it can be trained without target networks or EMA updates. Under deterministic dynamics, the LBLP solution is a stationary point of the detached update under a coefficient condition independent of $γ$ and $K$, and the inequality constraints allow discounted returns along dataset trajectories to serve as lower bounds without off-policy correction or action chunking. On OGBench, ALBUM uses a single critic with a Gaussian policy, matches the average performance of FQL, and is comparable to recent action-chunking methods, while using the fewest parameters and the least peak GPU memory among all compared methods. --- ### AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos Authors: Kirill Mazur, Nikita Karaev, Matthew Chang, Jitendra Malik, Nur Muhammad "Mahi'' Shafiullah Published: 2026-09-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.24487v1 In this work, we present a method for shape reconstruction and tracking from video via agentic analysis-by-synthesis. Unlike prior methods which first estimate dense pixel correspondences and then recover object motion from them, our method infers a structured 3D object model, including its geometry and kinematic structure, and uses this model to optimise object track estimates over time. In our optimisation loop, a Vision-Language Model (VLM) agent iteratively refines shape or generalised pose through a render-and-compare loop, combining coarse visual reasoning with numerical pose optimisation for precise state estimation. This structured formulation enables our method to track through large motion, articulation, and severe occlusion without relying on pixel-matching objectives. Quantitatively, on ARCTIC, our method substantially outperforms state-of-the-art 3D point-tracking baselines for articulated objects, and on HOT3D it outperforms all evaluated rigid-object tracking baselines. --- ### VPRune: Efficient Training-free Pre-LLM Visual Token Pruning Authors: Guangchuan Lv, Dianxing Shi, Dingjie Fu Published: 2026-09-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.24485v2 Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction often causes substantial performance degradation. We identify three key factors behind this degradation: text-guided selection bias, information loss from discarded tokens, and positional distortion caused by sequence compaction. Based on these observations, we propose \textbf{VPRune}, a training-free pre-LLM pruning framework consisting of visual-only diversity selection, similarity-guided token recycling, and position-preserving restoration. Experiments on FastVLM-1.5B across multiple vision-language benchmarks demonstrate that VPRune achieves a favorable accuracy--compression trade-off, with particularly pronounced advantages under aggressive compression. Furthermore, evaluations on edge-device show that VPRune effectively reduces end-to-end inference latency while maintaining superior task performance, demonstrating its practicality for resource-constrained LVLM deployment. --- ### STA-TFM: Spatio-Temporal Aggregation Across Views TransForMer for Pose Estimation Authors: Mena Kamel, Natalie Won, Amrut Sarangi, Sven Jager, Albert Pla Planas Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24482v1 Monocular 3D human pose estimation (HPE) remains challenging due to depth ambiguity, occlu- sions, and the need for temporal consistency. While multi-view methods provide superior accuracy over monocular approaches, they often require complex setups. We introduce STA-TFM, a transformer-based architecture that combines spatial and temporal information for multi-view pose estimation. The approach leverages DSTformer, a monocular feature extractor, to capture long-range pose dependencies within each view. A fusion transformer then aggregates information across views to produce coherent 3D estimates. To address training data scarcity, we use a data generation pipeline that transforms any existing 3D pose dataset into multi-view setups with controllable parameters. Experiments on various datasets demonstrate that STA-TFM outperforms existing camera-parameter-free multi-view methods. STA-TFM achieves 50.9% and 49.5% reductions in mean per joint position error (MPJPE) and mean per joint velocity error (MPJVE) on the DHP19 dataset. Furthermore, it achieves 6.7% and 7.7% respective reductions on HAA4D, and a 15.2% MPJPE reduction on TotalCapture. STA-TFM handles noisy and missing 2D inputs, supporting potential deployment in healthcare monitoring, athletic assessment, and immersive technologies. Code, training checkpoints, and data are available at https://zenodo.org/records/22832620. --- ### Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards Authors: Kalash Shah, Kunal Singh, Snehan J, Shreyas Singh Published: 2026-09-21 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2609.24480v1 Deploying Large Language Models (LLMs) in healthcare requires robust performance across two complementary dimensions - diagnostic reasoning: the convergent, evidence-driven task of inferring a patient's condition from clinical data to produce a diagnosis, and clinical healthcare reasoning: the broader, navigational judgment required to communicate, plan, and adapt across multi-turn clinical interactions where a single correct answer may not exist. Recent benchmarks such as HealthBench and MedXpertQA reveal persistent weaknesses in both areas, exposing failures in complex diagnostic scenarios and limitations in contextual, patient-centered dialogue. We introduce a sequential training framework that targets these facets using synthetic data and rubric-based reinforcement learning. First, we improve diagnostic reasoning using MedBullets-derived questions with rule- and rubric-guided Reinforcement Learning (RL). We then shift to clinical reasoning by generating 5.3k synthetic multi-turn scenarios, each paired with multi-dimensional rubrics to comprehensively assess the response. This approach yields over 10% improvement on MedXpertQA, and our 30B model achieves 50.1% accuracy on HealthBench-Hard, surpassing proprietary baselines including GPT-5 (thinking). Our results show that targeted synthetic datasets and rubric-based training can systematically improve both diagnostic and interactive clinical reasoning in medical LLMs. --- ### Spatial Action Review: