Nequix (Meta FAIR, NeurIPS 2025 AI4Mat / ICML 2026)

github.com/atomicarchitects/nequix
Active76updated 5 months ago
Python
MIT

Equivariant foundation models for materials "on a budget", releasing pre-trained universal interatomic potentials (nequix-mp-1 on MPtrj, nequix-omat-1 on OMat24, nequix-oam-1 combining OMat24, sAlex, and MPtrj frontier datasets) with phonon fine-tuning (PFT) for accurate lattice dynamics and analytical Hessians; pip-installable with ASE calculator and JAX/PyTorch backends with OpenEquivariance kernels (Atomic Architects, 76+ stars, MIT License, 2025-2026)

Sourced from

  • Awesome AI for Sciencegithub.com/atomicarchitects/nequix
  • GitHubgithub.com/atomicarchitects/nequix

Related resources

E(3)-equivariant neural network interatomic potentials achieving DFT accuracy with up to 1000× less training data than invariant models, foundational architecture behind MACE and Allegro (Harvard, MIT, Nature Communications 2022)

Active9541 month ago
Python
MIT

Highly scalable equivariant deep learning interatomic potentials enabling million-atom molecular dynamics simulations with ab initio accuracy, building on E(3)-equivariant architectures for large-scale atomistic modeling (mir-group, MIT License, 480+ stars)

Active4983 months ago
Python
MIT

Deep learning atomistic model across elements, temperatures, and pressures

Active5851 month ago
Python
MIT

Aims to provide useful high-level interfaces that make ML for materials science as easy as possible.

Active4661 month ago
Jupyter Notebook
BSD-3-Clause

Materials informatics benchmark

Stale2142 years ago
Python
MIT

Deep learning library for Chemistry based on Tensorflow

Active6.9K1 month ago
Python
MIT