| 1 | MoSE3: Learning World-Space SE(3) at Every Pixel | Jiahuan Cheng, Zhiyi Li, Tian Xia +3 | cs.CV | 2026-10-02 |
| 2 | What Should World Models Forget? Stratified Retention for Continual Adaptation | Nishit Anand, Ramani Duraiswami, Dinesh Manocha | cs.LG | 2026-10-02 |
| 3 | From Mixing to Tearing: Graph Decomposition in Decentralized Optimization via Message Passing | Kuangyu Ding, Gesualdo Scutari | math.OC | 2026-10-02 |
| #4 | World Embedding Benchmark | Yiqi Liu, Ruifeng Yuan, Yang Wang +7 | cs.CV | 2026-10-02 |
| #5 | UniIntervene++: An Adaptive Intervention Agent for Efficient Real-World Reinforcement Learning | Yudong Lin, Haoyuan Deng, Zhuoxuan Yuan +3 | cs.LG | 2026-10-02 |
| #6 | Learning to Assess Heartbeat Observability for mmWave Heart-Rate Sensing | Yuxuan Hu, Shilin Shan, Jianfei Yang +1 | cs.AI | 2026-10-02 |
| #7 | DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation | Jiahao Zhan, Yan Wang, Yongrui Ma +5 | cs.CV | 2026-10-02 |
| #8 | Fed-ADApt: Federated Anytime Depth Adaptation for Resource-Aware Medical Image Segmentation | Abhijeet Parida, Zhifan Jiang, Pooneh Roshanitabrizi +6 | cs.CV | 2026-10-02 |
| #9 | Preserving Anatomical Continuity: Three-Stage Pipeline for Colon Segmentation in 3D Abdominal CT Scans | Deshan Kalupahana, Sonit Singh, Praveen Ravindran +1 | cs.CV | 2026-10-02 |
| #10 | When Is Accuracy Evidence? A Unified Theory of Generalisation, Validation, and Information Fusion | JM Gorriz | stat.ML | 2026-10-02 |
| #11 | Causal Representation Learning with Instantaneous and Lagged Relations via Nonstationarity | Tatsuya Yamada, Hiroshi Morioka, Yoshinobu Kawahara | cs.LG | 2026-10-02 |
| #12 | Beyond Entropy: Self-Diagnostic Multi-Role Token Optimization for Video Reasoning | Yudong Han, Yong Wang, Zaiquan Yang +4 | cs.CV | 2026-10-02 |
| #13 | Native Action-Prior Learning from Videos for World Action Models | Zhaochong An, Fei Zhang, Menglin Jia +10 | cs.CV | 2026-10-02 |
| #14 | From Patching to Pruning Visual Computation in Vision Language Models | Rahul Chowdhury, Timothy A Rupprecht, Xuan Shen +3 | cs.CV | 2026-10-02 |
| #15 | Multilingual GSM-Symbolic: What determines capability transfer across languages? | Kenneth Enevoldsen, Riley Herchert, Sofie Mosegaard +22 | cs.AI | 2026-10-02 |
| #16 | JOVE: Joint Execution and Verification for Resource-Aware LLM Task Graphs | Haoran Zhang, Dongjun Kim, Seohyeon Cha +4 | cs.AI | 2026-10-02 |
| #17 | Cross-cohort TB classification using clinical data gathered in Uganda and South Africa | Joshua M. Jansen van Vüren, Devendra S. Parihar, Daphne Naidoo +8 | cs.LG | 2026-10-02 |
| #18 | Uncertainty as a Proxy for Semantic Correctness in Diffusion-Based Medical Image Synthesis | Yuxuan Ou, Konstantinos Kamnitsas, OxAAA Study +3 | cs.CV | 2026-10-02 |
| #19 | Kernel Singular Value Decomposition with Extension to Multiple Data Sources | Xinjie Zeng, Qinghua Tao, Johan Suykens | cs.LG | 2026-10-02 |
| #20 | Behavior Pack Optimization for Video MLLM Post-Training | Zhaolu Kang, Shiyu Liu, Tailong Luo +12 | cs.CV | 2026-10-02 |
| #21 | Foresight: planning future perception in streaming VLMs without retraining | Ashok Prasad Neupane, Dipan Bartaula, Ankit Belbase +5 | cs.CV | 2026-10-02 |
| #22 | Emergent Structure in the Marginal Attention Space of Language Models | Valentino Maiorca, Walter Nelson, Francesco Locatello | cs.CL | 2026-10-02 |
| #23 | S2S-JEPA: Predicting the Predictable at Subseasonal-to-Seasonal Timescales | Chenyu Dong, Gianmarco Mengaldo | physics.ao-ph | 2026-10-02 |
| #24 | RIFAR: Reliability and Forgetting-Aware Replay for Continual Robot Learning | Zirong Song, Zheng Lu, Haoran Liao +4 | cs.AI | 2026-10-02 |
| #25 | Where to Look Is Not How to Fix: Pre-Denoising Diagnostics and Modality-Dependent Control in Diffusion Composition | Fangzheng Wu, Brian Summa | cs.CV | 2026-10-02 |
