OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction Paper • 2610.01762 • Published 26 days ago • 240
LEGO-Anything: Coding Agents for 3D Scene Reconstruction Paper • 2609.36380 • Published 29 days ago • 104
Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models Paper • 2609.12641 • Published Sep 11 • 80
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models Paper • 2608.27550 • Published Aug 27 • 81
RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning Paper • 2609.03199 • Published Sep 2 • 121