Search papers, labs, and topics across Lattice.
3
0
3
Predicting task-relevant latent futures, not raw pixels, unlocks efficient and effective long-horizon VLA control, outperforming reactive policies by over 11 percentage points.
SeMoCo achieves unprecedented reconstruction accuracy by decoupling semantic meaning from kinematic details in motion representations.
GraspALL achieves 32-44% better garment grasping accuracy in low-light by adaptively fusing RGB and depth data based on a learned illumination intensity reference.
