| Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments | Agents | Yuxin Chen +11 | May 26, 2026 | 16 |
| Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement | Agents | Dingwei Chen +7 | May 26, 2026 | 16 |
| RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models | Image & video gen | Xing Cong +5 | May 26, 2026 | 16 |
| Does Seeing More Mean Knowing More? Mono-Anchored Advantage Normalization for Multi-Source Visual Reasoning | Vision & multimodal | Fanhu Zeng +5 | May 25, 2026 | 16 |
| RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator | Data & benchmarks | Zhenwei Tang +5 | May 20, 2026 | 16 |
| Scalable Visual Pretraining for Language Intelligence | Vision & multimodal | Yiming Zhang +15 | Jul 10, 2026 | 15 |
| Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE | Agents | Haozhan Tang +4 | Jul 8, 2026 | 15 |
| Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning | Agents | Zhenyu Hou +3 | Jul 8, 2026 | 15 |
| PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation | Image & video gen | Haofei Xu +9 | Jul 2, 2026 | 15 |
| JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications | Vision & multimodal | Oxygen AIIC +39 | Jun 29, 2026 | 15 |
| InstanceControl: Controllable Complex Image Generation without Instance Labeling | Image & video gen | Xiaoyu Liu +6 | Jun 30, 2026 | 15 |
| When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search | Vision & multimodal | Yiling Tao +5 | Jun 26, 2026 | 15 |
| Valdi: Value Diffusion World Models | Image & video gen | Christopher Lindenberg +1 | Jul 1, 2026 | 15 |
| MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training | Reinforcement learning | Wenhan Ma +12 | Jun 29, 2026 | 15 |
| Little Brains, Big Feats: Exploring Compact Language Models | Code | Dari Baturova +5 | Jun 29, 2026 | 15 |
| Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis | Image & video gen | Shufan Li +6 | Jun 29, 2026 | 15 |
| SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning | Vision & multimodal | SingGuard Team | Jun 22, 2026 | 15 |
| Training Open Models for Agentic Phone Use | Agents | Zhengyang Tang +25 | Jun 22, 2026 | 15 |
| Deep Research in Physical Sciences: A Multi-Agent Framework and Comprehensive Benchmark | Agents | Yigeng Jiang +27 | Jun 17, 2026 | 15 |
| Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding | Vision & multimodal | Jingyuan Huang +6 | Jun 16, 2026 | 15 |
| Reinforcing Dual-Path Reasoning in Spatial Vision Language Models | Vision & multimodal | Yatai Ji +15 | Jun 16, 2026 | 15 |
| Variable-Width Transformers | Efficiency & systems | Zhaofeng Wu +5 | Jun 16, 2026 | 15 |
| EgoCS-400K: An Egocentric Gameplay Dataset for World Models | Robotics | Rongjin Guo +6 | Jun 16, 2026 | 15 |
| Self-Evolving Visual Questioner | Vision & multimodal | Yijun Liang +5 | Jun 11, 2026 | 15 |
| SP^3: Spherical Priors for Plug-and-Play Restoration | Image & video gen | Sean Man +3 | Jun 15, 2026 | 15 |
| Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning | Agents | NVIDIA +39 | Jun 12, 2026 | 15 |
| Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack | Robotics | He Zhang +25 | Jun 12, 2026 | 15 |
| Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback | Image & video gen | Huaisong Zhang +9 | Jun 4, 2026 | 15 |
| ICA Lens: Interpreting Language Models Without Training Another Dictionary | Safety & alignment | Sida Liu +1 | Jun 10, 2026 | 15 |
| i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models | Image & video gen | Boya Zeng +6 | Jun 9, 2026 | 15 |
| Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It | Safety & alignment | Xinyu Zhou +6 | Jun 9, 2026 | 15 |
| SwiftVR: Real-Time One-Step Generative Video Restoration | Image & video gen | Jiaqi Yan +7 | Jun 8, 2026 | 15 |
| Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders | Speech & audio | Georgii Aparin +3 | Jun 5, 2026 | 15 |
