Yong Jae Lee

Yong Jae Lee is a Professor in the Department of Computer Sciences at the University of Wisconsin-Madison, where he holds the prestigious Susan Beth Horwitz Professorship. He leads the Wisconsin AI and Vision Lab (WAIV) and has been at UW-Madison since Fall 2021. Prior to this, he served as an Assistant and then Associate Professor at UC Davis for six years, and spent time as a Postdoctoral Fellow at UC Berkeley and Carnegie Mellon University.

Lee's research focuses on computer vision and machine learning, with particular emphasis on creating robust AI systems that can understand our multimodal world with minimal human supervision. His work spans deep learning for computer vision, image synthesis, video understanding, and multimodal learning. His recent publications demonstrate a strong focus on large multimodal models, vision-language systems, and addressing challenges in model robustness and efficiency.

His lab has developed influential systems like YOLACT for real-time instance segmentation, which won the Most Innovative Award at the COCO Object Detection Challenge at ICCV 2019. Current research directions include personalized vision-language systems, efficient multimodal models, and addressing cultural biases in generative AI.

• H.I. Romnes Faculty Fellowship (2025)
• Susan Beth Horwitz Professorship (2025)
• NSF CAREER Award
• Army Research Office Young Investigator Award
• UC Davis College of Engineering Outstanding Junior Faculty Award
• Best Paper Award at BMVC 2020
• Most Innovative Award at COCO Object Detection Challenge, ICCV 2019

Professor Lee has advised numerous PhD students who have gone on to successful careers at leading tech companies and research institutions. His research has been supported by major funding agencies including the National Science Foundation (multiple grants), Army Research Office, NASA, and industry partners like Intel, Adobe, Nvidia, Amazon, and Google. He leads the Wisconsin AI and Vision Lab (WAIV), which currently includes multiple PhD students and undergraduate researchers working on cutting-edge vision and language understanding problems.