cv
A brief resume is displayed below. Please download the PDF to see a longer version.
Basics
| Name | Jeongjae Lee |
| Label | Masters Student |
| jaysquirrel2000@gmail.com | |
| Url | https://jaylee2000.github.io/ |
Work
-
2024.09 - 2025.08 Postbaccalaureate Researcher
Graduate School of AI, KAIST
Worked on foundational model for clinical time-series data. Improved a CycleGAN-based scatter correction software for Chest X-ray images.
- TimeVQVAE
- Wavelet-CycleGAN
-
2023.01 - 2023.12 Research Intern
DeepMetrics
Involved in a project devising a method for automated control of mechanical ventilators in intensive care units.
- Decision Tree
- Time-Series Data
-
2022.06 - 2022.12 Research Intern
Seoul National University
Involved in development of Foldseek. Developed optimized code for LDDT alignment score computation, and established an automated protein database update pipeline for Foldseek's web server.
- Spatial Hashing
- SIMD Instructions
Education
Awards
- 2024
Summa Cum Laude
Seoul National University
- 2019
Presidential Science Scholarship
Korea Scholarship Foundation
Full tuition plus 2.5 million won per semester, awarded to talented students majoring in science or engineering.
- 2022
Medical AI Scholarship
Korea Health Industry Development Institute
3 million won per semester, merit-based scholarship
Publications
-
2026.04.19 Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
arXiv
RSM unifies reward-based fine-tuning for diffusion and flow-matching models.
-
2025.09.30 PCPO: Proportionate Credit Policy Optimization for Aligning Image Generation Models
ICLR 2026
PCPO is an improvement on GRPO for preference alignment of diffusion and flow-matching models.
-
2023.05.08 Fast and accurate protein structure search with Foldseek
Nature Biotechnology
Foldseek enables fast and sensitive comparisons of large protein structure sets.
Languages
| Korean | |
| Native speaker |
| English | |
| Fluent |
Interests
| Reward-Aligned Generation | |
| Reinforcement Learning | |
| Denoising Generative Models |
| Medical Artificial Intelligence | |
| Medical Informatics | |
| Biomedical Signal Processing |
References
| Professor Jong Chul Ye | |
| Current research advisor at KAIST. He is a leading expert in inverse problems, and has published numerous papers in top-tier journals and conferences. |
| Professor Hyun Oh Song | |
| Research advisor at DeepMetrics. He is an established researcher in deep (reinforcement) learning, and is the CEO of DeepMetrics, a medical AI startup. |
| Professor Martin Steinegger | |
| Research advisor at Seoul National University. He is a leading expert in bioinformatics, and has published many papers in top-tier journals. He created many open-source bioinformatics tools, including Foldseek and mmseqs. |