Skip to content

#

e3nn

Here are 14 public repositories matching this topic...

Language: All

Filter by language

All 14 Python 8 Jupyter Notebook 3 Cuda 1

Sort: Most stars

Sort options

Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

chaitjo / geometric-gnn-dojo

Geometric GNN Dojo provides unified implementations and experiments to explore the design space of Geometric Graph Neural Networks (ICML 2023)

pytorch graph-isomorphism geometric-deep-learning graph-neural-networks pytorch-geometric equivariance geometric-graphs equivariant-networks e3nn

Updated Oct 9, 2025
Jupyter Notebook

atomicarchitects / equiformer_v2

[ICLR 2024] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

machine-learning deep-learning molecular-dynamics pytorch computational-chemistry computational-physics drug-discovery materials-science force-fields geometric-deep-learning graph-neural-networks interatomic-potentials ai-for-science e3nn equivariant-neural-networks equivariant-graph-neural-network catalyst-design equiformer

Updated Apr 10, 2026
Python

atomicarchitects / equiformer

[ICLR 2023 Spotlight] Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs

machine-learning deep-learning molecular-dynamics pytorch computational-chemistry drug-discovery materials-science force-fields geometric-deep-learning graph-neural-networks interatomic-potentials ai-for-science e3nn equivariant-neural-networks equivariant-graph-neural-network catalyst-design equiformer

Updated Feb 11, 2025
Python

atomicarchitects / equiformer_v3

EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers

machine-learning deep-learning molecular-dynamics pytorch drug-discovery force-field materials-science geometric-deep-learning e3nn machine-learning-interatomic-potential equivariant-neural-networks equivariant-graph-neural-network material-discovery catalyst-design mlip equiformer

Updated Apr 17, 2026
Python

Infatoshi / batmobile

High-performance CUDA kernels for equivariant graph neural networks (MACE, NequIP, Allegro). 10-20x faster than e3nn.

machine-learning cuda molecular-dynamics pytorch gpu-computing mace e3nn equivariant-neural-networks

Updated Jan 17, 2026
Cuda

atomicarchitects / DeNS

[TMLR 2024 J2C Certification] Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fields

molecular-dynamics computational-chemistry drug-discovery denoising-autoencoders force-fields geometric-deep-learning graph-neural-networks self-supervised-learning e3nn equivariant-graph-neural-network

Updated Feb 11, 2025
Python

atomicarchitects / tensor-spherical-harmonics

Fully-Differentiable Tensor Spherical Harmonics in JAX

physics spherical-harmonics equivariance e3nn

Updated Apr 11, 2026
Jupyter Notebook

brian-hepler-phd / Spherical-CNN

Interactive exploration of equivariant neural networks on homogeneous spaces, with a focus on the sphere S2 as SO(3)/SO(2). From Lecture 8 of the Lie groups course with Quantum Formalism

machine-learning pytorch scientific-computing lie-groups representation-theory geometric-deep-learning spherical-cnn homogeneous-spaces e3nn equivariant-neural-networks

Updated May 6, 2025
Jupyter Notebook

Mandala-org / Mandala

Mandala is an E(3)-Equivariant Graph Neural Network Framework for Learning Electronic-Structure Operators with Observable Guidance based on e3nn.

torch density-functional-theory hamiltonian electronic-structure gnns density-matrix e3nn equivariant-graph-neural-network

Updated Sep 7, 2026
Python

Rutgers-ZRG / EosNet

EOSNet: Graph neural network with Gaussian Overlap Matrix (GOM) fingerprints for predicting material properties. Supports CGCNN and e3nn equivariant backbones, s and s+p orbitals, and differentiable GOM for MLIP energy/force prediction.

machine-learning fingerprints crystal-structure graph-neural-network e3nn mlip

Updated May 4, 2026
Python

Islamomar-1 / ShapePharm3D

3D pharmacophore-conditioned molecular diffusion with an E(3)-equivariant EGNN backbone. Generates shape-complementary, drug-like molecules conditioned on pharmacophore point clouds and PMI/SSD shape descriptors. Inspired by ShEPhERD (Adams et al., ICLR Oral 2025). PyTorch · e3nn · RDKit.

deep-learning cheminformatics pytorch computational-chemistry drug-discovery rdkit molecular-design generative-models pharmacophore geometric-deep-learning graph-neural-networks diffusion-models molecular-generation egnn e3nn equivariant-neural-networks 3d-molecules shape-based-design scaffold-hopping bioisostere

Updated Jun 29, 2026

mghourchian86-creator / equiformer_v3

Implement SE(3)-equivariant graph attention transformers for efficient and expressive molecular modeling in PyTorch.

machine-learning deep-learning molecular-dynamics pytorch drug-discovery materials-science geometric-deep-learning e3nn machine-learning-interatomic-potential equivariant-neural-networks equivariant-graph-neural-network material-discovery catalyst-design mlip equiformer

Updated Sep 8, 2026

Tasty-Ramen2010 / metal-e3nn

Fused Metal kernels for e3nn tensor products on Apple GPUs — 3.1-6.7x faster than stock e3nn, no build step

metal pytorch openmm computational-chemistry gpu-acceleration mps apple-silicon e3nn equivariant-neural-networks

Updated Aug 1, 2026
Python

en970 / Equ-GNN

E(3)-equivariant GNNs for protein-ligand binding-affinity prediction (EGNN + e3nn tensor-product), with a machine-precision invariance test suite.

bioinformatics deep-learning cheminformatics structural-biology protein-structure computational-biology pytorch drug-discovery message-passing geometric-deep-learning graph-neural-networks pytorch-geometric binding-affinity protein-ligand egnn e3nn equivariant-neural-networks se3-equivariance molecular-machine-learning pdbbind

Updated Jul 16, 2026
Python

Add this topic to your repo

To associate your repository with the e3nn topic, visit your repo's landing page and select "manage topics."