Jaehyun Choi

chlwogusatkaistdotacdotkr

About

I am a Ph.D. student at the SIIT Lab at KAIST, supervised by Prof. Junmo Kim, interested in distribution matching (dataset condensation and domain adaptation / generalization) and generative models. During my M.S., I was a member of the VC Lab at SKKU, supervised by Prof. Jae-Pil Heo. I am actively seeking internship opportunities to apply my research in practical settings and contribute to innovative AI projects.

Publications | Conference(C), Workshop(W), Journal(J), Preprint(P), Equal Contribution(*)

2025

[C13]

AH-OCDA: Amplitude-based Curriculum Learning and Hopfield Segmentation Model for Open Compound Domain Adaptation

Jaehyun Choi*, Junwon Ko*, Dong-Jae Lee*, Junmo Kim

WACV 2025 | [Paper]

2024

[C12]

Self-supervised Transformation Learning for Equivariant Representations

Jaemyung Yu, Jaehyun Choi, Dong-Jae Lee, HyeongGwon Hong, Junmo Kim

NeurIPS 2024 | [Paper] | [Code] | [Project Page]

[C11]

Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance

Jiwan Hur, Dong-Jae Lee, Gyojin Han, Jaehyun Choi, Junmo Kim

NeurIPS 2024 (Bronze Prize - Samsung HumanTech Paper Awards) | [Paper] | [Code]

[W3]

PSGMM: Pulmonary Segment Segmentation Based on Gaussian Mixture Model

Seunghee Koh, Chanho Lee, Jae Young Lee, Jaehyun Choi, Youngno Yoon, Changyoung Lee, Junmo Kim

Workshop on Shape in Medical Imaging @ MICAAI 2024 | [Paper]

[C10]

Learning Neural Deformation Representation for 4D Dynamic Shape Generation

Gyojin Han, Jiwan Hur, Jaehyun Choi, Junmo Kim

ECCV 2024 | [Paper]

[C9]

Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency

Woonghyun Ka*, Jae Young Lee*, Jaehyun Choi, Junmo Kim

ICASSP 2024 | [Paper]

[C8]

Modeling Stereo-Confidence Out of the End-to-End Stereo-Matching Network via Disparity Plane Sweep

Jae Young Lee*, Woonghyun Ka*, Jaehyun Choi, Junmo Kim

AAAI 2024 | [Paper] | [Code]

[C7]

Expanding Expressiveness of Diffusion Models with Limited Data via Self-Distillation based Fine-Tuning

Jiwan Hur, Jaehyun Choi, Gyojin Han, Dong-Jae Lee, Junmo Kim

WACV 2024 | [Paper] | [Code]

2023

[C6]

Few-Shot Anomaly Detection with Adversarial Loss for Robust Feature Representation

Jae Young Lee, Wonjun Lee, Jaehyun Choi, Yongkwi Lee, Young Seog Yoon

BMVC 2023 | [Paper]

[J3]

TCX: Texture and Channel Swappings for Domain Generalization

Jaehyun Choi, Hyun Seok Seong, Sang Uk Park, Jae-Pil Heo

Pattern Recognition Letters (Impact Factor: 5.1) | [Paper]

[C5/W2]

Data Poisoning Attack Aiming the Vulnerability of Continual Learning

Gyojin Han*, Jaehyun Choi*, Hyeong Gwon Hong, Junmo Kim

ICIP 2023 (ML Safety@NeurIPS'22) | [Paper]

[C4]

Deep Cross-Modal Steganography using Neural Representations

Gyojin Han, Dong-Jae Lee, Jiwan Hur, Jaehyun Choi, Junmo Kim

ICIP 2023 (Oral) | [Paper]

[J2]

Multi-Scale Foreground-Background Separation for Light Field Depth Estimation with Deep Convolutional Networks

Jae Young Lee, Jiwan Hur, Jaehyun Choi, Junmo Kim

Pattern Recognition Letters (Impact Factor: 5.1) | [Paper]

[C3]

