Search papers, labs, and topics across Lattice.
3
0
5
0
Skip the costly robot teleoperation data: ZeroWBC learns surprisingly natural humanoid control policies directly from human egocentric videos.
Ditch slow, iterative sampling: a new Mean-Flow method achieves up to 84x faster action generation for vision-language-action robotic control.
Diffusion policies get a 19% adaptability boost in dynamic robotic tasks, without retraining, thanks to a closed-loop architecture that dynamically corrects actions in real-time.
