Moo Jin Kim

Moo Jin Kim is a Ph.D. student in Computer Science at Stanford University, where he is advised by Chelsea Finn and Percy Liang. He conducts research in robotics, machine learning, and NLP, with a focus on vision-language-action models. He is best known as a core developer of OpenVLA, an open-source 7B-parameter vision-language-action model for robotic manipulation, and OpenVLA-OFT, an optimized fine-tuning recipe that achieves state-of-the-art performance on robot manipulation benchmarks.