Publications

Google Scholar DBLP OpenReview

* Equal contribution. C: Conference, J: Journal, P: Pre-print, U: Under Review.

Working papers

SuperClip Pyramid for Video Temporal Grounding

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

Under review w/ KT Gen AI Lab

HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG

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

Under review w/ Amazon Alexa AI

Fate: A Faithful Audio-Visual Question Answering Benchmark Through Modality-Specific Temporal Grounding

Jun Hyung Park*, Seungmin Yun*, Sanghyeok Lee, Injae Kim, Joonmyung Choi, Hyunwoo J. Kim

Under review w/ KT Gen AI Lab

Hysteresis Parallel Decoding for Diffusion Large Language Models

Sehyung Kim, Mujin Shin, Sanghyeok Lee, Jihwna Park, Sungsik Cho, Sungwook Choi, Hyunwoo J. Kim

Under review w/ Hyundai Mobis

VideoGPS: Navigating an Agent-Readable Video Map for Long-Video QA

Seohyun Lee, Joonmyung Choi, Seoung Choi, Jonathan Minho Chung, Chaehyeon Kim, Sanghyeok Lee, Noori Kim, Heera Kim, Hyunwoo J. Kim

Under review w/ Hanwha Vision

2026

C12

DocPrune: Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning

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

CVPR 2026 w/ Adobe Research

C11

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

CVPR 2026

Code

C10

Transferable Model-agnostic Adaptation for Enhancing Vision-Language Models without Backpropagation

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

AAAI 2026 Oral Presentation

Code

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

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

AAAI 2026 w/ Google Cloud AI

Code

Parameter-Efficient Fine-Tuning via Meta-Regularizer

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

International Journal of Computer Vision, 2026 Impact Factor: 9.3

2025

Representation Shift: Unifying Token Compression with FlashAttention

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

ICCV 2025 w/ Adobe Research

Code

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

Sanghyeok Lee, Joonmyung Choi, Hyunwoo J. Kim

CVPR 2025

Code

2024

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

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

CVPR 2024

Code

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

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

CVPR 2024

Code

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

Code

2023

Read-only Prompt Optimization for Vision-Language Few-shot Learning

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

ICCV 2023

Code

Self-positioning Point-based Transformer for Point Cloud Understanding

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

CVPR 2023 w/ Meta Reality Labs

Code

2022

SageMix: Saliency-Guided Mixup for Point Clouds

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

NeurIPS 2022 w/ Meta Reality Labs

Code

2021

Point Cloud Augmentation with Weighted Local Transformations

Sihyeon Kim*, Sanghyeok Lee*, Dasol Hwang, Jaewon Lee, Seong Jae Hwang, Hyunwoo J. Kim

ICCV 2021 w/ University of Pittsburgh

Code