OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling Paper • 2506.20512 • Published 5 days ago • 34
Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts Models Paper • 2506.18945 • Published 7 days ago • 38
RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation Paper • 2506.18088 • Published 8 days ago • 16
AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models Paper • 2506.19851 • Published 5 days ago • 52
Bi-VLA: Vision-Language-Action Model-Based System for Bimanual Robotic Dexterous Manipulations Paper • 2405.06039 • Published May 9, 2024 • 1