E3J: An Efficient and Open-Source Backend for Euclidean Equivariant Operations on GPU and TPU
cs.LG, cs.DC, cs.MS, physics.comp-ph
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/ax-ml/jax
Sources
- Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
- MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
- MACE-OFF: Transferable Short Range Machine Learning Force Fields for Organic Molecules
- UMA: A Family of Universal Models for Atoms
- Importance of equivariant and invariant symmetries for fluid flow modeling
- SE(3)-equivariant prediction of molecular wavefunctions and electronic densities
- e3nn: Euclidean Neural Networks
- Machine Learning Interatomic Potentials: library for efficient training, model development and simulation of molecular systems
- E3x: $\mathrm{E}(3)$-Equivariant Deep Learning Made Easy
- Complete and Efficient Covariants for 3D Point Configurations with Application to Learning Molecular Quantum Properties
- An Efficient Sparse Kernel Generator for O(3)-Equivariant Deep Networks
- Asymptotically Fast Clebsch-Gordan Tensor Products with Vector Spherical Harmonics
- Integral Formulas for Vector Signal Tensor Products
- Fast contracted Clebsch--Gordan tensor products for equivariant graph neural networks
- Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction
- E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory
- EquiformerV3: Scaling Efficient, Expressive, and General SE(3)-Equivariant Graph Attention Transformers
- A recipe for scalable attention-based MLIPs: unlocking long-range accuracy with all-to-all node attention
- An Elementary Introduction to Groups and Representations
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks