| 1 | Skill-Space Shooting for Autonomous Robot Policy Improvement | Zihang Rui, Renhao Wang, Haoxu Huang +1 | cs.RO | 2026-09-29 |
| 2 | DMA$^2$: Pixel-space Distribution Matching with Adversarial and Anchor Losses | Xin Lin, Zhifei Zhang, Yuqian Zhou +6 | cs.CV | 2026-09-29 |
| 3 | LongLive-Plug: Once-for-All Distillation for Video Generation | Shuai Yang, Luozhou Wang, Wei Huang +9 | cs.CV | 2026-09-29 |
| #4 | LIFT: Layout-In-Future Video Generation under Large Viewpoint Change via On-Policy Self-Distillation | Shengxiang Ji, Boyang Wang, Haiyang Xu +9 | cs.CV | 2026-09-29 |
| #5 | Multi-Agent Flow Matching with Decoupled Generative Guidance | Ruoyu Lin, Magnus Egerstedt, Fabio Pasqualetti | cs.LG | 2026-09-29 |
| #6 | Latent Inference-Time Guidance of Time Series Foundation Models | Chloé Hashimoto-Cullen, Amaury Durand, Laurent Bozzi +3 | stat.ML | 2026-09-29 |
| #7 | EpiCon: Collective Agent Learning through Co-Evolving Multimodal Memory | Ziyun Zeng, Hang Hua, Shaden Alshammari +3 | cs.CV | 2026-09-29 |
| #8 | Guide, Then Let Go: Gap-Adaptive Teacher Scheduling for Sparse-Reward Agentic RL | Youling Huang, Tiankuo Xu, Jiaji Liu +10 | cs.AI | 2026-09-29 |
| #9 | How Many Labels Does a Language Need? Annotation Budgets and Cross-Lingual Pooling for African-Language Text Classification | Bhanu Prakash Vangala, Sowmya Guda, Navya Vangala | cs.CL | 2026-09-29 |
| #10 | Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents | Sicheng Xie, Yitong Chen, Haidong Cao +3 | cs.RO | 2026-09-29 |
| #11 | Pixel-Level Transformers in Remote Sensing: A Canopy Height Case Study | Sven Ligensa, Jan Pauls, Karsten Schrödter +2 | cs.CV | 2026-09-29 |
| #12 | Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model | Van Bach Nguyen, Jörg Schlötterer, Christin Seifer | cs.CV | 2026-09-29 |
| #13 | TReVS: Integrating Textual Relevance and Visual Saliency for Efficient Vision-Language Model Token Pruning | Jing Wang, Zhiping Wu, Dongdong Ren +3 | cs.CV | 2026-09-29 |
| #14 | SkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation | Renxi Wang, Mingshan Hee, Fajri Koto +2 | cs.AI | 2026-09-29 |
| #15 | Hierarchical Compression of Vision-Language Model Benchmarks | Hyunjong Ok, Seunggu Kang, Jaeho Lee | cs.LG | 2026-09-29 |
| #16 | From Dissonance to Orchestration: Teacher Intervention in On-Policy Distillation | Yuhao Wang, Ruiyang Ren, Yinan Zhang +3 | cs.CL | 2026-09-29 |
| #17 | Direct Experience World-Model Optimization: Learning the World Beyond Action Imitation | Xiangcheng Zhan, Zirui Chen, Yicheng Zhao +2 | cs.AI | 2026-09-29 |
| #18 | FLASH: A "Generate Once, Synthesize Many" Framework for Synthetic Anomaly Generation in Industrial Anomaly Detection | Abhay Kumar Das, Rajesh Gangireddy, Ashwin Vaidya +1 | cs.CV | 2026-09-29 |
| #19 | Interacting particle guidance for sampling reward-tilted generative priors | Adhithyan Kalaivanan, Zheng Zhao, Jens Sjölund +1 | cs.LG | 2026-09-29 |
| #20 | From Judgment Quality to Downstream Utility: Rethinking LLM-as-a-Judge for Open-Ended Tasks | Zheng Zhang, Lufei Li, Xinyue Tan +4 | cs.AI | 2026-09-29 |
| #21 | MSTypography: Multi-character Semantic Typography via Balancing Word Legibility and Object Recognizability | Xinye Yang, Xinding Zhu, Kai Fang +4 | cs.CV | 2026-09-29 |
| #22 | Multi-Granularity Language-Guided Imitation Learning via Instruction Decomposition | Yi-Pei Chiu, Wei-Ta Chu | cs.CV | 2026-09-29 |
| #23 | OmniRoute: Mapping Temporal Semantic Evidence to Audio-Visual Token Budgets for Efficient Omnimodal Large Language Models | Yuchen Deng, Zidang Cai, Feidiao Yang +4 | cs.CV | 2026-09-29 |
| #24 | Iterative Exact Discrete Guidance for Energy-Based Sampling | Yuwen Qian, Yidong Ouyang, Zhengyan Wan +1 | cs.LG | 2026-09-29 |
| #25 | Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation | Xingtong Ge, Yutong Wang, Lunjie Zhu +7 | cs.CV | 2026-09-29 |
