Minkyu Kim

Ph.D. student KAIST

minkyu-kim@kaist.ac.kr

Summary

Hello! I'm a Ph.D. student in Artificial Intelligence at KAIST, advised by Sungsoo Ahn in the Lab. I received my B.S. in Mathematics from POSTECH and am currently a research intern at Mila, hosted by Alex Hernández-García. My research focuses on flow-based generative models and diffusion samplers for AI for science, with applications to molecular conformer generation, catalyst design, and materials discovery.

Publications

Most recent publications on Google Scholar

CatFlow: Co-generation of Slab-Adsorbate Systems via Flow Matching

Minkyu Kim, Nayoung Kim, Honghui Kim, Sungsoo Ahn

ICML 2026

AtomMOF: All-Atom Flow Matching for MOF-Adsorbate Structure Prediction

Nayoung Kim, Honghui Kim, Sihyun Yu, Minkyu Kim, Seongsu Kim, Sungsoo Ahn

arXiv preprint, 2026

On Scalable and Efficient Training of Diffusion Samplers

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

NeurIPS 2025

Energy-Based Generator Matching: A Neural Sampler for General State Space

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

NeurIPS 2025

CatFlow: Co-generation of Slab-Adsorbate Systems via Flow Matching

Minkyu Kim, Nayoung Kim, Honghui Kim, Sungsoo Ahn

ICML 2026

AtomMOF: All-Atom Flow Matching for MOF-Adsorbate Structure Prediction

Nayoung Kim, Honghui Kim, Sihyun Yu, Minkyu Kim, Seongsu Kim, Sungsoo Ahn

arXiv preprint, 2026

On Scalable and Efficient Training of Diffusion Samplers

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

NeurIPS 2025

Energy-Based Generator Matching: A Neural Sampler for General State Space

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

NeurIPS 2025

Internships

Education

Full Resume in PDF.

Volunteering

Website Design

Thanks Martin Saveski for this awesome webiste template!