Seonghwan Kim
Orcid: 0009-0007-9131-8864Affiliations:
- KAIST AI, Seoul, South Korea
According to our database1,
Seonghwan Kim authored at least 12 papers
between 2022 and 2026.
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2026
Riemannian denoising model for molecular structure optimization with chemical accuracy.
Nat. Comput. Sci., February, 2026
Learning Adaptive Perturbation-Conditioned Contexts for Robust Transcriptional Response Prediction.
CoRR, February, 2026
2025
Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
2024
Riemannian Denoising Score Matching for Molecular Structure Optimization with Accurate Energy.
CoRR, 2024
CoRR, 2024
Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models.
CoRR, 2024
2023
A 2D Graph-Based Generative Approach For Exploring Transition States Using Diffusion Model.
CoRR, 2023
Predicting quantum chemical property with easy-to-obtain geometry via positional denoising.
CoRR, 2023
The StarCraft Multi-Agent Exploration Challenges: Learning Multi-Stage Tasks and Environmental Factors Without Precise Reward Functions.
IEEE Access, 2023
GeoTMI: Predicting Quantum Chemical Property with Easy-to-Obtain Geometry via Positional Denoising.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
2022
The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions.
CoRR, 2022