CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Bayesian optimization in PyTorch

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

functorch is JAX-like composable function transforms for PyTorch.

PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) and inference in Bayesian neural networks

The nnsight package enables interpreting and manipulating the internals of deep learned models.

This repository is part of a "Space Science with Python" tutorial series. The corresponding articles that explain each part are available on Medium (https://medium.com/@thomas.albin). If you do not…

A clean implementation of MuZero and AlphaZero following the AlphaZero General framework. Train and Pit both algorithms against each other, and investigate reliability of learned MuZero MDP models.

Uniform Manifold Approximation with Two-phase Optimization (IEEE VIS 2022 short)

Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"

Mixed integer programming for computing lipschitz constants of ReLU Networks

Code for replicating experiments from the paper, Preference Exploration for Efficient Bayesian Optimization with Multiple Outcomes, published in AISTATS 2022.

Jupyter Notebook using a differential equation integration solver based on a Leapfrog Algorithm and vectorized ODEs to simulate and plot the orbits from different objects in the solar system with i…

Code to support the guide to logical induction for software engineers (not yet published).