| 1 | PhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions | Yue Gong, Le Zhang, Rui Chen +5 | cs.CV | 2026-10-29 |
| 2 | Coupled Guidance for Flow Matching | Mateo Clémente, Léo Maxime Brunswic, Rui Heng Yang +1 | cs.LG | 2026-10-29 |
| 3 | Reward-Adaptive Co-Evolution of Policy and Rubric | Yizhu Chen, Jianguang Jiang, Jiameng Huang +5 | cs.AI | 2026-10-29 |
| #4 | Upcycling Language Models for Multiple Specialized Domains | Mingzi Cao, Xi Wang, Nikolaos Aletras | cs.CL | 2026-10-29 |
| #5 | Localizing Concepts in Visual Autoregressive Models | Nanxiang Jiang, Yang Liu, Yuanhao Wang +1 | cs.CV | 2026-10-29 |
| #6 | HEMO: Harness Self-Evolution for Multi-Objective Combinatorial Optimization | Jianghan Zhu, Cong Zhang, Ni Zhang +3 | cs.NE | 2026-10-29 |
| #7 | KARMA: Training-Free Knowledge-Atomic Harness Evolution for Industrial Advertising Agents | Xinhua Miao, Yuanzhen Rong, Weiru Zhang +1 | cs.AI | 2026-10-29 |
| #8 | Intrinsic Distribution Matching | Deyuan Liu, Yansen Han, Kaiwen Zheng +7 | cs.CV | 2026-10-29 |
| #9 | UniTele: Learning Device-Conditioned Degradations for Unified Smartphone Telephoto Super-Resolution | Yuchen Zhang, Aojie Li, Wei Cheng +5 | cs.CV | 2026-10-29 |
| #10 | Evaluating Cultural Knowledge Editing in Vision-Language Models | Malvina Nikandrou, Georgios Pantazopoulos, Ioannis Konstas +1 | cs.CV | 2026-10-29 |
| #11 | ROAD: Modern Adversarial Training for Simple One-Step Distillation at Scale | Xiaoou Li, Shan You, Tao Huang | cs.CV | 2026-10-29 |
| #12 | Robust LIDAR Sensor-to-Sensor Domain Generalization via Accumulated-Point Scene Completion | Christoph B Rist, Larissa T Triess, Markus Enzweiler +1 | cs.CV | 2026-10-29 |
| #13 | Agent-Wise Test-Time Normalization for Camera-Based Cooperative Perception with Corrupted Collaborators | Yu Wang, Shaohua Wang, Yicheng Li +1 | cs.CV | 2026-10-29 |
| #14 | Softmax Routing Dynamics in Mixture-of-Experts Models: Collapse and Recovery | Shengze Xu, Maolin Deng, Tieyong Zeng | cs.LG | 2026-10-29 |
| #15 | Timbre: Reliability-aware harmonic consensus for label-free multimodal test-time rexinforcement learning | Haotian Lyu, Haoyu Wang, Ru Wang +4 | cs.AI | 2026-10-29 |
| #16 | Anatomical Prior-Guided Routing for 3D Lung Tumor Segmentation | Uihyeon Maeng, Jonghun Kim, Hyunjin Park | cs.CV | 2026-10-29 |
| #17 | CASE: Concept-Aware Segmentation from Positive and Negative Visual Exemplars | Yi-Jen Tsai, Yen-Yu Lin, Chien-Yao Wang | cs.CV | 2026-10-29 |
| #18 | BEVLight: Generalizable Traffic Signal Control from UAV Bird's-Eye Views | Maonan Wang, Yuxin Cai, Junming Liu +5 | eess.SY | 2026-10-29 |
| #19 | TaxoMFM: A Taxonomy-Aware Foundation Model for the Human Gut Microbiome | Haochen Xue, Anastasia Godneva, Yulong Li +6 | cs.LG | 2026-10-29 |
| #20 | Unlocking Any-Order Generation in Pretrained Autoregressive Image Models | Rishav Pramanik, Marco Pedersoli, Zhaozheng Yin | cs.CV | 2026-10-29 |
| #21 | MemSteer: Turning User Histories into Supervision for Agent Memory Optimization | Jie Huang, Cuiling Lan, Qize Yu +2 | cs.AI | 2026-10-29 |
| #22 | Reasoning or Pattern Exploitation? Mechanistic Insights from RL-Trained Language Models | Aishik Nagar, Cheston Tan | cs.AI | 2026-10-29 |
| #23 | STRATA: Reinforcement-driven Active Sampling with Tri-paradigm Adaptation for Efficient 3D Spatial Transcriptomics | Junchao Zhu, Ruining Deng, Chongyu Qu +7 | cs.CV | 2026-10-29 |
| #24 | Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection | Xinyan Wang, Xiaogeng Liu, Jun Shao +1 | cs.CR | 2026-10-29 |
| #25 | When Does Closed-Loop Curriculum Adaptation Help GRPO? An Analysis on Countdown | Yuv Raj Pant, Moshiur Rahman Tonmoy, Kaiqun Fu | cs.LG | 2026-10-28 |
| #26 | How Architecture, Typology, and Adaptation Strategies Shape ASR for Low-Resource African Languages: A Controlled Empirical Study | Mercy Muchai, Kevin Chege, Nick Mumero Mwangi +4 | cs.CL | 2026-10-28 |
