Search papers, labs, and topics across Lattice.
2
0
0
A flow matching model learns a dynamically feasible trajectory manifold, enabling dexterous manipulation retargeting with orders of magnitude fewer samples than MPC.
Co-training generative world models on 1,880 hours of retargeted human motion and video unlocks an 84% real-world humanoid loco-manipulation success rate while drastically slashing the need for costly teleoperated robot data.
