🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.

Training PyTorch models with differential privacy

Mono-Repo containing Java backend, React Frontend and Lambdas

Leaf: A Benchmark for Federated Settings

A guidance language for controlling large language models.

Structured Outputs

Ischemic stroke segmentation tool.

Google's differential privacy libraries.

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

VIBESegmentator: Full Torso Segmentation for the NAKO and UK Biobank in Volumetric Interpolated Breath-hold Examination Body Images

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

An extremely fast Python linter and code formatter, written in Rust.

A time management utility for GNOME based on the pomodoro technique!

Zero-copy MPI communication of JAX arrays, for turbo-charged HPC applications in Python ⚡

Fast, memory-efficient, scalable optimization of deep learning with differential privacy

A codebase that makes differentially private training of transformers easy.

A JAX research toolkit for building, editing, and visualizing neural networks.

Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)

Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation

🤖 Machine Learning Summer School Guide

A playbook for systematically maximizing the performance of deep learning models.

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

Compositional Linear Algebra

FFCV: Fast Forward Computer Vision (and other ML workloads!)

Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/

A tiny library for stochastic dataset caching in PyTorch.