Scholar
Jaewoo Jeong
Google Scholar ID: 1TqLFogAAAAJ
Korea Advanced Institue of Science and Technology
Citations & Impact
Citations
226
H-index
5
i10-index
5
Publications
12
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Recipient of the 2024 Qualcomm Innovation Fellowship Korea.
- Published 'Interaction-Merged Motion Planning' at ICCV 2025 (Highlight).
- Published 'Non-differentiable Reward Optimization for Diffusion-based Autonomous Motion Planning' at IROS 2025.
- Published 'Multi-modal Knowledge Distillation-based Human Trajectory Forecasting' at CVPR 2025.
- Published 'Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning' at CVPR 2024 (Highlight).
- Published 'T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory' at CVPR 2024.
- Published 'Improving Transferability for Cross-domain Trajectory Prediction via Neural Stochastic Differential Equation' at AAAI 2024.
- Authored multiple publications in manufacturing, including in Advanced Materials (IF=29.4), Scientific Reports (IF=4.6), etc.
Background
- 3rd-year Ph.D. candidate at KAIST, advised by Prof. Kuk-Jin Yoon.
- Research interests include motion prediction/planning and multimodal LLMs.
- Aims to develop AI models that enhance human-computer and human-robot interactions to improve daily life.
- Discovered passion for computational algorithms during undergraduate research in computational fluid mechanics at the University of Minnesota-Twin Cities.
- Conducted master's research on computer vision-based manufacturing at MNIL, KAIST.
- Currently focusing on AI for computer vision in the Visual Intelligence Lab (VILab) at KAIST.
Co-authors