| #26 | Benchmarking Automatic Speech Recognition Tools for Iberian Languages | Fernando López, Pablo Gómez, David Solans +2 | cs.CL | 2026-09-29 |
| #27 | Less Supervision, Better Generalization: Weakly Supervised Fake Region Localization in Diffusion-Edited Images | Junhee Lee, Donghyeon Jeon, Taeoh Kim +2 | cs.CV | 2026-09-29 |
| #28 | Safer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning | Muhammad Zeeshan Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu +2 | cs.CR | 2026-09-29 |
| #29 | On-Policy Visual Evidence Distillation | Shaohang Wei, Feifan Song, Guangyue Peng +9 | cs.CV | 2026-09-29 |
| #30 | Motion Concept Unlearning in Video Diffusion Models | Ping Liu, Chi Zhang | cs.CV | 2026-09-29 |
| #31 | Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving | Yiming Wang, Yikang Liu, Qingyuan Tian +4 | cs.LG | 2026-09-29 |
| #32 | Can Agents Design Libraries for Agents? | Gabriel Orlanski, Alex L. Zhang, Avi Trost +4 | cs.AI | 2026-09-29 |
| #33 | When Semantics Matter: Reliability-Aware Semantic-Rhythm Control for Co-Speech Gesture Generation | Zhirui Xing, Long Ye, Kaige Li +2 | cs.CV | 2026-09-29 |
| #34 | MLToolBench: Learning Tool-Augmented Agents for Machine Learning Development | Xin Yu, Lizhu Zhang, Jiamu Bai +7 | cs.AI | 2026-09-29 |
| #35 | FairDiff: Mitigating the Self-Reinforcing Matthew Effect in Diffusion Recommender Models | Song-Li Wu, Xianquan Wang, Zhaocheng Du +2 | cs.AI | 2026-09-29 |
| #36 | Text2Sim: Agentic Physics-Based Simulation Generation with Distilled Expertise | Xiaoyu Xiong, Tsun-Hsuan Wang, Yi-Ling Qiao +2 | cs.GR | 2026-09-29 |
| #37 | Efficient and Scalable Physics-Guided Fully Convolutional Spatiotemporal Learning for 3D Microstructure Evolution Prediction | Michael Trimboli, Wenxi Liu, Xianqi Li | cs.LG | 2026-09-29 |
| #38 | AVIO: Learning to Add and Remove Sounding Objects in Audiovisual Scenes | Weihan Xu, Kan Jen Cheng, Koichi Saito +8 | cs.AI | 2026-09-29 |
| #39 | DisCoMBO: Steering Expert-in-the-Loop Black Box Optimization via Distributional Conformance | Jonas Seng, Bennet Wittelsbach, Kristian Kersting | cs.LG | 2026-09-29 |
| #40 | RA-CFGCache: From Branch-Level Criteria to Guided-Risk Control under Classifier-Free Guidance | Yiming Liu, Ben Wan, Tongxuan Liu +5 | cs.CV | 2026-09-29 |
| #41 | FineART: Fine-grained Annotated Robotic Trajectory Dataset and Vision-Language-Action Model for Bimanual Manipulation | Jade Choghari, Pepijn Kooijmans, Mansi Agarwal +8 | cs.RO | 2026-09-29 |
| #42 | An Empirical Study and Assessment of EU AI Act Compliance Checkers | Zhen Tao, Alize Kahraman, Shidong Pan +4 | cs.AI | 2026-09-28 |
| #43 | FastGuide: Accelerating Reward Guidance for Diffusion Large Language Models | Darshan Thaker, Lachlan Ewen MacDonald, René Vidal | cs.CL | 2026-09-28 |
| #44 | EvoMO-SR: Multiobjective LLM-based Evolution of Symbolic Expressions with substructure guidance | Cristina Rossetti, Anna V. Kononova, Thomas Bäck +2 | cs.LG | 2026-09-28 |
| #45 | Learning Continuous Patient Trajectories from Electronic Health Records | Silas Ruhrberg Estévez, Kara Liu, Christopher Chiu +4 | cs.LG | 2026-09-28 |
| #46 | Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion | Chong Wang, Zixuan Fu, Shiqi Huang +3 | cs.CV | 2026-09-28 |
| #47 | Infrared Subtraction with Artificial Intelligence | Wenjie He, Xiaohui Liu, Yandong Liu +1 | hep-ph | 2026-09-28 |
| #48 | How to Loop MoE: Flatten the Experts, Untie the Attention | Shouren Wang, Chuang Ma, Mohsen Hariri +6 | cs.LG | 2026-09-28 |
| #49 | FinAutoRubric: Expert-Guided Automatic Rubric Generation for Evaluating Financial Research Agents | Hoyoung Lee, Suyeol Yun, Jack Haverty +17 | cs.AI | 2026-09-28 |
| #50 | GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space | Kerui Ren, Tao Lu, Linning Xu +5 | cs.CV | 2026-09-28 |