| CARVIEW |
VisualMimic Team
*Equal contribution †Equal advising
VisualMimic enables *generalizable* visuomotor skills across time & space.
VisualMimic enables humanoid loco-manipulation with *whole-body dexterity*.
VisualMimic Framework
Unveiling Key Designs in VisualMimic
Interface Design for High-Level/Low-Level Communication
Training Low-Level Tracker with Teacher-Student Distillation
More Results
Diverse Simulation Tasks with Vision
Real-World Results
Sim2Sim Results
Related Work
Acknowledgements
We would like to thank all members of the CogAI group and The Movement Lab from Stanford University for their support. We also thank the Stanford Robotics Center for providing the experiment space. This work is in part supported by Stanford Institute for Human-Centered AI (HAI), Stanford Robotics Center (SRC), ONR MURI N00014-22-1-2740, ONR MURI N00014-24-1-2748, and NSF:FRR 215385.
BibTeX
@article{yin2025visualmimic,
title={VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation},
author= {Shaofeng Yin and Yanjie Ze and Hong-Xing Yu and C. Karen Liu and Jiajun Wu},
year= {2025},
journal= {arXiv preprint arXiv:2509.20322}
}