Search papers, labs, and topics across Lattice.
3
0
3
2
By integrating selective visual processing with adaptive action pathways, this framework achieves unprecedented success rates in bimanual manipulation tasks, outperforming traditional approaches.
Achieve robust sim-to-real transfer for robotic catching by training a multi-agent system on raw pixel inputs, bypassing the need for explicit 3D pose estimation.
Task-aware attention slashes compute in robot VLA models by adaptively routing visual inputs based on relevance, boosting efficiency without sacrificing control performance.
