Justin Lee

grad_headshot.jpg
The Ohio State University

Seeking PhD opportunities for Fall 2026.

4th-year undergraduate majoring in Computer Science at The Ohio State University, advised by Dr. Wei-Lun (Harry) Chao.

My research interests broadly center on understanding the limitations of generative AI. My previous work has examined why applying machine unlearning to diffusion models in a continual setting leads to a state in which the model can no longer produce semantically meaningful outputs. I have also explored multimodal large language models and their weaknesses in comparative reasoning.

For publications please visit my Google Scholar
Also please check out our new project Continual Unlearning for Image Generation

News

Dec 17, 2025 Selected as an Honorable Mention for the 2026 CRA Outstanding Undergraduate Researcher Award.

Publications

  1. Under Review
    Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective
    J Lee, Z Mai, J Yoo, C Fan, C Zhang, and 1 more author
    Under Review, 2025
    PDF
  2. ICML Workshop
    An Empirical Exploration of Continual Unlearning for Image Generation
    J Lee, Z Mai, C Fan, and WL Chao
    In ICML 2025 Workshop on Machine Unlearning for Generative AI, 2025
    HTML PDF
  3. Under Review
    TaxaAdapter: Coupling Vision Taxonomy Models with Diffusion for Fine-Grained Species Generation
    M Khurana, A Monsefi, J Lee, D Carlyn, J Chae, and 6 more authors
    Under Review, 2025
  4. NeurIPS
    MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs
    J Kii*, Z Mai*, J Lee, A Chowdhury, Z Wang, and 4 more authors
    In The Thirty-eight Conference on Neural Information Processing Systems, 2024
    HTML PDF
  5. TIGE
    Artificial Intelligence Advances Digital Pathomics for Confocal Endomicroscopy Diagnosis of Pancreatic Cysts
    A Abdelbaki, Z Li, TY Pan, J Lee, A Chowdhury, and 3 more authors
    Techniques and Innovations in Gastrointestinal Endoscopy, 2025
    PDF