Search papers, labs, and topics across Lattice.
3
0
6
0
Achieving mask-free video virtual try-on is now possible with BooM-VVT, which significantly reduces reliance on costly video-level data while enhancing garment realism.
Forget scalar rewards: GenEvolve distills structured visual experiences from successful and failed generation trajectories, enabling token-level supervision for self-improving image generation agents.
Forget static imitation learning: LaST-R1 unlocks near-perfect robotic manipulation (99.8% success) by adaptively reasoning about physical dynamics *before* acting, then refining with RL.
