Gihyun Kwon

Download CV

e-mail

Google Scholar

Gihyun Kwon

Ph.D. candidate in KAIST

Dept. of Bio & Brain Engineering

advised by Professor Jong Chul Ye

@ KAIST AI BISPL

prev. Research Intern @ Adobe

Education

Ph. D. in Bio & Brain Engineering

Korea Advanced Institute of Science and Technology (KAIST), 2020-present

M.S. in Electrical Engineering

Korea Advanced Institute of Science and Technology (KAIST), 2018-2020

B.S. in Electronic Engineering

Hanyang University, 2014-2018

Publication

Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models

Gihyun Kwon, Simon Jenni, Joon-young Lee, Jong Chul Ye, Fabian Caba Heilbron

IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR 2024)

[To appear]

Contrastive Denoising Score for Text-guided Latent Diffusion Image Editing

Hyelin Nam, Gihyun Kwon, Geon Yeong Park, Jong Chul Ye

IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR 2024)

[Arxiv]

ED-NeRF: Efficient Text-guided Editing of 3D Scene using Latent Space NeRF

Jangho Park*, Gihyun Kwon*, Jong Chul Ye (co-fist authors)

The Twelfth International Conference on Learning Representations (ICLR 2024)

[Arxiv]

Unpaired Image-to-Image Translation via Neural Schrödinger Bridge

Beomsu Kim*, Gihyun Kwon*, Kwanyoung Kim, Jong Chul Ye (co-fist authors)

The Twelfth International Conference on Learning Representations (ICLR 2024)

[Arxiv] [Github]

Patch-wise Graph Contrastive Learning for Image Translation

Chanyong Jung, Gihyun Kwon, Jong Chul Ye

Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI 2024)

[Arxiv]

One-Shot Adaptation of GAN in Just One CLIP

Gihyun Kwon, Jong Chul Ye

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023

[Arxiv] [Github] [IEEE]

Diffusion-based Image Translation using Disentangled Style and Content Representation

Gihyun Kwon, Jong Chul Ye

The Eleventh International Conference on Learning Representations, ICLR 2023

[Arxiv] [Github]

CLIPstyler: Image Style Transfer with a Single Text Condition

Gihyun Kwon, Jong Chul Ye

IEEE/CVF Conference on Computer Vision and Pattern Recognition , CVPR 2022

[CVF] [Arxiv] [Github] [Demo]

Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks

Chanyong Jung*, Gihyun Kwon*, Jong Chul Ye ( *co-first authors)

IEEE/CVF Conference on Computer Vision and Pattern Recognition , CVPR 2022

[CVF] [Arxiv] [Github]

Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation

Gihyun Kwon, Jong Chul Ye

IEEE/CVF International Conference on Computer Vision , ICCV 2021

[CVF] [Arxiv] [Github]

Generation of 3D brain MRI using auto-encoding generative adversarial networks

Gihyun Kwon, Chihye Han, Dae-shik Kim

International Conference on Medical Image Computing and Computer-Assisted Intervention , MICCAI 2019

[Arxiv] [Springer] [Github]

Progressive face super-resolution via attention to facial landmark

Deokyun Kim*, Minseon Kim*, Gihyun Kwon*, Dae-shik Kim ( *co-first authors)

British Machine Vision Conference , BMVC 2019

[Arxiv] [Github]

Representation of white-and black-box adversarial examples in deep neural networks and humans: A functional magnetic resonance imaging study

Chihye Han, Wonjun Yoon, Gihyun Kwon, Daeshik Kim, Seungkyu Nam

International Joint Conference on Neural Networks , IJCNN 2019

[Arxiv]

Preprint

Improving Diffusion-based Image Translation using Asymmetric Gradient Guidance

Gihyun Kwon, Jong Chul Ye

Arxiv, 2023

[Arxiv] [Github]

Zero-shot Generation of Coherent Storybook from Plain Text Story using Diffusion Models

Hyeonho Jeong, Gihyun Kwon, Jong Chul Ye

Arxiv, 2023

[Arxiv]

Research Experiences

Research Intern at Leiden University Medical Center, Leiden, The Netherlands, “Development of Deep-learning Model for the diagnosis of Neuropsychiatric Systemic Lupus Erythematosus (NP-SLE)” (Jun. 2019 ~ Aug. 2019)
Research Intern at Adobe Inc, San Jose, United States, “Development of multi-concept personalization for story scene generation using Diffusion Models” (Jul. 2023 ~ Sep. 2023)

Awards and Honors

Graduation with honors : SUMMA CUM LAUDE & Dean’s Award, Hanyang University (2018)
Full Scholarships at Hanyang University
1 st place in Graduation Portfolio Competition “VITNESS: An Exercise Assistance Android Application Using Image Processing”, Hanyang University (2017)

Project Experiences

Development of AI-based X-Ray CBT program- Field-oriented Technology Development Project for Customs Administration, Ministry of Science & ICT and Korea Customs Service, Korea (2021.07~ present )
Study on Mechanism of Light Therapy through fMRI Data of Normal Subjects and Deep Learning Structure Design for Brain fMRI Data Analysis, Attachable Photo Therapeutics Center for e-Healthcare, ERC, Korea (2018 ~ 2020)

Patents

Gihyun Kwon, Jong Chul Ye, " Generation of X-ray baggage images using Latent Diffusion Model for training agents", Korea-Application No. 10-2022-0182431 (Patent Pending)
Gihyun Kwon, Jong Chul Ye, " Image Style Transfer with a Single Text Condition", Korea-Application No. 10-2021-0167844 (Patent Pending)
D.Kim, H.Lee, H.Choi, S.Koo, I.Kim, G.Park, S.Cho, M.Kim, G.Kwon, D.Kim, H.Lee, "Material solvent proposal program using artificial intelligence", Korea- Application No.10-2019-0068182 (Patent Pending)

Reviewer Experiences

Top-tier Machine Learning Conferences : CVPR (2021, 2022, 2023, 2024), ECCV(2022, 2024), ICCV(2023), NeurIPS(2023), ICML(2024)
Journals : Transactions on Medical Imaging(2020,2021), Medical Image Analysis(2021), Transactions on Graphics(2022) ,Transactions on Pattern Analysis and Machine Intelligence(TPAMI) (2022,2023,2024)