A Visual Analytics Dashboard for Auditing Language-to-Action Hand-offs in Electron Microscopy Authors: Samia Mohinta, Albert Cardona Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24470v1 Multimodal large language models (MLLMs) are increasingly explored as interfaces for scientific image analysis, where a visual question-answering (VQA) response may be paired with a spatial output that guides a downstream stage. A supervisor reads the language answer, while a downstream workflow such as segmentation or region review consumes the point-set output. We call this transition from inspecting the answer to relying on its point action the language-to-action hand-off. A silent failure occurs when the answer is correct while the paired action misses annotated objects needed downstream, so answer-based oversight clears a region whose action is unreliable. We introduce Spatial Action Review, a visual analytics dashboard for auditing this failure mode in electron microscopy (EM) mitochondria analysis. It links paired answer-action records through an answer-action ledger, a task-by-dataset risk map, and an image-region audit view, connecting aggregate patterns to image evidence while an adjustable action-reliability gate supports re-audit. The review ends in a human-AI hand-off, where a supervisor records whether the action is accepted, escalated, held under a stricter gate, or flagged for model revision. Across 541 image regions from an EM-adapted Qwen3-VL case-study run, point actions fail the gate in 54.4% of records with a correct VQA response, and 27.4% of all records are silent failures. A correct answer is associated with only a 5.8-percentage-point higher probability of a reliable action, with a bootstrap interval spanning zero; the point-biserial correlation between answer correctness and object coverage is 0.061. This weak coupling persists across five model conditions on 753 matched image regions. Spatial Action Review makes answer-action mismatches visible and ties them to image evidence and a recorded decision before MLLM outputs enter autonomous scientific workflows. --- ### MIGA:Shared-Geometry Gaussian Representation with Implicit Amplitude Modeling for Accelerated 3D Multi-Echo MRI Authors: Jingran Xu, Yuanyuan Liu, Yanjie Zhu Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24468v1 Three-dimensional multi-echo MRI provides rich anatomical and quantitative information, but repeated volumetric encoding prolongs acquisition and motivates k-space undersampling. Reconstructing undersampled multi-echo data requires exploiting shared anatomy while preserving echo-dependent signal variation; full-volume modeling also introduces substantial computational and memory demands. We propose MIGA, a scan-specific framework comprising shared anisotropic Gaussian geometry, a coordinate-conditioned multi-output amplitude network, and explicit echo-specific phase variables. The Gaussian geometry provides common spatial support across echoes, the implicit network models spatially structured amplitude variations, and the phase variables retain echo-specific complex signal information. All components are jointly optimized using only the acquired multi-coil k-space, requiring no fully sampled training data. Experiments showed that MIGA consistently outperformed the comparison methods across imaging tasks and acceleration factors, with larger improvements under stronger undersampling. MIGA also achieved a favorable quality-cost balance among the evaluated full-volume multi-echo methods. These results support the effectiveness of combining shared Gaussian geometry with implicit echo-dependent amplitude modeling for accelerated 3D multi-echo MRI reconstruction. --- ### A Temporal Knowledge Graph for Music Festival Lineup Forecasting Authors: Julia Gastinger, Thilo Dieing, Christian Meilicke, Heiner Stuckenschmidt Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.24467v1 Music festival lineups emerge from complex relationships among artists, genres, releases, labels, and past performances, making the prediction of future lineups a natural fit for temporal knowledge graph (TKG) forecasting. In this work, we present a TKG covering 380 festivals over 55 years, comprising more than 90K festival performance quadruples along with information on festivals, artist tours, and artist metadata, and release it as a resource for TKG forecasting evaluation. We formalize festival lineup forecasting as temporal link prediction between artists and festivals at future timestamps. We evaluate six TKG forecasting models on this task, analyze their capabilities and limitations, and compare them against Large Language Models applied zero-shot. Our resource complements existing TKG benchmarks by grounding evaluation in a concrete, real-world application domain. --- ### RAILS: Retrieval-Augmented Incremental LLM Clustering at Scale Authors: Armin Oliya, Aleksandra Sawczuk, Radosław Białobrzeski Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.24464v1 Using a Large Language Model (LLM) as the clusterer at production scale is hard: prompts cannot hold the entire label space, and per-document serial processing does not deliver the throughput real workloads require. We present RAILS, a retrieval-augmented incremental LLM clusterer that turns clustering into a simple loop over a growing label pool and scales through document batching with bounded concurrency. On six public benchmarks RAILS exceeds the strongest prior LLM-clustering method on average, lifting accuracy from 51.2% to 59.3%, NMI from 67.2% to 74.8%, and ARI from 45.4% to 54.7%. We further report production-deployment evidence from a SaaS ticket-topic-discovery pipeline, where RAILS has replaced a traditional HDBSCAN stage with higher clustering quality, transparent prompt-driven control, and stateful incremental operation. --- ### Conduit: An Experience Data Plane for Distributed Reinforcement Learning Authors: Sitong Zhang, Tuo Shi, Mario Di Francesco, Zeke Wang, Bo Zhao Published: 2026-09-21 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2609.24456v1 Distributed reinforcement learning (RL) scales training by parallelizing actors and learners around an Experience Buffer. As RL workloads grow, however, the buffer becomes more than a replay queue: it is the storage substrate