Search papers, labs, and topics across Lattice.
2
0
3
10
End-effector traces boost cross-embodiment transfer in robot manipulation, enhancing real-world task performance by 28% when leveraging simulation data.
End-to-end training of Vision-Language-Action models just got a whole lot easier: VLA Foundry unifies LLM, VLM, and VLA training in a single open-source framework.
