Jaeseok Byun
Jaeseok Byun
Ph.D student at Seoul National University
(M.IN.D lab , Advisor : Taesup Moon)
wotjr3868 [at] snu.ac.kr
Google Scholar | Github | Linkedin
I'm a graduate research assistant working towards developing practical AI algorithms in resource-constrained systems. I have previously worked as a research intern at Amazon AGI and Microsoft Research Asia, and as a visiting student researcher at Stanford University. My primary research focus lies in the image denoising and multi-modal representation learning.
Backward Compatible Embedding Adapters for Multimodal Large Language Models.
Jaeseok Byun, Gukyeong Kwon, Han-Kai Hsu, Meher Gitika Karumuri, Zhikang Zhang, Hao Yang, and Davide Modolo.
Preprint, 2026. (Work done during internship)
Region-Aware Text-to-Image Retrieval with Efficient Region-Informed Sequential Query Embedding
Seokhyeon Jeong*, Jaeseok Byun*, Paul Hongsuck Seo, and Taesup Moon. (*: Equal Contribution)
Preprint, 2025.
Efficient and Robust SEM Image Denoising for Wafer Defect Inspection
Hyungwoong Bae, Jaeseok Byun, Yongwoo Lee, and Taesup Moon.
Microscropy and Microanalysis, 2025.
MA-CIR: Multi-modal Arithmetic Benchmarks for Composed Image Retrieval
Jaeseok Byun, Youngkyun Jang, Seokhyeon Jeong, Donghyun Kim, and Taesup Moon.
ICCV, 2025.
RTD: Reducing Task Discrepancy of Text Encoders for Zero-Shot Composed Image Retrieval
Jaeseok Byun*, Seokhyeon Jeong*, Wonjae Kim, Sanghyuk Chun, and Taesup Moon. (*: Equal Contribution)
ICCV, 2025.
MAFA: Managing False Negatives for Vision-Language Pre-training
Jaeseok Byun*, Dohoon Kim*, and Taesup Moon. (*: Equal Contribution)
CVPR, 2024.
GRIT-VLP: Grouped Mini-batch Sampling for Vision-Language Pre-training
Jaeseok Byun*, Taebaek Hwang*, Jianlong Fu, and Taesup Moon. (*: Equal Contribution)
ECCV, 2022.
FBI-Denoiser: Fast Blind Image Denoiser for Source-Dependent Noise.
Jaeseok Byun*, Sungmin Cha*, and Taesup Moon. (*: Equal Contribution)
CVPR, 2021. (Oral Presentation)
Learning Blind Pixelwise Affine Image Denoiser with Single Noisy Images
Jaeseok Byun and Taesup Moon
IEEE Signal Processing Letters (SPL, IF=3.268), 2020.
Applied Scientist Intern, Amazon AGI [2025.09 ~ 2025.12] (Manager: Davide Modolo, Mentor: Gukyeong Kwon)
Visiting Student Researcher, Stanford [2025.02 ~ 2025.08] (Mentor: Tsachy Weissman)
Research Intern, Microsoft Research Asia [2021.10 ~ 2022.05] (Mentor: Jianlong Fu)
Intern, SKT Data Analytics COE [2018.01 ~ 2018.02] (Mentor: Sehoon Lee)
Intern, MISO(O2O platform Start-up) [2017.07 ~ 2017.08]
Military Service [2014.07 ~ 2016.07]
CVPR 2025 Outstanding Reviewer [05.2025]
SBS foundation scholarship [06.2022 ~ Present]
Stars of tomorrow of Excellence in MSRA internship [05.2022]
Future Gauss Lecturer from Gauss Labs [02.2022]
Big Contest Challenge League, Second Prize [2017.11]
Institute of Applied Statistics in SKKU, First Prize [2017.02]
Wooseok Jungho Scholarship [2016.09~2019.06]
ICML 2023-2025, NeurIPS 2023-2025, EMNLP 2023, ICLR 2024-2026, CVPR 2024-2026, ICCV 2025, ECCV 2026, TMLR 2024-2026, AAAI 2024-2026
President, Statistical Analysis study club, SKKU [2016.09 ~ 2017.12]