I’m a first-year ECE Ph.D. student at Carnegie Mellon University advised by Giulia Fanti. I obtained my Bachelor’s degree in Computer Science at Soongsil University. During my undergraduate years, I worked with Professors Jaegul Choo and Jong Chul Ye. Previously, I was a research intern at SI Analytics, Kakao Enterprise, and NAVER AI Lab.
Research interest. I work on deep generative modeling and its various applications. In particular, I focus on developing generative models that are scalable and easy to sample from.
Contact: sangyunl@andrew.cmu.edu
News
- [Jan. 2024] I will start my internship at NVIDIA this summer (Host: Arash Vahdat)
- [Jun. 2023] One paper is accepted to ICML 2023 SPIGM Workshop.
- [Apr. 2023] One paper is accepted to ICML.
- [Apr. 2023] I will be joining CMU ECE as a Ph.D. student in Fall 2023.
Research
- Sangyun Lee, Gayoung Lee, Hyunsu Kim, Junho Kim, and Youngjung Uh, “Diffusion Models with Grouped Latents for Interpretable Latent Space”, ICML 2023 Workshop on Structured Probabilistic Inference & Generative Modeling [Abstract]
- Sangyun Lee, Beomsu Kim, and Jong Chul Ye, “Minimizing Trajectory Curvature of ODE-based Generative Models”, ICML 2023 [Abstract] [Code]
- Sangyun Lee, Hyungjin Chung, Jaehyeon Kim, and Jong Chul Ye, “Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis”, NeurIPS 2022 Workshop on Score-Based Methods [Abstract] [code]
- Sangyun Lee*, Gyojung Gu*, Sunghyun Park, Seunghwan Choi, and Jaegul Choo, “High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions”, ECCV 2022 [Abstract] [Code]
- Sangyun Lee, Sewoong Ahn, and Kwangjin Yoon, “Learning Multiple Probabilistic Degradation Generators for Unsupervised Real World Image Super Resolution”, ECCV 2022 Workshop on Learning from Limited and Imperfect Data [Abstract]
(* denotes equal contributions.)
Invited Talk
Modulabs (2022.11.24 ~ 2022.12.08)
- A Unified Framework for Diffusion Models [Slide] [Video (Korean)]
- Diffusion Models for Conditional Generation [Slide] [Video (Korean)]
- Diffusion Models Everywhere [Slide] [Video (Korean)]
Patent
Sangyun Lee and Kwangjin Yoon, super resolution imaging method using collaborative learning. Korean Patent 1024062870000, filed Dec 31, 2021, and issued June 2, 2022.