Hyungjin Chung

About Me

I am a Lead AI Research Scientist at EverEx. Before joining EverEx, I did my Ph.D. at KAIST where I was advised by Jong Chul Ye. During my Ph.D., I also spent my time as a research intern at NVIDIA Research, Google Research, and Los Alamos National Laboratory. I pioneered and advanced some of the most widely acknowledged works on diffusion model-based inverse problem solvers. I’m interested broadly in the intersection of generative models, imaging, multimodality, and their applications to real-world problems.

I am looking for highly motivated researchers to work with me at EverEx for pushing the boundaries of video understanding LLMs. If you are interested, send me an email with your CV attached.

News

[2025.03] 3 papers (SteerX, VideoRFSplat, CapeLLM) are accepted to ICCV 2025.
[2025.03] A paper (FreeMCG) is accepted to CVPR 2025.
[2025.02] CFG++ is awarded Silver prize in 31st Samsung Humantech Paper Award.
[2025.01] Two papers (CFG++,TReg) are accepted to ICLR 2025.
[2024.11] Defended my Ph.D. thesis! (Title: Practical approximations of posterior sampling in diffusion model-based inverse problems)

Publications

ICCV

SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering

Byeongjun Park*, Hyojun Go*, Hyelin Nam, Byung-Hoon Kim Hyungjin Chung+, Changick Kim+

IEEE/CVF International Conference on Computer Vision, 2025.

PDF Code Project Page

ICCV

VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling

Hyojun Go*, Byeongjun Park*, Hyelin Nam, Byung-Hoon Kim Hyungjin Chung+, Changick Kim+

IEEE/CVF International Conference on Computer Vision, 2025.

PDF Code Project Page

ICCV

CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models

Junho Kim, Hyungjin Chung+, Byung-Hoon Kim+

IEEE/CVF International Conference on Computer Vision, 2025.

PDF

CVPR

Derivative-Free Diffusion Manifold-Constrained Gradient for Unified XAI

Won Jun Kim*, Hyungjin Chung*, Jaemin Kim*, Sangmin Lee, Byeongsu Sim, Jong Chul Ye

IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025.

PDF

ICLR

CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models

Hyungjin Chung*, Jeongsol Kim*, Geon Yeong Park*, Hyelin Nam*, Jong Chul Ye

International Conference on Learning Representations, 2025.

PDF Code Project Page Silver prize, 31st Samsung Humantech Paper Award

ICLR

Regularization by texts for latent diffusion inverse solvers

Jeongsol Kim*, Geon Yeong Park*, Hyungjin Chung, Jong Chul Ye

International Conference on Learning Representations, 2025.

PDF Code Project Page Spotlight presentation

IEEE TMI

Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image Reconstruction

Riccardo Barbano*, Alexander Denker*, Hyungjin Chung*, Tae Hoon Roh, Simon Arrdige, Peter Maass, Bangti Jin, Jong Chul Ye

IEEE Transactions on Medical Imaging, 2025.

PDF Code

IEEE JBHI

Fundus image enhancement through direct diffusion bridges

Sehui Kim*, Hyungjin Chung*, Se Hie Park, Eui-Sang Chung, Kayoung Yi, Jong Chul Ye

IEEE Journal of Biomedical and Health Informatics, 2024.

PDF Code

ECCV

Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problems

Hyungjin Chung, Jong Chul Ye

European Conference on Computer Vision, 2024.

PDF Code Gold prize, 30th Samsung Humantech Paper Award

ICML

Prompt-tuning Latent Diffusion Models for Inverse Problems

Hyungjin Chung, Jong Chul Ye, Peyman Milanfar, Mauricio Delbracio

International Conference on Machine Learning, 2024.

PDF

ICLR

Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems

Hyungjin Chung, Suhyeon Lee, Jong Chul Ye

International Conference on Learning Representations, 2024.

PDF Code

ICCV

Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models

Suhyeon Lee*, Hyungjin Chung*, Minyoung Park, Jonghyuk Park, Wi-Sun Ryu, Jong Chul Ye

IEEE/CVF International Conference on Computer Vision, 2023.

PDF Code

CVPR

Parallel Diffusion Models of Operator and Image for Blind Inverse Problems

Hyungjin Chung*, Jeongsol Kim*, Sehui Kim, Jong Chul Ye

IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023.

