Profile Picture

Seonghwan Kim

Postdoctoral Fellow at AI-CRED, KAIST

dmdtka00@kaist.ac.kr, dmdtka0084@gmail.com

Scholar | Linkedin | Github

About Me

Hi! I am a postdoctoral researcher at the AI-CRED Institute, KAIST, working with Prof. Woo Youn Kim and Prof. Sungsoo Ahn. I received my Ph.D. in Chemistry from KAIST, where I worked in the Intelligent Chemistry Lab under the supervision of Prof. Woo Youn Kim. My research lies at the intersection of computational chemistry, machine learning. Recently, my interests have expanded toward biology-driven modeling — exploring how molecular interactions give rise to cellular behavior. I aim to bridge molecular- and cellular-level processes through multi-modal and interpretable generative models.

Publications

Riemannian Denoising Score Matching for Molecular Structure Optimization with Accurate Energy

Jeheon Woo*, Seonghwan Kim*, Woo Youn Kim†

Accepted in Principle, Nat. Comp. Sci., 2025

Paper

TOC figure

MoAgent: A Hypothesis-Driven Multi-Agent Framework for Drug Mechanism of Action Discovery

Jun Hyeong Kim*, Seokhyun Moon*, Seonghwan Kim, Junhyeok Jeon, Taein Kim, Jisu Seo, Songmi Kim, Woo Youn Kim†

NeurIPS AI4D3 workshop 2025

Paper

TOC figure

FragFM: Efficient Fragment-Based Molecular Generation via Discrete Flow Matching

Joongwon Lee*, Seonghwan Kim*, Woo Youn Kim†

ICLR GEM workshop 2025

Paper

TOC figure

Discrete Diffusion Schr\"odinger Bridge Matching for Graph Transformation

Jun Hyeong Kim*, Seonghwan Kim*, Seokhyun Moon*, Hyeongwoo Kim*, Jeheon Woo*, Woo Youn Kim†

ICLR 2025

Paper

TOC figure

Collective Variable Free Transition Path Sampling with Generative Flow Network

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

ICLR 2025

Paper

Diffusion-based generative AI for exploring transition states from 2D molecular graphs

Seonghwan Kim*, Jeheon Woo*, Woo Youn Kim†

Nature Communications, 2024

Paper | Code

TOC figure

GeoTMI: Predicting Quantum Chemical Property with Easy-to-Obtain Geometry via Positional Denoising

Hyeonsu Kim*, Jeheon Woo*, Seonghwan Kim*, Seokhyun Moon*, Junhyung Kim*, and Woo Youn Kim†

NeurIPS 2023

Paper | Code

TOC figure

Gaussian-Approximated Poisson Preconditioner for Iterative Diagonalization in Real-Space Density Functional Theory

Jeheon Woo*, Seonghwan Kim*, Woo Youn Kim†

The Journal of Physical Chemistry A, 2023

Paper | Code

Dynamic Precision Approach for Accelerating Large-Scale Eigenvalue Solvers in Electronic Structure Calculations on Graphics Processing Units

Jeheon Woo*, Seonghwan Kim*, Woo Youn Kim†

Journal of Chemical Theory and Computation, 2023

Paper | Code

TOC figure

Awards

Recipient, 9th EDISON Computational Chemistry software application competition

Recipient, 2023 Samsung AI Challenge, 2nd Award

Recipient, Award for Industry-Academia Cooperation at the Final Exchange Meeting of Samsung Electronics DS Division (Grand Prize)