Call for Papers

Submission deadline: Friday, 12 March 2021 (23:59 AoE)

Author notification: Wednesday, 31 March 2021

Camera ready deadline: Friday, 30 April 2021 (23:59 AoE)

Workshop: Friday, 7 May 2021
The workshop will be held virtually due to risks and travel restrictions associated with SARS-CoV-2/COVID-19. For more information from ICLR, please see the ICLR conference website.

You may submit your paper through CMT, by following this link.

We encourage submissions related to learning simulations using deep learning. The areas of simulation span areas in science and engineering. Here is a non-exhaustive list of areas of learning simulation:

  • Learning simulation for physics, including by not limited to simulations in particle physics, plasma physics, astrophysics, etc.

  • Learning simulation in chemistry and biology

  • Learning PDEs, in areas including fluid dynamics, aerodynamics, and other engineering domains.

  • Learning simulation for materials

  • Learning simulation in robotics

  • Learning simulation in graphics scenes

We welcome submissions that address the following aspects of learning simulation:

  • Novel deep learning architectures and/or objectives for learning simulation

  • Application of a deep learning method to one or several important simulation domains, improving on previous methods

  • Deep learning methods to speed up simulations

  • New benchmarks and/or evaluation metrics for learning simulation

  • Theoretical understanding and analysis of architectures and/or objectives.

We will welcome original research papers of no more than 4 pages, not including references or supplementary materials. We request and recommend that authors rely on the supplementary material only to include minor details (e.g., hyperparameter settings) that do not fit in the 4 pages.

All accepted papers will be presented in the virtual poster session, with three contributed works, being selected for an oral presentation.

All submissions must use the ICLR template. Submissions should be in .pdf format, and the review process is double-blind—therefore the papers should be appropriately anonymised. Previously published work (or under-review) is acceptable.

Should you have any questions, please reach out to us via email: