equivariant-neural-networks

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

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

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

Tools for exploiting Morphological Symmetries in robotics

Library to make any existing neural network architecture equivariant

One learned latent for geometry + physics + manufacturability: give it a box and a load, get a solver-certified bracket. SE(3)-equivariant field model, immersed FEA, live 3D designer.

Annotated implementations of equivariant (graph) neural networks in Jax: EGNN, SEGNN, NequIP.

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

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

[ICML'25] "Rethinking Addressing in Language Models via Contextualized Equivariant Positional Encoding" by Jiajun Zhu, Peihao Wang, Ruisi Cai, Jason D. Lee, Pan Li, Zhangyang Wang

Torch-based library for ML problems with symmetry priors. It provides equivariant neural network modules, models, and utilities for leveraging group symmetries in data.

[KDD26 Oral AI4S Track] The official implementation of the paper "EqCollide: Equivariant and Collision-Aware Deformable Objects Neural Simulator"

Contact-grounded SE(3)-equivariant dexterous grasp generative flows

Designing antibody CDRs with flexible CDR definition, using equivariant graph neural networks. Bioinformatics (2024).

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.

Scientific machine learning for JAX/Flax NNX: neural operators (FNO family, DeepONet, PINO, UNO), physics-informed networks (PINN, FBPINN, XPINN), E(3)-equivariant atomistic potentials (SchNet, PaiNN, NequIP), differentiable Kohn-Sham DFT, SINDy equation discovery, uncertainty quantification (conformal, GPs, SBI), PDEBench benchmarking.

Variational algorithms for finding ground states of lattice gauge theories using gauge equivariant neural network ansätze. Phys. Rev. B 110, 165133 (2024).

This project measures whether Cl(3,0) geometric algebra layers bring anything beyond exact SO(3) equivariance on small synthetic 3D vector tasks.

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

Cross-neighbour Hermitian density operators for equivariant machine-learned interatomic potentials