PDF Code Project Page Video

CVPR

Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models

Hyungjin Chung*, Dohoon Ryu*, Michael T. Mccann, Marc L. Klasky, Jong Chul Ye

IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023.

PDF Code Video

ICLR

Diffusion Posterior Sampling for General Noisy Inverse Problems

Hyungjin Chung*, Jeongsol Kim*, Michael T. Mccann, Marc L. Klasky, Jong Chul Ye

International Conference on Learning Representations, 2023.

PDF Code Project Page Spotlight; Gold prize, 29th Samsung Humantech Paper Award

NeurIPS

Improving Diffusion Models for Inverse Problems using Manifold Constraints

Hyungjin Chung*, Byeongsu Sim*, Dohoon Ryu, Jong Chul Ye

Advances in Neural Information Processing Systems, 2022.

PDF Code

CVPR

Come-Closer-Diffuse-Faster Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction

Hyungjin Chung, Byeongsu Sim, Jong Chul Ye

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

PDF

IEEE TMI

MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion

Hyungjin Chung, Eun Sun Lee, Jong Chul Ye

IEEE Transactions on Medical Imaging, 2022.

PDF

MeDIA

Score-based diffusion models for accelerated MRI

Hyungjin Chung, Jong Chul Ye

Medical Image Analysis, 2022.

PDF Code

ACS Nano

Low-dose sparse-view HAADF-STEM-EDX tomography of nanocrystals using unsupervised deep learning

Eunju Cha*, Hyungjin Chung*, Jaeduck Jang, Junho Lee, Eunha Lee, Jong Chul Ye

ACS Nano, 2022.

PDF

Deep Learning Model for Diagnosing Gastric Mucosal Lesions Using Endoscopic Images: Development, Validation, and Method Comparison

Joon Yeul Nam*, Hyungjin Chung*, Kyu Sung Choi* Hyuk Lee*, Seung Jun Han*, Tae Jun Kim, Hosim Soh, Eun Kang, Soo_jeong Cho, Jong Chul Ye, Jong Pil Im, Sang Gyun Kim, Yoon Jun Kim, Joo Sung Kim, Jung-Hwan Yoo, Hyunsoo Chung, Jeong-Hoon Lee

Gastrointestinal Endoscopy, 2021.

PDF

Nat. Mach. Intell.

Deep learning STEM-EDX tomography of nanocrystals

Yoseob Han*, Jaeduck Jang*, Eunju Cha*, Junho Lee*, Hyungjin Chung*, Myoungho Jeong, Tae-Gon Kim, Byeong Gyu Chae, Hee Goo Kim, Shinae Jun, Sungwoo Hwang, Eunha Lee, Jong Chul Ye

Nature Machine Intelligence, 2021.

PDF Code 2021 March Issue Cover

Nat. Mach. Intell.

Reusability report: Feature disentanglement in generating a three-dimensional structure from a two-dimensional slice with sliceGAN

Hyungjin Chung, Jong Chul Ye

Nature Machine Intelligence, 2021.

PDF Code

Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement

Mehmet Akcakaya, Burhaneddin Yaman, Hyungjin Chung, Jong Chul Ye

IEEE Signal Processing Magazine, 2021.

PDF

MeDIA

Two-Stage Deep Learning for Accelerated 3D Time-of-Flight MRA without Matched Training Data

Hyungjin Chung, Eunju Cha, Leonard Sunwoo, Jong Chul Ye

Medical Image Analysis, 2020.

PDF

IEEE TCI

Missing Cone Artifacts Removal in ODT using Unsupervised Deep Learning in Projection Domain

Hyungjin Chung, Jaeyoung Huh, Geon Kim, Yong Keun Park, Jong Chul Ye

IEEE Transactions on Computational Imaging, 2020.

PDF

Unpaired training of deep learning tMRA for flexible spatio-temporal resolution

Gyutaek Oh, Byeongsu Sim, Hyungjin Chung, Leonard Sunwoo, Jong Chul Ye

IEEE Transactions on Computational Imaging, 2020.

PDF

Unpaired training of deep learning tMRA for flexible spatio-temporal resolution

Eunju Cha, Hyungjin Chung, Eung Yeop Kim, Jong Chul Ye

IEEE Transactions on Medical Imaging, 2020.

PDF