Optimal Transport for Generative Modeling: From Training to Fine-Tuning > 세미나

본문 바로가기
사이트 내 전체검색


세미나

모드선택 :              
세미나 신청은 모드에서 세미나실 사용여부를 먼저 확인하세요

Optimal Transport for Generative Modeling: From Training to Fine-Tunin…

김선우 0 588
구분 ACM
일정 2026-06-15 16:00 ~ 18:00
강연자 최재웅 (성균관대학교)
기타
담당교수 이다빈
Optimal transport (OT) theory provides a principled framework for modeling transformations between probability distributions. From this perspective, generative models can be viewed as mechanisms for transporting a simple prior distribution to a target data distribution. 
In this talk, we present a unified perspective on generative modeling through OT. We discuss how OT-based frameworks provide principled tools for both training and fine-tuning generative models.
First, we introduce Unbalanced Optimal Transport (UOT)-based methods for robust training, long-tailed generation, and unlearning. Second, we discuss Wasserstein Gradient Flow (WGF)-based methods, where generative modeling and reward-guided fine-tuning are formulated as steepest-descent dynamics of functionals in Wasserstein space. Finally, we present Schrödinger Bridge and stochastic optimal control perspectives for efficient path-space generative modeling and reward alignment.

세미나명

   

상단으로

Research Institute of Mathematics
서울특별시 관악구 대학동 서울대학교 자연과학대학 129동 305호
Tel. 02-880-6562 / Fax. 02-877-6541 su305@snu.ac.kr

COPYRIGHT ⓒ 자연과학대학 수학연구소 ALL RIGHT RESERVED.