Bio

I am Juil Koo, a second-year PhD student in the KAIST Visual AI Group, led by Prof. Minhyuk Sung. In summer 2024, I interned at Adobe Research, closely collaborating with Duygu Ceylan, Paul Guerrero and Chun-Hao Huang.

My research interests primarily revolve around stochastic differential equations and 3D geometry. Recently, I've been focusing on understanding the underlying fundamentals of diffusion models and leveraging their rich priors to unlock their potential in diverse applications. Prior to this, I mainly worked on the intersection between 3D geometry and language. I aim to address practical problems through theoretical insights.

My Erdős number is 3 (Juil Koo → Leonidas Guibas → Frances Yao → Paul Erdős).

"A painting of a boy using a laptop in front of a pond with water lilies, by Claude Monet", generated by DALL·E 2 and DALL·E 3.

3D Gallery

News

Publications

SyncTweedies: A General Generative Framework Based on Synchronized Diffusions
Jaihoon Kim*, Juil Koo*, Kyeongmin Yeo*, Minhyuk Sung (* co-first author.) NeurIPS 2024 [Project] [Paper] [Code]
Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses
Seungwoo Yoo, Juil Koo, Kyeongmin Yeo, Minhyuk Sung NeurIPS 2024 [Paper]
Posterior Distillation Sampling
Juil Koo, Chanho Park, Minhyuk Sung CVPR 2024 [Project] [Paper] [Code] [Video]
SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation
Juil Koo*, Seungwoo Yoo*, Minh Hieu Nguyen*, Minhyuk Sung (* co-first author.) ICCV 2023 [Project] [Paper] [Code]
PartGlot: Learning Shape Part Segmentation from Language Reference Games
Juil Koo, Ian Huang, Panos Achlioptas, Leonidas Guibas, Minhyuk Sung CVPR 2022 (Oral) [Project] [Paper] [Code] [Video]

Academic Service