I am a Ph.D. candidate at the Graduate School of Artificial Intelligence, KAIST, being co-advised by Juho Lee and Hongseok Yang. My research interests encompass machine learning, Bayesian inference (MCMC, VI), symmetry in AI, and AI for science.
Publications
- Gyeonghoon Ko, Hyunsu Kim, Juho Lee, NeurIPS 2024 Learning Infinitesimal Generators of Continuous Symmetries from Data
- Hyunsu Kim, Yegon Kim, Hongseok Yang, Juho Lee, ICML 2024 Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts
- Hyunsu Kim*, Jongmin Yoon*, Juho Lee, ICLR 2024 Fast Ensembling with Diffusion Schrödinger Bridge
- Seunghyun Kim*, Hyunsu Kim*, Eungu Yun*, Hwangrae Lee, Jaehun Lee, Juho Lee, ICML 2023 Probabilistic imputation for time-series classification with missing data
- Hyunsu Kim, Hyungi Lee, Hongseok Yang, Juho Lee, ICML 2023 Regularizing towards soft equivariance under mixed symmetries,
- Hyunsu Kim, Juho Lee, Hongseok Yang, AABI 2020 Adaptive strategy for resetting a non-stationary markov chain during learning via joint stochastic approximation
Honors and Awards
- 2019-present Government-sponsored graduate scholarship - KAIST
- 2014-2018 The Presidential Science Scholarship - Korean National Government
- 2014-2019 Full undergraduate scholarship - KAIST
- 2013 Honorable Mention - International Science and Engineering Fair (ISEF)
- 2013 1st Prize - Korea Science and Engineering Fair (KSEF)
- 2009 Bronze Medal - Middle School Korea Biology Olympiad
Educations
- 2021.09 - present, Ph.D. In Artificial Intelligence, KAIST
- 2019.03 - 2021.08, M.S. In Computer Science, KAIST
- 2014.03 - 2019.02, B.S. In Physics And Computer Science, KAIST