Search papers, labs, and topics across Lattice.
Affiliation:
3
0
2
4
Humanoid robots can now learn complex loco-manipulation by transferring visual-motion priors from over 10,000 hours of human data, achieving top performance on simulated and real-world tasks.
Dexterous teleoperation can now achieve high-fidelity hand-state estimation with just a few calibration poses, bypassing per-user model retraining.
Achieve robust and general humanoid control with FAST, a framework that adapts to new motions while maintaining balance, outperforming SOTA baselines in real-world deployment.
