Portrait de Sujin yun

Sujin yun

sujin.yun@mila.quebec
Doctorat - UdeM
Superviseur⋅e principal⋅e
Aaron Courville
Sujets de recherche
Apprentissage par renforcement
Modèles génératifs
Site web
Google Scholar

Publications

Diffusion Alignment as Variataional Expectation-Maximization
Jaewoo Lee
Minsu Kim
Sanghyeok Choi
Inhyuck Song
Sujin yun
Hyeongyu Kang
Woocheol Shin
Taeyoung YUN
Kiyoung Om
Jinkyoo Park
Diffusion alignment aims to optimize diffusion models for the downstream objective. While existing methods based on reinforcement learning o… (voir plus)r direct backpropagation achieve considerable success in maximizing rewards, they often suffer from reward over-optimization and mode collapse. We introduce Diffusion Alignment as Variational Expectation-Maximization (DAV), a framework that formulates diffusion alignment as an iterative process alternating between two complementary phases: the E-step and the M-step. In the E-step, we employ test-time search to generate diverse and reward-aligned samples. In the M-step, we refine the diffusion model using samples discovered by the E-step. We demonstrate that DAV can optimize reward while preserving diversity for both continuous and discrete tasks: text-to-image synthesis and DNA sequence design.
2025-12-31
International Conference on Learning Representations (Accept (Poster))
openreview.net
openreview.net