ebekkers / ponita
Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Space.
☆81Updated 10 months ago
Alternatives and similar repositories for ponita:
Users that are interested in ponita are comparing it to the libraries listed below
- [ICLR 2024 Spotlight] Official Implementation of "Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Product…☆58Updated 5 months ago
- E(3) Steerable Graph Neural Network☆116Updated 2 years ago
- Code for “FlowMM Generating Materials with Riemannian Flow Matching” and "FlowLLM: Flow Matching for Material Generation with Large Langu…☆121Updated 5 months ago
- Code used by the "Clifford Group Equivariant Neural Networks" paper.☆80Updated 10 months ago
- Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems☆44Updated this week
- Code repository of the paper "Clifford-Steerable Convolutional Neural Networks"☆47Updated 8 months ago
- jax library for E3 Equivariant Neural Networks☆204Updated 2 months ago
- SE(3) Equivariant Augmented Coupling Flows. NeurIPS 2023.☆24Updated last year
- [ICLR 2023 Spotlight] Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs☆234Updated 2 months ago
- E3x is a JAX library for constructing efficient E(3)-equivariant deep learning architectures built on top of Flax.☆103Updated last week
- code for "Riemannian Flow Matching on General Geometries".☆218Updated last year
- Implementation of the Equiformer, SE3/E3 equivariant attention network that reaches new SOTA, and adopted for use by EquiFold for protein…☆265Updated 4 months ago
- This Denoising Force Field (DFF) codebase provides a Pytorch framework for the method presented in Two for one: Diffusion models and forc…☆58Updated 10 months ago
- A short and easy PyTorch implementation of E(n) Equivariant Graph Neural Networks☆131Updated 3 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…☆209Updated this week
- Lagrangian formulation of Doob's h-transform allowing for efficient rare event sampling☆49Updated 3 weeks ago
- Annotated implementations of equivariant (graph) neural networks in Jax: EGNN, SEGNN, NequIP.☆31Updated last month
- [ICLR 2024] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations☆262Updated 2 months ago
- ☆28Updated 2 years ago
- ☆182Updated 2 months ago
- Official implementation of All Atom Diffusion Transformers☆179Updated 2 weeks ago
- MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation☆99Updated 7 months ago
- ☆34Updated 2 months ago
- ☆157Updated 5 years ago
- ☆60Updated 3 years ago
- FoldFlow: SE(3)-Stochastic Flow Matching for Protein Backbone Generation☆220Updated 4 months ago
- ICML2024: Equivariant Graph Neural Operator for Modeling 3D Dynamics☆57Updated last year
- PySCF on IPU☆42Updated last year
- Code for the paper Iterated Denoising Energy Matching for Sampling from Boltzmann Densities.☆51Updated last week
- Tools for building equivariant polynomials on reductive Lie groups.☆30Updated last year