I am an assistant professor at the Graduate School of AI at KAIST. I lead the Structured and Probabilistic Machine Learning (SPML) Lab. I focus on developing machine learning algorithms for molecules, with applications to drug or material discovery.
Contact: sungsoo.ahn@kaist.ac.kr
Regulars: Minsu Kim (post-doc), Yinhua Park (post-doc), Yunhui Jang, Hyosoon Jang, Hyomin Kim, Seonghyun Park, Seongsu Kim, Kiyoung Seong, Minkyu Kim, Dongyeop Woo, Nayoung Kim, Hyunjin Seo, Taewon Kim
Alumnis: Haeji Go, Juwon Hwang
Search-Based Correction of Reasoning Chains for Language Models
Minsu Kim, Jean-Pierre René Falet, Oliver Ethan Richardson, ..., Sungsoo Ahn, Yoshua Bengio
Learning Flexible Forward Trajectories for Masked Molecular Diffusion
Hyunjin Seo, Taewon Kim, Sihyun Yu, Sungsoo Ahn
Self-Training LLMs with Reasoning-Level Confidence
Hyosoon Jang, Yunhui Jang, Sungjae Lee, Jungseul Ok, Sungsoo Ahn
Can LLMs Generate Diverse Molecules? Towards Alignment with Structural Diversity
Hyosoon Jang, Yunhui Jang, Jaehyung Kim, Sungsoo Ahn
Learning Collective Variables from Time-lagged Generation
Seonghyun Park, Kiyoung Seong, Soojung Yang, Rafael Gomez-Bombarelli, Sungsoo Ahn
International Conference on Machine Learning (ICML) GenBio Workshop 2025
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
Energy-based Generator Matching: A Neural Sampler for General State Space
Dongyeop Woo, Minsu Kim, Minkyu Kim, Kiyoung Seong, Sungsoo Ahn
Neural Information Processing Systems (NeurIPS) 2025
On Scalable and Efficient Training of Diffusion Samplers
Minkyu Kim*, Kiyoung Seong*, Dongyeop Woo, Sungsoo Ahn, Minsu Kim
Neural Information Processing Systems (NeurIPS) 2025
Flexible MOF Generation with Torsion-Aware Flow Matching
Nayoung Kim, Seongsu Kim, Sungsoo Ahn
Neural Information Processing Systems (NeurIPS) 2025
Self-Training Large Language Models with Confident Reasoning
Hyosoon Jang, Yunhui Jang, Sungjae Lee, Jungseul Ok, Sungsoo Ahn
Empirical Methods in Natural Language Processing (EMNLP) 2025 (Findings)
Improving Chemical Understanding of LLMs via SMILES Parsing
Yunhui Jang, Jaehyung Kim, Sungsoo Ahn
Empirical Methods in Natural Language Processing (EMNLP) 2025 (Main)
MT-Mol: Multi Agent System with Tool-based Reasoning for Molecular Optimization
Hyomin Kim, Yunhui Jang, Sungsoo Ahn
Empirical Methods in Natural Language Processing (EMNLP) 2025 (Findings)
RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark
Federico Berto, Chuanbo Hua, Junyoung Park, ... , Sungsoo Ahn, ... , Jinkyoo Park
Knowledge Discovery and Data Mining (KDD) 2025 (Datasets and Benchmarks Track)
Structural Reasoning Improves Molecular Understanding of LLM
Yunhui Jang, Jaehyung Kim, Sungsoo Ahn
Neural Information Processing Systems (NeurIPS) AIDrugX Workshop, 2024
Annual Meeting of the Association for Computational Linguistics, 2025 (Main)
Enhancing LLM Agent Safety via Causal Influence Prompting
Dongyoon Hahm, Woogyeol Jin, June Suk Choi, Sungsoo Ahn, Kimin Lee
Annual Meeting of the Association for Computational Linguistics, 2025 (Findings)
Decoupled Sequence and Structure Generation for Realistic Antibody Design
Nayoung Kim, Minsu Kim, Sungsoo Ahn, Jinkyoo Park
Transactions on Machine Learning Research, 2024
ReBind: Enhancing Ground-state Molecular Conformation Prediction via Force-Based Graph Rewiring
