Ph.D Student,Korea University,South Korea
Jaehwan Jeong is an emerging researcher in AI and computer vision, with a strong academic background and collaborations with top institutions. His work in deepfake defense and generative models positions him well for awards in AI safety and multi-modal learning. However, securing additional accepted publications and leading independent research could further bolster his case for the Best Researcher Award.
Publication Profile
Education :
Jaehwan Jeong is currently pursuing a Ph.D. in Artificial Intelligence at Korea University, Seoul, South Korea (2024–2029, expected). He completed his Bachelor of Engineering (B.E.) in Electrical & Electronic Engineering from Chung-Ang University, Seoul, in 2021. His academic journey has been focused on artificial intelligence, deep learning, and computer vision.
Experience:
Ph.D. Student Researcher | Computer Vision Lab, Korea University (Mar. 2024 – Present),Under the supervision of Prof. Sangpil Kim, Jaehwan is conducting advanced research in:,3D Multi-modal Data Integration (ongoing research),Adversarial Noise for Deepfake AI Safety (collaboration with Dr. Jaewook Chung, Samsung Research),Multi-modal Audio-to-Video Generation (collaboration with Dr. Eugenio Culurciello, Purdue University),Undergraduate Research Intern | Computer Vision Lab, Korea University (Jul. 2023 – Feb. 2024),As an intern, he contributed to:,Diffusion-based Video Generation (collaboration with Dr. Wonmin Byeon, NVIDIA Research),Multi-modal Audio-to-Video Editing (collaboration with Dr. Feng Yang, Google Research),Military Service | Republic of Korea Army (Mar. 2021 – Jun. 2023),Jaehwan served as a Military Officer (1st and 2nd Lieutenant) in the Signal Company, 5th Armored Brigade. His responsibilities included:,Managing wired communication networks (UTP, Optical cables),Planning operational and tactical strategies
Research Focus:
Jaehwan’s research interests include:,3D Reconstruction & Knowledge Graphs,AI Safety & Deepfake Protection,Generative Models & Multi-modal Learning,Machine Learning & Deep Learning,Computer Vision
Skills:
Jaehwan possesses strong expertise in:,Programming: Python, Shell Scripting, Git, LaTeX,Deep Learning Frameworks: PyTorch, PyTorch Lightning, TensorFlow,AI & ML Libraries: Hugging Face, Scikit-Learn
-
MTVG: Multi-text Video Generation with Text-to-Video Models
- Authors: Gyeongrok Oh, Jaehwan Jeong, Sieun Kim, Wonmin Byeon, Jinkyu Kim, Sungwoong Kim, Hyeokmin Kwon, Sangpil Kim
- Publication: arXiv preprint arXiv:2312.04086
- Year: 2023
- Citation: Oh, G., Jeong, J., Kim, S., Byeon, W., Kim, J., Kim, S., Kwon, H., & Kim, S. (2023). MTVG: Multi-text Video Generation with Text-to-Video Models. arXiv preprint arXiv:2312.04086.
-
MEVG: Multi-event Video Generation with Text-to-Video Models
- Authors: Gyeongrok Oh, Jaehwan Jeong, Sieun Kim, Wonmin Byeon, Jinkyu Kim, Sungwoong Kim, Sangpil Kim
- Publication: European Conference on Computer Vision (ECCV), pages 401–418
- Year: 2025
- Citation: Oh, G., Jeong, J., Kim, S., Byeon, W., Kim, J., Kim, S., & Kim, S. (2025). MEVG: Multi-event Video Generation with Text-to-Video Models. In A. Leonardis, E. Ricci, S. Roth, O. Russakovsky, T. Sattler, & G. Varol (Eds.), Computer Vision – ECCV 2024 (pp. 401–418). Springer.
-
FaceShield: Defending Facial Image against Deepfake Threats
- Authors: Jaehwan Jeong, Seungmin In, Sieun Kim, Hyojin Shin, Jaeho Jeong, Seunghyun Yoon, Jaewon Chung, Sungwoong Kim
- Publication: arXiv preprint arXiv:2412.09921
- Year: 2024
- Citation: Jeong, J., In, S., Kim, S., Shin, H., Jeong, J., Yoon, S., Chung, J., & Kim, S. (2024). FaceShield: Defending Facial Image against Deepfake Threats. arXiv preprint arXiv:2412.09921.
Jeong is a strong candidate for the award but would benefit from more accepted publications and demonstrated leadership in independent research. His ongoing Ph.D. work and collaborations with Samsung, NVIDIA, and Google make him a promising researcher with significant potential.