Search papers, labs, and topics across Lattice.
The University of Tokyo
2
0
3
FlexLAM achieves superior performance over fixed-capacity models by dynamically adjusting latent action lengths, revolutionizing how we approach action alignment in video decision-making.
YUBI's finger-driven design enables seamless data collection for bimanual manipulation, yielding a dataset that allows for effective policy transfer across diverse robotic systems.
