About Me

I am Phillip (Yuseung) Lee, a first year PhD student at KAIST Graduate School of AI, advised by Prof. Minhyuk Sung. I was also fortunate to have closely collaborated with Prof. Leonidas Guibas. I received both my M.S. and my B.S. degree at KAIST.

My research interests revolve around enhancing the spatial control and understanding of large foundation models. Specifically, I have worked on enhancing the spatial control of diffusion models for image generation, and advancing the spatial reasoning capabilities of vision-language models (VLMs).

For details, refer to my Curriculum Vitae (CV).

News

• [Nov. 2024] I successfully defended my Masters thesis on "Spatial Grounding with Pretrained Image Diffusion Models". Slides are available here.
• [Oct. 2024] I gave an oral presentation on ReGround at U&ME Workshop in ECCV 2024. Slides are available here.
• [Sep. 2024] GrounDiT is accepted to NeurIPS 2024!
• [Jul. 2024] ReGround is accepted to ECCV 2024!
• [May. 2024] SyncDiffusion is featured in KAIST Annual R&D Report as a Research Highlight of 2023!
• [Dec. 2023] I gave a spotlight presentation on SyncDiffusion at ML4CD Workshop in NeurIPS 2023 and also presented at Workshop on Diffusion Models. Slides are available here.
• [Sep. 2023] SyncDiffusion is accepted to NeurIPS 2023!
• [Aug. 2023] Started Master's Progam at KAIST Graduate School of AI. (Advisor: Prof. Minhyuk Sung)
• [Jun. 2022] Joined KAIST Visual AI Group as a research intern.

Publications

Teaching

• Teaching Assistant, Fall 2023, Machine Learning for 3D Data (CS479), KAIST
• Teaching Assistant, Fall 2024, Diffusion Models and Their Applications (CS492-D), KAIST
• Teaching Assistant, Spring 2025, Machine Learning for 3D Data (CS479), KAIST

Academic Services

• Reviewer: NeurIPS 2024, ICLR 2025, ICML 2025, TPAMI 2025

Powered by Jekyll and Minimal Light theme.