Search papers, labs, and topics across Lattice.
2
0
5
5
MLLMs possess an intrinsic "S-Space" that acts as a spatial workspace, encoding object coordinates and enabling viewpoint transformations, even under non-spatial queries.
Swapping out your VLA's visual backbone for a video predictive embedding (V-JEPA 2) might be the surprisingly simple trick to unlock substantial gains in robotic manipulation performance.
