gerkone / segnn-jax
Steerable E(3) GNN in jax
☆22Updated last year
Related projects ⓘ
Alternatives and complementary repositories for segnn-jax
- ☆18Updated last year
- C++/CUDA library for SO(3) equivariant operations☆19Updated last month
- Tools for building equivariant polynomials on reductive Lie groups.☆26Updated last year
- ☆21Updated 7 months ago
- Higher order equivariant graph neural networks for 3D point clouds☆33Updated last year
- Annotated implementations of equivariant graph neural networks in Jax: EGNN, SEGNN, NequIP.☆21Updated this week
- ☆11Updated last year
- A repo to finetune NNIPs by training on observables☆12Updated 7 months ago
- Equivariant machine learning interatomic potentials in JAX.☆62Updated last year
- Code repository for "Finding symmetry breaking order parameters with Euclidean Neural Networks"☆12Updated 3 years ago
- An implementation of SchNet in JAX and JAX-MD.☆17Updated 2 years ago
- Reference implementation of "Ewald-based Long-Range Message Passing for Molecular Graphs" (ICML 2023)☆42Updated last year
- Robust NN MD simulator☆19Updated last year
- Pure C implementation of e3nn☆15Updated this week
- CUDA implementations of MACE models☆10Updated 4 months ago
- ☆11Updated 6 months ago
- Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting☆30Updated 8 months ago
- MESS: Modern Electronic Structure Simulations☆17Updated last month
- This repo contains the datasets used for the paper The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials.☆17Updated 2 years ago
- cuEquivariance is a math library that is a collective of low-level primitives and tensor ops to accelerate widely-used models, like DiffD…☆53Updated this week
- ☆27Updated 2 years ago
- Molecular mechanics systems and simulation data☆15Updated 5 months ago
- E3x is a JAX library for constructing efficient E(3)-equivariant deep learning architectures built on top of Flax.☆90Updated last week
- Text-based modeling of materials.☆25Updated 3 weeks ago
- A Newtonian message passing network for deep learning of interatomic potentials and forces☆32Updated 3 months ago
- Implementation of various equivariant models in JAX☆12Updated 7 months ago
- MESS: Modern Electronic Structure Simulations☆20Updated last month
- Training Neural Network potentials through customizable routines in JAX.☆21Updated 2 months ago
- Lagrangian formulation of Doob's h-transform allowing for efficient rare event sampling☆39Updated 3 weeks ago
- SE(3) Equivariant Augmented Coupling Flows. NeurIPS 2023.☆23Updated 7 months ago