About Me

I’m Dohyun Kim, 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.

Education

• Integrated M.S./Ph.D. in Computer Science and Engineering
  Korea University, Seoul, Korea
  Sep. 2024 – Present

• B.S. in Biomedical Engineering
  Korea University, Seoul, Korea
  Mar. 2019 – Aug. 2024

Work Experience

• Visiting Researcher, University of Michigan, Ann Arbor, MI
  Advisor: Prof. Honglak Lee
  Jun. 2025 – Dec. 2025 (Expected)

Publications

• Compositional SVG Generation via VLM-Driven Hierarchical Semantic Parsing
  *Sehwan Park, *Taehoon Kim, Geonhee Han, Dohyun Kim, Seung Wook Kim, Paul Hongsuck Seo (* equal contribution)
  In EMNLP 2026

• Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision
  Dohyun Kim, Seungwoo Lyu, Seung Wook Kim, Paul Hongsuck Seo
  In ECCV 2026 [Project Page]

• Random Conditioning for Diffusion Model Compression with Distillation
  *Dohyun Kim, *Sehwan Park, Geonhee Han, Seung Wook Kim, Paul Hongsuck Seo (* equal contribution)
  In CVPR 2025 [Project Page]