| #27 | A 211K Parameter Foundation Model: Genetic Prompting in Neural Cellular Automata | John Kalkhof, Niklas Ihm, Daniel Kirste +1 | cs.CV | 2026-10-28 |
| #28 | Explore Where It Matters: Targeted Exploration for Efficient Rover Adaptation | Jacob Levy, Arthur Bouton, Tristan D. Hassler +2 | cs.RO | 2026-10-28 |
| #29 | Enhanced image forensics through partial C2PA-based provenance information | Riccardo Ziglio, Eleonora Marchesini, Andrea Montibeller +3 | cs.CR | 2026-10-28 |
| #30 | SaiVLA-JEPA: Evaluating Future Latent Prediction in JEPA-Conditioned VLA Control | Rufeng Xiao, Ruihao Xiao, Wei Chen +1 | cs.RO | 2026-10-28 |
| #31 | Continual Adaptation Across Modalities: Learning and Forgetting in Unified Multimodal Models | Xinrui Wang, Zhihao Chen, Jia Tang +4 | cs.LG | 2026-10-28 |
| #32 | DecisionUnlearn-Bench: Unlearning Probabilistic Decisions under Changing Schemas | Tiantong Wu, Wei Yang Bryan Lim | cs.CR | 2026-10-28 |
| #33 | Pronunciation-Supervised Text-to-Speech for Irish (Gaeilge) | William Lane | cs.CL | 2026-10-28 |
| #34 | SparseTokenGS: Gaussian-based Sparse-View CBCT Reconstruction via Reusable Token Pool | Zihan Deng, Zhenzhen Gong, Yujie Liu +10 | cs.CV | 2026-10-28 |
| #35 | Human Evaluation with Automatic Scores: Separating Sampling and Estimation Gains | Yang Liu, Ran Zou, Zhengtao Gui +1 | cs.CL | 2026-10-28 |
| #36 | Too Hard, Too Easy, Just Right: Performance-Driven Challenge Adaptation in Virtual Reality Firefighter Training | Xuan Wang, Jianan Jiang, Rongqian Chen +2 | cs.AI | 2026-10-28 |
| #37 | Beyond Aggregate WER: In-domain Adaptation, Learner Speech, Code-Switching, and Speaker Attribution in Online Spanish Learning Classrooms | Olga Kellert, Samhitha Harish, Johnatan E Bonilla +3 | cs.CL | 2026-10-27 |
| #38 | Large Language Models for Accurate Medical Chart Abstraction: Enabling Scalable and Secure Artificial Intelligence Deployment in Stroke | Zhusi Zhong, Carl M. Porto, David Hong +13 | cs.CL | 2026-10-27 |
| #39 | Preserving Safety During Sequential Fine-Tuning: A Factorial and Geometric Analysis of Replay | George Ruellan, Diana Benavides-Prado | cs.LG | 2026-10-27 |
| #40 | QMUL_AK at AISA-ArabicFC: Schema-Constrained Function Calling with ALLaM | Ali Khairallah, Arkaitz Zubiaga | cs.CL | 2026-10-27 |
| #41 | Meta-Initialization of Implicit Neural Representations to Accelerate Deformable Medical Image Registration | Marat O. Zinovev, Dmitry V. Sorokin | cs.CV | 2026-10-27 |
| #42 | Federated Learning for Semantic Communications over Multiple Access Channels | Yalin E. Sagduyu, Tugba Erpek, Yi Shi | cs.IT | 2026-10-27 |
| #43 | FAD-KV: Adaptive Dictionary KV Caching for Efficient Reasoning Decoding | Yuxuan Zhu, David H. Yang, Parisa Shiravani +5 | cs.CL | 2026-10-27 |
| #44 | Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage | Chenfan Qu, Yachao Liang, Mingqi Fang +27 | cs.CV | 2026-10-27 |
| #45 | FilingLoop: Evaluating and Evolving LLM Agents for Corporate Disclosure Review and Revision | Wentao Zhang, Yilei Zhao, Guangyan Gan +2 | cs.AI | 2026-10-27 |
| #46 | Depth through Recurrence: Towards Ultra-Efficient On-Device ASR | Chen Feng, Tianyi Xu, Ramchalam Kinattinkara Ramakrishnan +5 | cs.LG | 2026-10-27 |
| #47 | When Should We Intervene at Test Time? | Jiahao Zhang, Xinling Wen, Liangliang Li +1 | cs.LG | 2026-10-27 |
| #48 | GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting | Joseph Natter, Long Vu, Yifan Zhang +3 | cs.LG | 2026-10-27 |
| #49 | A note on data-efficient finetuning of vision foundation models | Niclas Hergenröther, Antonio Orvieto | cs.CV | 2026-10-27 |
| #50 | Zhengrong-Spatial-Aware 1.0: Advancing 3D Multimodal Intelligence | Yu Zhang, Xiaogang Wang, Yuhang Cheng +2 | cs.CV | 2026-10-27 |