Minwoo Kim

I am a PhD student in the Department of Electrical and Computer Engineering at Inha University, advised by Hongki Lim. My research interests include generative models and inverse problems, and I am currently working on multimodal generative modeling.

Previously: I obtained my Bachelor’s degree in Electronic Engineering and my Master’s degree in Electrical and Computer Engineering, both from Inha University.

selected publications

  1. ICML
    Geometry-Correct Diffusion Posterior Sampling with Denoiser-Pullback Curvature Guidance and Manifold-Aligned Damping
    Seunghyeok Shin*, Minwoo Kim*, Dabin Kim, and Hongki Lim
    International Conference on Machine Learning (ICML), 2026
    Openreview arXiv Code Demo
  2. ICLR
    FAST-DIPS: Adjoint-Free Analytic Steps and Hard-Constrained Likelihood Correction for Diffusion-Prior Inverse Problems
    Minwoo Kim*, Seunghyeok Shin*, and Hongki Lim
    International Conference on Learning Representations (ICLR), 2026
    Openreview arXiv Code Demo
  3. Preprint
    SURE Guided Posterior Sampling: Trajectory Correction for Diffusion-Based Inverse Problems
    Minwoo Kim and Hongki Lim
    Preprint, 2025
    arXiv