CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization Paper • 2607.25659 • Published Jul 28 • 84
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published Jul 21 • 312
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model Paper • 2607.17977 • Published Jul 20 • 198
Search and Refine During Think: Autonomous Retrieval-Augmented Reasoning of LLMs Paper • 2505.11277 • Published May 16, 2025 • 64
ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory Paper • 2607.10350 • Published Jul 15 • 85
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published Jul 16 • 212
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation Paper • 2607.12752 • Published Jul 15 • 21
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Paper • 2607.14935 • Published Jul 16 • 172
PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages Paper • 2607.05992 • Published Jul 7 • 6
RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation Paper • 2607.06558 • Published Jul 7 • 79
MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision Paper • 2606.17162 • Published Jun 15 • 178
DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams Paper • 2606.21337 • Published Jun 19 • 75