Ji Ma

UMR achieves unprecedented motion fidelity by learning dense point cloud correspondences, eliminating the need for manual semantic mappings in humanoid motion retargeting.

Quadrupedal robots can now autonomously and dynamically navigate narrow gates, achieving lifelike agility previously thought unattainable.

HiPHI significantly expands the diversity of human motion data, offering a game-changing resource for training humanoid AI in complex real-world tasks.

Real-time MRI-guided interventions are now possible with a master-slave robotic system that allows for unprecedented control and precision in needle-based procedures.

A new flow matching prior can drastically enhance humanoid motion tracking by guiding policy exploration with geometric insights from unordered pose data.