| Looped World Models | Image & video gen | Hongyuan Adam Lu +30 | Jun 16, 2026 | 467 |
| ABot-Earth 0.5: Generative 3D Earth Model | Robotics | Ming Qian +27 | Jun 8, 2026 | 466 |
| Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players | Robotics | Fangfu Liu +9 | May 27, 2026 | 423 |
| Agents' Last Exam | Agents | Yiyou Sun +39 | Jun 3, 2026 | 338 |
| Orca: The World is in Your Mind | Robotics | Yihao Wang +39 | Jun 29, 2026 | 311 |
| On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters | Efficiency & systems | Mind Lab +39 | Jun 1, 2026 | 224 |
| LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling | Agents | Jian Yang +18 | Jun 16, 2026 | 207 |
| JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence | Speech & audio | Dingyu Yao +14 | Jun 10, 2026 | 204 |
| Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs | Agents | Haozhe Zhao +8 | May 28, 2026 | 192 |
| Kwai Keye-VL-2.0 Technical Report | Vision & multimodal | Kwai Keye Team +39 | Jun 9, 2026 | 188 |
| Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models | Robotics | Yifu Yuan +22 | Jun 9, 2026 | 165 |
| The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning | Reinforcement learning | Jing Liang +11 | Jun 28, 2026 | 161 |
| MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision | Agents | Ye Jin +3 | Jun 15, 2026 | 159 |
| Agentic Abstention: Do Agents Know When to Stop Instead of Act? | Agents | Han Luo +2 | Jun 27, 2026 | 146 |
| Qwen-AgentWorld: Language World Models for General Agents | Image & video gen | Yuxin Zuo +32 | Jun 23, 2026 | 145 |
| Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding | Code | Jianuo Huang +5 | May 28, 2026 | 143 |
| AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security | Agents | Dongrui Liu +49 | May 28, 2026 | 142 |
| MiniMax Sparse Attention | Vision & multimodal | Xunhao Lai +10 | Jun 11, 2026 | 141 |
| EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments | Agents | Jundong Xu +13 | Jun 11, 2026 | 140 |
| Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments | Robotics | Qiuyue Wang +39 | May 28, 2026 | 140 |
| LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding | Vision & multimodal | Shihao Wang +12 | May 26, 2026 | 139 |
| Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance | Image & video gen | Kangsheng Duan +5 | Jun 17, 2026 | 137 |
| Vidu S1: A Real-Time Interactive Video Generation Model | Speech & audio | Jintao Zhang +26 | Jul 3, 2026 | 127 |
| Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories | Speech & audio | Kevin Qinghong Lin +5 | Jun 9, 2026 | 127 |
| Are We Ready For An Agent-Native Memory System? | Agents | Wei Zhou +7 | Jun 23, 2026 | 124 |
| Program-as-Weights: A Programming Paradigm for Fuzzy Functions | Code | Wentao Zhang +5 | Jul 2, 2026 | 118 |
| Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models | Vision & multimodal | Mahtab Bigverdi +10 | Jun 3, 2026 | 117 |
| Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models | Speech & audio | Lianghua Huang +23 | Jun 23, 2026 | 115 |
| Geometric Action Model for Robot Policy Learning | Robotics | Jisang Han +9 | Jun 15, 2026 | 115 |
| Toward Generalist Autonomous Research via Hypothesis-Tree Refinement | Agents | Jiajie Jin +17 | Jun 10, 2026 | 115 |
| DreamX-World 1.0: A General-Purpose Interactive World Model | Image & video gen | DreamX Team +22 | Jun 15, 2026 | 112 |
| COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation | Agents | Tianyi Zhou +4 | May 29, 2026 | 111 |
| SWE-Explore: Benchmarking How Coding Agents Explore Repositories | Agents | Shaoqiu Zhang +10 | Jun 5, 2026 | 110 |
| Dockerless: Environment-Free Program Verifier for Coding Agents | Agents | Wenhao Zeng +12 | Jun 26, 2026 | 109 |
| Cosmos 3: Omnimodal World Models for Physical AI | Robotics | Aditi +39 | Jun 1, 2026 | 108 |
| Audio Interaction Model | Speech & audio | Zhifei Xie +10 | Jun 3, 2026 | 107 |
| OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data | Image & video gen | Jiwen Liu +10 | Jun 11, 2026 | 106 |
| DOPD: Dual On-policy Distillation | Vision & multimodal | Xinlei Yu +15 | Jun 29, 2026 | 104 |
| VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models | Reinforcement learning | Sen Xu +8 | Jun 15, 2026 | 104 |
| SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning | Vision & multimodal | Seokju Cho +10 | Jun 11, 2026 | 104 |
| GrepSeek: Training Search Agents for Direct Corpus Interaction | Agents | Alireza Salemi +6 | May 28, 2026 | 104 |
| WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces | Vision & multimodal | Wanli Li +6 | Jun 8, 2026 | 102 |
| Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent | Agents | Lei Bai +39 | Jun 29, 2026 | 98 |
| PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems | Agents | Jiayu Liu +10 | Jun 21, 2026 | 95 |
| Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings | Code | Songhao Wu +5 | Jun 5, 2026 | 91 |
| MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling | Theory | Jiacheng Chen +22 | Jun 11, 2026 | 90 |
| Agent Explorative Policy Optimization for Multimodal Agentic Reasoning | Vision & multimodal | Minki Kang +6 | May 27, 2026 | 90 |
| RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation | Robotics | Haoyu Zhao +5 | Jul 7, 2026 | 89 |
| FastContext: Training Efficient Repository Explorer for Coding Agents | Agents | Shaoqiu Zhang +7 | Jun 12, 2026 | 89 |
| OCC-RAG: Optimal Cognitive Core for Faithful Question Answering | Safety & alignment | Maksim Savkin +9 | May 30, 2026 | 89 |
| Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale | Agents | Ang Li +39 | Jun 13, 2026 | 87 |
| Redesign Mixture-of-Experts Routers with Manifold Power Iteration | Safety & alignment | Songhao Wu +3 | Jun 10, 2026 | 87 |
| ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research | Vision & multimodal | Wanghan Xu +39 | May 28, 2026 | 87 |
| ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation | Code | Hongru Hou +7 | May 27, 2026 | 87 |
| Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution | Code | Liliana Hotsko +3 | Jun 4, 2026 | 86 |
| AlayaWorld: Long-Horizon and Playable Video World Generation | Robotics | AlayaWorld Team +16 | Jul 7, 2026 | 85 |
| Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning | Vision & multimodal | Chen Tang +28 | Jul 8, 2026 | 84 |
| LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing | Image & video gen | Xinyu Wang +3 | Jun 25, 2026 | 82 |
| DanceOPD: On-Policy Generative Field Distillation | Image & video gen | Wei Zhou +10 | Jun 25, 2026 | 81 |
| InterleaveThinker: Reinforcing Agentic Interleaved Generation | Robotics | Dian Zheng +6 | Jun 11, 2026 | 80 |
| EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions | Vision & multimodal | Jincheng Zhong +7 | Jun 22, 2026 | 79 |
| Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention | Efficiency & systems | Vishesh Tripathi +1 | Jun 18, 2026 | 79 |
| Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? | Vision & multimodal | Jiaqi Tang +8 | Jun 6, 2026 | 79 |
| EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation | Speech & audio | Songlin Yang +25 | May 22, 2026 | 79 |
| OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources | Efficiency & systems | Jinheon Baek +7 | May 28, 2026 | 77 |
| RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation | Robotics | Haoyu Zhao +8 | Jul 7, 2026 | 76 |
| BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding | Image & video gen | Hao Zhang +5 | Jun 30, 2026 | 76 |
| Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models | Robotics | Nikita Kachaev +12 | Jun 17, 2026 | 76 |
| OpenRath: Session-Centered Runtime State for Agent Systems | Agents | Fukang Wen +2 | Jun 17, 2026 | 76 |
| Learning from the Self-future: On-policy Self-distillation for dLLMs | Image & video gen | Yifu Luo +6 | Jun 16, 2026 | 76 |
| APPO: Agentic Procedural Policy Optimization | Agents | Xucong Wang +7 | Jun 10, 2026 | 76 |
| FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents | Agents | Jia Deng +11 | Jun 10, 2026 | 75 |
| Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution | Agents | Xucong Wang +6 | Jun 9, 2026 | 75 |
| OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers | Data & benchmarks | Siyuan Li +11 | Jul 4, 2026 | 74 |
| DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams | Image & video gen | Cong Wan +8 | Jun 19, 2026 | 74 |
| DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects | Robotics | Tianshan Zhang +4 | Jun 13, 2026 | 74 |
| From Pixels to Words -- Towards Native One-Vision Models at Scale | Vision & multimodal | Haiwen Diao +20 | May 27, 2026 | 73 |
| Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents | Agents | Shuo Ji +2 | Jun 4, 2026 | 72 |
| On the Geometry of On-Policy Distillation | Reinforcement learning | Zhennan Shen +8 | Jun 5, 2026 | 71 |
| SpatialBench: Is Your Spatial Foundation Model an All-Round Player? | Robotics | Haosong Peng +12 | May 26, 2026 | 71 |
| Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling | Efficiency & systems | Xiang Hu +12 | Jul 3, 2026 | 68 |
| UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning | Vision & multimodal | Niu Lian +10 | Jul 5, 2026 | 68 |
| Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks | Agents | Mengyu Zheng +15 | Jun 10, 2026 | 68 |
| DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation | Image & video gen | Nan Chen +9 | Jun 24, 2026 | 67 |
| Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application | Agents | Jiachun Li +14 | Jun 10, 2026 | 67 |
| Latent Spatial Memory for Video World Models | Image & video gen | Weijie Wang +9 | Jun 8, 2026 | 66 |
| A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks | Agents | Tomer Keren +5 | May 27, 2026 | 65 |
| Trust-Region Behavior Blending for On-Policy Distillation | Efficiency & systems | Daniil Plyusov +6 | May 29, 2026 | 65 |
| PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models | Image & video gen | Yueyi Sun +10 | Jun 17, 2026 | 64 |
| MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research | Agents | Dingbang Wu +10 | May 25, 2026 | 64 |
| Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients | Vision & multimodal | Byung-Kwan Lee +10 | Jun 16, 2026 | 63 |
| In-Context World Modeling for Robotic Control | Robotics | Siyin Wang +6 | Jun 25, 2026 | 62 |
| NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers? | Agents | Yuru Wang +16 | Jun 23, 2026 | 62 |
| LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents | Agents | Aofan Yu +10 | Jun 4, 2026 | 62 |
| Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism | Agents | Haoxiang Zhang +6 | May 29, 2026 | 62 |
| PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space | Image & video gen | Sensen Gao +5 | Jul 6, 2026 | 61 |
| ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog | Vision & multimodal | Lingao Xiao +19 | Jul 5, 2026 | 61 |
| AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents | Agents | Xiangchen Cheng +9 | Jul 2, 2026 | 61 |
| FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention | Code | Yan Wang +12 | Jun 8, 2026 | 61 |
| CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation | Image & video gen | Fangtai Wu +9 | May 25, 2026 | 61 |