Published multiple papers at NeurIPS 2025, including MetaMind, Debate or Vote: Which Yields Better Results, Visual Instruction Bottleneck Tuning (Vittle), Latent-space Synthesis for Preference Data, GLSim: A Simple but Effective Method for Reducing Object Hallucination in Multi-Modal Language Models, and more.
Research Experience
Currently an Associate Professor in the Department of Computer Sciences at the University of Wisconsin-Madison, and a member of machine learning@uw-madison and a faculty affiliate with the Data Science Institute.
Education
Ph.D. from Cornell University in 2017, advised by Turing laureate John E. Hopcroft; Postdoc researcher in the Computer Science department at Stanford University, working with Christopher Ré.
Background
Associate Professor in the Department of Computer Sciences at the University of Wisconsin-Madison. Research interests include the foundations of safe and reliable AI systems, addressing challenges that arise in both model development and deployment.