1. X
  2. Cusuh
Log inSign up
Cusuh
140 posts
user avatar
Cusuh
@cusuh_
Research Scientist @ Adobe | ML PhD from Georgia Tech | previously Google Research, MPI
cusuh.github.io
Joined April 2010
205
Following
876
Followers
RepliesRepliesMediaMedia

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

TermsยทPrivacyยทCookiesยทAccessibilityยทAds Infoยทยฉ 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • Pinned
    user avatar
    Cusuh
    @cusuh_
    Nov 3, 2023
    Defended my PhD today!!! ๐Ÿฅณ Thank you to everyone who supported me along the way, especially my advisor @jhhays for taking a chance on my clueless little undergrad self and putting up with me ever since. I'll be joining Adobe next month as a research scientist under @aseemaa!
    24K
  • user avatar
    Cusuh
    @cusuh_
    Aug 6, 2023
    I'll be presenting our work on multimodal conditioning modules (MCM) at #SIGGRAPH2023 this week! MCM is a small network that enables multimodal image synthesis using pretrained diffusion models without any direct updates to the diffusion model parameters. mcm-diffusion.github.io
    Image
    19K
  • user avatar
    Cusuh
    @cusuh_
    Jun 16, 2020
    I'm thrilled to have been selected as one of the outstanding reviewers for #CVPR2020!!
    Image
  • user avatar
    Cusuh
    @cusuh_
    Oct 21, 2019
    I gave my first lecture today for CS 4476 Computer Vision!
  • user avatar
    Cusuh
    @cusuh_
    Jun 19, 2020
    We present DoSE, the density of states estimator for OOD detection. DoSE is a fully unsupervised method that utilizes the "probability of model probabilities," and can be easily applied to any pre-trained model: arxiv.org/abs/2006.09273 w/ Warren, Andy, @balajiln, Alex, & Josh
    Image
  • user avatar
    Cusuh
    @cusuh_
    Dec 3, 2020
    Super grateful to have been selected as an outstanding reviewer! :)
    user avatar
    ACCV2020
    @accv2020
    Dec 2, 2020
    Replying to @accv2020
    We thank all the reviewers of #ACCV2020. Here is a list of the 66 outstanding reviewers who stood out even among them in their thoroughness and thoughtfulness.
    Image
  • user avatar
    Cusuh
    @cusuh_
    Mar 4, 2020
    New work done in collaboration with @GoogleAI, "Automatic Differentiation Variational Inference with Mixtures", allowing for mixture distributions as the approximate posterior in VI and proposing SIWAE, a tighter lower bound on the evidence:
    arXiv logo
    arxiv.org
    Automatic Differentiation Variational Inference with Mixtures
    Automatic Differentiation Variational Inference (ADVI) is a useful tool for efficiently learning probabilistic models in machine learning. Generally approximate posteriors learned by ADVI are...
  • user avatar
    Cusuh
    @cusuh_
    Jul 20, 2022
    Excited to share "CoGS: Controllable Generation and Search from Sketch and Style" at #ECCV2022! (w/ Gemma Canet Tarrรฉs, @tuvbui, @jhhays, @JCollomosse, Zhe Lin) Project page: cusuh.github.io/CoGS/
    Image
  • user avatar
    Cusuh
    @cusuh_
    Nov 3, 2023
    Replying to @cusuh_
    PS I'm looking to hire a research intern for summer 2024 to work on image/video generation or multimodal learning. If you're interested, please apply online and send me an email :) bit.ly/46Usi4J
    3.7K
  • user avatar
    Cusuh
    @cusuh_
    Apr 12, 2021
    Very excited that DoSE was selected as an oral at #AISTATS2021! Stop by poster session 1 tomorrow (April 13) and/or the talk during the "Generalization/Reinforcement Learning/Optimization" session on Thursday (April 15) to learn more.
    user avatar
    Cusuh
    @cusuh_
    Jun 19, 2020
    We present DoSE, the density of states estimator for OOD detection. DoSE is a fully unsupervised method that utilizes the "probability of model probabilities," and can be easily applied to any pre-trained model: arxiv.org/abs/2006.09273 w/ Warren, Andy, @balajiln, Alex, & Josh
    Image
  • user avatar
    Cusuh
    @cusuh_
    Apr 9, 2022
    The coolest/most creative gift I've seen by far!! Adobe's intern team has really outdone itself this year. ๐Ÿ‘๐Ÿ“ท
    Image
  • user avatar
    Cusuh
    @cusuh_
    Oct 4, 2019
    Grateful for the opportunity to chat with @JeffDean over breakfast during his short visit to Georgia Tech!
    user avatar
    Machine Learning at Georgia Tech
    @mlatgt
    Oct 4, 2019
    Jeff Dean was kind enough to spend time with our students while on campus to deliver his talk to more than 600 attendees. Thanks again for sharing your perspectives on the future of tech, diversity, and more with our students. We enjoyed it! ๐Ÿ“: b.gatech.edu/2oPxbMY
    Image
    Image
    Image
    Image
  • user avatar
    Cusuh
    @cusuh_
    Aug 9, 2019
    Today marks the end of my internship at @GoogleAI. Thank you to everyone for making it such a great experience! :) Next step: starting my PhD in ML at @GeorgiaTech/@mlatgt.
  • user avatar
    Cusuh
    @cusuh_
    Jun 18, 2022
    So excited to be attending #CVPR2022 n person! Looking forward to seeing familiar faces (especially some of my virtual collaborators) and meeting new ones ๐Ÿ˜
Advertisement
Advertisement