Prof.
Hyungi Lee
이현기 교수
Education
학력
Ph.D. KAIST, Kim Jaechul Graduate School of AI ()
M.S. KAIST, AI ()
B.S. KAIST, Mathematical Sciences ()
M.S. KAIST, AI ()
B.S. KAIST, Mathematical Sciences ()
Career
경력
Present Assistant Professor, Dept. of AI, Kookmin University
현재 국민대학교 AI학부 조교수
Research Overview 연구 개요
Research focuses on Bayesian Neural Networks, stochastic processes in machine learning, Neural Tangent Kernel, Transfer Learning, and uncertainty calibration of Large Language Models.
베이지안 신경망, 기계학습에서의 확률 과정, 뉴럴 탄젠트 커널, 전이 학습, 대규모 언어 모델의 불확실성 보정에 관한 연구를 수행합니다.
Research Areas 연구 분야
- Bayesian Neural Networks
- Stochastic Processes in ML
- Neural Tangent Kernel
- Transfer Learning
- LLM Uncertainty Calibration
- 베이지안 신경망
- 기계학습 확률 과정
- 뉴럴 탄젠트 커널
- 전이 학습
- LLM 불확실성 보정
Major Achievements 주요 연구 성과
- PANGEA: Projection-based augmentation for domain adaptation in LLMs (NeurIPS 2025)
- 4 papers at NeurIPS 2025, 3 papers at ICLR 2025
Recent Publications 주요 논문
- S. Lee, G. Nam, M. Choi, H. Lee, and J. Lee, "PANGEA: Projection-Based Augmentation with Non-Relevant General Data for Enhanced Domain Adaptation in LLMs," NeurIPS, 2025
- H. Lee, M. Choi, H. Kim, K. Cho, R. Ranganath, and J. Lee, "Test Time Scaling for Neural Processes," NeurIPS, 2025
- C. Jang, D. Cho, S. Lee, H. Lee, and J. Lee, "Reliable Decision-Making via Calibration-Oriented Retrieval-Augmented Generation," NeurIPS, 2025
- Y. Jung, H. Lee, W. Chen, T. Mollenhoff, Y. Li, J. Lee, and M. E. Khan, "Compact Memory for Continual Logistic Regression," NeurIPS, 2025
- H. Lee, C. Jang, D. B. Lee, and J. Lee, "Dimension Agnostic Neural Processes," ICLR, 2025
- H. Lee, S. Lee, and J. Lee, "Variational Bayesian Pseudo-Coreset," ICLR, 2025
- B. Park, H. Lee, and J. Lee, "Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Series," ICLR, 2025
- C. Jang, H. Lee, J. Kim, and J. Lee, "Model Fusion through Bayesian Optimization in Language Model Fine-Tuning," NeurIPS (Spotlight), 2024