[C10] TransMiter: Transferable Model-agnostic Adaptation for Enhancing Vision-Language Models without Backpropagation

Jihwan Park, Taehoon song, Sanghyeok Lee, Miso Choi, Hyunwoo J. Kim 

AAAI Conference on Artificial Intelligence (AAAI), 2026  (Oral Presentation)

[C9] TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token Focusing

Jongha Kim, Minseong Bae, Sanghyeok Lee, Jinsung Yoon, Hyunwoo J. Kim

AAAI Conference on Artificial Intelligence (AAAI), 2026

2025

[C8] Representation Shift: Unifying Token Compression with FlashAttention

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

International Conference on Computer Vision (ICCV), 2025

Collaboration with Adobe Research

[C7] EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality

Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim

Conference on Computer Vision and Pattern Recognition (CVPR), 2025

[J1] Parameter-Efficient Fine-Tuning via Meta-Regularizer

Jinyoung Park, Juyeon Ko, Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim

International Journal of Computer Vision (IJCV), 2025. (Impact Factor:9.3)

[U] GraphEvo-R1: Graph Evolution with Reinforcement Learning for Retrieval Augmented Generation

Jinyoung Park, Sanghyeok Lee, Omar Zia Khan, Hyunwoo J. Kim, Joo-Kyung Kim

under review

Collaboration with Amazon

[U] SuperClip Pyramid with Positional Parameterization for Video Temporal Grounding

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

under review

Collaboration with KT Gen AI Lab

[U] DocPrune : Understanding Document Layouts for Efficient Token Compression in Question Answering

Joonmyung Choi, Sanghyeok Lee, Jongha Kim, Sehyung Kim, Dohwan Ko, Jihyung Kil, Hyunwoo J. Kim

under review

Collaboration with Adobe Research

[U] MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models

Dohwan Ko, Jinyoung Park, Seoung Choi, Sanghyeok Lee, Seohyun Lee, Hyunwoo J. Kim

under review

2024

[C6] vid-TLDR: Training Free Token merging for Light-weight Video Transformer

Joonmyung Choi*, Sanghyeok Lee*, Jaewon Chu, Minhyuk Choi, Hyunwoo J. Kim

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

[C5] Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers

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

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

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

Juhan Cha*, Minseok Joo*, Jihwan Park, Sanghyeok Lee, Injae Kim, Hyunwoo J. Kim

arxiv preprint

2023

[C4] Read-only Prompt Optimization for Vision-Language Few-shot Learning

DongJun Lee*, Seokwon Song*, Jihee Suh, Joonmyung Choi, Sanghyeok Lee, Hyunwoo J. Kim

International Conference on Computer Vision (ICCV), 2023

[C3] Self-positioning Point-based Transformer for Point Cloud Understanding

Jinyoung Park*, Sanghyeok Lee*, Sihyeon Kim, Yunyang Xiong, Hyunwoo J. Kim

Conference on Computer Vision and Pattern Recognition (CVPR), 2023

Collaboration with Meta Reality Labs

2022

[C2] SageMix: Saliency-Guided Mixup for Point Clouds

Sanghyeok Lee*, Minkyu Jeon*, Injae Kim, Yunyang Xiong, Hyunwoo J. Kim

Conference on Neural Information Processing Systems (NeurIPS), 2022

Collaboration with Meta Reality Labs

2021