Bae HeeSun

• Research Interest

  • Machine Learning; Representation Learning

  • Generalization with Distribution Shift

    • Learning with noisy label

    • Domain Generalization

• Publication (* denotes the equal contribution. )

• Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning (International Conference on Learning Representation (ICLR 2024), Vienna, Austria, May 07-11, 2024)

  • Heesun Bae, Seungjae Shin, Byeonghu Na and Il-Chul Moon

• • Unknown Domain Inconsistency Minimization for Domain Generalization (International Conference on Learning Representation (ICLR 2024), Vienna, Austria, May 07-11, 2024)

    • Seungjae Shin*, Heesun Bae*, Byeonghu Na, Yoon-yeong Kim, Il-Chul Moon

  • Label-Noise Robust Diffusion Models (International Conference on Learning Representation (ICLR 2024), Vienna, Austria, May 07-11, 2024)

    • Byeonghu Na, Yeongmin Kim, HeeSun Bae, Jung Hyun Lee, Se Jung Kwon, Wanmo Kang, Il-Chul Moon

  • Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior (AAAI Conference on Artificial Intelligence (AAAI), Vancouver, Canada, Feb 20-27, 2024)

    • Youngjae Cho, HeeSun Bae, Seungjae Shin, YeoDong Youn, Weonyoung Joo, and Il-chul Moon 

  • Loss Curvature Matching for Dataset Selection and Condensation (International Conference on Artificial Intelligence and Statistics (AISTATS 23), Valencia, Spain, Apr 25-27, 2023)

    • Seungjae Shin*, Heesun Bae*, DongHyeok Shin, Weonyoung Joo, Il-Chul Moon

  • From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model (International Conference on Machine Learning (ICML) 2022)

    • HeeSun Bae*, Seungjae Shin*, Byeonghu Na, JoonHo Jang, Kyungwoo Song, Il-Chul Moon

  • Improving Group-based Robustness and Calibration via Ordered Risk and Confidence Regularization (Workshop on Spurious Correlations, Invariance, and Stability on International Conference on Machine Learning (ICML-SCIS) 2022)

• Seungjae Shin, Byeonghu Na, HeeSun Bae, JoonHo Jang, Hyemi Kim, Kyungwoo Song, Youngjae Cho, Il-Chul Moon 

• • Evaluation of optimal scene time interval for out-of-hospital cardiac arrest using a deep neural network (American Journal of Emergency Medicine  (IF = 3.7))

• Seungjae Shin*, Heesun Bae*, Giwoon Kim, Youngsoon Cho, Dongwook Lee, Donggil Jeong, HyunJoon Kim, Hyunjung Lee,  Hyungjun Moon

• Education

  • Ph.D. Candidate in Industrial Engineering, KAIST, Daejeon, Korea (advisor: Prof. Il-Chul Moon) (2022.03 - present)

  • M.S. in Industrial Engineering, KAIST, Daejeon, Korea (advisor: Prof. Il-Chul Moon) (2020.03 - 2022.02)

  • B.S. in Industrial Engineering, KAIST, Daejeon, Korea (2015.03 - 2020.02)

• Experience

  • Research Internship, NAVER(2023.08~2023.11)

  • Exchange Student, Industral Engineeering (wirtschaftsingenieurwesen), Technische Universität Berlin (TUB) (2018.03 ~2018.08)

• Awards

• Winner, Qualcomm Innovation Fellowship Korea 2023

• Winner, Qualcomm Innovation Fellowship Korea 2022

• IE Frontier, Excellence prize, KAIST, 2017

• Academic Services

Conference Reviewer 

• • ICML(2023, 2024), NeurIPS(2022, 2023),  ICLR(2024), AISTATS(2023)
    
    

• last update: 18th, Jan, 2024