Research
Interests
My research focuses on understanding and designing representation learning frameworks that are generalizable, interpretable, and controllable. I aim to develop representations that generalize across diverse tasks and domains, are interpretable to support meaningful insights and decisions, and are controllable to enable direct manipulation for various applications.
Publications
Supervised Dimension Contrastive Learning
Jaemyung Yu, SungHyun Baek, Jongsuk Kim, Junmo Kim
Under Review
Efficient Multi-View 3D Representation via View-Agnostic Single-View Transformations
Jaemyung Yu, Jiwan Hur, Dong-Jae Lee, Jaehoon Cho, Junmo Kim
Under Review
IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation
SungHyun Baek, Jaemyung Yu, Seunghee Koh, Minsu Kim, Hyeonseong Jeon, Junmo Kim
Under Review
Frequency-Aware Token Reduction for Efficient Vision Transformer
Dong-Jae Lee, Jiwan Hur, Jaehyun Choi, Jaemyung Yu, Junmo Kim
Under Review
PRISM: Video Dataset Condensation with Progressive Refinement and Insertion for Sparse Motion
Jaehyun Choi, Jiwan Hur, Gyojin Han, Jaemyung Yu, Junmo Kim
arXiv 2025 | [Paper]
FairASR: Fair Audio Contrastive Learning for Automatic Speech Recognition
Jongsuk Kim, Jaemyung Yu, Minchan Kwon, Junmo Kim
Interspeech 2025 | [Paper]
 Self-supervised Transformation Learning for Equivariant Representations
Jaemyung Yu, Jaehyun Choi, Dong-Jae Lee, Hyeong Gwon Hong, Junmo Kim
Camera Distortion-aware 3D human Pose Estimation in Video with Optimization-based Meta-Learning
Hanbyel Cho, Yooshin Cho, Jaemyung Yu, Junmo Kim
Education
Korea Advanced Institute of Science and Technology (KAIST)
Ph.D. in Electrical Engineering (advisor: Junmo Kim)
Korea Advanced Institute of Science and Technology (KAIST)
M.S. in Electrical Engineering (advisor: Junmo Kim)
Korea Advanced Institute of Science and Technology (KAIST)
B.S. in Computer Science and Mathematics (double major)
Mar. 2019 - Aug. 2025
Mar. 2017 - Feb. 2019
Mar. 2013 - Feb. 2017
jaemyung at kaist dot ac dot kr