maxxxzdn/erwin

Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems [ICML'25]

31
/ 100
Emerging

This tool helps scientists and engineers analyze complex physical systems that can be represented as large collections of points in 3D space, like atoms in a molecule or parts of a mechanical structure. It takes in the positions and features of these points and efficiently processes them to understand their relationships and overall system behavior. This is ideal for researchers in molecular dynamics, materials science, robotics, or anyone working with large-scale point cloud data.

112 stars. No commits in the last 6 months.

Use this if you need to perform efficient, hierarchical analysis on very large point cloud datasets, such as those found in simulations of physical systems, where understanding local and global interactions is critical.

Not ideal if your data is primarily grid-based images or sequences, or if your systems have a small number of components where simpler analysis methods would suffice.

molecular-dynamics materials-science computational-physics point-cloud-analysis robotics
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

112

Forks

11

Language

Python

License

Last pushed

Oct 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/maxxxzdn/erwin"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.