sophiaas / spectral-universalityLinks
Official PyTorch and JAX Implementation of "Harmonics of Learning: Universal Fourier Features Emerge in Invariant Networks"
☆40Updated last year
Alternatives and similar repositories for spectral-universality
Users that are interested in spectral-universality are comparing it to the libraries listed below
Sorting:
- The Energy Transformer block, in JAX☆63Updated 2 years ago
- Official Implementation of the ICML 2023 paper: "Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally …☆77Updated 2 years ago
- The Official PyTorch Implementation of "Brain-like Variational Inference" (NeurIPS 2025 Paper)☆65Updated 2 months ago
- Neural Optimal Transport with Lagrangian Costs☆61Updated 8 months ago
- Deep Networks Grok All the Time and Here is Why☆38Updated last year
- Official implementation of E(n)-equivariant Graph Neural Cellular Automata☆35Updated 3 months ago
- Implementation of approximate free-energy minimization in PyTorch☆21Updated 4 years ago
- Euclidean Wasserstein-2 optimal transportation☆47Updated 2 years ago
- ☆22Updated 4 years ago
- A library implementing the kernels for and experiments using extrinsic gauge equivariant vector field Gaussian Processes☆26Updated 4 years ago
- Fast singularity detection with kernel☆38Updated 2 years ago
- Implicit Convolutional Kernels for Steerable CNNs [NeurIPS'23]☆30Updated 11 months ago
- Meta-learning inductive biases in the form of useful conserved quantities.☆39Updated 3 years ago
- Quantify geometric intelligence in natural and artificial brains.☆51Updated 7 months ago
- Official repository of "Spontaneous symmetry breaking in generative diffusion models"☆43Updated last year
- Supplementary code for the paper "Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces"☆45Updated 2 years ago
- Riemannian Optimization Using JAX☆53Updated 2 years ago
- Official repository for the paper "Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules" (…☆23Updated 7 months ago
- ☆45Updated 2 months ago
- Riemannian Convex Potential Maps☆67Updated 2 years ago
- Free-form flows are a generative model training a pair of neural networks via maximum likelihood☆50Updated 7 months ago
- NF-Layers for constructing neural functionals.☆93Updated 2 years ago
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆41Updated last year
- ☆56Updated last year
- Loopy belief propagation for factor graphs on discrete variables in JAX☆164Updated last year
- Implementation of Action Matching for the Schrödinger equation☆25Updated 2 years ago
- ☆39Updated 3 years ago
- About A collection of AWESOME things about information geometry Topics☆176Updated last year
- Transformers with doubly stochastic attention☆53Updated 3 years ago
- ☆28Updated 2 years ago