I am a PhD student at System Intelligence lab in KAIST. I am fortunate to be advised by Professor Jinkyoo Park. Here is my cv.

My research interest lies in aligning generative models with human intention through the principles of reinforcement learning and probabilistic inference. I enjoy applying aligning techniques to real-world applications such as visual generation, robotics control, and scientific discovery.

If you would like to discuss research, explore collaborations, or just have a chat, please feel free to contact me anytime at jaewoo@kaist.ac.kr — I am always happy to hear from you!

🔥 News

• 2026.06:  🎉🎉 3 workshop papers accepted at ICML 2026 (SPIGM, DEMO, RLxF)
• 2026.01:  🎉🎉 2 papers accepted at ICLR 2026
• 2026.01:  🎉🎉 1 paper accepted at AISTATS 2026
• 2025.05:  🎉🎉 1 paper accepted at ICML 2025
• 2024.09:  🎉🎉 2 papers accepted at NeurIPS 2024

📖 Educations

• 2025.03 - current, Ph.D in Industrial and Systems Engineering, KAIST
• 2023.03 - 2025.02, M.S in Graduate School of AI, KAIST
• 2016.03 - 2022.02, B.S in Mechanical Engineering, Sungkyunkwan University

💻 Working Experiences

• 2023.03 - current, Cofounder & Research Engineer, MongooseAI
• 2022.02 - 2023.02, Software Engineer, Samsung Electronics AI Center
• 2021.07 - 2021.08, Intern Data Scientist, Samsung Electronics AI Center

📝 Publications

(*: Equal Contribution, †: Equal Corresponding Author)

Preprints

• [P3] Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference
  [paper] / [code]
  Jaewoo Lee*, Hyeongyu Kang*, Dohyun Kim, Kyuil Sim, Woocheol Shin, Minsu Kim, Taeyoung Yun, Jeongjae Lee, Sanghyeok Choi, Tabitha Edith Lee, Jong Chul Ye†, Jinkyoo Park†
  arXiv 2026
  ICML 2026 SPIGM Workshop

• [P2] Automated Kernel Discovery Towards Understanding High-dimensional Bayesian Optimization
  [paper] / [code]
  Taeyoung Yun*, Woocheol Shin*, Inhyuck Song, Jaewoo Lee, Jinkyoo Park
  arXiv 2026
  ICML 2026 DEMO Workshop

• [P1] Robust Exploration through Generative Replay
  Inhyuck Song, Taeyoung Yun, Jaewoo Lee, Jinkyoo Park
  ICML 2026 RLxF Workshop

Conference Publications

• [C6] Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning
  [paper] / [code]
  Chihyeon Song, Jaewoo Lee, Jinkyoo Park
  AISTATS 2026

• [C5] Diffusion Fine-Tuning via Reparameterized Policy Gradient of the Soft Q-Function
  [paper] / [code]
  Hyeongyu Kang*, Jaewoo Lee*, Woocheol Shin*, Kiyoung Om, Jinkyoo Park
  ICLR 2026

• [C4] Diffusion Alignment as Variational Expectation-Maximization
  [paper] / [code]
  Jaewoo Lee, Minsu Kim, Sanghyeok Choi, Inhyuck Song, Sujin Yun, Hyeongyu Kang, Woocheol Shin, Taeyoung Yun, Kiyoung Om, Jinkyoo Park
  ICLR 2026

• [C3] Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization
  [paper] / [code]
  Taeyoung Yun*, Kiyoung Om*, Jaewoo Lee, Sujin Yun, Jinkyoo Park
  ICML 2025
  ICLR 2025 FPI Workshop

• [C2] Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization
  [paper] / [code]
  Taeyoung Yun, Sujin Yun, Jaewoo Lee, Jinkyoo Park
  NeurIPS 2024

• [C1] GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning
  [paper] / [code]
  Jaewoo Lee*, Sujin Yun*, Taeyoung Yun, Jinkyoo Park
  NeurIPS 2024
  ICLR 2024 GenAI4DM Workshop (Spotlight)

🎖 Honors and Awards

• 2021.09 Dean’s List, Sungkyunkwan University (honor for academic excellence)
• 2021.02 Excellence Award for Optimizing Shipbuilding Process Competition (Korea Shipbuilding and Offshore Engineering)
• 2020.09 Dean’s List, Sungkyunkwan University (honor for academic excellence)