Search papers, labs, and topics across Lattice.
4
0
7
0
HarnessEval-W transforms world model evaluation from mere scoring to a transparent reasoning process that mirrors human judgment.
R2RDreamer achieves spatial generalization improvements in manipulation tasks by leveraging 3D-aware data augmentation without the pitfalls of complex scene setups or sim-to-real gaps.
By explicitly aligning visuomotor representations with the action space's rigid-body geometry, OASIS achieves superior robotic manipulation performance compared to methods relying on implicit geometry recovery.
Generating robotic manipulation data that respects object affordances is now possible at scale, but current imitation learning methods still struggle with tasks like pouring and hanging, revealing a critical gap.
