Dahye Kim

Contact. dahye [at] bu [dot] edu

prof_pic.jpg

665 Commonwealth Ave.

Boston, MA 02215

Hi, thanks for stopping by! 👋

I am a first-year CS PhD student at Boston University, where I am fortunate to be advised by Prof. Deepti Ghadiyaram. Prior to joining BU, I completed my Master’s degree at Yonsei University under the guidance of Prof. Kwanghoon Sohn.

💭 My current research interests include

  • Image generation / Diffusion models
  • Interpretability / Safety

but not limited to!

news

Jun 30, 2025 Join Amazon as an Applied Scientist Intern in Seattle! 🏙️
Jun 25, 2025 🎉 Revelio is accepted at ICCV 2025! 🌺
May 03, 2025 🎉 Revelio is selected for an oral presentation at the CVPR 2025 MIV Workshop ! 🎸
Feb 03, 2025 New preprint is out: check out Concept Steerers 🪄
Nov 26, 2024 New preprint is out: check out Revelio 🔎

publications

  1. steerers.png
    Concept Steerers: Leveraging K-Sparse Autoencoders for Controllable Generations
    Dahye Kim, and Deepti Ghadiyaram
    arXiv preprint arXiv:2501.19066, 2025
    arXiv Code Website
  2. revelio.png
    Revelio: Interpreting and leveraging semantic information in diffusion models
    Dahye Kim*, Xavier Thomas*, and Deepti Ghadiyaram
    ICCV, 2025
    arXiv Code Poster Website
  3. kim2023language.png
    Language-free training for zero-shot video grounding
    Dahye Kim, Jungin Park, Jiyoung Lee, Seongheon Park, and Kwanghoon Sohn
    WACV, 2023
    arXiv PDF
  4. park2023normality.png
    Normality guided multiple instance learning for weakly supervised video anomaly detection
    Seongheon Park, Hanjae Kim, Minsu Kim, Dahye Kim, and Kwanghoon Sohn
    WACV, 2023
    PDF