Liyiming Ke
Liyiming Ke is a research scientist at Physical Intelligence, where she contributes to the company's robotic foundation model efforts including the π0 and π0.5 models. She completed her PhD at the University of Washington under Siddhartha Srinivasa, focusing on data-driven fine manipulation and dexterous tasks such as robotic chopstick use. She is known for her work on RL Token, a method for rapidly specializing vision-language-action models for precise manipulation through online reinforcement learning.
“I said: if the algorithm can succeed on chopsticks, it proves that on other methods it should be even easier to succeed. If you're going to do something, do the hardest version to succeed.”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.