Susung Hong

switzerland.jpg

Welcome to my website! I am a Ph.D. student at the Allen School at the University of Washington, co-advised by Ira Kemelmacher-Shlizerman, Steve Seitz, and Brian Curless.

I ultimately aim to create a better clone of our world capable of incubating intelligence, with a dual focus on visual and symbolic knowledge. To this end, I am currently interested in scalable generative models, large datasets, and their potential to construct sophisticated and interactive environments.

news

Sep 25, 2024 Our two papers, Smoothed Energy Guidance (SEG) and Effective Rank Regularizaiton for 3DGS have been accepted to NeurIPS 2024.
May 02, 2024 Our ReDream paper has been accepted to ICML 2024.
Sep 22, 2023 Our Debiased-SDS paper has been accepted to NeurIPS 2023.
Jul 14, 2023 Our Self-Attention Guidance (SAG) paper has been accepted to ICCV 2023.
Feb 16, 2023 Self-Attention Guidance (SAG) is now available at huggingface/diffusers :hugs::firecracker:

selected publications

  1. NeurIPS
    seg.jpg
    Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention
    Susung Hong
    NeurIPS, 2024
    arXiv Website
  2. NeurIPS
    erank.jpg
    Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting
    Junha Hyung, Susung Hong, Sungwon Hwang, Jaeseong Lee, Jaegul Choo, and Jin-Hwa Kim
    NeurIPS, 2024
    arXiv Website
  3. ICML
    redream.gif
    Retrieval-Augmented Score Distillation for Text-to-3D Generation
    Junyoung Seo*, Susung Hong*, Wooseok Jang*, Inès Hyeonsu Kim, Minseop Kwak, Doyup Lee, and Seungryong Kim
    ICML, 2024
    arXiv Website
  4. ICCV
    sag.jpg
    Improving Sample Quality of Diffusion Models Using Self-Attention Guidance
    Susung Hong, Gyuseong Lee, Wooseok Jang, and Seungryong Kim
    ICCV, 2023
    arXiv Website