Professor
Jongheon Jeong
Assistant Professor
Department of Artificial Intelligence, Korea University
Research Interests:
Deep learning, Machine learning
AI Safety (Alignment, Robustness, Monitoring, ...)
Multi-modal foundation models, Generative models
Anomaly detection
Biography
Jongheon Jeong is an assistant professor in the Department of Artificial Intelligence at Korea University (KU), leading the Trustworthy AI Lab (TAIL @ KU). He obtained his Ph.D. in Electrical Engineering from KAIST in 2023, and B.S. in Mathematics and Computer Science from KAIST in 2017. During his Ph.D. studies, he worked at Amazon Web Services (AWS) as an Applied Scientist Intern in 2021 (Seattle, WA) and 2022 (Bellevue, WA). He received the Best Doctoral Dissertation Award from the KAIST College of Engineering in 2024, and the Qualcomm Innovation Fellowship Korea 2020 from two of his papers. His research interest lies in broad areas of AI Safety, towards making deep learning more reliable against various out-of-distribution scenarios. Ultimately, his research aims to discover (if exist) simple answers that close the gap between humans and machines, understanding why neural networks behave so differently from us and how we make such reliable yet efficient inferences.
Ph.D. Thesis
On the Trade-off between Robustness and Accuracy in Smoothed Classifiers
Jongheon Jeong
School of Electrical Engineering, Korea Advanced Institute of Science and Technology, 2023
Best Doctoral Dissertation Award, KAIST College of Engineering, 2024
Advisor: Jinwoo Shin (KAIST)
Honer & Awards
Best Doctoral Dissertation Award, KAIST College of Engineering, Feb 2024
NeurIPS 2023 Scholar Award, Oct 2023
Finalist, Qualcomm Innovation Fellowship Korea 2021, Nov 2021
Best Paper Award, Korean Artificial Intelligence Association, Nov 2021
Winner, Qualcomm Innovation Fellowship Korea 2020, Dec 2020
NeurIPS 2020 Top (10%) Reviewer Award, Oct 2020
3rd place, Automatic Machine Learning Challenge (AutoML, Final phase), ChaLearn, May 2016
Services
Conference reviewers
Neural Information Processing Systems (NeurIPS)
International Conference on Learning Representations (ICLR)
International Conference on Machine Learning (ICML)
AAAI Conference on Artificial Intelligence (AAAI)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
European Conference on Computer Vision (ECCV)
Workshop reviewers
NeurIPS 2024 Workshop on Towards Safe & Trustworthy Agents (SATA 2024)
NeurIPS 2023 Workshop on Distribution Shifts (DistShift 2023)
CVPR 2023 Workshop on Visual Anomaly and Novelty Detection (VAND 2023)
ICML 2020 Workshop on Uncertainty & Robustness in Deep Learning (UDL 2020)
Journal reviewers
International Journal of Computer Vision (IJCV)
Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
Transactions on Machine Learning Research (TMLR)
ACM Transactions on Modeling and Performance Evaluation of Computing Systems (ACM ToMPECS)