INNF+ 2020

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


Normalizing flows are explicit likelihood models using invertible neural networks to construct flexible probability distributions of high-dimensional data. Compared to other generative models, the main advantage of normalizing flows is that they can offer exact and efficient likelihood computation and data generation. Since their recent introduction, flow-based models have seen a significant resurgence of interest in the machine learning community. As a result, powerful flow-based models have been developed, with successes in density estimation, variational inference, and generative modeling of images, audio, and video.

This workshop is the 2nd iteration of the ICML workshop on Invertible Neural Networks and Normalizing Flows (INNF 2019). For this year's INNF+ workshop, we expand the scope of the workshop and consider likelihood-based models more broadly, including flow-based models, latent variable models and autoregressive models.

The main goals of this workshop are:
  • To increase cross-polination between research on different kinds of explicit likelihood models
  • To highlight new directions and track ongoing developments in likelihood-based modeling
  • To identify existing applications and explore new ones.

  • [July 13] Talks will be streamed here.
  • [July 2] See the How It Works tab for details regarding this year's virtual workshop.
  • [June 3] Following the decision made by NeurIPS, we've also extended the submission deadline (till June 10th) to express our support for the black community.

Key Dates

  • Paper submission deadline: June 10th, at 23h59 anywhere on earth
  • ICML 2020: July 12-18
  • INNF+ 2020: July 18 (9:30-17:40 UTC) - Link to Video Streams

Diversity and Inclusion

We're committed to creating an inclusive and welcoming workshop. Participants are encouraged to report any violations of the ICML code of conduct to the ICML Diversity and Inclusion chairs and the INNF workshop organizers. We've strived to create a diverse program and reviewer pool for our workshop, and to share our call for papers widely. However, we also are grateful for suggestions of any individual researchers or research groups who we might have missed.
Also, consider applying to the Diversity and Inclusion Fellowship, which provides free registrations for participants from under-represented groups.

Questions? Contact us at