I am a PhD student at KAIST Computer Vision and Learning Lab. My research interests lie in generative AI, multimodal learning, and physical AI, with a focus on building adaptive and reasoning-capable generative systems. Previously, I worked on controllable and personalized generative models for visual content, studying how pretrained diffusion and foundation models can efficiently adapt to new concepts, identities, and styles with minimal supervision. Recently, I have become increasingly interested in video generative models, world models, and generative modeling for physical interaction and embodied systems. I am particularly interested in how generative models can understand, predict, and reason about dynamics in the physical world through scalable inference and simulation. More broadly, I am interested in connecting generative modeling, inference-time computation, and multimodal reasoning toward more capable and interactive AI systems.

I am always open to discussions and collaborations!

Selected Publications

    Education

    • Korea Advanced Institute of Science and Technology (KAIST)
      Ph.D. student in Artificial Intelligence
      Mar 2023 — present
    • Pohang University of Science and Technology (POSTECH)
      M.S. in Computer Science and Engineering
      Aug 2022
    • Seoul National University of Science and Technology (SeoulTech)
      B.S. in Electrical and Information Engineering
      Feb 2020

    Work Experience

    • NAVER Cloud - Visual Generation Team (Resident)
      Oct 2025 — Apr 2026
    • NAVER Webtoon - Generative Model Team (Intern)
      Aug 2022 — Feb 2023

    Teaching Experience

    • Computational Image Generation and Manipulation, KAIST
      Fall 2025
    • Deep Reinforcement Learning, KAIST
      Spring 2023
    • Data Structure, POSTECH
      Spring 2021