Reinforcement Learning-Based Black-Box Model Inversion Attacks

Gyojin Han, Jaehyun Choi, Haeil Lee, Junmo Kim

CVPR 2023 | [Paper] | [Code]

[C2/W1]

Fix the Noise: Disentangling Source Feature for Controllable Domain Translation

Dongyeun Lee, Jae Young Lee, Doyeon Kim, Jaehyun Choi, Jaejun Yoo, Junmo Kim

CVPR 2023 (AI4CC@CVPR'22 - Best Paper Awards) | [Paper] | [Code]

[C1]

I See-Through You: A Framework for Removing Foreground Occlusion in Both Sparse and Dense Light Field Images

Jiwan Hur*, Jae Young Lee*, Jaehyun Choi, Junmo Kim

WACV 2023 | [Paper] | [Code]

2022

[J1]

Pivot-Guided Embedding for Domain Generalization

Hyun Seok Seong, Jaehyun Choi, Woojin Jeong, Jae-Pil Heo

IEEE Access (Impact Factor: 3.5) | [Paper] | [Code]

Pre-
print

[P9]

Gradient-Guided Temporal Densifying for Video Dataset Condensation

Jaehyun Choi, Jiwan Hur, Gyojin Han, Jaemyung Yu, Junmo Kim

[P8]

Prompt-based Layer-dependent Token Pruning for Efficient Vision Transformer

Deon-Jae Lee, Jiwan Hur, Jaehyun Choi, Jaemyung Yu, Junmo Kim

[P7]

Exploiting Domain Information for Dataset Condensation

Jaehyun Choi, Gyojin Han, Dong-Jae Lee, SungHyun Baek, Junmo Kim

[P6]

DDE: Efficient Continual Test Time Adaptation with Dynamic Domain Experts

SungHyun Baek, Jaehyun Choi, Jaemyung Yu, Seoyeon Gye, Minsu Kim, Hyeonseong Jeon, Junmo Kim

[P5]

Frequency-Aware Token Reducing for Efficient Vision Transformer

Dong-Jae Lee, Jiwan Hur, Jaemyung Yu, Jaehyun Choi, SungHyun Baek, Junmo Kim

[P4]

PSGMM++: Pulmonary Segment Segmentation with Anatomical Insights

Seunghee Koh, Chanho Lee, Jaehyun Choi, Jae Young Lee, Minseo Kim, Youngno Yoon, Changyoung Lee, Junmo Kim

[P3]

Unveiling Temporal Telltales: Are Unconditional Video Generation Models Implicitly Encoding Temporal Information?

Jaehyun Choi, Gyojin Han, Jiwan Hur, Jae Young Lee, Junmo Kim

[P2]

Boundary Recovering Network for Temporal Action Detection

Jihwan Kim, Jaehyun Choi, Yerim Jeon, Jae-Pil Heo

[P1]

FSOD-FBS: Light Field Salient Object Detection Based on Foreground-Background Separation with Deep Convolutional Network

Jae Young Lee, Jaehyun Choi, Sewhan Chun, Jongsuk Kim, Rae-Hong Park, Junmo Kim

Education

Ph.D. in Electrical Engineering @ KAIST (Korea Advanced Institute of Science and Technology)

Aug. 2021 - Present

M.S. in Artificial Intelligence @ SKKU (Sungkyunkwan University)

Aug. 2019 - Aug. 2021

B.S. in Electrical Engineering and Computer Science @ SUNY (State University of New York) at Buffalo

Aug. 2012 - Feb. 2019

Experience

Research Assistant @ ETRI (Electronics and Telecommunications Research Institute)

Aug. 2022 - Dec. 2022

Academic Services

Conference Reviewer

ICML: 2025

ICCV: 2025

ACM MM: 2025

NeurIPS: 2025

Honor & Awards

Bronze Prize, 31st Samsung HumanTech Paper Awards (Sponsored by Samsung)

Feb. 2025

Best Paper Award, Workshop on AI for Content Creation @ CVPR 2022 (Sponsored by Google)

Jun. 2022

Page updated

Google Sites

Report abuse