25 skills found
e3nn / E3nnA modular framework for neural networks with Euclidean symmetry
chaitjo / Geometric Gnn DojoGeometric GNN Dojo provides unified implementations and experiments to explore the design space of Geometric Graph Neural Networks (ICML 2023)
atomicarchitects / Equiformer V2[ICLR 2024] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
atomicarchitects / Equiformer[ICLR 2023 Spotlight] Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs
e3nn / E3nn Jaxjax library for E3 Equivariant Neural Networks
blondegeek / E3nn Tutorialrepository and website for tutorials on 3d Euclidean equivariant neural networks
Infatoshi / BatmobileHigh-performance CUDA kernels for equivariant graph neural networks (MACE, NequIP, Allegro). 10-20x faster than e3nn.
atomicarchitects / DeNS[TMLR 2024 J2C Certification] Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fields
SCAN-NRAD / E3nn UnetNo description available
zhantaochen / Phonondos E3nnCode Repository for "Direct prediction of phonon density of states with Euclidean neural network"
teddykoker / E3nn.cPure C implementation of e3nn
prescient-design / E3toolsBuilding Blocks for Equivariant Neural Networks in e3nn and PyTorch 2.0
Hongyu-yu / T E3nnTime-reversal Euclidean neural networks based on e3nn
blondegeek / E3nn Symm BreakingCode repository for "Finding symmetry breaking order parameters with Euclidean Neural Networks"
brian-hepler-phd / Spherical CNNInteractive 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
e3nn / E3nn Tutorial Mrs Fall 2021e3nn tutorial for Materials Research Society Fall Meeting 2021
Dsantra92 / E3nn.jlE(3)-equivariant graph neural networks (e3nn) for Julia
thu-wangz17 / E3nn Notese3nn从入门到放弃
shiangfang / E3nn ModelsNo description available
Rutgers-ZRG / EosNetEOSNet: 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.
