About Me

I'm an associate professor in the University Libraries and School of Information Studies at Purdue, with a joint appointment in the School of Applied and Creative Computing. I'm also affiliated with the Institute for Physical Artificial Intelligence (IPAI) and the Applied AI Research Center. My research centers on foundation model adaptation, representation learning, and trustworthy AI for real-world, information-rich tasks. Before joining Purdue, I was an Assistant Professor in the Department of Computer Engineering at the Rochester Institute of Technology. Over the years I've had the privilege of mentoring a group of sharp students. Sometimes they even listen to me. Outside of work, I love traveling the world and playing tennis (3.0–3.5), and I share my home with two cats, Tiger (小虎) and Meimei (妹妹), who keep the place lively.

Research Interests

My work is in Applied AI, mostly about the post-training and adaptation of foundation models. I've worked on vision, robotics, medicine, reasoning, and science problems. I'm especially interested in getting AI to work with hard-to-reach knowledge, the kind that's one-of-a-kind, restricted, and rarely written down more than once. The goal is to make these models genuinely useful and reliable in places where mistakes are costly. Two questions drive most of my work.

How can we adapt large models efficiently? I work on post-training methods, like parameter-efficient fine-tuning, prompt and representation tuning, and model fusion, that let a pretrained model pick up new tasks with very little data and compute, and few trainable parameters.

How can we make them reliable in the real world? I build robust, multimodal systems using fast-and-slow reasoning, calibration, and safety methods, so they stay dependable under distribution shift and adversarial conditions, and hold up when they're used for decisions that matter.

Prospective Students

I take 1–2 incoming PhD students every year (through the Computer Science or Computer and Information Technology programs). Before making a funded offer, I usually start with a 4–6 month internship working alongside one of my senior PhD students, a low-pressure way for both of us to see whether it’s a good fit. Once you join, I treat you as an apprentice. We’ll work side by side, talking through problems and publishing together, and when you’re ready I’ll help send you off to a strong next step. At the same time, I count on you to be independent enough to take on problems and move them forward on your own. As an advisor, I’m demanding most of the time and short-tempered periodically, but I’m working on it.

Alumni

Services

  • Area Chair, The Association for Computational Linguistics (ACL), since 2026
  • Area Chair, The Conference on Computer Vision and Pattern Recognition (CVPR), since 2023
  • Senior PC, The International Joint Conference on Artificial Intelligence (IJCAI), since 2023
  • Senior PC, The Association for the Advancement of Artificial Intelligence (AAAI), since 2023
  • Associate Editor, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), since 2023
  • Associate Editor, Neurocomputing, since 2024
  • Associate Editor, ACM Journal on Autonomous Transportation (JATS), since 2023

Publications

For my full list of publications, please refer to my Google Scholar