Jeongjae Lee

I am an M.S. student at KAIST AI’s BISPL lab, advised by Jong Chul Ye. Currently, I am working with Danyal Rehman at Aureka Biotechnologies. I received my B.S. in Electrical and Computer Engineering from Seoul National University (Summa Cum Laude).

Research Interests

My research focuses on generative modeling and reward alignment. I have worked on developing principled, scalable alignment methods for flow-based models. Recently, I have been focusing on applications to biology.

news

Oct 2026	New preprints: DFR and GeoFix.
Oct 2026	Recognized as a Top Reviewer at NeurIPS 2026.
Oct 2026	Joined Aureka Biotechnologies as a research intern.
Sep 2026	RSM and FAV accepted to NeurIPS 2026.
Jul 2026	RSM received the Best Paper Award at the ICML 2026 SPIGM Workshop (2 of 270 submissions).

selected publications

Distribution-based Regularization for Reward Fine-tuning Diffusion and Flow Models

Romeo Passaro^*, Jeongjae Lee^*, Jong Chul Ye, and 4 more authors

arXiv preprint, 2026

arXiv Code
Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models

Jeongjae Lee^*, Jinho Chang^*, Jeongsol Kim^†, and 1 more author

In Advances in Neural Information Processing Systems (NeurIPS), 2026

Also at the ICML 2026 Workshop on Structured Probabilistic Inference and Generative Modeling.

Best Paper arXiv Code Website

Best Paper Award at the ICML 2026 SPIGM Workshop (one of 2 recipients among 270 submissions).
PCPO: Proportionate Credit Policy Optimization for Aligning Image Generation Models

Jeongjae Lee, and Jong Chul Ye

In International Conference on Learning Representations (ICLR), 2026

HTML Code