| dots.tts Technical Report | Speech & audio | Shi Lian +8 | Jun 5, 2026 | 15 |
| Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators | Vision & multimodal | Chenming Zhu +6 | Jun 4, 2026 | 15 |
| PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training | Vision & multimodal | Zelun Zhang +14 | Jun 2, 2026 | 15 |
| Joint Agent Memory and Exploration Learning via Novelty Signals | Agents | Shizuo Tian +11 | Jun 1, 2026 | 15 |
| When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems | Agents | Corrado Rainone +3 | May 28, 2026 | 15 |
| UI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI Agents | Vision & multimodal | Yuxiang Chai +5 | May 28, 2026 | 15 |
| Geometry Matters: 3D Foundation Priors for Learning Semantic Correspondence | Image & video gen | Artur Jesslen +2 | May 28, 2026 | 15 |
| HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs | Code | Yansong Ning +4 | May 27, 2026 | 15 |
| VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild | Agents | Xiaohongshu Inc | May 27, 2026 | 15 |
| Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders | Reinforcement learning | Yi Jing +6 | May 26, 2026 | 15 |
| MobileMoE: Scaling On-Device Mixture of Experts | Efficiency & systems | Yanbei Chen +7 | May 26, 2026 | 15 |
| Rethinking VLM Representation for VLA Initialization | Robotics | Weifeng Lin +7 | May 25, 2026 | 15 |
| DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs | Agents | Yi Li +5 | May 24, 2026 | 15 |
| OpenCoF: Learning to Reason Through Video Generation | Image & video gen | Xinyan Chen +4 | Jul 9, 2026 | 14 |
| Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model | Image & video gen | Xinyin Ma +5 | Jul 3, 2026 | 14 |
| LLM-as-a-Verifier: A General-Purpose Verification Framework | Robotics | Jacky Kwok +8 | Jul 6, 2026 | 14 |
| Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming | Vision & multimodal | Yong Yang +9 | Jun 30, 2026 | 14 |
| From SRA to Self-Flow: Data Augmentation or Self-Supervision? | Image & video gen | Dengyang Jiang +3 | Jul 2, 2026 | 14 |
| When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors | Efficiency & systems | Yuqing Yang +7 | Jun 30, 2026 | 14 |
| SWE-Together: Evaluating Coding Agents in Interactive User Sessions | Agents | Yifan Wu +10 | Jun 29, 2026 | 14 |
| Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents | Robotics | Haoran Zhang +7 | Jun 22, 2026 | 14 |
| Tmax: A simple recipe for terminal agents | Agents | Hamish Ivison +5 | Jun 22, 2026 | 14 |
| DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks | Agents | Jingxuan Han +10 | Jun 11, 2026 | 14 |
| Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models | Image & video gen | Yanming Zhang +5 | Jun 15, 2026 | 14 |
| ENPIRE: Agentic Robot Policy Self-Improvement in the Real World | Robotics | Wenli Xiao +16 | Jun 18, 2026 | 14 |
| HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining | Robotics | Juncheng Ma +21 | Jun 18, 2026 | 14 |
| Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification | Image & video gen | Wujian Peng +9 | Jun 16, 2026 | 14 |
| UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer | Image & video gen | Shuai Wang +5 | Jun 15, 2026 | 14 |
| MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold | Image & video gen | Yang Zhou +6 | Jun 11, 2026 | 14 |
| World Model Self-Distillation: Training World Models to Solve General Tasks | Robotics | Sebastian Stapf +3 | Jun 10, 2026 | 14 |
| AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing | Robotics | Jisong Cai +12 | Jun 8, 2026 | 14 |
| OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning | Speech & audio | Jiahao Wang +15 | Jun 7, 2026 | 14 |
| Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses | Agents | Xiaojun Wu +9 | Jun 6, 2026 | 14 |
| DEI: Diversity in Evolutionary Inference for Quality-Diversity Search | Code | John Donaghy +1 | May 26, 2026 | 14 |
