Sergey Levine
@svlevine
Associate Professor at UC Berkeley
Co-founder, Physical Intelligence
加入 April 2018
144 正在關注 136.1K 粉絲
Now we can have self-refinement for VLAs in the real world (with the aid of a big VLM)! VLM critiques VLA rollouts and iteratively refines the commands to make it perform better.
