profile1.png

Junoh Kang

I am a third-year Ph.D. student at the SNU Computer Vision Lab, advised by Bohyung Han. I aim to solve problems of deep learning in a theoretically concrete manner by leveraging my expertise: mathematics applied to problem description and solution. My primary research interest is generative models.

Besides the research, I am also interested in economics, investment, and playing sports such as tennis, golf, and futsal.

news

May 27, 2025 We release a new project page for flexible video editing technique. STR-Match: Matching SpatioTemporal Relevence Score for Training-Free Video Editing can even change cat into dragon, basketball, … etc,.!! Feel free to explore.
Jan 24, 2025 Our paper, FIFO-Diffusion: Generating Infinite Videos from Text without Training, awards gold medal on 30th Samsung Humantech paper award.
Jan 24, 2025 Our paper, FIFO-Diffusion: Generating Infinite Videos from Text without Training, awards gold medal on 30th Samsung Humantech paper award.

publications

(*) denotes equal contribution

2025

  1. ICLR
    Enhanced Diffusion Sampling via Extrapolation with Multiple ODE Solutions
    Jinyoung Choi, Junoh Kang, and Bohyung Han
    In ICLR, 2025
  2. arXiv
    STR-Match: Matching SpatioTemporal Relevance Score for Training-Free Video Editing
    Junsung LeeJunoh Kang, and Bohyung Han
    2025

2024

  1. CVPR
    Observation-Guided Diffusion Probabilistic Models
    Junoh Kang*, Jinyoung Choi*, Sungik Choi, and Bohyung Han
    In CVPR, 2024
  2. NeurIPS
    FIFO-Diffusion: Generating Infinite Videos from Text without Training
    Jihwan Kim*Junoh Kang*, Jinyoung Choi, and Bohyung Han
    In NuerIPS, 2024

2023

  1. CVPR
    Open-Set Representation Learning Through Combinatorial Embedding
    Geeho Kim, Junoh Kang, and Bohyung Han
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023