Kiyoung Seong

Ph.D. student, KAIST

kyseong98@kaist.ac.kr

Bio

I am a Ph.D. candidate at KAIST AI, advised by Sungsoo Ahn, and a research intern at the Materials Intelligence Lab at LG AI Research, supervised by Changyoung Park.

My research goal is to develop AI tools for materials and drug discovery. Specifically, I focus on developing AI evaluation and generation tools potentially used for agentic AI systems.

My recent work includes accelerating molecular dynamics simulations using generative flow networks (ICLR'25), learning machine learning collective variables from time-lagged generation (ICML'25), and sampling ensembles from diffusion samplers (NeurIPS'25).

Publications

Most recent publications on Google Scholar.

Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers

Kiyoung Seong, Seonghyun Park, Seonghwan Kim, Woo Youn Kim, Sungsoo Ahn

ICLR'25: International Conference on Learning Representations, 2025.

Paper Code Project Page

On scalable and efficient training of diffusion samplers

Minkyu Kim*, Kiyoung Seong*, Dongyeop Woo, Sungsoo Ahn, Minsu Kim

NeurIPS'25: Advances in Neural Information Processing Systems, 2025.

* Equal contribution

Paper

Learning Collective Variables from Time-lagged Generation

Seonghyun Park, Kiyoung Seong, Soojung Yang, Rafael Gomez-Bombarelli, Sungsoo Ahn

ICML'25: International Conference on Machine Learning (GenBio workshop), 2025.

Paper

Energy-based generator matching: A neural sampler for general state space

Dongyeop Woo, Minsu Kim, Minkyu Kim, Kiyoung Seong, Sungsoo Ahn

NeurIPS'25: Advances in Neural Information Processing Systems, 2025.

Paper

Vitæ

Kiyoung Seong
kyseong98@kaist.ac.kr