PyTorch implementation for our ICLR 2024 paper "Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization"

Official code for "Stochastic Localization via Iterative Posterior Sampling"

Lagrangian formulation of Doob's h-transform allowing for efficient rare event sampling

Collecting research materials on neural samplers with diffusion/flow models

A standardized protein design benchmark for motif-scaffolding problems

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

Official Implementation of paper "Training Neural Samplers with Reverse Diffusive KL Divergence"

A library for learning Gaussian mixture models for variational inference

[ICML 2024] Official implementation for "Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling".

Implementation of methods to sample from Boltzmann distributions

Code for the paper Iterated Denoising Energy Matching for Sampling from Boltzmann Densities.

Matlab code implementing Hamiltonian Annealed Importance Sampling for importance weight, partition function, and log likelihood estimation for models with continuous state spaces

Fast protein backbone generation with SE(3) flow matching.

TorchCFM: a Conditional Flow Matching library

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

MIMIC Code Repository: Code shared by the research community for the MIMIC family of databases

High-Resolution Image Synthesis with Latent Diffusion Models

Causal Inference with Invariant Prediction

Python implementation of the Invariant Causal Prediction (ICP) algorithm, from the 2015 paper "Causal inference using invariant prediction: identification and confidence intervals" by Jonas Peters,…

MLX: An array framework for Apple silicon

An optimization-based algorithm to accurately estimate the causal effects and robustly predict under distribution shifts. It leverages the invariance of causality over multiple environments.

Practically and asymptotically accurate conditional sampling from diffusion generative models without conditional training

Implementation for SE(3) diffusion model with application to protein backbone generation

Diffusion models for probabilistic programming

A python package providing a benchmark with various specified distribution shift patterns.

some scripts for the couplings enthusiasts!

A MNIST-like fashion product database. Benchmark 👇