Stars
This package implements various flow-based MCMC algorithms for statistical analyses and sampling.
Shortcut flow matching Pytorch implementation
State of the art inference for your bayesian models.
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
A Python library for amortized Bayesian workflows using generative neural networks.
A Metropolis-Hastings MCMC sampler accelerated via diffusion models
Code of the paper "Listening to the Noise: Blind Denoising with Gibbs Diffusion"
Dingo: Deep inference for gravitational-wave observations
Diffusion Generative Modeling and Posterior Sampling in Simulation-Based Inference
Unofficial implementation of "Simplifying, Stabilizing & Scaling Continuous-Time Consistency Models" for MNIST
Amortized Probabilistic Conditioning for Optimization, Simulation and Inference (Chang et al., 2024)
Neural Network-Boosted Importance Nested Sampling for Bayesian Statistics
Official implementation of Metric Flow Matching (NeurIPS 2024)
Minimal implementation of flow matching with JAX
Flow and consistency matching in Flax
Official implementation of our paper "Bidirectional Consistency Models"; and reproduced Improved Consistency Models (iCT).
Stable Consistency Tuning: Understanding and Improving Consistency models
Stream-level flow matching from a Bayesian decision theoretic perspective
The official codebase for Reflected Flow Matching (ICML 2024)
Official repository for the preprint "On Sampling with Approximate Transport Maps" in PyTorch.
Annotated Flow Matching paper
Official code for "Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs" (ICML 2023)
The official Implementation of PeriodWave and PeriodWave-Turbo
pocoMC: A Python implementation of Preconditioned Monte Carlo for accelerated Bayesian Computation