Research Interests
Machine learning and deep learning:
few-shot learning, meta-learning, multi-task learning, transfer learning
Education
KAIST, Daejeon, Korea
PhD., School of Computing
Sep 2022 - PresentAdvisor: Prof. Seunghoon Hong
M.S., School of Computing
Mar 2020 - Aug 2022Advisor: Prof. Seunghoon Hong
B.S., Department of Mathematical Science
Mar 2015 - Feb 2020Double major in Computer Science
Publication
[1] Donggyun Kim, Jinwoo Kim, Seongwoong Cho, Chong Luo, Seunghoon Hong, "Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching", In Proceedings of the International Conference on Learning Representations (ICLR), 2023. (notable-top-5%, oral presentation)
[2] Donggyun Kim, Seongwoong Cho, Wonkwang Lee, Seunghoon Hong, "Multi-Task Neural Processes", In Proceedings of the International Conference on Learning Representations (ICLR), 2022.
[3] Wonkwang Lee, Donggyun Kim, Seunghoon Hong, Honglak Lee, "High-Fidelity Synthesis with Disentangled Representation", In Proceedings of the European Conference on Computer Vision (ECCV), 2020.
Awards
Outstanding Paper Award in ICLR 2023
Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
29th Samsung Humantech Paper Award (silver prize)
Feb 2023Qualcomm Innovation Fellowship South Korea (QIFK) 2022 Finalist
Oct 2022Project Experience
Uncertainty Modeling and Calibration for Safe AI
KAIST, Korea
Mar 2020 - Mar 2021Selected as Venture Research Program for Graduate and Ph.D. student in KAIST.
Studied semi-supervised learning methods for semantic segmentation and applied them to safety-critical applications such as medical imaging.
Personalized Dialogue Systems
NCSoft Corporation, Korea
Mar 2019 - Dec 2019Industry-university cooperation research project in KAIST.
Studied personalized dialogue systems with Transformer and researched the advancement of memory networks.
Work Experience
SK hynix Inc., Incheon, Korea
Summer Internship, Data Science group
Jun 2018 - Aug 2018Studied statistical systems in the semiconductor manufacturing process and developed wafer defect classifier using CNN.
Teaching Experience
Teaching Assistant
CS492I: Special Topics in Computer Science <Introduction to Deep Learning> (lecture in KAIST, Fall 2022)
Samsung AI Vision Class: Advanced Curriculum (lecture in Samsung Electronics Co., Ltd., Summer 2021)
CS492H: Deep Learning for Real-World Problem (lecture in KAIST, Spring & Fall 2020)
CS101: Introduction to Programming (lecture in KAIST, Fall 2018)
Undergraduate Tutor
CS376: Machine Learning (lecture in KAIST, Fall 2019)