Bio

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

Gaze-hand Trajectory Merging for Efficient Egocentric Video Understanding

Jaewoo Jeong*, M. Kim*, Yujin Bae*, Kuk-Jin Yoon

Coming soon!

SRA: Spatial Reasoning Adapter via Evolving Social Interaction Graphs for Trajectory Prediction

Jaewoo Jeong*, S. Song*, H. Park, J. Cho, Yujin Bae, Giwon Lee, Daehee Park, Kuk-Jin Yoon

Coming soon!

Ego-Human Motion Prediction with 3D-Aware LLM

Yujin Bae*, Jaewoo Jeong*, Hyeonseong Kim*, Kuk-Jin Yoon

ECCV 2026* denotes equal contribution

Paper Code Project page

Multi-modal Knowledge Distillation-based Human Trajectory Forecasting

Jaewoo Jeong, Seohee Lee, Daehee Park, Giwon Lee, Kuk-Jin Yoon

CVPR 2025

Paper Code

Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning

Jaewoo Jeong*, Daehee Park*, Kuk-Jin Yoon

CVPR 2024 Highlight* denotes equal contribution

Paper Code Project page

T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory

Daehee Park, Jaeseok Jeong, Sung-Hoon Yoon, Jaewoo Jeong, Kuk-Jin Yoon

CVPR 2024

Paper Code

Improving Transferability for Cross-domain Trajectory Prediction via Neural Stochastic Differential Equation

Daehee Park, Jaewoo Jeong, Kuk-Jin Yoon

AAAI 2024

Paper Code

Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning

Giwon Lee*, Wooseong Jeong*, Daehee Park, Jaewoo Jeong, Kuk-Jin Yoon

ICCV 2025 Highlight* denotes equal contribution

Paper

Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion Planning

Giwon Lee*, Daehee Park*, Jaewoo Jeong*, Kuk-Jin Yoon

IROS 2025* denotes equal contribution

Paper

Analysis of Multiscale Condensation Phenomena Using a Zero-Shot Computer Vision Framework

Donghyeong Lee, Seokwan Roh, Jaewoo Jeong, Kuk-Jin Yoon, Jungchul Lee, and Youngsuk Nam

Advanced Science 2026

Paper

Near-infrared inspection and machine learning-based prediction for semiconductor membrane cavity structures

Mun Goung Jeong, Jaewoo Jeong, Taeyeong Kim, Bong Jae Lee, Jungchul Lee

NEMS 2023

Proceeding

Predicting AFM topography from optical microscopes using deep-learning

Jaewoo Jeong, Taeyeong Kim, Bong Jae Lee, Jungchul Lee

Advanced Intelligent Systems, 2022Selected as inside back cover

Paper

Simulation of Germanium-on-Nothing cavity’s morphological transformation using deep learning

Jaewoo Jeong, Taeyeong Kim, Jungchul Lee

Micro and Nano System Letters, 2022

Paper

PCA-based sub-surface structure and defect analysis for Germanium-on-Nothing using nanoscale surface topography

Jaewoo Jeong, Taeyeong Kim, Bong Jae Lee, Jungchul Lee

Scientific Reports, 2022

Paper

Cellular and biomolecular detection based on suspended microchannel resonators

Juhee Ko, Jaewoo Jeong, Sukbom Son, Jungchul Lee

Biomedical Engineering Letters, 2021

Paper

3D Printed Polymer Photodetectors

Sung Hyun Park, Ruitao Su, Jaewoo Jeong, Shuang-Zhuang Guo, Kaiyan Qiu, Daeha Joung, Fanben Meng, Michael C. McAlpine

Advanced Materials, 2018

Paper

Projects

• 2026.1 ~ 2026.12Agentic vision langugae navigation modelsGS E&C
• 2025.3 ~ 2025.12Visual perception for elder care robot systemNRF of Korea
• 2024.6 ~ 2025.6Long tail vehicle trajectory prediction for autonomous vehicle systemsHyundai Motor Group
• 2023.5 ~ 2023.12Surround view depth estimation for autonomous vehicle systemsHyundai NGV
• 2023.2 ~ 2023.12Synthetic-to-Real domain adaptation for military object detectionLIG Nex1