| UniSHARP: Universal Sharp Monocular View Synthesis | Safety & alignment | Meixi Song +6 | Jun 5, 2026 | 14 |
| Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them | Image & video gen | Woojung Han +5 | Jun 4, 2026 | 14 |
| SIA: Self Improving AI with Harness & Weight Updates | Agents | Prannay Hebbar +6 | May 26, 2026 | 14 |
| AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation | Image & video gen | Haobo Li +8 | Jun 2, 2026 | 14 |
| MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills? | Vision & multimodal | Xinyu Che +12 | Jun 1, 2026 | 14 |
| Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling | Reinforcement learning | Runpeng Dai +4 | Jun 2, 2026 | 14 |
| Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation | Image & video gen | Ziyue Lin +8 | May 31, 2026 | 14 |
| TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation | Vision & multimodal | Xinkai Ma +23 | Jun 1, 2026 | 14 |
| LVSA: Training-Free Sparse Attention for Long Video Diffusion | Image & video gen | Gael Glorian +4 | May 29, 2026 | 14 |
| Brain-IT-VQA: From Brain Signals to Answers | Vision & multimodal | Roman Beliy +4 | May 28, 2026 | 14 |
| CubePart: An Open-Vocabulary Part-Controllable 3D Generator | Code | Yiheng Zhu +11 | May 27, 2026 | 14 |
| Towards Evaluation Engineering: An Empirical Study of ML Evaluation Harnesses in the Wild | Code | Zhimin Zhao +4 | May 22, 2026 | 14 |
| Video Generation Models are General-Purpose Vision Learners | Robotics | Letian Wang +11 | Jul 10, 2026 | 13 |
| MentalThink: Shaping Thoughts in Mental SVG World | Vision & multimodal | Kangheng Lin +13 | Jul 3, 2026 | 13 |
| MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering | Vision & multimodal | Dang Quang Thien Tran +9 | Jul 1, 2026 | 13 |
| BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery | Agents | Jieyi Wang +11 | Jun 19, 2026 | 13 |
| How Good Can Linear Models Be for Time-Series Forecasting? | Safety & alignment | Lang Huang +2 | Jun 25, 2026 | 13 |
| Interleaved Speech Language Models Latently Work In Text | Speech & audio | Talia Sternberg +2 | Jun 21, 2026 | 13 |
| SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation | Robotics | Nadun Ranawaka +17 | Jun 26, 2026 | 13 |
| GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems | Agents | Xiaocheng Yang +3 | Jun 26, 2026 | 13 |
| LISA: Likelihood Score Alignment for Visual-condition Controllable Generation | Image & video gen | Yanghao Wang +6 | Jun 25, 2026 | 13 |
| STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability | Agents | Haipeng Luo +6 | Jun 17, 2026 | 13 |
| MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model | Speech & audio | Lichen Bai +16 | Jun 16, 2026 | 13 |
| GD^2PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization | Code | Haotian Liu +13 | Jun 15, 2026 | 13 |
| CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks? | Agents | Yuxin Zhang +4 | Jun 13, 2026 | 13 |
| Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking | Agents | Jiwan Chung +3 | Apr 8, 2026 | 13 |
| World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible | Image & video gen | Hao Zhang +8 | Jun 11, 2026 | 13 |
| The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment | Vision & multimodal | Filippo Tonini +5 | Jun 9, 2026 | 13 |
| iMaC: Translating Actions into Motion and Contact Images for Embodied World Models | Robotics | Zhenyu Wu +10 | Jun 8, 2026 | 13 |
| HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness | Agents | Xiaoxuan Wang +5 | Jun 11, 2026 | 13 |
| Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill | Agents | Tao Chen +12 | Jun 2, 2026 | 13 |
| Ψ-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues | Agents | Peixuan Han +5 | Jun 1, 2026 | 13 |
| HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos | Vision & multimodal | Jeongeun Park +6 | May 19, 2026 | 13 |