Call for Papers

We invite researchers working at the intersection of machine learning and simulation techniques (e.g., physics, graphics, molecular systems) to submit their latest work to our workshop. Accepted papers will be presented as posters during the poster session.

Topics

We are seeking submissions in topics including, but not limited to:

• Differentiable simulators and neural surrogates in various domains (e.g., graphics, EM-wave propagation, physics, molecular systems)
• Probabilistic Inverse Problems (e.g., simulation-based inference, posterior and likelihood estimation)
• Probabilistic Simulation (e.g. probabilistic ODE and PDE solvers, uncertainty quantification in operators, especially for data assimilation)
• Techniques to speed-up simulation (e.g., neural surrogates, efficient blackbox optimization)
• Improving simulation accuracy (e.g., mitigating sim2real gap, learnable formulation)
• Hybrid simulation and rendering approaches (e.g., neural fields)
• Generative modelling for simulation (e.g., biomolecule structure synthesis, material generation, image generation for autonomous vehicles)
• Datasets, gyms, and simulation softwares

Important Dates

• Submission deadline: August 23 August 30, 2024, AoE
• Acceptance notification: September 23 September 30, 2024, AoE ¹
• Workshop date: December 15, 2024

Submission Details

• Submission system: ~~Submit on OpenReview
• Template: NeurIPS single-column. Feel free to use D3S3 style files.
  • The checklist and requirements (e.g., broader impact, open access to data and code) is optional, but encouraged for responsible ML research.
• Page limit: 4 pages, excluding references and appendices
• Double-blind reviewing: Authors should anonymize their submissions
• Publication: All accepted papers will be made available on the workshop website. Workshop is non-archival and will not have proceedings
• Originality: Original and unpublished works are highly encouraged. We welcome various types of submissions on novel approaches, results, benchmarks, datasets, and in-progress research. We will prudently consider previously published works, if we think it will constructively adds to discussions and knowledge sharing at the workshop. In this case, authors should make it clear that the work was previously published and why they believe the workshop will benefit
• Dual-submission policy: You can submit papers that are under review at another venue (e.g., NeurIPS, other workshops) at the time of submission
• Attending the workshop: Workshop is primarily in-person. If accepted, authors are asked to prepare a poster and if possible, to present it

Camera-Ready Instructions

• Camera-ready submission deadline: October 15, 2024, AoE
  • Please resolve any important issues pointed out by reviewers.
• Template: Feel free to use D3S3 style files. You need to include the final option: \usepackage[final]{d3s3_neurips_2024}.
  • The page limit for the main content is still 4 pages, followed by references, and ending with an optional appendix.
  • Make sure your paper is deanonymized.
• How to upload camera-ready: Upload a single PDF on OpenReview, by clicking Edit → Camera-Ready revision in your submission’s page.

Questions

If you have any questions, email us at d3s3.organizers@gmail.com