Jaehyuk Jang
Ph.D. Student
Computational Intelligence Lab
Korea Advanced Institute of Science and Technology (KAIST)
jhyuk [at] kaist.ac.kr, 1120jhyuk [at] gmail.com
Ph.D. Student
Computational Intelligence Lab
Korea Advanced Institute of Science and Technology (KAIST)
jhyuk [at] kaist.ac.kr, 1120jhyuk [at] gmail.com
I'm Jaehyuk Jang, a Ph.D. student at Korea Advanced Institute of Science and Technology (KAIST), advised by Prof. Changick Kim.
Education
B.S. in Electrical Engineering from Hanyang University, 2016.3-2020.2
M.S. in Electrical Engineering from KAIST, 2020.3-2022.2
Ph.D. in Electrical Engineering from KAIST, 2022.3-present
Research Interests
Deep learning, especially computer vision, is my area of interest.
Visual Perception (classification, segmentation)
Anomaly / Change detection
Multimodal learning
Large multimodal model
but not limited to.
Publications
(C: Conference, J: Journal, P: Preprint, *: Equal Contribution)
2025
[J2] FCGNet: Foreground and Class Guided Network for Human Parsing [paper]
Jaehyuk Jang, Y. Wang, Changick Kim
Pattern Recognition (PR), 2025
[C4] Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models [paper] [arXiv] [Project page]
S. Woo*, D. Kim*, Jaehyuk Jang*, Y. Choi, Changick Kim
Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL Findings), 2025
2024
[P1] RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in LVLMs [paper] [arXiv] [Project page]
S. Woo*, Jaehyuk Jang*, D. Kim*, Y. Choi, Changick Kim
arXiV, 2024
Jaehyuk Jang, Y. Wang, Changick Kim
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024
2023
[J1] Subdivided Mask Dispersion Framework for Semi-Supervised Semantic Segmentation [paper]
Y. Wang, Jaehyuk Jang, Changick Kim
Pattern Recognition Letters (PRL), 2023
[C2] Noise-Augmented Missing Modality Aware Prompt based Learning for Robust Visual Recognition [paper]
Y. Wang, Jaehyuk Jang, Changick Kim
IEEE International Conference on Visual Communications and Image Processing (VCIP), 2023
2021
[C1] ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments [paper] [arXiv] [Project page] [NVIDIA AI Enterprise Supported]
J.-M. Park*, Jaehyuk Jang*, S.-M. Yoo, S.-K. Lee, U.-H. Kim, Jong-Hwan Kim
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
Project
미래 안보기술 연구 (2024.3~2024.12)
안보기술연구센터
광역 해양 감시∙수색을 위한 하이브리드 광학레이다 개발 기획 연구 (2023.7~2023.12)
Korea Institute of Marine Science & Technology Promotion (KIMST)
나노 광학 구조 이미지 센서 해상도 개선 알고리즘 연구 (2022.7~2023.7)
Samsung Advanced Institute of Technology (SAIT)
실사 수준의 디지털 휴먼 생성과 30fps급 실감 렌더링 기술 개발 (2022.3~2024.12)
Institute of Information & Communications Technology Planning & Evaluation (IITP)
현실 세계에서 변화하는 상황에 따라 지속적으로 자가 개선하는 인공지능 기술 개발 (2020.3-2021.12)
Institute of Information & Communications Technology Planning & Evaluation (IITP)