HeeSun Bae

 

Ph.D. Candidate

Applied Artificial Intelligence Laboratory

Department of Industrial and Systems Engineering

KAIST, Daejeon, Republic of Korea

Contact: cat2507 [at] kaist.ac.kr / baeheesun96 [at] gmail.com

 

RESEARCH INTEREST

• Machine learning
• Representation Learning
• Distribution Shift
• Generalization Problem: Noisy label, Spurious Correlation

 

EDUCATION

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, the Republic of Korea (Mar. 2022 ~ )

• Course of Doctor's Degree in AAILab, ISysE
• Academic Advisor: Professor Il-Chul Moon

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, the Republic of Korea (Mar. 2020 ~ Feb. 2022)

• Course of Master's Degree in AAILab, ISysE
• Academic Advisor: Professor Il-Chul Moon

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, the Republic of Korea (Mar. 2015 ~ Feb. 2020)

• Bachelor of Science in Industrial and Systems Engineering

 

 

PUBLICATIONS

 

International Conference

• HeeSun Bae*, Seungjae Shin*, Byeonghu Na, JoonHo Jang, Kyungwoo Song, Il-Chul Moon, From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model, International Conference on Machine Learning (ICML 2022), Baltimore, Jul 17, 2022
• Seungjae Shin, Byeonghu Na, HeeSun Bae, JoonHo Jang, Hyemi Kim, Kyungwoo Song, Youngjae Cho, and Il-Chul Moon. 2022. Improving Group-based Robustness and Calibration via Ordered Risk and Confidence Regularization. In The Workshop on Spurious Correlations, Invariance, and Stability, International Conference on Machine Learning (SCIS at ICML 2022), July 22, 2022, Baltimore, Maryland USA. 

 

Domestic

• 배희선, 신승재, 문일철, 배장원 (2021) "스마트 그리드 기반 에너지 시스템 운영을 위한 배전계통 조류계산 시뮬레이션 모델 개발"  한국시뮬레이션학회

 

AWARDS

• IE Frontier 우수상, KAIST, 2017

 

LAB 

HeeSun Bae is a member of Applied Artificial Intelligence Laboratory. (2020.03 ~)