Discrete Normalizing Flows implemented in PyTorch

Code for the paper https://arxiv.org/abs/2402.04997

Minimal implementation of flow matching with JAX

Minimalistic 4D-parallelism distributed training framework for education purpose

macOS menu bar app that shows how full the International Space Station's urine tank is in real time

Neural multiclass ab initio reconstruction for cryo-EM.

A package to train machine learning models on geospatial data, mainly for weather and climate. Used to run ArchesWeather and ArchesWeatherGen

A C++ standalone library for machine learning

keyboard layout that changes by markov frequency

Probabilistic Torch is library for deep generative models that extends PyTorch

Official implementation of our paper "Bidirectional Consistency Models"; and reproduced Improved Consistency Models (iCT).

Fast solver for L1-type problems: Lasso, sparse Logisitic regression, Group Lasso, weighted Lasso, Multitask Lasso, etc.

Making your benchmark of optimization algorithms simple and open

Flow Annealed Importance Sampling Bootstrap (FAB) with JAX.

Flow Annealed Importance Sampling Bootstrap (FAB). ICLR 2023.

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.

Implementation of papers in 100 lines of code.

Fit and compare complex models reliably and rapidly. Advanced nested sampling.

An SE(3)-invariant autoencoder for generating the periodic structure of materials [ICLR 2022]

Deep PXRD Crystallography with CDVAE.

DISCS: The code base for the Benchmark for Discrete Sampling

We all depend on Open Source. Pay the maintainers by joining the Open Source Pledge.

JAX bindings to the Flatiron Institute Non-uniform Fast Fourier Transform (FINUFFT) library

The Python ensemble sampling toolkit for affine-invariant MCMC

AlphaFold 3 inference pipeline.