Portrait of Nayoung Kim

Nayoung Kim

Ph.D. Student · Graduate School of AI, KAIST

I am a final-year Ph.D. student at KAIST’s Graduate School of AI, advised by Sungsoo Ahn. I develop generative models for structure prediction and design of materials and biomolecules, with the goal of accelerating materials and drug discovery. My research focuses on flow-based models for crystal structure prediction for metal-organic frameworks and molecular crystals. More broadly, I am interested in how generative models can capture molecular geometry and interactions to enable the discovery of new materials and therapeutics.

✉ Email CV Google Scholar GitHub LinkedIn

News

Sep 25, 2026 📄 One paper accepted to NeurIPS 2026.
May 14, 2026 🏅 Recognized as a Gold Reviewer for ICML 2026.
May 11, 2026 📄 Two papers accepted to ICML 2026.
Sep 18, 2025 📄 Two papers accepted to NeurIPS 2025, including one spotlight presentation.
Jan 23, 2025 📄 One paper accepted to ICLR 2025.
Jan 13, 2025 📄 One paper accepted to TMLR 2025.
Oct 11, 2024 📄 One paper accepted to NeurIPS 2024 Workshop.

Publications

2026

Figure 3: Packora model architecture
Preprint
Packora: Systematic Design for Generative Molecular Crystal Structure Prediction
Nayoung Kim, Kiyoung Seong, Sungsoo Ahn
arXiv preprint, 2026
arXiv Project Page Code
@article{kim2026packora, title={Packora: Systematic Design for Generative Molecular Crystal Structure Prediction}, author={Kim, Nayoung and Seong, Kiyoung and Ahn, Sungsoo}, journal={arXiv preprint arXiv:2608.26962}, year={2026} }
AI Co-Scientist paper thumbnail
Preprint
Discovering Crystal Structure Prediction Algorithms with an AI Co-Scientist
Kiyoung Seong, Nayoung Kim, Sungsoo Ahn
arXiv preprint, 2026
arXiv HACO Code MaskGXT Code
AtomMOF paper thumbnail
Poster
AtomMOF: All-Atom Flow Matching for MOF-Adsorbate Structure Prediction
Nayoung Kim, Honghui Kim, Sihyun Yu, Minkyu Kim, Seongsu Kim, Sungsoo Ahn
Neural Information Processing Systems (NeurIPS), 2026
arXiv Code
CatFlow paper thumbnail
Poster
CatFlow: Co-generation of Slab-Adsorbate Systems via Flow Matching
Minkyu Kim, Nayoung Kim, Honghui Kim, Sungsoo Ahn
International Conference on Machine Learning (ICML), 2026
arXiv Code
Machine Learning Hamiltonians paper thumbnail
Poster
Machine Learning Hamiltonians are Accurate Energy-Force Predictors
Seongsu Kim, Chanhui Lee, Yoonho Kim, Seongjun Yun, Honghui Kim, Nayoung Kim, Changyoung Park, Sehui Han, Sungbin Lim, Sungsoo Ahn
International Conference on Machine Learning (ICML), 2026
arXiv Code

2025

Flexible MOF paper thumbnail
Poster
Flexible MOF Generation with Torsion-Aware Flow Matching
Nayoung Kim, Seongsu Kim, Sungsoo Ahn
Neural Information Processing Systems (NeurIPS), 2025
arXiv Code
@inproceedings{kim2025flexible, title={Flexible MOF Generation with Torsion-Aware Flow Matching}, author={Kim, Nayoung and Kim, Seongsu and Ahn, Sungsoo}, booktitle={Advances in Neural Information Processing Systems}, year={2025}, url={https://openreview.net/forum?id=cLJfumTWLI} }
QHFlow paper thumbnail
Spotlight
High-order Equivariant Flow Matching for Density Functional Theory Hamiltonian Prediction
Seongsu Kim, Nayoung Kim, Dongwoo Kim, Sungsoo Ahn
Neural Information Processing Systems (NeurIPS), 2025
arXiv Code
@inproceedings{kim2025high, title={High-order Equivariant Flow Matching for Density Functional Theory Hamiltonian Prediction}, author={Kim, Seongsu and Kim, Nayoung and Kim, Dongwoo and Ahn, Sungsoo}, booktitle={Advances in Neural Information Processing Systems}, year={2025} }
MOFFlow paper thumbnail
Poster
MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworks
Nayoung Kim, Seongsu Kim, Minsu Kim, Jinkyoo Park, Sungsoo Ahn
International Conference on Learning Representations (ICLR), 2025
arXiv Code
@inproceedings{kim2024mofflow, title={MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworks}, author={Kim, Nayoung and Kim, Seongsu and Kim, Minsu and Park, Jinkyoo and Ahn, Sungsoo}, booktitle={The Thirteenth International Conference on Learning Representations}, year={2025}, url={https://openreview.net/forum?id=dNT3abOsLo} }
ASSD paper thumbnail
Poster
Decoupled Sequence and Structure Generation for Realistic Antibody Design
Nayoung Kim, Minsu Kim, Sungsoo Ahn, Jinkyoo Park
Transactions on Machine Learning Research (TMLR), 2025
arXiv Code
@article{kim2025decoupled, title={Decoupled Sequence and Structure Generation for Realistic Antibody Design}, author={Kim, Nayoung and Kim, Minsu and Ahn, Sungsoo and Park, Jinkyoo}, journal={Transactions on Machine Learning Research}, year={2025} }
Seasonal Animation