Search papers, labs, and topics across Lattice.
2
0
2
0
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.
Tool-using LLMs face a near-universal robustness gap, but combining Bayesian Tool Memory with reinforcement learning can boost recovery performance by over 40% in failure scenarios.
