[C8]  Representation Shift: Unifying Token Compression with FlashAttention
International Conference on Computer Vision (ICCV), 2025

• Joonmyung Choi*, Sanghyeok Lee*, Byungoh Ko, Eunseo Kim, Jihyung Kil, Hyunwoo J. Kim

[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

[J1] Parameter-Efficient Fine-Tuning via Meta-Regularizer
International Journal of Computer Vision (IJCV), 2025

• Jinyoung Park, Juyeon Ko, 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] SuperClip Pyramid with Positional Parameterization for Video Temporal Grounding
under review, 2025

• Sanghyeok Lee, Juyeon Ko, Joonmyung Choi, Jongha Kim, Hyunwoo J. Kim

[U] TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token Focusing
under review, 2025

• Jongha Kim, Minseong Bae, Sanghyeok Lee, Jinsung Yoon, 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 Transformers

Conference on Computer Vision and Pattern Recognition (CVPR), 2024

• Sanghyeok Lee*, Joonmyung Choi*, Hyunwoo J. Kim

[P] Robust Multimodal 3D Object Detection via Modality-Agnostic Decoding and Proximity-based Modality Ensemble

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

Graduate Student Researcher @ Korea University (Machine Learning & Vision Lab)

Sep 2020 - Aug 2025

Projects:

1. Media Content Summarization through Video Understanding (Aug 2024 - Jul 2025)

   • Project Lead, Funded by KT, Collaboration with KT Gen AI Lab, Vision AI Team.

   • Developed video temporal grounding and LLM-based end-to-end video summarization models.

2. Blood Image Analysis for the Diagnosis of Infectious Diseases and Blood Cancers (Jul 2022 - Dec 2024)

   • Project lead, Funded by the Korea Health Industry Development Institute (KHIDI).

   • Developed malaria-infected sample classification and infected cell detection models with diverse blood image modalities (bright-field, Giemsa-stained, fluorescence, and LAMP-MS assay images)

3. Developing a Deep Learning–based Program for Tooth Axis Identification and Automated Orthodontic Set-Ups (Feb 2020 - Nov 2021)

   • Project Lead, Funded by the Korea Technology and Information Promotion Agency for SMEs (TIPA).

   • Developed 3D teeth classification and object detection models, and a 3D alignment system for automated tooth axis set-up.