Taewon Kim*, Hyunjin Seo*, Sungsoo Ahn, Eunho Yang
International Conference on Learning Representations (ICLR) 2025
Adaptive Teachers for Amortized Samplers
Minsu Kim*, Sanghyeok Choi*, Taeyoung Yun, Emmanuel Bengio, Leo Feng, Jarrid Rector-Brooks, Sungsoo Ahn, Jinkyoo Park, Nikolay Malkin, and Yoshua Bengio
International Conference on Learning Representations (ICLR) 2025
Generative Flows on Synthetic Pathway for Drug Design
Seonghwan Seo, Minsu Kim, Tony Shen, Martin Ester, Jinkyoo Park, Sungsoo Ahn, Woo Youn Kim
Neural Information Processing Systems (NeurIPS) AIDrugX Workshop, 2024
International Conference on Learning Representations (ICLR) 2025
MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworks
Nayoung Kim, Seongsu Kim, Minsu Kim, Jinkyoo Park, Sungsoo Ahn
Neural Information Processing Systems (NeurIPS) AIDrugX Workshop, 2024
International Conference on Learning Representations (ICLR) 2025
Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers
Kiyoung Seong, Seonghyun Park, Seonghwan Kim, Woo Youn Kim, Sungsoo Ahn
International Conference of Machine Learning (ICML) SPIGM Workshop, 2024
International Conference on Learning Representations (ICLR) 2025
Non-backtracking Graph Neural Networks
Seonghyun Park, Narae Ryu, Gahee Kim, Dongyeop Woo, Se-Young Yun, Sungsoo Ahn
Transactions on Machine Learning Research, 2024
Neural Information Processing Systems (NeurIPS) GLFrontiers Workshop, 2023 (oral presentation)
Pessimistic Backward Policy for GFlowNets
Hyosoon Jang, Yunhui Jang, Minsu Kim, Jinkyoo Park, Sungsoo Ahn
Neural Information Processing Systems (NeurIPS), 2024
Hybrid Neural Representation for Spherical Data
Hyomin Kim, Yunhui Jang, Jaeho Lee, Sungsoo Ahn
International Conference on Machine Learning (ICML), 2024
Gaussian Plane-Wave Neural Operator for Electron Density Estimation
Seongsu Kim, Sungsoo Ahn
International Conference on Machine Learning (ICML), 2024
Removing Multiple Biases through the Lens of Multi-task Learning
Nayeong Kim, Juwon Kang, Sungsoo Ahn, Jungseul Ok, Suha Kwak
International Conference on Machine Learning (ICML), 2024
International Conference on Machine Learning (ICML) Spurious Correlations, Invariance and Stability Workshop, 2023
Enhancing Sample Efficiency in Black-box Combinatorial Optimization via Symmetric Replay Training
Hyeonah Kim, Minsu Kim, Sungsoo Ahn, Jinkyoo Park
International Conference on Machine Learning (ICML), 2024
International Conference on Machine Learning (ICML) Sampling and Optimization in Discrete Space Workshop, 2023
Tackling Complex Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More
Fanchen Bu, Hyeonsoo Jo, Soo Yong Lee, Sungsoo Ahn, Kijung Shin
International Conference on Machine Learning (ICML), 2024
Breadth-First Exploration in Adaptive Grid-based Reinforcement Learning
Youngsik Yoon, Gangbok Lee, Sungsoo Ahn, Jungseul Ok
International Conference on Machine Learning (ICML), 2024
Fragment-based Multi-view Molecular Contrastive Learning
Seojin Kim, Jaehyun Nam, Junsu Kim, Hankook Lee, Sungsoo Ahn, Jinwoo Shin
Transactions on Machine Learning Research (TMLR), 2024
International Conference on Learning Representations (ICLR) ML4Materials Workshop, 2023
EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost
Jaeseung Heo, Seungbeom Lee, Sungsoo Ahn, Dongwoo Kim
