Search papers, labs, and topics across Lattice.
3
36
5
7
Seemingly impressive VLA performance on robotic benchmarks crumbles when stress-tested with causal interventions, exposing a reliance on brittle shortcuts rather than genuine embodied reasoning.
Stop averaging over noisy robot data: PTR selectively trusts training samples based on how well their post-action consequences align with learned representations, leading to more robust offline policy learning.
Forget synthetic data and limited teleoperation: Being-H0 leverages the dexterity and scalability of human hand videos for VLA pretraining, unlocking superior performance in complex manipulation tasks.
