RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning Paper • 2609.03199 • Published 10 days ago • 116
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? Paper • 2609.01437 • Published 11 days ago • 264
RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests Paper • 2608.27831 • Published 12 days ago • 32
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models Paper • 2608.25518 • Published 17 days ago • 196
HarnessEval-W: Agentifying the Evaluation of Visual Worlds Paper • 2608.16859 • Published 26 days ago • 340
Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation Paper • 2608.09420 • Published Aug 10 • 8
DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation Paper • 2607.26811 • Published Jul 29 • 93
Progress Reward Modeling for Robotic Learning: A Comprehensive Survey Paper • 2607.21655 • Published Jul 22 • 193
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published Jul 21 • 313
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model Paper • 2607.17977 • Published Jul 20 • 199
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Paper • 2607.14935 • Published Jul 16 • 172
X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras Paper • 2607.12993 • Published Jul 14 • 131