Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more

🍓 Build and train energy-based and diffusion models in PyTorch ⚡.

Ying Nian Wu's UCLA Statistical Machine Learning Tutorial on generative modeling.

A primer on Bayesian Neural Networks. The aim of this reading list is to facilitate the entry of new researchers into the field of Bayesian Deep Learning, by providing an overview of key papers. More details: "A Primer on Bayesian Neural Networks: Review and Debates"

[NeurIPS 2021] SNIPS: Solving Noisy Inverse Problems Stochastically

A demo shows how to combine Langevin dynamics with score matching for generative models.

Langevin dynamics based tours of data, in Javascript with R wrapper.

Sampling-based approach to analyse neural networks using TensorFlow

A python code to calculate the Brownian motion of colloidal particles in a time varying force field.

The code enables to perform Bayesian inference in an efficient manner through the use of Hamiltonian Neural Networks (HNNs), Deep Neural Networks (DNNs), Neural ODEs, and Symplectic Neural Networks (SympNets) used with state-of-the-art sampling schemes like Hamiltonian Monte Carlo (HMC) and the No-U-Turn-Sampler (NUTS).

Code for enumerating and evaluating numerical methods for Langevin dynamics using near-equilibrium estimates of the KL-divergence. Accompanies https://doi.org/10.3390/e20050318

[ICCV 2025] Official implementation of "Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin".

Python solver for the Brownian, Stochastic, or Noisy Differential Equations

Agent-based simulation of social interaction (Social Force Model and Self-Propelled Brownian Particles)

Noise-conditional score networks for music composition by annealed Langevin dynamics

A simulation framework for nonequilibrium statistical physics

[ICML2025] Regularized Langevin Dynamics for Combinatorial Optimization

Implementation of CODE: Confident Ordinary Differential Editing

Utilities for determining maximum tolerable timesteps. See https://doi.org/10.3390/e20050318

Simulation of Langevin dynamics

Finding Optimal Langevin Inferred Equations

Official implementation of our NeurIPS 2025 poster paper "PID-controlled Langevin Dynamics for Faster Sampling of Generative Models"

Software platform for Thermodynamic Sampling Units - probabilistic computing emulator

Python module for (symbolic) evaluation of the short-time Fokker-Planck propagator to arbitrary accuracy

The GitHub repository for "Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics", ICML 2024

The GitHub repository for "Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo", AISTATS 2024.

The official code release for "More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling", Reinforcement Learning Conference (RLC) 2024

Bayesian Neural Network (BNN) implementations based on Langevin Dynamics and tested on real-world data

Simulation of a particle in a 2D Lennard-Jones gas for studying brownian motion, the Langevin equation, and non-equilibrium fluctuation-dissipation relations. Langevin simulation for studying first passage time, survival probabilities under various resetting schemes.

Spring