[CAU-AI핵심 기술세미나] Generative Modeling via Neural Optimal Transport, 최재웅 조교수 (성균관대학교) - 2025년 11월 18일 13:00

2025년 11월 18일 13:00에 진행되는 중앙대학교 AI대학원 CAU-AI핵심 기술세미나 진행 안내드립니다.

관심있는 분들의 많은 참여 부탁드립니다.

Presenter:  최재웅 조교수 (성균관대학교)

Prof. Jaewoong Choi is an Assistant Professor in the Department of Statistics at Sungkyunkwan University (SKKU). His research focuses on developing statistical and mathematical frameworks to analyze, understand, and improve artificial intelligence systems. In particular, his work centers on optimal transport theory and its applications in machine learning, including generative modeling approaches such as optimal transport maps, diffusion models, flow matching, and Schrödinger bridges. He is also interested in exploring the geometrical properties of AI models, with an emphasis on understanding the structure of latent spaces.

Date & Time: 2025년 11월 18일 13:00

Place: Offline 310-513

Title: Generative Modeling via Neural Optimal Transport

Optimal Transport (OT) provides a principled framework for transforming one probability distribution into another via a cost-minimizing map.

Leveraging this framework to transport a simple prior distribution to a complex data distribution has emerged as a powerful approach for generative modeling, including OT maps, flow matching, and diffusion models. 

In this talk, I will introduce two recent approaches to generative modeling built on OT and Wasserstein gradient flow, highlighting their theoretical insights and practical implications.

*This seminar was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (2021-0-01341, Artificial Intelligence Graduate School Program(Chung-Ang University))