david-knigge / enf-min-jaxLinks
A minimal implementation of Equivariant Neural Fields (https://arxiv.org/abs/2406.05753).
☆25Updated 9 months ago
Alternatives and similar repositories for enf-min-jax
Users that are interested in enf-min-jax are comparing it to the libraries listed below
Sorting:
- ☆14Updated 9 months ago
- Clifford-Steerable Convolutional Neural Networks [ICML'24]☆49Updated 6 months ago
- Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems [ICML'25]☆107Updated last month
- 3D Gaussian Splatting in JAX☆65Updated last year
- Code for "Manifold Diffusion Geometry: Curvature, Tangent Spaces, and Dimension"☆44Updated last year
- Implicit Convolutional Kernels for Steerable CNNs [NeurIPS'23]☆29Updated 8 months ago
- Code used by the "Clifford Group Equivariant Neural Networks" paper.☆85Updated last year
- Einstein Fields official implementation in JAX.☆62Updated 2 months ago
- ☆34Updated 3 months ago
- Repo to the paper "Lie Point Symmetry Data Augmentation for Neural PDE Solvers"☆54Updated 2 years ago
- Flow-matching algorithms in JAX☆107Updated last year
- Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/☆31Updated 2 years ago
- 🚀 A powerful library for efficient training of Neural Fields at scale.☆29Updated last year
- ☆176Updated 4 months ago
- Free-form flows are a generative model training a pair of neural networks via maximum likelihood☆49Updated 4 months ago
- ☆128Updated 11 months ago
- Graph neural networks in JAX.☆68Updated last year
- ☆63Updated 2 years ago
- TorchFSM: Fourier Spectral Method with PyTorch☆50Updated last week
- S2FFT: Differentiable and accelerated spherical transforms☆209Updated this week
- Use Jax functions in Pytorch☆253Updated 2 years ago
- Neural Optimal Transport with Lagrangian Costs☆60Updated 5 months ago
- Zonal Spherical Harmonics in d Dimensions in TensorFlow, PyTorch and Jax☆34Updated last year
- Library to make any existing neural network architecture equivariant☆54Updated last year
- Wraps PyTorch code in a JIT-compatible way for JAX. Supports automatically defining gradients for reverse-mode AutoDiff.☆58Updated 3 months ago
- ☆211Updated 9 months ago
- ☆12Updated last year
- ☆166Updated last year
- Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Space.☆87Updated last year
- ☆17Updated 3 years ago