Seungjae Shin

2020.03.12 11:00

신승재 Views:2219


Seungjae Shin


Ph.D. Candidate

Applied Artificial Intelligence Laboratory

Department of Industrial and Systems Engineering

KAIST, Daejeon, Republic of Korea

Contact: tmdwo0910 [at] / tmdwo0910 [at]
Homepage :





  • Dataset Optimization (e.g. Dataset Selection, Dataset Condensation)
  • Representation Learning, Generative Model
  • Generalization (e.g. Debiasing, Fairness)




Korea Advanced Institute of Science and Technology (KAIST), Daejeon, the Republic of Korea (Mar. 2020 - present)

  • 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. 2018 ~ Feb. 2020)

  • 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. 2013 ~ Feb. 2018)

  • Bachelor of Science in Industrial and Systems Engineering (Minor. Science in Business and Technology Management) 


PUBLICATIONS (denotes the equal contribution.)



  • Seungjae Shin*, HeeSun Bae*, DongHyeok Shin, Weonyoung Joo, Il-Chul Moon "Loss Curvature Matching for Dataset Selection and Condensation", International Conference on Artificial Intelligence and Statistics (AISTATS) 202
  • Seungjae Shin*, Heesun Bae*, Giwoon Kim, Youngsoon Cho, Dongwook Lee, Donggil Jeong, HyunJoon Kim, Hyunjung Lee, Hyungjun Moon, "Evaluation of Optimal Scene Time Interval for Out-of-hospital Cardiac Arrest using a Deep Neural Network", American Journal of Emergency Medicine 
  • Seungjae Shin, Byeonghu Na, HeeSun Bae, JoonHo Jang, Hyemi Kim, Kyungwoo Song, Youngjae Cho, 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
  • 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 
  • Dongjun Kim, Seungjae Shin, Kyungwoo Song, Wanmo Kang, Il-Chul Moon, "Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation", International Conference on Machine Learning (ICML 2022), Baltimore, Jul 17, 2022
  • Hyuck Lee, Seungjae Shin, Heeyoung Kim "ABC : Auxiliary Balanced Classifier for Class-imbalanced Semi-supervised Learning" Conference on Neural Information Processing Systems (NeurIPS), 2021.
  • Mingi Ji, Seungjae Shin, Seunghyun Hwang, Gibeom Park, Il-Chul Moon "Refine Myself by Teaching Myself : Feature Refinement via Self-Knowledge Distillation" IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
  • Hyemi Kim, Seungjae Shin, JoonHo Jang, Kyungwoo Song, Weonyoung Joo, Wanmo Kang, Il-Chul Moon "Counterfactual Fairness with Disentangled Causal Effect Variational Autoencoder" AAAI Conference on Artificial Intelligence (AAAI) 2021.
  • Seungjae Shin, Kyungwoo Song, Joonho Jang, Hyemi Kim, Weonyoung Joo, and Il-Chul Moon “Neutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation” Findings of Empirical Methods in Natural Language Processing (Findings of EMNLP) 2020.
  • Kyungwoo Song, JoonHo Jang, Seungjae Shin, and Il-Chul Moon “Bivariate Beta-LSTM” AAAI Conference on Artificial Intelligence (AAAI) 2020.
  • Joonho Jang, Seungjae Shin, Hyunjin Lee, Il-Chul Moon "Forecasting the Concentration of Particulate Matter in the Seoul Metropolitan Area Using a Gaussian Process Model" Sensors 2020
  • Yongjin Shin, Gihun Lee, Seungjae Shin, Se-young Yun, Il-Chul Moon "FEWER : Federated Weight Recovery" DistributedML'20: Proceedings of the 1st Workshop on Distributed Machine Learning



  • Dongjun Kim, Kyungwoo SongSeungjae Shin, Il-Chul Moon "Posterior-Aided Regularization for Likelihood-Free Inference"
  • Dongjun Kim, Weonyoung JooSeungjae Shin, Il-Chul Moon "Adversarial Likelihood-Free Inference on Black-Box Generator"
  • Weonyoung Joo, Dongjun KimSeungjae Shin, Il-Chul Moon "Generalized Gumbel-Softmax Gradient Estimator for Various Discrete Random Variables"



  • Dean's list, KAIST, 2014
  • Honor student scholarship, KAIST, 2016
  • 1st Prize (대상), KAIST Invention Award, 2017
  • 최우수논문상, KSC2017 학부생 논문경진대회, 2017
  • 송현상, KAIST ISysE, 2018
  • Winner, Qualcomm Innovation Fellowship Korea, 2022



Seungjae Shin is a member of Applied Artificial Intelligence Laboratory. (2018.03 ~)

No. Subject Author Date Views
13 Lee, GeunHo file SESLAB 2011.09.05 6858
12 JoonHo Jang file 장준호 2017.03.01 3277
11 Dongjun Kim file 김동준 2017.08.24 13436
10 Byeonghu Na file 나병후 2019.02.25 2085
» Seungjae Shin file 신승재 2020.03.12 2219
8 HeeSun Bae file 배희선 2020.03.16 1766
7 DongHyeok Shin file 신동혁 2020.03.16 1442
6 Yunkyeong Seo file 서윤경 2020.03.16 2093
5 Suhyeon Jo file 조수현 2021.02.23 1559
4 Muhyun Byun file 변무현 2021.02.26 829
3 Hyungho Na file 나형호 2021.02.28 825
2 Hyeonmin Lee file 이현민 2021.03.01 879
1 Changseok Han file ChangseokHan 2022.02.23 416