Dohyun Kim

I’m an integrated M.S./Ph.D. student in the Department of Computer Science and Engineering at Korea University, advised by Prof. Paul Hongsuck Seo in the Multimodal Interactive Intelligence Laboratory (MIIL).

My research interests center on multimodal and generative models, with a particular focus on diffusion models. I have worked on topics such as data-efficient compression of diffusion models and preference-based optimization for text-to-image generation. I am broadly open to diverse directions in generative AI, multimodal learning, and beyond.

I’m currently a Research Intern at Trillion Labs. Previously, I visited the University of Michigan, working with Prof. Honglak Lee.

Email/Google Scholar/GitHub/LinkedIn