Search papers, labs, and topics across Lattice.
4
0
2
16
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.
HINT achieves a remarkable balance between semantic intent and visual adaptability, leading to substantial gains in robot manipulation success rates.
Asynchronous multimodal policies can significantly outperform traditional synchronous methods by leveraging native inference rates and dynamic guidance.
Calibration-free dexterous hand retargeting achieves intuitive control and superior performance without the need for hand-specific tuning.
