Ziheng Xi

TTP enables robots to learn dexterous manipulation from human tactile experiences, achieving unprecedented performance in complex tasks.

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.