Kyeongmin Yeo

aaaaa@kaist.ac.kr.

32v_profile.png

KAIST '22

Visual AI Lab M.S. Student

Generative AI & Computer Graphics

I am a M.S. student at the KAIST Visual AI Lab, advised by Prof. Minhyuk Sung. My research mainly focuses on generative AI, especially diffusion-based and flow-based models. I am particularly interested in the application of these models in computer vision and content creation.

selected publications

  1. matlat-thumbnail.png
    MatLat: Material Latent Space for PBR Texture Generation
    Kyeongmin Yeo, Yunhong Min, Jaihoon Kim, and Minhyuk Sung
    In CVPR 2026, 2026
    Highlight
  2. psisampler-thumbnail.png
    Ψ-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
    Taehoon Yoon*, Yunhong Min*, Kyeongmin Yeo*, and Minhyuk Sung
    In NeurIPS 2025, 2025
    Spotlight
  3. stochsync-thumbnail.png
    StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces
    Kyeongmin Yeo*, Jaihoon Kim*, and Minhyuk Sung
    In The Thirteenth International Conference on Learning Representations, 2025
  4. synctweedies-thumbnail.png
    SyncTweedies: A General Generative Framework Based on Synchronized Diffusions
    Jaihoon Kim*, Juil Koo*, Kyeongmin Yeo*, and Minhyuk Sung
    In NeurIPS 2024, 2024