Jiantao Jiao


I am an Assistant Professor in the Department of Electrical Engineering and Computer Sciences and Department of Statistics at University of California, Berkeley. I received the Ph.D. degree from Stanford University in 2018. I co-direct the Center for the Theoretical Foundations of Learning, Inference, Information, Intelligence, Mathematics, and Microeconomics at Berkeley (CLIMB). I am also a member of the Berkeley Artificial Intelligence Research (BAIR) Lab, the Berkeley Laboratory of Information and System Sciences (BLISS), and the Berkeley Center for Responsible, Decentralized Intelligence (RDI). My recent research has been focusing on generative AI and foundation models, covering the entire pipeline of data curation, pre-training, supervised fine-tuning, instruction fine-tuning, reinforcement learning with human feedback (RLHF), inference, and building security guardrails to defend against jailbreaking and prompt injection.

I am also broadly interested in statistical machine learning, optimization, privacy and security of machine learning systems, reinforcement learning, the economic perspective of machine learning, and the applications of machine learning in natural language processing, code generation, computer vision, autonomous driving, and robotics.

Recently, I co-founded Nexusflow, where we harness our cutting edge research to democratize GenAI agents for enterprises.

Recent publications


University of California, Berkeley

Department of Electrical Engineering and Computer Sciences

257M Cory Hall

Berkeley, CA 94720-1770

Email: jiantao [at] cs [dot] berkeley [dot] edu

Due to the large volume of emails that I receive, I generally do not respond to unsolicited inquiries about student or postdoc openings, or research advice. Nevertheless, if you have a strong quantitative background and think your interests are compatible with mine, please feel free to contact me.