Youngrae Kim

About Me

I am a first-year Ph.D. student in Computer Engineering at the University of Southern California (USC). Previously, I received my M.S. degree in Computer Science from Korea Advanced Institute of Science and Technology (KAIST) under the supervision of Prof. Dongman Lee.

Research Interests

Areas: Computer Vision, Machine Learning

• Controllable representation learning : Modern visual models contain biased and difficult-to-understand representations, leading to potentially catastrophic results. I am interested in developing a learning framework for unbiased, interpretable, and general visual representations.
• Optimization through interaction with the surroundings: Although a large dataset is used to train the model, the extremely dynamic real world contains a distribution of blind spots that typical models cannot address. I am interested in detecting this gap and optimizing a model by interacting with its surroundings.

News

• [Oct. 2024] Our paper on test-time adaptation is accepted to WACV 2025.
• [Aug. 2024] Our paper on test-time adaptation is accepted to ECCV 2024 Workshop on Vision-Centric Autonomous Driving.
• [Jul. 2024] Our paper on disentangled video representation learning is accepted for oral presentation at ECCV 2024.
• [Jul. 2024] Our paper on few-shot learning for image restoration is accepted to ECCV 2024.
• [Apr. 2024] I’ve been accepted to USC as a Ph.D. student.

Selected Publications

Academic Services

Reviewer

IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR)
Association for the Advancement of Artificial Intelligence Conference (AAAI)
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

Teaching Experiences

Teaching Assistant

Data Structure (CS206) course, School of Computing, KAIST (Fall 2022)
Operating System (CS330) course, School of Computing, KAIST (Spring 2022)

Powered by Jekyll and Minimal Light theme.