Call for Papers

We invite researchers in diffusion models to submit their latest work to our workshop. Accepted papers will be presented as posters during the poster sessions. Selected works will also be highlighted as contributed talks.

Topics

We invite researchers from machine learning and related fields to submit their latest work on theory and applications of diffusion models to the workshop. We encourage submissions related (but not limited) to the following topics:

  • Theory and methodology of diffusion models
    • Stochastic differential equations for generative models
    • Probabilistic inference, variational inference
    • Novel training methodology or architectures
    • Improved/accelerated diffusion model inference
    • Limitations and drawbacks of diffusion models
    • Theoretical properties of diffusion models
  • Applications of diffusion models
    • Generation of images, video, audio, molecules, motion, etc.
    • Conditional generation, guidance, controllability, and personalization
    • 3D applications of diffusion models
    • Solving inverse problems
    • Image/video editing
    • Science and engineering applications

Important Dates

  • Submission Deadline: September 29th, 2023 Extension!. October 3rd 23:59 GMT
  • Acceptance Notification: October 27th, 2023

Submission Details

To ensure your submission is considered, please adhere to the following guidelines:

  • Formatting Instructions: Use the following style files when preparing your submission. Papers need to be prepared and submitted as a single file: We accept short (4 pages) papers, with unlimited pages for references and appendix in both cases. The maximum size of submissions is 50 MB. While your submission can contain a supplement or appendix, please note that reviewers are not obliged to review supplementary material.
  • Reviews: The review process will be double-blind. All submissions must be anonymized and the leakage of any identification information is prohibited.
  • Dual Submission Policy: If the submission was accepted at prior conferences, journal, or workshops (including Neurips 2023), it should be extended to be considered for acceptance at our workshop. Papers that are currently under review are welcome to be submitted to our workshop.
  • If your paper is accepted it will not appear in any proceedings, journal, or book. We will post the list of accepted papers on the workshop website.

To submit your work, please visit the OpenReview submission website.

Questions

If you have any questions, please do not hesitate to contact us at diffusion.workshop.2023@gmail.com.