Search papers, labs, and topics across Lattice.
3
0
5
3
Results show that robust visuomotor learning benefits from structuring, rather than removing, visual embodiment information, and embodiment canonicalization in 3D point clouds substantially improves human-to-robot policy transfer without robot demonstrations.
LLMs can now plan complex, long-horizon household tasks from ambiguous instructions with significantly improved performance, thanks to a novel reinforcement learning approach that corrects intermediate reasoning steps.
Achieve one-shot skill transfer in imitation learning by disentangling intent from execution, allowing robots to adapt to new environments simply by injecting the "Intent" token from a demonstration.
