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 controllable generative modeling with large models (e.g., LLMs, Diffusion/Flow-based models) via exploring their latent spaces. Especially, I’m interested in building an amortized sampler that can extract crucial latents for generating desired samples. To accomplish this, my research focuses on the amortizing inference of generative models with off-policy RL approaches.

I’m also interested in various decision making problems such as Multi-turn/Multi-agent RL. I’ve also participated in several transportation-related projects based on high-dimensional black-box optimization methods.

🔥 News

• 2025.06:  🎉🎉 I started internship at Mila, Hosted by Yoshua Bengio
• 2025.05:  🎉🎉 5 papers accepted in 2025 (1 ICLR, 1 CVPR, 2 ICML, 1 KDD)
• 2024.12:  🎉🎉 5 papers accepted in 2024 (1 ICLR, 1 ICML, 1 KDD, 2 NeurIPS)
• 2024.09:  🎉🎉 I started remote internship at HKUST, Hosted by Ling Pan

📖 Educations

• 2024.05 - current, Ph.D in Industrial and Systems Engineering, KAIST (Korea Advanced Institute of Science and Technology)
• 2022.09 - 2024.02, M.S in Graduate School of AI, KAIST
• 2018.03 - 2022.08, B.S in Industrial and Systems Engineering & Computer Science, KAIST

💻 Internships

• 2025.06 - 2025.08, Internship at Mila, hosted by Yoshua Bengio
• 2024.09 - 2025.03, Remote Internship at HKUST (Hong Kong University of Science and Technology), hosted by Ling Pan
• 2021.03 - 2021.08, Internship at Kakao Recommendation Team

📝 Publications

(*: Equal Contribution)

• Active Attacks: Red-teaming LLMs via Adaptive Environments
  [paper], [code]
  Taeyoung Yun, Pierre-Luc St-Charles, Jinkyoo Park, Yoshua Bengio, and Minsu Kim
  Arxiv 2025

• Posterior Inference in Latent Space for Scalable Constrained Black-box Optimization
  [paper], [code]
  Kiyoung Om*, Kyuil Sim*, Taeyoung Yun*, Hyeongyu Kang, and Jinkyoo Park
  Arxiv 2025

• Wind Farm Layout Optimization with Diffusion Models
  [paper], [code]
  Yujin Shin*, Taeyoung Yun*, Sujin Yun, Sungpil Woo, Sunhwan Lim, and Jinkyoo Park
  KDD 2025

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

• Improved Off-policy Reinforcement Learning in Biological Sequence Design
  [paper], [code]
  Hyeonah Kim, Minsu Kim, Taeyoung Yun, Sanghyeok Choi, Emmanuel Bengio, Alex Hernández-García, and Jinkyoo Park
  ICML 2025 (based on NeurIPS Workshop)

• Learning to Sample Effective and Diverse Prompts for Text-to-Image Generation
  [paper], [code]
  Taeyoung Yun, Dinghuai Zhang, Jinkyoo Park, and Ling Pan
  CVPR 2025

• Adaptive Teachers for Amortized Samplers
  [paper], [code]
  Minsu Kim*, Sanghyeok Choi*, Taeyoung Yun, Emmanuel Bengio, Leo Feng, Jarrid Rector-Brooks, Sungsoo Ahn, Jinkyoo Park, Nikolay Malkin, and Yoshua Bengio
  ICLR 2025

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

• GTA: Generative Trajetory Augmentation with Guidance for Offline Reinforcement Learning
  [paper], [code]
  Jaewoo Lee*, Sujin Yun*, Taeyoung Yun, and Jinkyoo Park
  NeurIPS 2024 (based on ICLR Workshop)

• An Offline Meta Black-box Optimization Framework for Adaptive Design of Urban Traffic Light Management Systems
  [paper], [code]
  Taeyoung Yun*, Kanghoon Lee*, Sujin Yun, Ilmyung Kim, Won-Woo Jung, Min-Cheol Kwon, Kyujin Choi, Yoohyeon Lee, and Jinkyoo Park
  KDD 2024

• Learning to Scale Logits for Temperature-conditional GFlowNets
  [paper], [code]
  Minsu Kim*, Juhwan Ko*, Taeyoung Yun*, Dinghuai Zhang, Ling Pan, Woochang Kim, Jinkyoo Park, and Yoshua Bengio
  ICML 2024 (based on NIPS Workshop)

• Local Search GFlowNets
  [paper], [code]
  Minsu Kim, Taeyoung Yun, Emmanuel Bengio, Dinghuai Zhang, Yoshua Bengio, Sungsoo Ahn, and Jinkyoo Park
  ICLR (Spotlight) 2024

🎖 Honors and Awards

• 2021.12 Excellence Award on DACON NH Big Data Competition.
• 2021.09 Dean’s List (Honor for Top 2% Students).