Search papers, labs, and topics across Lattice.
Beijing Humanoid Robot Innovation Center ,, China University of Mining & Technology , Beijing
2
0
4
9
A single visual interface, action views, bridges the gap between video generation models and diverse robotic embodiments, enabling unified action modeling and execution.
GroupVideo achieves unprecedented fidelity in multi-character video generation, resolving identity confusion and unnatural motions that plague existing methods.
