CV

Education

• Gyeonggi Science High School for The Gifted, 2010.03-2013.02
• B.S. in Mathematics, KAIST, 2013.03-2020.08
• M.S. in AI, KAIST, 2020.09-2022.08
• PhD. in AI, KAIST, 2022.08-present

Experience

• Visiting Student at RIKEN AIP, supervised by Mohammad Emtiyaz Khan, 2024.11 - 2025.02
• Visiting Scholar at New York University, supervised by Rajesh Ranganath, 2025.02 - 2025.06 (expected)

Publications

• Dimension Agnostic Neural Processess
  Hyungi Lee, Chaeyun Jang, Dong Bok Lee, Juho Lee
  ICLR 2025 (To Appear)

• Variational Bayesian Pseudo-Coreset
  Hyungi Lee, Seungyoo Lee, Juho Lee
  ICLR 2025 (To Appear)

• Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series
  Byoungwoo Park, Hyungi Lee, Juho Lee
  ICLR 2025 (To Appear)

• Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
  Chaeyun Jang*, Hyungi Lee*, Jungtaek Kim, Juho Lee
  * Equal contribution
  NeurIPS 2024 (spotlight)

• Enhancing Transfer Learning with Flexible Nonparametric Posterior Sampling
  Hyungi Lee*, Giung Nam*, Edwin Fong, Juho Lee
  * Equal contribution
  ICLR 2024

• Sparse Weight Averaging with Multiple Particles for Iterative Magitude Pruning
  Moonseok Choi*, Hyungi Lee*, Giung Nam*, Juho Lee
  * Equal contribution
  ICLR 2024

• Function Space Bayesian Pseudocoreset for Bayesian Neural Networks
  Balhae Kim, Hyungi Lee, Juho Lee
  NeurIPS 2023

• Traversing Between Modes in Function Space for Fast Ensembling
  Eunggu Yun*, Hyungi Lee*, Giung Nam*, Juho Lee
  * Equal contribution
  ICML 2023

• Regularizing Towards Soft Equivariance Under Mixed Symmetries
  Hyunsu Kim, Hyungi Lee, Hongseok Yang, Juho Lee
  ICML 2023

• Martingale Posterior Neural Processes
  Hyungi Lee, Eunggu Yun, Giung Nam, Edwin Fong, Juho Lee
  ICLR 2023 (spotlight)

• Improving ensemble distillation with weight averaging and diversifying perturbation
  Giung Nam, Hyungi Lee, Byeongho Heo, Juho Lee
  ICML 2022

• Scale Mixture of Neural Network Gaussian Processes
  Hyungi Lee, Eunggu Yun, Hongseok Yang, Juho Lee
  ICLR 2022

Workshop

• Efficient Modeling of Irregular Time-Series with Stochastic Optimal Control
  Byoungwoo Park*, Hyungi Lee*, Juho Lee
  *Equal contribution
  NeurIPS 2024 Workshop Bayesian Decision-making and Uncertainty

• Function Space Bayesian Pseudocoreset for Bayesian Neural Networks
  Balhae Kim, Hyungi Lee, Juho Lee
  ICML 2023 Workshop

• Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
  Chaeyun Jang, Jungtaek Kim, Hyungi Lee, Juho Lee
  The 3rd NeurIPS Workshop on Efficient Natural Language and Speech Processing (ENLSP)