of a large-capacity, latency-critical experience path that every iteration traverses to move, transform, sample, and batch experiences before learner updates can begin. Existing RL systems embed this path inside framework control flow or expose it as a request-driven buffer service, leaving experience placement fixed and experience-path work difficult to schedule independently as a runtime-level optimization target. We present Conduit, a framework-agnostic runtime that exposes RL experience management as an explicit systems optimization problem. At its core is the Experience Data Plane (EDP), a runtime abstraction that separates RL experience-handling semantics from framework-specific execution logic by exposing experience ingestion, experience placement, and experience delivery as explicit control points. Built on EDP, Conduit introduces capacity-constrained, bandwidth-aware placement, which distributes experience state across CPU/GPU memory tiers and nodes under heterogeneous interconnect and device-memory constraints, and latency-aware scheduling, which controls when experience-path handling runs to reduce exposed experience-path latency while preserving RL semantics. Integrated with RLlib without changing its framework execution logic, Conduit reduces exposed experience-path latency by up to 97% and end-to-end iteration latency by up to 38%, scales to 1,024 GPUs, and preserves convergence. --- ### MECAIL: Communication-Aware Incremental Learning for Object Detection with 14.6 KB Spatiotemporal Experts Authors: Matthias Neuwirth-Trapp, Maarten Bieshaar, Danda Paudel, Konrad Schindler, Luc Van Gool, Christos Sakaridis Published: 2026-09-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2609.24455v1 Intelligent transportation systems require Incremental Learning (IL) to continually improve their overall performance in dynamic environments. However, most edge devices lack the computational resources to support on-device IL, requiring updates to be transmitted from centralized servers. We propose using this setup to obtain dense, specialized module coverage that adapts a fixed base model to specific spatiotemporal contexts, such as parking lots, gas stations, ferries, or construction sites. However, in order to reliably transmit these modules to the edge device, using TCP, UDP, and BTP over V2X, Wi-Fi, and 2G-5G hardware, we establish a strict limit of 14.6 KB per module to fit within the first TCP window and to minimize UDP/BTP fragmentation. We further introduce Mixture-of-Experts for Communication-Aware Incremental Learning (MECAIL), the first method that meets this strict requirement, in which each new domain or environment is served by a small expert network that adapts the base model. We validate MECAIL on D-RICO and ODinW-13, where it largely matches the performance of parameter-heavy approaches while enabling practical, bandwidth-efficient large-scale deployment. This allows comprehensive coverage by experts for highly specific, focused, and temporary situations. --- ### Predicting Postprandial Glycemic Response from Meal Images, Clinical Variables, and Gut Microbiome Information Authors: Varvara Kondratyeva, Kamilia Zaripova, Nassir Navab, Azade Farshad Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.24453v1 Predicting postprandial glycemic response (PPGR) is fundamental to personalized nutrition and type 2 diabetes management, yet existing approaches typically rely on manually reported dietary intake, limiting their scalability in free-living settings. We propose a multimodal framework that replaces manual dietary logging with image-derived macronutrient estimates and integrates them with clinical variables and gut microbiome information for personalized PPGR prediction. The framework jointly performs image-based macronutrient estimation and glucose prediction, while an attention-based prediction module models interactions between dietary and host-specific information. We evaluate the proposed approach on a real-world dataset comprising meal images, continuous glucose monitoring, clinical variables, and gut microbiome profiles. The proposed model outperforms existing PPGR baselines using image-derived nutritional inputs and approaches the performance of methods that rely on manually reported macronutrients despite using automatically estimated nutritional information. These results demonstrate that combining image-derived nutrition with complementary clinical and gut microbiome information provides a practical foundation for scalable personalized PPGR prediction. --- ### Do LiDAR Language Models Really Understand Spatio-temporal Relationships? Authors: Runyi Yang, Murat Akkoyun, Di Wen, Ruiping Liu, Yufan Chen, Junwei Zheng, Xiaoye Wang, Kailun Yang, Danda Pani Paudel, Luc Van Gool, Kunyu Peng Published: 2026-09-21 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2609.24452v1 Recent 4D LiDAR language models aim to reason about objects and their evolving spatial relationships. Yet, in our evaluation, always selecting the same option nearly matches the multiple-choice accuracy of two B4DL-derived configurations. We introduce LiDAR-Hallu, a geometry-referenced benchmark and diagnostic protocol with 10,000 questions across 150 nuScenes scenes. It covers object existence, ego-relative position, distance ordering, relative motion, and temporal localization, with explicit rules for selecting objects, comparing times, and determining reference answers. Our protocol combines fixed-answer and candidate-content controls, cross-scene pairs with identical prompts but opposite reference answers, and relation-specific recall. Analysis of 100,000 recorded responses reveals failures hidden by aggregate accuracy. Candidate duration alone makes temporal answers predictable without observing LiDAR. On paired questions, the models frequently give the same answer to scenes requiring opposite answers. Relation-specific analysis further shows that both configurations miss every positive lateral-motion case across all tested conditions. Temporal-shuffle contrastive decoding provides little net improvement, as repairs are largely offset by new errors and the main failures persist. These results show that evaluating spatio-temporal reasoning requires testing whether models distinguish the queried physical