A library of algorithms for approximate nearest neighbor search in high dimensions, along with a set of useful tools for designing such algorithms.

Forth does tensors, in CUDA.

A fast RWKV Tokenizer written in Rust

work-in-progress structure-based ascii art

Making it easier to work with shaders

Rudimentary Roam replica with Org-mode

pixel art editor, test version

Simplifying reinforcement learning for complex game environments

TPU pod commander is a package for managing and launching jobs on Google Cloud TPU pods.

Wings3D is an advanced sub-division 3D modeller.

Abusing the TypeScript type checker as a spell checker because I just can't help myself.

If it quacks like a tensor...

LC-3 parser, assembler, and simulator written in Rust

The development repository for LessWrong2 and the EA Forum, based on Vulcan JS

DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.

prime is a framework for efficient, globally distributed training of AI models over the internet.

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

Entropy Based Sampling and Parallel CoT Decoding

GPU implementation of a fast generalized ANS (asymmetric numeral system) entropy encoder and decoder, with extensions for lossless compression of numerical and other data types in HPC/ML applications.

An implementation of the DeepMind's AlphaFold based on PyTorch for research

This module helps you scrape panoramas from Google's streetview

We propose the first multi-human body-part segmentation model, called Human3D 🧑‍🤝‍🧑, that directly operates on 3D scenes. In an extensive analysis, we validate the benefits of training on synthetic…

PyTorch implementation of FlowDiffuser: Advancing Optical Flow Estimation with Diffusion Models (CVPR-2024)

Lightweight stereo matching network based on MobileNet blocks

Basic Circuit Simulator