Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective
Justin Lee*, Zheda Mai*, Jinsu Yoo, Chongyu Fan, Cheng Zhang, Wei-Lun Chao
Ph.D. Student ยท University of Michigan
Justin Lee
I am an EECS Ph.D. student at the University of Michigan, advised by Dr. Qing Qu as part of the DeepThink Lab. Previously, I earned my B.S. in Computer Science and Engineering from The Ohio State University, where I was advised by Dr. Wei-Lun (Harry) Chao and mentored by Zheda Mai.
My current research interests broadly focus on deep learning theory and world models.
Contact: jhylee [at] umich [dot] edu
Publications
TaxaAdapter: Coupling Vision Taxonomy Models with Diffusion for Fine-Grained Species Generation
Mridul Khurana, Amin Karimi Monsefi, Justin Lee, Medha Sawhney, David Carlyn, Julia Chae, Jianyang Gu, Rajiv Ramnath, Sara Beery, Wei-Lun Chao, Anuj Karpatne, Cheng Zhang
MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs
Jihyung Kil, Zheda Mai, Justin Lee, Arpita Chowdhury, Zihe Wang, Kerrie Cheng, Lemeng Wang, Ye Liu, Wei-Lun Chao
Artificial Intelligence Advances Digital Pathomics for Confocal Endomicroscopy Diagnosis of Pancreatic Cysts
Ahmed Abdelbaki, Ziwei Li, Tai-Yu Pan, Justin Lee, Arpita Chowdhury, Stacey Culp, Bipul Gnyawali, Tassiana G. Maloof, Aayush B. Vishwanath, Sohil Narasimha Reddy, Dylan Mink, Wei Chen, Phil A. Hart, Timothy M. Pawlik, Wei-Lun Chao, Somashekar G. Krishna
Awards
Received OSU CSE UG Student Research Award .
Selected as an Honorable Mention for the 2026 CRA Outstanding Undergraduate Researcher Award .