Search papers, labs, and topics across Lattice.
2
0
5
2
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.
