Great work by @francois-rozet.bsky.social. Some really unexpected insights about compression in LDMs. It was such a privilege to have him with us @polymathicai.bsky.social!

Heading off to #NeurIPS2024 today! Feel free to reach out if you're around to catch up!

If you're interested, please visit our poster sessions tomorrow at 11 PST for MPP (neurips.cc/virtual/2024...) or on Thursday at 11 for the Well (neurips.cc/virtual/2024...).

Thanks! We really admire the BlastNet projects as well and definitely see them as an influence.

This was a huge collaborative effort with too many contributors to list in one post, but it wouldn't have been possible without all of our teammates @polymathicai.bsky.social and elsewhere.

We hope that access to more realistic problems pushes the development of #AI4Science forward!

and many more! All data in the Well is stored in a uniform format and whether its 2D or 3D it's accessible through the same API. The Well additionally includes benchmarking tools such as baseline models, tensor-aware augmentations, and metric implementations:

To only recently described variations of non-Newtonian turbulence:

to orientation-dependent forcings in biological systems:

To high resolution vortices resulting from discontinuous initial conditions:

The dataset contains a wide range of challenges from chemistry, biology, fluids, astrophysics including difficulties spanning from sharp discontinuities in the coefficient fields:

The Well was curated in collaboration with domain experts and numerical software developers specifically to provide challenging dynamics reflective of practical scientific research while staying accessible to machine learning audiences in terms of resolution and geometry.

Today along with my project co-lead @rubenohana.bsky.social and the team at @polymathicai.bsky.social I'm excited to announce the release of the Well, a 15TB collection of 15+ datasets for physical simulation.

Paper: openreview.net/pdf?id=00Sx5...
Github: github.com/PolymathicAI...