Jongoh Jeong (μ μ’
μ€)
jeong2 [at] kaist.ac.kr / [CV] [Google Scholar] [Github] [LinkedIn]Β
Embedded Files
I am a Ph.D. student in the Robotics Program at the Korea Advanced Institute of Science and Technology (KAIST), advised by Kuk-Jin Yoon in the Visual Intelligence Lab.
My research focuses on building robust and data-efficient omni-modal models with minimal human supervision.
π€ I am open to research collaborations, coffee chats, and internship or full-time opportunities. Please feel free to contact me.
W2Research Interests
TL;DR: Self-Driving β Robust Perception β Model Reliability β Noisy Multimodal Learning β Cross-Modal Alignment β Reliable Omnimodal ModelsΒ
My goal is to make omnimodal models reliable under practical limits on data, compute, and annotation. I first encountered these constraints while developing real-time perception systems for autonomous driving in adverse weather using multiple sensors [J1, C1, C2, C5]. This work showed that reliable deployment requires robustness to unseen conditions while meeting strict latency and safety requirements. I therefore studied model failures directly, using generative models to identify weaknesses in black-box systems and develop transferable methods for exposing them across architectures [W2βC3, C4, W3βC6].
Expanding to vision-language learning to meet recently growing research demands, I found that the data quality to be the primary bottleneck, and image-text pairs are costly to collect, difficult to verify, and often noisy. My current work thus develops methods that discover useful cross-modal correspondence and aligning different modalities [C7, C8]. I am further extending this direction toward multimodal alignment, retrieval-augmented generation, and methods that enable (industry-led) pre-trained models to reinforce one another without retraining from scratch. My long-term goal is to build omni-modal models that are reliable, efficient, and deployable in practice beyond controlled benchmarks.
π Education
Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea
Β Β Β Β Β π« (current) Ph.D. in Robotics, Advisor: Prof. Kuk-Jin Yoon, 2022.08 - Present
Β Β Β Β Β π M.S. in Electrical Engineering, Advisor: Prof. Jong-Hwan Kim, 2020.08 - 2022.08
The Cooper Union for the Advancement of Science and Art, New York, NY, USA
Β Β Β Β Β π B.E. in Electrical Engineering, 2014.09 - 2020.05 (*2016-2018: military duty leave)
π PublicationsΒ Β (W: Peer-reviewed Workshop, C: Peer-reviewed Conference, J: Peer-reviewed Journal, P: Pre-print, K-C: Korean Conference)
Β Β Β Research Interests:
Computer Vision (Robust/data-efficient representation learning, Multimodal Models, Retrieval-Augmented Generation) [P1, P3, C5, C7, C8]Β
Machine Learning (Robust, safe, trustworthy, adversarial AI) [J2, W2βC3, C4, W3βC6]
Robotic/Machine Vision (Autonomous driving, sensor fusion) [J1, C1, K-C1, C2, P2]
[C8] Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation (To appear)
Jongoh Jeong, Sun-Kyung Lee, Β and Kuk-Jin Yoon.Β
The 19th European Conference on Computer Vision (ECCV), Sep. 2026. (acceptance rate: 27.53 %)
[C7] Multimodal Distribution Matching for Vision-Language Dataset DistillationΒ
Jongoh Jeong*, Hoyong Kwon*, Minseok Kim*, Β and Kuk-Jin Yoon. (*Shared authorship)
IEEE/CVF Computer Vision and Pattern Recognition (CVPR), Jun. 2026.Β (acceptance rate: 25.42%)
*Also presented at CVPR 2026 Workshop on Emerging Directions in Data for Multimodal Foundation Models (DataMFM)
[Paper][Web][Project][Video] *LinkedIn Post
[C5] DOODLE: Diffusion-based Out-of-Distribution Learning for Open-set LiDAR Semantic Segmentation
[C4] Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks
Hunmin Yang, Jongoh Jeong, and Kuk-Jin Yoon
The 18th European Conference on Computer Vision (ECCV), Sep. 2024. (Oral, 8.37% of accepted, 2.33% of submitted)
*Also presented at KCCV 2024 [KAIST News]
[P3] Task-oriented Learnable Diffusion Timesteps for Universal Few-shot Learning of Dense Tasks
Changgyoon Oh*, Jegyeong Cho*, Jongoh Jeong and Kuk-Jin Yoon Β
Pre-print, 2024. (*Shared authorship)
[Preprint]
[P2] AVOID: The Adverse Visual Conditions Dataset with Obstacles for Driving Scene Understanding
Jongoh Jeong*, Taek-Jin Song*, Jong-Hwan Kim, and Kuk-Jin Yoon
arXiv, 2024. (*Shared authorship)
[arXiv]
[P1] Exploring Syn-to-Real Domain Adaptation for Military Target Detection
Jongoh Jeong, Youngjin Oh, Gyeongrae Nam, Jeongeun Lee, and Kuk-Jin Yoon
arXiv, Oct. 2023.Β
[arXiv]
[K-C1] Real-time Road Obstacle Detection and Avoidance Network for Autonomous Driving under Adverse Weather
Jongoh Jeong, Taek-Jin Song, Jong-Hwan Kim, and Kuk-Jin Yoon.
Image Processing and Image Understanding, (IPIU), Jan. 2023.Β
ποΈ Research Projects
C-arm X-ray imagingΒ system development for DK Medical Systems (Jul.'25 β Jun.'26)
AI/SW Project for Commissioned Education (Ministry of National Defense (MND), Jun.'22 β Dec.'26)
Synthetic Military Target Data Generation for Domain Adaptive Object Detection (LIGNex1, Oct.β22 β Sep.β23)
Development of Artificial Intelligence Technology that Continuously Improves Itself as the Situation Changes in the Real World (Korea MSIT (IITP), No.2020-0-00440, Sep.β20 βAug.β22)
Development of Real-time Smart Solution for Solder Mount Technology (SMT) (Koh-Young Tech., Sep.β20 β Aug.β22)
π€ Academic Activities
Reviewer
AAAI, ICLR, NeurIPS, 2026 - Present
IEEE Transactions on Information Forensics and Security (T-IFS), 2026 - Present
IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT), 2026 - Present
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2026 - Present
IEEE Transactions on Multimedia (T-MM), 2026 - Present
IEEE Transactions on Cybernetics (T-CYB), 2026 - Present
IEEE Transactions on Geoscience and Remote Sensing (T-GRS), 2024 - Present
IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2022 - Present
IEEE Access, 2022 - Present
NeurIPS Workshop on Machine Learning for Health (ML4H), 2020 - Present
Professional Society Membership
IEEE Computer Society, 2025
Order of the Engineer, 2020 β Present
IEEE-Eta Kappa Nu (Student Member) 2018 β Present
ACM (Student Member) 2018 β Present
Page updated
Google Sites
Report abuse