Sohwi Lim

KAIST AMI LAB

prof_pic.jpg

I am currently M.S student studying at KAIST, Daejeon, South Korea and a member of AMI Lab advised by Prof. Tae-Hyun Oh. My research interests include multi-modal learning and its applications in computer vision, but not limited to.

news

May 2026 Two papers have been accepted to ICML 2026!
Feb 2026 Our paper has been accepted to CVPR 2026!
Feb 2026 Our paper has received Outstanding Poster Presentation Award from IPIU 2026!
Dec 2025 Our paper has received Best Excellence Prize ($5,000 prize), Electronics Times ICT Paper Awards 2025!
Nov 2025 Our paper has been accepted to WACV 2026!

selected publications

  1. arXiv
    Early Failure Detection and Intervention in Video Diffusion Models
    Kwon Byung-Ki, Sohwi Lim, Nam Hyeon-Woo, Moon Ye-Bin, and Tae-Hyun Oh
    2026
    arXiv
  2. ICML
    Zero-Shot Rankability: Revealing Latent Ordinal Structure in Multimodal Large Language Models via Language
    Nam Hyeon-Woo, Moon Ye-Bin, Sohwi Lim, Kwon Byung-Ki, and Tae-Hyun Oh
    In Proceedings of the International Conference on Machine Learning (ICML), 2026
  3. ICML
    mclc.png
    Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers
    Lee Hyoseok, Sohwi Lim, Eunju Cha, and Tae-Hyun Oh
    In Proceedings of the International Conference on Machine Learning (ICML), 2026
    arXiv
  4. CVPR
    clay.png
    CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space
    Sohwi Lim, Lee Hyoseok, Jungjoon Park, and Tae-Hyun Oh
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
    Website
  5. WACV
    patchretrieval.png
    Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching
    Wonseok Choi, Sohwi Lim, Nam Hyeon-Woo, Moon Ye-Bin, Dong-Ju Jeong, Jinyoung Hwang, and Tae-Hyun Oh
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2026
    arXiv Website