relationships, rather than relying on individual-answer accuracy alone. The source code, checkpoints, and data are released at https://github.com/Awesome4D/4DMLLM_Hallucination_Bench. --- ### ActGov: Governing LLM Agent Actions via Policy-Constrained Validation Authors: Kaiyuan Zhang, Yuke Peng, Ke Jiang, Yinqian Zhang Published: 2026-09-21 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.24446v2 Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subsequent actions and exceed user authorization. Existing defenses isolate injected content or constrain execution with predefined plans and static policies, but these approaches are brittle under dynamic workflows and scale poorly across extensible tool ecosystems. In this work, we present ActGov, a runtime enforcement framework that validates each LLM-proposed tool action before it causes external effects. Built on a unified semantic model of authorization, actions, runtime context, and security constraints, the ActGov-Policy component iteratively constructs a policy set from tool specifications, benign tasks, and observed failure traces, with each update verified through SMT-based counterexample checking. At runtime, ActGov-Runtime abstracts each tool call into finite policy records and permits it only if it remains within the task-scoped authorization boundary and satisfies all applicable policies. This per-action enforcement preserves authorization throughout long-horizon, dynamically branching workflows. We evaluate ActGov on the AgentDojo and AgentDyn benchmarks across multiple models and attack configurations. It shows that ActGov consistently reduces the success rate of indirect prompt-injection attacks while preserving task utility, significantly outperforming existing defenses. These results demonstrate that ActGov can enforce fine-grained authorization over dynamic agent executions without relying on the underlying LLM to correctly identify malicious instructions. --- ### WPBench: A Comprehensive Benchmark for Wind Power Forecasting Authors: Yuhan Zhu, Jilin Hu, Xinying Cai, Yingshan Li, Li Ma, Xiangfei Qiu Linsen Li, Kai Zhang, Yao Fu, Weihao Jiang, Bin Yang Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.24444v1 Accurate, reliable, and deployable wind power forecasting is critical for power system dispatch, renewable energy integration, and electricity market operations. Progress in this field hinges on the ability to empirically and comprehensively benchmark forecasting methods. Yet existing benchmarks fall short of supporting systematic evaluation in four key aspects: 1) limited coverage of wind power scenarios across turbine scale, variable composition, and spatial structure; 2) incomplete coverage of forecasting model families; 3) evaluation metrics misaligned with wind power requirements; and 4) limited structure-aware diagnostics beyond individual temporal patterns. To address these limitations, we propose WPBench, a comprehensive, fair, and extensible benchmark for wind power forecasting. WPBench integrates 26 public datasets organized by turbine scale and variable composition, spanning single-turbine, multi-turbine, univariate, and multivariate settings. Under unified processing, training, and evaluation protocols, it benchmarks 19 representative models covering traditional methods, deep temporal models, spatio-temporal models, and foundation models. Beyond point-wise errors, WPBench assesses forecast-curve fidelity and computational efficiency, and delivers structure-aware diagnostics across temporal, variable-dependency, and spatial-dependency perspectives. Together, these capabilities enable systematic model comparison across diverse wind scenarios and provide a reusable platform for future research. --- ### Horizon-Aware Early Event Prediction for Tokamak Disruption Alarms Authors: Takeshi Koshizuka, Takaharu Yaguchi Published: 2026-09-21 Categories: physics.plasm-ph, cs.LG arXiv: https://arxiv.org/abs/2609.24443v1 Reliable disruption prediction is essential for the safe operation of future tokamaks. Existing full-distribution survival methods model the complete residual time-to-disruption distribution, whereas operational decisions primarily depend on disruption risk within a finite prediction horizon. This mismatch motivates introducing Early Event Prediction (EEP) objectives into survival-based disruption prediction. We take Deep Survival Machines (DSM) as the full-distribution baseline and propose applying two established EEP methods to tokamak disruption prediction: Temporal Label Smoothing (TLS), which directly predicts disruption probability within a finite horizon, and survTLS, which additionally models the event-time distribution within that horizon. Using a common causal encoder, we compare these methods on DIII-D, Alcator C-Mod, and EAST. We distinguish threshold-free deadline ranking from validation-selected fixed-policy alarm performance and evaluate prediction horizons and encoder architectures. TLS achieves the best mean alarm performance on DIII-D and EAST, whereas all methods perform poorly on Alcator C-Mod. survTLS does not consistently outperform DSM, suggesting that directly learning horizon-level event probability is more effective than modeling detailed within-horizon event-time distributions in the present setting. Finally, the selected prediction horizons and encoder-ablation results vary across devices, reflecting differences in disruption characteristics. --- ### MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecasting Authors: Xinying Cai, Junkai Lu, Yuhan Zhu, Xiaoyun Yu, Xiangfei Qiu, Jilin Hu Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.24441v1 Multivariate time-series forecasting is essential to many real-world applications. Recent large vision models (LVMs) offer a promising paradigm by transferring cross-domain visual priors to time-series forecasting. However, existing LVM-based methods face two key challenges: balancing independent visual representation spaces with cross-variable dependency modeling, and adapting vision backbones pretrained on natural images to the distinct temporal semantics of time-series images. To address these challenges, we propose MUSE, a dependency-aware adaptation framework built on a fully frozen pretrained MAE. First, the Variable Context Refinement Module (VCR) aggregates shared temporal information within each variable and models cross-variable contextual dependencies while preserving independent visual spaces. Second, the Temporal-Periodic Refinement Module (TPR) performs lightweight refinement at different encoder depths and explicitly models across-period temporal dependencies and within-period periodic dependencies. The two modules independently produce forecasts, which are fused through a learnable prediction-level gate. Experiments on 10 real-world datasets demonstrate that MUSE achieves state-of-the-art performance. --- ### Comparing Latent Concept Formation in State Space Models and Transformers via Sparse Autoencoders Authors: Rithin Nagaraj, Rupa Laalasa Oruganti, Prerna Subhashchandra Kunder, Ashwini M Joshi Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.24440v1 The quadratic scaling of Transformer self-attention has driven the adoption of sub-quadratic Selective State Space Models (SSMs) like Mamba, which compress past context into a fixed-size recurrent hidden state. This strict informational bottleneck raises a foundational question for mechanistic interpretability: do SSMs and Transformers learn fundamentally distinct latent representations? In this work, we employ Sparse Autoencoders (SAEs) to conduct a large-scale, feature-level correspondence analysis between Mamba-130m and Pythia-70m over a 10-million token corpus. Contrary to hypotheses predicting widespread architectural divergence, we find no evidence of systematic representational divergence between architectures: across the observed Jaccard distribution, 99.98% of Mamba features cluster toward the upper alignment boundary, providing preliminary feature-level support for the Universality Hypothesis. We further identify and qualitatively characterize this microscopic fraction (0.02%) of diverging features, finding patterns consistent with the hypothesis that the recurrent bottleneck selectively limits the parsing of rigid syntax rather than broad semantic ontology. We demonstrate that while Pythia's unconstrained attention permits the monosemantic decomposition of distinct formatting edge-cases, Mamba is forced to compress unrelated syntactical anomalies into polysemantic "junk drawer" neurons to preserve state capacity. Collectively, these results suggest that architectural routing mechanisms may have negligible impact on core semantic understanding, with representational divergence confined to extreme structural margins. --- ### FoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent Folding Authors: Hung T. Ho, Khanh D. Nguyen, Quang D. Nguyen, Thanh Q. Duong, Ngan Le, Meng Guo, Vien A. Ngo, An T. Le Published: 2026-09-21 Categories: cs.RO, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2609.24433v1 Low-bit vision-language-action inference must reduce observation-to-action latency while preserving robot behavior. We present FoldQuantVLA, a post-training quantization framework that carries a consistent activation representation through calibration, weight rounding, and native integer execution. It combines channel scaling and block Hadamard transforms with dynamic per-token quantization, without policy retraining. Custom TensorRT plugins execute projections in both the language backbone and iterative action expert with four-bit weights and activations (W4A4) on Ada GPUs and Jetson AGX Orin. Evaluation spans LIBERO, SimplerEnv, and two robot platforms. Across three GR00T checkpoints and $π_{0.5}$, W4A4 achieves $1.20$ to $1.33\times$ speedups over floating-point TensorRT on Orin and $1.25$ to $1.52\times$ on desktop. Retaining language attention-output and feed-forward down projections at eight bits (W8A8) improves held-out action fidelity on all four checkpoints. Across four real-robot tasks, this configuration raises observed GR00T N1.7 success from $80.0\%$ with uniform W4A4 to $92.5\%$ over 80 trials per configuration, with a measured additional Orin latency of 1 ms. --- ### 1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation Authors: Huanxin Sheng, Zhiling Ye, Haonan Wang, Jian Wang, Jinjie Gu, Jian Kang Published: 2026-09-21 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.24432v1 Sparse on-policy distillation (OPD) allocates teacher supervision to a small subset of tokens in student-generated trajectories. However, useful teacher guidance can yield a noisy update when its gradient is estimated from a sampled next token. We study this estimation problem at a fixed prefix in information geometry and propose an information-efficiency ratio (IER) based on a signal-to-noise decomposition. IER characterizes relative gradient estimation error under an optimal scalar baseline. A candidate-set approximation enables token selection based on IER and its combination with existing usefulness scores, while retaining the sampled reverse-KL training objective. On mathematical and medical reasoning tasks, adding IER improves existing selectors in multiple settings, with sparse configurations matching or exceeding full OPD without token selection at small token budgets of 0.1\%--1\%. These results support accounting for both usefulness and gradient-estimation reliability when allocating sparse supervision. Our code is available at https://github.com/BruceSheng1202/IER-OPD. --- ### Estimating Accurate Hand Pose in Camera Space with Vision Transformer Authors: Kaiwen Ren, Yiran Jiang, Yongjing Ye, Shihong Xia Published: 2026-09-21 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2609.24424v2 Monocular RGB-based hand pose estimation has emerged as a critical research frontier in computer vision. The local hand pose estimation methods predict hand poses relative to the wrist, while global hand pose estimation also requires estimating the wrist's position in the camera coordinate system. However, this camera-space estimation confronts two fundamental challenges: (1) depth ambiguity in monocular settings, and (2) the coupling effect of hand local poses and global wrist positions in the perspective projections. In particular, this coupling reflects that the projections are jointly determined by local hand poses, wrist positions, and camera intrinsics. To overcome these challenges, our framework proposes two key innovations: Transformation-Isomorphism Supervision for