Nequix (Meta FAIR, NeurIPS 2025 AI4Mat / ICML 2026)
github.com/atomicarchitects/nequixEquivariant 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 Science — github.com/atomicarchitects/nequix
- GitHub — github.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)
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)
Deep learning atomistic model across elements, temperatures, and pressures
Aims to provide useful high-level interfaces that make ML for materials science as easy as possible.
Deep learning library for Chemistry based on Tensorflow