Dark Data Discovery for Neuro Datasets

A reinforcement learning codebase focusing on the emergence of cooperation and alignment in multi-agent AI systems.

Jax implementation of normcorre

Pure-Python DAG-based high-performance SHM-backed pub-sub and multi-processing pattern

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

Code repository for the Animal AI Olympics competition

Generative Manifold Network

Package for extracting and mapping the results of every single tensor operation in a PyTorch model in one line of code.

Estimating the dimensionality of neural data using Shared Variance Component Analysis (SVCA)

Aligning AI With Shared Human Values (ICLR 2021)

High accuracy RAG for answering questions from scientific documents with citations

PsyCalibrator

A 1D analogue of the MNIST dataset for measuring spatial biases and answering Science of Deep Learning questions.

Official Implementation of POYO-1 https://poyo-brain.github.io/

A reservoir computing toolbox for neuroscientists

Python client library for Mistral AI platform

[ICLR 2023] Code for BrainBERT

A modular, easy to extend GFlowNet library

JAX-based neural network library

Flax is a neural network library for JAX that is designed for flexibility.

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.

Fast and simple stream processing of files in tar files, useful for deep learning, big data, and many other applications.

Vector (and Scalar) Quantization, in Pytorch

Implementation of NWT, audio-to-video generation, in Pytorch

This is the development home of the workflow management system Snakemake. For general information, see

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.