hand-depth information extraction and Perspective Information Embedding for resolving above coupling effect of local pose and wrist position, both integrated within the mainstream encoder-decoder architecture. Besides, we propose a novel framerate-aware multi-dataset training strategy for sequential pose refinement. Our fully integrated approach achieves at most 37.1\% superiority in CS-MJE over SOTA on HO3D. Project page: https://github.com/Mine268/CS-ViT. --- ### Complexities of Weak Proximal Oracle Methods for Composite Convex Optimization Authors: Dan Garber Published: 2026-09-21 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2609.24423v1 We consider a standard convex composite optimization problem with either smooth or nonsmooth objective function, and under quadratic growth. In recent years, several works gave algorithms based on a \textit{weak proximal oracle} (WPO) that essentially match in oracle complexities proximal (sub)gradient methods relying on exact prox operations. Importantly, such WPOs, which relax the strong optimality condition of the standard prox operator, may admit much more efficient implementation in terms of runtime when optimal solutions have some sparse structure. A question remained if such WPO-based methods can be accelerated (in the sense of Nesterov's accelerated gradient). In this work we provide a negative answer by establishing lower bounds against both deterministic and randomized methods. Thus, while WPOs can substantially reduce the cost of individual oracle calls, this comes with an inherent loss in oracle complexity. We also provide a new upper-bound for WPO-based nonsmooth convex composite optimization, nearly matching the proximal subgradient method. --- ### Prior-Amortized In-Context Bayesian Inference for Generalized Linear Mixed-Effects Models Authors: Alex Kipnis, Marcel Binz, Eric Schulz Published: 2026-09-21 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2609.24422v1 Hierarchical data is ubiquitous in the empirical sciences and is most commonly analyzed with generalized linear mixed-effects models (GLMMs). Bayesian inference for GLMMs yields calibrated uncertainty but requires MCMC; the No-U-Turn Sampler (NUTS) is the gold standard but is slow and must restart from scratch for every new dataset, model and prior. We introduce metabeta, a pretrained neural network for prior-amortized in-context Bayesian inference over GLMMs. Unlike previous neural posterior estimators that fix the prior at training time, metabeta accepts prior families and hyperparameters as inputs at test time, enabling zero-shot generalization. Two set transformers and conditional normalizing flows mirror the posterior's two-level structure (global parameters shared across groups, local parameters per group). The model is trained on millions of realistic simulated datasets spanning continuous, binary, and count outcomes. By default, the flow posterior is refined by Independence Metropolis-Hastings against the unnormalized posterior, so its correctness rests on the sampler rather than the network; this yields tuning-free inference two to three orders of magnitude faster than NUTS. Alternatively, the flow can warm-start NUTS, giving nearly identical inference with substantially increased speed and stability. On controlled benchmarks with ground-truth parameters, metabeta matches NUTS in parameter recovery, calibration and out-of-sample prediction. On out-of-distribution real datasets, its posteriors closely match those of NUTS across all parameter types, and they remain faithful under misspecified likelihoods and priors, out-of-distribution predictors, collinear designs, and data-poor regimes. The model is open-source and open-weights and thus immediately deployable. --- ### A Three-Way Testing Framework for Quantifying Epistemic Calibration Uncertainty in SBI Authors: Luben M. C. Cabezas, Pedro L. C. Rodrigues, Rafael Izbicki Published: 2026-09-21 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2609.24419v1 Current experimental scientists increasingly rely on simulation-based inference (SBI) to invert complex models with intractable likelihoods. A primary goal in these settings is to obtain credible regions with valid coverage. While recent model-agnostic conformal calibration methods have succeeded in constructing credible sets with prescribed local Bayesian coverage, their approximate nature introduces inherent epistemic uncertainty in the calibration process. In this work, we propose a novel tool for diagnosing calibration uncertainty. Our approach is based on a simple three-way hypothesis testing procedure. We demonstrate how this tool can be used to effectively assess necessary simulation budgets for calibration sets and analyze the epistemic uncertainty associated with cutoff estimation. --- ### ARM: Attention with Routed-Memory for Learnable Sparse Control Authors: Qiuhao Zeng, Jerry Huang, Peng Lu, Ruiyi Fang, Gezheng Xu, Zihao Jing, Yufei Cui, Charles Ling, Gang Niu, Boyu Wang Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.24417v1 Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are necessary for stable computation. Techniques such as selective token eviction and pruning have vastly mitigated these issues, but often discard core information to manage the growing cache. In this paper, we propose Attention with Routed Memory (ARM) a novel KV caching structure that introduces a fully differentiable, fixed-size memory system organized as a hierarchical router. Via a Gumbel-Softmax, ARM learns to select memory slots and perform sigmoid-gated updates that softly combine new and stored information, avoiding hard eviction and reducing information loss. By further training a policy to dynamically select varying amounts of memory at inference, ARM adapts its accesses for both simple contexts and inputs that require deeper reasoning, enabling more scalable and effective retrieval on both short- and long-contexts. Experimental results on standard commonsense and long-context reasoning benchmarks demonstrate that ARM achieves superior performance and efficiency compared to fixed KV-caching approaches, while remaining efficient and scalable in terms of both memory and generation latency. --- ### End-to-end Jordanian dialect speech-to-text self-supervised learning framework