About
I am an Associate Professor in the Department of Computer Sciences at the University of Wisconsin-Madison. I am a member of machine learning@uw-madison and a faculty affiliate with the Data Science Institute. Previously, I was a postdoc researcher in the Computer Science department at Stanford University, working with Christopher Ré.
I completed my PhD from Cornell University in 2017, where I was advised by Turing laureate John E. Hopcroft and worked closely with Kilian Q. Weinberger.
My research focuses on the foundations of safe and reliable AI systems, addressing challenges that arise in both model development and deployment in the wild. This involves handling out-of-distribution data and quantifying uncertainty of machine learning models. Currently, we are building towards LLM systems that are reliable by design, with behaviors that can be rigorously understood and reasoned about. This enables principled control throughout the model lifecycle, from training to deployment. Our research investigates core questions around:
- Reliable agentic LLM systems: Coordinated decision-making across interacting language models, emergent strategies and collective reasoning, and uncertainty quantification for agentic LLMs.
- Reliable inference-time compute: Understanding and detecting hallucinations, deception, and unfaithful reasoning. Advancing steering mechanisms and socially aligned reasoning.
- Reliable post-training methodologies: Developing new reinforcement learning and reward modeling techniques to enhance alignment and reasoning capabilities.
My research has been recognized by the Alfred P. Sloan Fellowship (2025), MIT Innovators Under 35 Award (2023), NSF CAREER Award (2023), AFOSR Young Investigator (YIP) Award (2022), Forbes 30 Under 30 in Science (2020), and multiple faculty research awards from Google, Meta, and Amazon. I was named the "Innovator of the Year" by MIT Technology Review in 2023. Our research has also won the Outstanding Paper Award at NeurIPS 2022 and ICLR 2022.
[Openings]: In an effort to maintain a healthy group size, I have very limited PhD openings for the Fall 2026 admission cycle and will only consider applicants with an exceptional research fit. For questions regarding the application process, please see the FAQ. I strongly recommend reading my [Advising Statement] before applying or contacting me.
Recent news
1/2026: 8 papers accepted by ICLR 2026.
11/2025: We will organize Simons Institute Workshop on Agentic AI in the Wild: From Hallucinations to Reliable Autonomy.
9/2025: 11 papers accepted by NeurIPS 2025.
7/2025: Promoted to associate professor with early tenure.
2/18/2025: Honored to receive Alfred P. Sloan Fellowship.
7/1/2025: Received Google ML and Systems Faculty Award.
6/15/2025: Shawn received the NSF Graduate Research Fellowship.
5/16/2025: Xuefeng defended his Ph.D. thesis - congratulations Dr. Du!
5/1/2025: 5 papers accepted by ICML 2025.
3/3/2025: Appointed as the Program Chair for ICML 2026 in Seoul, South Korea.
[Services]:
[Teaching]:
Misc
I travel and occasionally take photos. Here is my pictorial Travel Memo. This is the treasure I shoot with.
Sponsors
We are thankful for the generous funding award and gift from the following sponsors:
