Sanghyeok Lee
I earned my Ph.D. in the Department of Computer Sciences at Korea University, advised by Prof. Hyunwoo J. Kim (Machine Learning & Vision Lab, MLV Lab). Starting in September 2025, I will join KAIST as a postdoctoral researcher.
My research interests include Efficient Deep Learning, Efficient Adaptation, Computer Vision, 3D Vision, and Multi-modal Learning.
Visit CV and Publications for more information.
Contact: cat0626 [at] korea [dot] ac [dot] kr
2025
June
Our paper (Representation Shift) got accepted to ICCV 2025!
Representation Shift: Unifying Token Compression with FlashAttention
May
(May) Served as a Program Committee member for the MICCAI 3rd International Workshop on Foundation Models for General Medical AI.
Feb
Our paper (EfficientViM) got accepted to CVPR 2025!
EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
2024
Aug
Received the Outstanding Paper Award @ Korea Univ.
May
Served as a Program Committee member for the MICCAI 2nd International Workshop on Foundation Models for General Medical AI.
Feb
Our papers (MCTF, vid-TLDR) got accepted to CVPR 2024! (Travel Award)
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers
vid-TLDR: Training Free Token merging for Light-weight Video Transformer
2023
Jul
Our paper (RPO) got accepted to ICCV 2023!
Read-only Prompt Optimization for Vision-Language Few-shot Learning
Feb
Our paper (SPoTr) got accepted to CVPR 2023! (100+ citations)
Self-positioning Point-based Transformer for Point Cloud Understanding
2021
Jul
Our paper (PointWOLF) got accepted to ICCV 2021!
Point Cloud Augmentation with Weighted Local Transformations
2025
(Sep) [Upcoming] Starting a postdoctoral position at KAIST (InnoCORE Postdoctoral Fellowship).
(Jun) Our paper (Representation Shift) got accepted to ICCV 2025!
(May) Served as a Program Committee member for the MICCAI 3rd International Workshop on Foundation Models for General Medical AI.
(Apr) Hit the 300 citations milestone on Google Scholar!
(Feb) Our paper (EfficientViM) got accepted to CVPR 2025!
2024
(Aug) Received the Outstanding Paper Award @ Korea Univ.
(May) Served as a Program Committee member for the MICCAI 2nd International Workshop on Foundation Models for General Medical AI.
(Mar) Invited talk on Token Reductions for Efficient Vision Transformers at Naver AI Lab (Naver 1784).
(Feb) Our papers (MCTF, vid-TLDR) got accepted to CVPR 2024! (Travel Award)
2023
(Aug) Invited poster presentation of SageMix at KCCV 2023.
(Jul) Our paper (RPO) got accepted to ICCV 2023!
(Feb) Invited talk and tutorial on 3D Point Cloud and Transformer at Korean Computer Vision Society (KCVS) Workshop.
(Feb) Our paper (SPoTr) got accepted to CVPR 2023!
2022
(Sep) Our paper (SageMix) got accepted to NeurIPS 2022. (Travel Award)
(Aug) Invited poster presentation of PointWOLF at KCCV 2022.
2021
(Jul) Our paper (PointWOLF) got accepted to ICCV 2021.