Authors: Ali A. Safieh, Ibrahim Abu Alhaol, Rawan Ghnemat Published: 2026-09-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.24410v1 Speech-to-text engines are extremely needed nowadays for different applications, representing an essential enabler in human-robot interaction. Still, some languages suffer from the lack of labeled speech data, especially in the Arabic dialects or any low-resource languages. The need for a self-supervised training process and self-training using noisy training is proven to be one of the up-and-coming feasible solutions. This article proposes an end-to-end, transformers-based model with a framework for low-resource languages. In addition, the framework incorporates customized audio-to-text processing algorithms to achieve a highly efficient Jordanian Arabic dialect speech-to-text system. The proposed framework enables ingesting data from many sources, making the ground truth from external sources possible by speeding up the manual annotation process. The framework allows the training process using noisy student training and self-supervised learning to utilize the unlabeled data in both pre- and post-training stages and incorporate multiple types of data augmentation. The proposed self-training approach outperforms the fine-tuned Wav2Vec model by 5% in terms of word error rate reduction. The outcome of this work provides the research community with a Jordanian-spoken data set along with an end-to-end approach to deal with low-resource languages. This is done by utilizing the power of the pretraining, post-training, and injecting noisy labeled and augmented data with minimal human intervention. It enables the development of new applications in the field of Arabic language speech-to-text area like the question-answering systems and intelligent control systems, and it will add human-like perception and hearing sensors to intelligent robots. --- ### DeCo: Efficient Decouple-to-Couple Learning for Multi-Task Visual Grounding Authors: Xiaoqiang Lu, Licheng Jiao, Long Sun, Yuting Yang, Xu Liu, Lingling Li, Wenping Ma, Fang Liu Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24409v1 Multi-task visual grounding requires models to jointly understand linguistic semantics and perform accurate visual localization and segmentation. Despite the success of multimodal large language models, effectively adapting them to multiple grounding objectives remains challenging. Existing methods commonly enforce task cooperation through shared representations, while overlooking the intrinsic conflict between task-oriented feature interests. In this paper, we introduce $\textbf{DeCo}$, an efficient $\textbf{De}$couple-to-$\textbf{Co}$uple learning framework that resolves this dilemma through a two-stage paradigm: task-specific representation decoupling followed by complementary prior coupling. Specifically, we first propose Task-aware Semantic Decoupling (TSD) to route shared visual cues into individual features under salient word-level guidance, alleviating representation interference between localization and segmentation. Furthermore, we observe that segmentation naturally provides informative localization priors due to dense supervision. Based on this insight, we introduce Hybrid Prior Coupling (HPC), which integrates sentence-level semantic prior with mask-derived spatial prior for enhanced grounding. Built upon a frozen multimodal encoder, DeCo requires lightweight trainable parameters while achieving strong generalization across multiple grounding objectives. Extensive experiments on RefCOCO/+, G-Ref, ReferIt, Flickr, DIOR-RSVG, SARVG1.0, RRSIS-D, RIS-LAD, and RefDIOR demonstrate that DeCo achieves state-of-the-art performance on both natural and remote sensing benchmarks. The code and models are available at https://github.com/xiaoqiang-lu/DeCo. --- ### Can Spiking Neural Networks play pinball? A neuromorphic motion detector for target tracking Authors: Mazdak Fatahi, Šárka Pryjmaková, Pierre Boulet, Giulia D'Angelo Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24403v1 Biological visual systems achieve continuous, low-latency motion perception by processing sparse, asynchronous spiking signals, enabling real-time tracking under strict energy constraints. Event-based cameras, inspired by the mammalian retina, replicate this efficiency by capturing only local brightness changes as asynchronous events, offering a natural substrate for spiking neural networks (SNNs) to parallelise computation and adapt to fast-changing scenes. Pinball provides a controlled yet dynamic testbed, requiring precise motion estimation and fast reaction to a small, rapidly moving target. This work presents a fully spiking, real-time perception-to-action pipeline for closed-loop pinball gameplay. A dynamic vision sensor observes a small, fast-moving ball, and a network of spiking Time-Difference Encoders on the SpiNNaker neuromorphic platform jointly estimates its position, speed, and direction. The system is characterised across receptive field size, accumulation window, and angular tuning width for real-time operation, and benchmarked in closed loop against human players across two flipper regimes of increasing physical realism. It achieves a hit rate of 56.1%, nearly double the human average, reacting within 21.7 ms (5 ms network latency) and consuming an estimated 148 μW using fewer than 25k neurons, among the fastest and most energy-efficient event-based closed-loop demonstrators benchmarked. Under more realistic flipper dynamics, tuning a single interpretable policy parameter reproduces the full spectrum of human play styles, from cautious to aggressive, with no change to the perception pipeline. A physical demonstrator, tracking a real ball and actuating real flippers in closed loop, confirms the principle operates beyond simulation. Its fully spiking, learning-free design offers a compact, energy-efficient example of real-time neuromorphic perception-to-action. --- ### Artificial Structure Function Search: Preserving Artificial Functional Connectivity for Structured Pruning Authors: Mindula Illeperuma, Rafael Pina, Charuka Herath, Sharmarke A. Gabayre, Varuna De Silva Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.24401v1 Structured pruning is a model compression technique that is used to reduce the