Search papers, labs, and topics across Lattice.
4
1
5
8
LingBot-Video bridges the gap between digital creativity and physical actuation, achieving unprecedented efficiency in video pretraining for embodied intelligence.
Disentangling geometry and texture in neural mesh representations unlocks versatile editing capabilities that traditional methods can't match.
Forget disjointed avatar components – Archon lets you generate complete, synchronized digital humans across text, audio, motion, and visuals with a single unified model.
Image editing, surprisingly, holds the key to robots that can nimbly manipulate objects in the real world.
