Talk Title: Robotic Foundation Models

Talk Abstract: In this talk, I'll discuss recent advances in general-purpose vision-language-action models that can control robotic systems to follow complex instructions. From basic "first generation" VLAs that can follow rudimentary language instructions, robotic foundation models have evolved to perform highly complex multi-stage tasks, incorporate diverse data modalities, and perform sophisticated test-time reasoning. I'll discuss recent advances, and frontiers for current research.

Bio: Sergey Levine received a BS and MS in Computer Science from Stanford University in 2009, and a Ph.D. in Computer Science from Stanford University in 2014. He joined the faculty of the Department of Electrical Engineering and Computer Sciences at UC Berkeley in fall 2016. His work focuses on machine learning for decision making and control, with an emphasis on deep learning and reinforcement learning algorithms. Applications of his work include autonomous robots and vehicles, as well as computer vision and graphics. His research includes developing algorithms for end-to-end training of deep neural network policies that combine perception and control, scalable algorithms for inverse reinforcement learning, deep reinforcement learning algorithms, and more.