computational cost of deploying deep neural networks on resource-constrained devices. Popular methods of pruning rely on opaque heuristics or weight-based criteria that give no indication as to the structural dependencies in the network. To address these limitations we present Artificial Structure Function Search (ASF-S): a novel structured pruning framework. ASF-S utilizes Principle Gradient Importance (PGI): a novel prune-candidate selection criteria that is inspired by structure-function relationships in the brain. By ensuring the pruned structure of the model respects topographical organization of the output layer, we define Artificial Functional Connectivity (AFC) for artificial neural networks. AFC provides evidence to demonstrate that accurate smaller networks can be found using careful prune candidate selection criteria. We present results for PGI as a selection criterion and for ASF-S as a pruning framework against recent benchmarks, demonstrating that our method yields model variants with 70\% parameter reduction, that can recover baseline accuracy without re-training the pruned layers. --- ### Probabilistic Modelling of Operational Design Domains, A New Approach for Testing AI Systems Authors: Hans-Werner Wiesbrock Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.24397v1 The conventional testing process quickly fails when applied to ML-based systems such as obstacle detection in vehicles: if an obstacle is not detected in a test, classical bug fixing is impossible and an AI system will always retain shortcomings. Test results can therefore only be interpreted statistically, which in turn requires test sets that are not only complete with respect to the operational design domain (ODD) of the system, but also representative of it. To this end, we introduce probabilistically extended ontologies (PEONs): ontologies describing the ODD, augmented with a probability distribution over the partitioning they induce. Instead of unmaintainable conditional probability tables, only marginal distributions and functionally described dependencies need to be specified; algorithms based on couplings and optimal transport complete this specification to a Bayesian network. From a PEON we derive the sampling of representative test cases, rigorous end-of-test criteria for given quality targets and significance levels, and methods for re-evaluating existing test results and for assessing the balance of training data. We demonstrate the practical modelling of a complex ODD using the example of automatic train operation. --- ### Climate Variability Modulates the Impact of Price Spikes on Food Insecurity Authors: Jordi Cerdà-Bautista, Vasileios Sitokonstantinou, Homer Durand, Gherardo Varando, Michele Ronco, Gustau Camps-Valls Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.24394v1 Climate variability influences whether a market disruption escalates into a food crisis, yet broad climate patterns like El Niño, tracked months before they alter hydro-climatic conditions, are still not incorporated as an early-warning component in food-security responses. We address this gap by introducing sensitivity regimes, a stratification of regions by the direction and strength of their vegetation response to the El Niño Southern Oscillation, and using them to estimate how food price spikes affect acute food insecurity across sub-Saharan Africa. Integrating remote sensing, socioeconomic data, and causal machine learning, we find that in regions where ENSO systematically suppresses vegetation, a price spike raises the share of the population at acute risk by 5.4 percentage points in the following month. In regions where vegetation is unaffected by or positively linked to ENSO, the estimated effect is smaller (around 2 percentage points) and statistically insignificant. These results demonstrate that climate context is critical for understanding food security vulnerabilities. Sensitivity regimes can be combined with operational price-spike triggers to stage anticipatory action: the ENSO state flags vulnerable regions months ahead, and a pre-positioned response in those regions to a price spike would avert the largest jump in acute food insecurity. --- ### NAVIR: Neuromorphic Audio-Visual Speech Recognition for Robust Human-Robot Interaction on Edge Hardware Authors: Leonidas Delimpasis, Panagiota Moraiti, Antonis Porichis, Panos Chatzakos, Michail Karamousadakis Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.24391v1 Voice-controlled interaction in industrial settings is hampered by acoustic noise, which severely degrades audio-only speech recognition. Audio-visual speech recognition (AVSR) addresses this by fusing lip-motion cues with the audio stream, but state-of-the-art pipelines rely on three-dimensional convolutions, recurrent units, and attention modules that exceed the budget of typical edge devices. We present NAVIR, an end-to-end AVSR system targeting the BrainChip Akida neuromorphic processor, which natively supports only sequential two-dimensional convolutional inference. The pipeline factorises spatial and temporal encoding into separate AkidaNet-based modules: a per-frame visual encoder, a temporal video encoder, and a spectrogram audio encoder, fused by a lightweight predictor head and decoded by constrained beam search. Models are trained with connectionist temporal classification on noise-augmented audio and then fine-tuned with quantization-aware training. On the GRID benchmark, the quantized audio-visual model reaches 14.0% word error rate (WER) under noise on the unseen-speaker split and 3.3% WER on the overlapped-speaker split, against 22.5% and 11.8% for audio-only baselines, and it attains 98.6% command accuracy at 1.5% WER on a task-specific industrial-command corpus. Operation-count analysis indicates a 13-fold energy advantage of the spiking formulation over its artificial neural network counterpart at 27.6% mean firing rate. On-board measurements show roughly 5-fold lower energy per inference than a Raspberry Pi central processing unit on the lip-reading model, and over 100-fold lower than a laptop graphics processing unit, while sustaining 14.5 inferences per second. To the best of our knowledge, this is the first complete multimodal AVSR pipeline running on neuromorphic hardware of this class. ---