Shun Zhang

Shun Zhang is a Senior Generative AI Engineer at NVIDIA, where they work on post-training multimodal and vision-language-action models. They earned a PhD in Computer Science from the University of Michigan in 2020, following an integrated BS/MS program in Computer Science from The University of Texas at Austin. Previously, Shun held research positions at IBM, focusing on the integration of reinforcement learning with foundation models, and served as a founding member of the technical staff at Asari AI, where they built an AI agent for skill discovery. Their earlier experience includes internships at Amazon and Semantic Designs, as well as serving as an undergraduate teaching assistant at The University of Texas at Austin. Shun has research interests in reinforcement learning, active learning, AI safety, and meta-reinforcement learning.