gabrielraya / symmetry_breaking_diffusion_models
Official repository of "Spontaneous symmetry breaking in generative diffusion models"
☆40Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for symmetry_breaking_diffusion_models
- Official Implementation of the ICML 2023 paper: "Neural Wave Machines: Learning Spatiotemporally Structured Representations with Locally …☆69Updated last year
- Official repository of Implicit Neural Convolutional Kernels for Steerable CNNs, Zhdanov et al.☆25Updated 7 months ago
- Flow-matching algorithms in JAX☆73Updated 2 months ago
- Transformers with doubly stochastic attention☆40Updated 2 years ago
- ☆33Updated last year
- Code repository of the paper "Clifford-Steerable Convolutional Neural Networks"☆40Updated 2 months ago
- Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations☆25Updated last year
- Visualizations of the theory behind diffusion models.☆73Updated 6 months ago
- Code for 'Periodic Activation Functions Induce Stationarity' (NeurIPS 2021)☆18Updated 3 years ago
- ☆11Updated 10 months ago
- Neural Diffusion Processes☆72Updated 3 months ago
- 🚀 A powerful library for efficient training of Neural Fields at scale.☆26Updated 9 months ago
- ☆48Updated 8 months ago
- Repo to the paper "Lie Point Symmetry Data Augmentation for Neural PDE Solvers"☆47Updated last year
- The 2D discrete wavelet transform for JAX☆38Updated last year
- Neural Optimal Transport with Lagrangian Costs☆47Updated 3 months ago
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆38Updated 9 months ago
- The Energy Transformer block, in JAX☆50Updated 10 months ago
- Modern Fixed Point Systems using Pytorch☆82Updated last year
- Riemannian Convex Potential Maps☆68Updated last year
- JAX exponential map normalising flows on sphere☆17Updated 4 years ago
- NF-Layers for constructing neural functionals.☆75Updated 10 months ago
- Euclidean Wasserstein-2 optimal transportation☆43Updated last year
- Code for the paper: Rotating Features for Object Discovery☆48Updated 2 months ago
- ☆149Updated 3 months ago
- ☆40Updated 4 months ago
- Free-form flows are a generative model training a pair of neural networks via maximum likelihood☆35Updated 4 months ago
- Official repository for our ICLR 2021 paper Evaluating the Disentanglement of Deep Generative Models with Manifold Topology☆36Updated 3 years ago
- Meta-learning inductive biases in the form of useful conserved quantities.☆37Updated last year
- Sequence Modeling with Multiresolution Convolutional Memory (ICML 2023)☆120Updated last year