Ph.D. candidate in the Department of Computer Science at Korea University under the supervision of Prof. Hyunwoo J. Kim. The PDF version of the CV is available at the following link.
Research Interests: Efficient Deep Learning, Efficient Adaptation, Computer Vision, 3D Vision, Multi-modal Learning, Point Clouds
B.S. (Mar 2016 ~ Sep 2020)
Bachelor of Science, Computer Science and Engineering at Korea University
GPA: 4.02 / 4.50 (94.5/100)
Ph.D. (Sep 2020 ~ Present)
M.S. & Ph.D. integrated program in Computer Science and Engineering at Korea University. (Advisor: Hyunwoo J. Kim)
GPA : 4.24 / 4.50 (97.0 / 100)
Teaching Fellow: COSE474 (Deep Learning, 2020)
Teaching Assitant: COSE361 (Artificial Intelligence, 2021-2022)
2025
[C7] EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
Conference on Computer Vision and Pattern Recognition (CVPR), 2025
Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim
[U] Transferable Model-agnostic Vision-Language Model Adaptation for Efficient Weak-to-Strong Generalization
under review, 2025
Jihwan Park, Taehoon song, Sanghyeok Lee, Miso Choi, Hyunwoo J. Kim
[U] Representation Shift: Unifying Token Compression with FlashAttention
under review, 2025
Joonmyung Choi*, Sanghyeok Lee*, Byungoh Ko, Eunseo Kim, Jihyung Kil, Hyunwoo J. Kim
2024
[C6] vid-TLDR: Training Free Token merging for Light-weight Video Transformer
Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Joonmyung Choi*, Sanghyeok Lee*, Jaewon Chu, Minhyuk Choi, Hyunwoo J. Kim
[C5] Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision
Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Sanghyeok Lee*, Joonmyung Choi*, Hyunwoo J. Kim
arxiv preprint, 2024
Juhan Cha*, Minseok Joo*, Jihwan Park, Sanghyeok Lee, Injae Kim, Hyunwoo J. Kim
2023
[C4] Read-only Prompt Optimization for Vision-Language Few-shot Learning
International Conference on Computer Vision (ICCV), 2023
DongJun Lee*, Seokwon Song*, Jihee Suh, Joonmyung Choi, Sanghyeok Lee, Hyunwoo J. Kim
[C3] Self-positioning Point-based Transformer for Point Cloud Understanding
Conference on Computer Vision and Pattern Recognition (CVPR), 2023
Jinyoung Park*, Sanghyeok Lee*, Sihyeon Kim, Yunyang Xiong, Hyunwoo J. Kim
2022
[C2] SageMix: Saliency-Guided Mixup for Point Clouds
Conference on Neural Information Processing Systems (NeurIPS), 2022
Sanghyeok Lee*, Minkyu Jeon*, Injae Kim, Yunyang Xiong, Hyunwoo J. Kim
2021
[C1] Point Cloud Augmentation with Weighted Local Transformations
International Conference on Computer Vision (ICCV), 2021
Sihyeon Kim*, Sanghyeok Lee*, Dasol Hwang, Jaewon Lee, Seong Jae Hwang, Hyunwoo J. Kim
Machine Learning & Vision Lab (MLV Lab) (Sep 2020 ~ Present)
Graduate Student Researcher
Ph.D. candidate in the Department of Computer Sciences at Korea University, advised by Dr. Hyunwoo J. Kim
Projects
Media Content Summarization through Video Understanding (Aug 2024 - Present)
Collaboration with KT Gen AI Lab, Vision AI Team
Video Summarization, Video Understanding, Efficient DL, MMLM
Blood Image Analysis for the Diagnosis of Infectious Diseases and Blood Cancers (Jul 2022 - Present)
Collaboration with Korea University Guro Hospital (Prof. Chaesung Lim)
Object Detection, Medical Imaging
3D Registration for Multiplex Imaging (Jul 2022 - Mar 2023)
Collaboration with the College of Medicine at Korea University (Prof. Woong Sun)
Alignment & registration in 2D & 3D, Medical imaging
AI Diagnostic System for Orthodontics (Feb 2020 - Nov 2021)
Project leader for an automated diagnosis software for a 3D dental model (Mylign)
3D classification, 3D object detection, 3D alignment, Medical imaging
Drone Laps (May 2021 ~ Dec 2021)
Initial Team Member
Early-stage startup for Drone-Based Autonomous Maintenance Service
Sponsored by the Korea Ministry of Science and ICT ($ 70,000)
Market research, Business model design
[P4] Biosensor for LAMP product detection in LAMP analysis
Chaeseung Lim, Woongsik Jang, Minkyeong Choi, Seoyeon Park, Hyunwoo J. Kim, Sanghyeok Lee, Injae Kime
Korean Patent (10-2024-0168968), filed on Nov 22, 2024.
[P3] 3D DATA AUGMENTATION METHOD USING WEIGHTED LOCAL TRANSFORMATION AND APPARATUS THEREFORE
Hyunwoo J. Kim, Sihyeon Kim, Sanghyeok Lee, Jinyoung Park
Korean Patent (10-2636217), registered on Feb 07, 2024.
[P2] METHOD FOR GENERATING HIGH QUALITY VIDEO WITH PROFESSIONAL FILMING TECHNIQUES THROUGH DEEP LEARNING TECHNOLOGY BASED 3D SPACE MODELING AND POINT-OF-VIEW SYNTHESIS AND APPARATUS FOR SAME
Hyunwoo J. Kim, Sihyeon Kim, Jooyeon Kim, Sanghyeok Lee
Korean Patent (10-2593135), registered on Oct 19, 2023.
[P1] METHOD AND APPARATUS FOR READ-ONLY PROMPT LEARNING
Hyunwoo J. Kim, Jinyoung Park, Joonmyung Choi, Sanghyeok Lee, Dongjun Lee, Seokwon Song, Jihee Suh
Korean Patent (10-2563550), registered on Aug 7, 2023.
[C1] EfficientViM (Efficient Vision Mamba for Computer Vision)
Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim
Korean Computer Program Copyright (C-2024-055621), registered on Dec 26, 2024.
[2] Token Reductions for Efficient Vision Transformers
Invited talk @ Naver AI Lab (Naver 1784), Mar 2024
[1] 3D Point Cloud and Transformer
Invited talk / Tutorial @ Korean Computer Vision Society (KCVS) Workshop, Feb 2023
Outstanding Paper Award @ Korea Univ. 2024
Travel Awards @ CVPR. 2024
Travel Awards @ NeurIPS. 2022
Research Grants @ Brain Korea 21(BK21). 2021, 2022
Future Research Fellowship @ Brain Korea 21(BK21). 2021, 2022
Teaching Assistantship @ Korea Univ. 2021,2022
Teaching Fellowship @ Korea Univ. 2020
Scholarship @ Korea Univ. 2016,2017,2018,2019,2020
Program Committee @ MICCAI 2024 2nd International Workshop on Foundation Models for General Medical AI (MedAGI)
Reviewer @ Computer Vision and Pattern Recognition (CVPR)
Reviewer @ Advances in Neural Information Processing Systems (NeurIPS)
Reviewer @ European Conference on Computer Vision (ECCV)
Reviewer @ International Conference on Computer Vision (ICCV)
Reviewer @ IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
Reviewer @ IEEE Transactions on Multimedia (TMM)
Reviewer @ IEEE Transactions on Image Processing (TIP)
Reviewer @ ACM Multimedia (ACMMM)
2024-2025
2023-2025
2023,2025
2024
2025
2024
2024-2025
2024
2025