Search papers, labs, and topics across Lattice.
4
0
6
3
A single image can now yield complete, high-fidelity 3D scenes, indoors and out, by adapting object-centric priors with adaptive chunking and explicit 2D-3D correspondence.
Human hand demonstrations don't need to be tracked or imitated to solve dexterous manipulation鈥攖hey just need to seed the simulation's reset distribution.
TerraZero achieves unprecedented training speed and safety for autonomous driving agents without relying on human demonstrations, setting a new benchmark in self-play simulation.
