"Distributions" that might not add to one.

Differentiable convex optimization layers

RobustBench: a standardized adversarial robustness benchmark [NeurIPS'21 Benchmarks and Datasets Track]

The Happy Faces Benchmark

Mixed integer programming for computing lipschitz constants of ReLU Networks

Generative Flow Networks

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

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

alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021, 2022, and 2023)

Monte Carlo tree search in JAX

An open source implementation of CLIP.

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

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.

Streaming sparse Gaussian process approximations

A highly efficient implementation of Gaussian Processes in PyTorch

Supporting code for Assistance Games as a Framework paper

Deep learning based retinal vessel segmentation for fluorescein angiography retinal images, IEEE Trans. Image Processing, 2020

A new algorithm for retrieving topological skeleton as a set of polylines from binary images

Hypothesis strategy to generate NetworkX graphs.

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

Bayesian optimization in PyTorch

Use Jax functions in Pytorch

Graph theory (network) library for visualisation and analysis

An extremely well tested and commented red black tree implementation. Worth a look if you are studying the material.

A Python Interpreter written in Rust

Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for collecting human feedback