| #26 | HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language Generation | Tiezheng Yu, Yuxin Jiang, Jinpeng Li +4 | cs.CL | 2026-10-02 |
| #27 | Balancing Multimodal Learning via Functional Progress | Zhongjing Gu, Fengqiang Wan, Yiming Cui +2 | cs.LG | 2026-10-02 |
| #28 | CrowdOcc: Monocular Semantic Scene Completion for Quadruped Robots in Crowded Indoor Environments | Feiyang Chen, Jincheng Hu, Yiduo Chen +5 | cs.CV | 2026-10-02 |
| #29 | DyadMem: A Long-Term Memory Benchmark of How Agents Work with Users | Yifei Tao, Xinyu Zhong, Henry Hengyuan Zhao +5 | cs.AI | 2026-10-02 |
| #30 | RYOPO: Bringing End-to-End Category-Level Object Pose Estimation into Real Time | Hakjin Lee, Junghoon Seo, Jaehoon Sim | cs.CV | 2026-10-02 |
| #31 | Rethinking Fixed Temporal Grids: Frequency-Disentangled Motion Generation | Yunjiao Zhou, Junlang Qian, Gen Li +3 | cs.CV | 2026-10-02 |
| #32 | Relevant Evidence Decoding for Audio-Visual Hallucination Mitigation | Hyunjae Ra, Aecheon Jung, Jungin Park +1 | cs.AI | 2026-10-02 |
| #33 | Understanding Trajectory Heterogeneity in Federated World Model Learning | Yipan Wei, Zhaokun Yan, Ziming Hong +2 | cs.LG | 2026-10-02 |
| #34 | SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention | Zihan Teng, Jiayu Zhao, Wentao Ren +4 | cs.LG | 2026-10-02 |
| #35 | Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level Privacy | Kaushik Bhargav Sivangi, Fani Deligianni | cs.CV | 2026-10-02 |
| #36 | Custom Forcing: Training-Free Subject Customization for Autoregressive Video Generation | Yunseung Ok, Hyunsoo Kim, Minseo Kim +1 | cs.CV | 2026-10-02 |
| #37 | ViTok: Improving Dense Semantics in AM-RADIO-Style Multi-Teacher Distillation with PHI-S and Masked Image Modelling | Hailun Xu, Kanchan Sarkar | cs.CV | 2026-10-02 |
| #38 | AgentTrap: Stateful Feedback Deception against Autonomous Penetration Testing Agents | Yuelin Wang, Jiongchi Yu, Yanbang Sun | cs.CR | 2026-10-02 |
| #39 | Distributionally Robust Survival Models under Subpopulation Shift and Outlier Contamination | Seonghwi Kim, Sung Ho Jo, Minwoo Chae | cs.LG | 2026-10-02 |
| #40 | DIVINE: Simple Cross-Market Stock Pretraining via Diverse Indicator Reconstruction | Kuan-Yu Chen, Shu-Cheng Zheng, Yu-Chen Den +2 | cs.LG | 2026-10-02 |
| #41 | NeuroLens: Learning Latent Embeddings of Neural Semantics from Chronic Recordings | Hanrui Lyu, Baiyuan Chen, Tianshu Tan +8 | cs.LG | 2026-10-02 |
| #42 | Counterfactual Action Evaluation, Observation Bottlenecks, and Representation Geometry in Joint-Embedding Predictive World Models | Arjun Subramanian | cs.LG | 2026-10-02 |
| #43 | Adaptive Mutual Distillation for Balanced Multi-Task Post-Training of Large Language Models | Baohang Li, Xiaocheng Feng, Yichong Huang +6 | cs.CL | 2026-10-02 |
| #44 | PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation | Chunghyun Park, Beomjun Kim, Seungcheol Park +5 | cs.RO | 2026-10-02 |
| #45 | FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training | Miaobo Hu, Shuhao Hu, Xiaobo Guo +4 | cs.AI | 2026-10-02 |
| #46 | Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite | Zongxia Li, Yucheng Shi, Zhongzhi Li +7 | cs.AI | 2026-10-02 |
| #47 | Text-Centric Post-Training for Omni-Modal Reasoning | Ziyang Cheng, Yuhao Wang, Hongcheng Liu +5 | cs.CL | 2026-10-02 |
| #48 | Modeling Shared and Individual Structure for Cross-Subject Continuous Affect Regression from EEG-fNIRS | Xuan Wang, Bing Wang, Shuai Chang +3 | cs.AI | 2026-10-02 |
| #49 | FiberGeoText: A Vision-Language Model for Population- Level Organization of Superficial White Matter | Yuqian Chen, R. Jarrett Rushmore, Guikun Chen +5 | cs.CV | 2026-10-02 |
| #50 | TPBench: A Turning-Point Benchmark for Dialogue Compression | Minji Park, Seunghyun Yoon, Hyuk Lim | cs.CL | 2026-10-02 |