I am a 4th year Ph.D. candidate advised by Prof. Kuk-Jin Yoon at Visual Intelligence Lab (VILab) , Korea Advanced Institute of Science and Technology (KAIST).
My research interests include, but are not limited to: motion understanding, prediction, and planning. Ultimately, my goal is to develop AI models that understand and predict human behavior, enriching human-computer and human-robot interactions to improve everyday life.
During my undergraduate years at U of Minnesota-Twin Cities, I discovered my passion for developing computational algorithms through my research in computational fluid mechanics. This enthralling experience had lead me to pursue graduate studies, starting from computer vision-based manufacturing during my master’s degree at MNIL , KAIST. For my PhD degree, I have moved to VILab , KAIST to focus my research on AI for computer vision.
My CV can be found here.
Awards 2025 Qualcomm Innovation Fellowship Korea Finalist 2024 Qualcomm Innovation Fellowship Korea Awardee Publications Motion understanding
Gaze-hand Trajectory Merging for Efficient Egocentric Video Understanding
J. Jeong* , M. Kim*, Y. Bae*, K. Yoon
Coming soon!
Motion prediction
SRA: Spatial Reasoning Adapter via Evolving Social Interaction Graphs for Trajectory Prediction
J. Jeong* , S. Song*, H. Park, J. Cho, Y. Bae, G. Lee, D. Park, K. Yoon
Coming soon!
Ego-Human Motion Prediction with 3D-Aware LLM
Y. Bae*, J. Jeong* , H. Kim*, K. Yoon
ECCV 2026 * denotes equal contribution
Multi-modal Knowledge Distillation-based Human Trajectory Forecasting
J. Jeong , S. Lee, D. Park, G. Lee, K. Yoon
CVPR 2025
Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning
J. Jeong *, D. Park*, K. Yoon
CVPR 2024 Highlight * denotes equal contribution
T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory
D. Park, J. Jeong, S. Yoon, J. Jeong , K. Yoon
CVPR 2024
Improving Transferability for Cross-domain Trajectory Prediction via Neural Stochastic Differential Equation
D. Park, J. Jeong , K. Yoon
AAAI 2024
Motion planning
Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning
G. Lee*, W. Jeong*, D. Park, J. Jeong , K. Yoon
ICCV 2025 Highlight * denotes equal contribution
Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion Planning
G. Lee*, D. Park*, J. Jeong *, K. Yoon
IROS 2025 * denotes equal contribution
Computer vision for manufacturing
Analysis of Multiscale Condensation Phenomena Using a Zero-Shot Computer Vision Framework
D. Lee, S. Roh, J. Jeong , K. Yoon, J. Lee, and Y. Nam
Advanced Science 2026
Near-infrared inspection and machine learning-based prediction for semiconductor membrane cavity structures
M. Jeong, J. Jeong , T. Kim, B. J. Lee, J. Lee
NEMS 2023
Predicting AFM topography from optical microscopes using deep-learning
J. Jeong , T. Kim, B. J. Lee, J. Lee
Advanced Intelligent Systems, 2022 Selected as inside back cover
Simulation of Germanium-on-Nothing cavity’s morphological transformation using deep learning
J. Jeong , T. Kim, B. J. Lee, J. Lee
Micro and Nano System Letters, 2022
PCA-based sub-surface structure and defect analysis for Germanium-on-Nothing using nanoscale surface topography
J. Jeong , T. Kim, B. J. Lee, J. Lee
Scientific Reports, 2022
Cellular and biomolecular detection based on suspended microchannel resonators
J. Ko, J. Jeong , S. Son, J. Lee
Biomedical Engineering Letters, 2021
3D Printed Polymer Photodetectors
S. H. Park, R. Su, J. Jeong , S. Z. Guo K. Qiu, D. Joung, F. Meng, M. C. McAlpine
Advanced Materials, 2018
Projects 2026.1 ~ 2026.12 Agentic vision langugae navigation models GS E&C 2025.3 ~ 2025.12 Visual perception for elder care robot system NRF of Korea 2024.6 ~ 2025.6 Long tail vehicle trajectory prediction for autonomous vehicle systems Hyundai Motor Group 2023.5 ~ 2023.12 Surround view depth estimation for autonomous vehicle systems Hyundai NGV 2023.2 ~ 2023.12 Synthetic-to-Real domain adaptation for military object detection LIG Nex1 
