INNF+ 2021

ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models

Submission Details

We invite researchers to submit their recent progress on the development, analysis or application of likelihood-based generative models, normalizing flows and invertible neural networks. Submissions should take the form of an extended abstract of 4 pages, excluding references, acknowledgements or appendices. Submissions whose main content is longer than 4 pages are not allowed. Submissions must be prepared in PDF format using the template. Reviewing will be double blind, and author names must be anonymized. Submissions may include supplementary material/appendix, but reviewers are not expected to read any supplementary material. Submissions that are currently under review or that have been recently accepted for publication to another conference are permitted (but must adhere to the 4 page limit and use the provided template).

Potential topics include but are not limited to:
  • Normalizing flows and other likelihood-based generative modeling
  • Designing invertible transformations parameterized by neural networks
  • Applications of explicit likelihood models, for example in approximate inference, reinforcement learning, probabilistic programming, or physical and life sciences.
  • Theoretical work in terms of optimization and/or expressivity of invertible networks

Submission website

Please submit your work via OpenReview.


  • Submission deadline: June 1st 23h59 AOE
  • Review deadline: June 11th 23h59 AOE
  • Accept/reject notification date: June 15th 23h59 AOE
  • Video recordings deadline: June 27th 23h59 AOE

Questions? Contact us at