maxxxzdn/erwin
Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems [ICML'25]
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.
Stars
112
Forks
11
Language
Python
License
—
Category
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.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action