International Joint Conferences on Artificial Intelligence (IJCAI), 2024
International Conference on Machine Learning (ICML) Data-centric Machine Learning Research Workshop, 2023
Learning Energy Decompositions for Partial Inference in GFlowNets
Hyosoon Jang, Minsu Kim, Sungsoo Ahn
International Conference on Learning Representations (ICLR), 2024 (oral presentation)
A Simple and Scalable Representation for Graph Generation
Yunhui Jang, Seul Lee, Sungsoo Ahn
International Conference on Learning Representations (ICLR), 2024
Neural Information Processing Systems (NeurIPS) GLFrontiers Workshop, 2023
Hierarchical Graph Generation with K^2 Trees
Yunhui Jang, Dongwoo Kim, Sungsoo Ahn
International Conference on Learning Representations (ICLR), 2024
International Conference on Machine Learning (ICML) Structured Probabilistic Inference & Generative Modeling Workshop, 2023
Local Search GFlowNets
Minsu Kim, Taeyoung Yun, Emmanuel Bengio, Dinghuai Zhang, Yoshua Bengio, Sungsoo Ahn, Jinkyoo Park
International Conference on Learning Representations (ICLR), 2024 (spotlight presentation)
Triplet Edge Attention for Algorithmic Reasoning
Yeonjoon Jung, Sungsoo Ahn
Learning on Graph Conference (LoG), 2023, extended abstract
Multi-resolution Spectral Coherence for Graph Generation with Score-based Diffusion
Hyuna Cho, Minjae Jeong, Sooyeon Jeon, Sungsoo Ahn, Won Hwa Kim
Neural Information Processing Systems (NeurIPS), 2023
Diffusion Probabilistic Models for Structured Node Classification
Hyosoon Jang, Seonghyun Park, Sangwoo Mo, Sungsoo Ahn
Neural Information Processing Systems (NeurIPS), 2023
International Conference on Machine Learning (ICML) Structured Probabilistic Inference & Generative Modeling Workshop, 2023,
Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences
Minsu Kim, Federico Berto, Sungsoo Ahn, Jinkyoo Park
Neural Information Processing Systems (NeurIPS), 2023
International Conference on Machine Learning (ICML) Structured Probabilistic Inference & Generative Modeling Workshop, 2023,
A Closer Look at the Intervention Procedure of Concept Bottleneck Models
Sungbin Shin, Yohan Jo, Sungsoo Ahn, Namhoon Lee
International Conference on Machine Learning (ICML), 2023
Neural Information Processing Systems Trustworthy and Socially Responsible Machine Learning Workshop, 2022
Imitating Graph-Based Planning with Goal-Conditioned Policies
Junsu Kim, Younggyo Seo, Sungsoo Ahn, Kyunghwan Son, Jinwoo Shin
International Conference on Learning Representations (ICLR), 2023
Substructure Atom Self-Attention for Molecular Property Prediction
Jiye Kim, Seungbeom Lee, Dongwoo Kim, Sungsoo Ahn, Jaesik Park
Neural Information Processing Systems (NeurIPS) AI4Science Workshop, 2022
Learning Debiased Classifier with Biased Committee
Nayeong Kim, Sehyun Hwang, Sungsoo Ahn, Jaesik Park, Suha Kwak
Neural Information Processing Systems (NeurIPS), 2022
International Conference on Machine Learning (ICML) Workshop on Spurious Correlations, Invariance, and Stability, 2022
Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning
Kyunghwan Son, Junsu Kim, Sungsoo Ahn, Roben Delos Reyes, Yung Yi, Jinwoo Shin
International Conference on Machine Learning (ICML), 2022
What Makes Better Augmentation Strategies? Augment Difficult but Not Too Different
Jaehyung Kim, Dongyeop Kang, Sungsoo Ahn, Jinwoo Shin
