Karl Pertsch

Karl Pertsch is a member of technical staff at Physical Intelligence, where he works on training robot foundation models. He completed his PhD in computer science at the University of Southern California under Joseph Lim and was a postdoctoral scholar at UC Berkeley and Stanford University co-advised by Sergey Levine and Chelsea Finn. He is best known for his research on robot learning, including the FAST efficient action tokenization method for vision-language-action models.