International Conference on Learning Representations (ICLR), 2022
Spanning Tree-based Graph Generation for Molecules
Sungsoo Ahn, Binghong Chen, Tianzhe Wang, and Le Song
International Conference on Learning Representations (ICLR), 2022 (spotlight presentation)
RoMA: Robust Model Adaptation for Offline Model-based Optimization
Sihyun Yu, Sungsoo Ahn, Le Song, and Jinwoo Shin
Neural Information Processing Systems (NeurIPS), 2021
Abstract Reasoning via Logic-guided Generation
Sihyun Yu, Sangwoo Mo, Sungsoo Ahn, and Jinwoo Shin
International Conference on Machine Learning (ICML), 2021, Workshop on Self-Supervised Learning for Reasoning and Perception (oral presentation)
Self-Improved Retrosynthetic Planning
Junsu Kim, Sungsoo Ahn, Hankook Lee, and Jinwoo Shin
International Conference on Machine Learning (ICML), 2021
RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning
Hankook Lee, Sungsoo Ahn, Seung-Woo Seo, You Young Song, Eunho Yang, Sung Ju Hwang, and Jinwoo Shin
International Joint Conference on Artificial Intelligence (IJCAI), 2021
Layer-adaptive sparsity for the Magnitude-based Pruning
Jaeho Lee, Sejun Park, Sangwoo Mo, Sungsoo Ahn, and Jinwoo Shin
International Conference on Learning Representations (ICLR), 2021
Learning from Failure: Training Debiased Classifier from Biased Classifier
Junhyun Nam, Hyuntak Cha, Sungsoo Ahn, Jaeho Lee, and Jinwoo Shin
Neural Information Processing Systems (NeurIPS), 2020
Guiding Deep Molecular Optimization with Genetic Exploration
Sungsoo Ahn, Junsu Kim, Hankook Lee, and Jinwoo Shin
Neural Information Processing Systems (NeurIPS), 2020
Learning What to Defer for Maximum Independent Sets
Sungsoo Ahn, Younggyo Seo, and Jinwoo Shin
International Conference on Machine Learning (ICML), 2020
Variational Information Distillation for Knowledge Transfer
Sungsoo Ahn, Shell Hu, Andreas Damianou, Neil Lawrence, and Zhenwen Dai
IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2019
Neural Information Processing Systems (NeurIPS) Workshop on Continual Learning, 2018
Bucket-Renormalization for Approximate Inference
Sungsoo Ahn, Michael Chertkov, Adrian Weller, and Jinwoo Shin
Journal of Statistical Mechanics: Theory and Experiment (JSTAT), vol. 2019, no. 12, pp. 124022, 2019
International Conference on Machine Learning (ICML), 2018
Maximum Weight Matching using Odd-sized Cycles: Max-Product Belief Propagation and Half-Integrality
Sungsoo Ahn, Michael Chertkov, Andrew E. Gelfand, Sejun Park, and Jinwoo Shin (alphabetical order)
IEEE Transactions on Information Theory, 2018
Gauged Mini-Bucket Elimination for Approximate Inference
Sungsoo Ahn, Michael Chertkov, Jinwoo Shin, and Adrian Weller
International Conference on Artificial Intelligence and Statistics (AISTATS), 2018
Gauging Variational Inference
Sungsoo Ahn, Michael Chertkov, and Jinwoo Shin
Journal of Statistical Mechanics: Theory and Experiment (JSTAT), vol. 2019, no. 12, pp. 124015, 2019
Neural Information Processing Systems (NeurIPS), 2017
Synthesis of MCMC and Belief Propagation
Sungsoo Ahn, Michael Chertkov, and Jinwoo Shin
Neural Information Processing Systems (NeurIPS), 2016 (oral presentation)
Minimum Weight Perfect Matching via Blossom Belief Propagation
Sungsoo Ahn, Sejun Park, Michael Chertkov, and Jinwoo Shin
Neural Information Processing Systems (NeurIPS), 2015 (spotlight presentation)