JAX implementation of Large Language Models. You can train GPT-2-like model with 青空文庫 (aozora bunko-clean dataset) or any other text dataset.

A high performance Python graph library implemented in Rust.

A python based light weight robot simulator for the algorithm development of robotics navigation, control, and learning

JRDB dataset: trajectory prediction baselines and data preprocessing

A Toolkit for OpenAI's Consistency Models.

macOS Native ROS 2

pointcloud2gazebo is a package that allows you to create a Gazebo World from a 3D point cloud.

Python package for point cloud registration using probabilistic model (Coherent Point Drift, GMMReg, SVR, GMMTree, FilterReg, Bayesian CPD)

Official implementation of "Counterfactual Fairness Filter for Fair-Delay Multi-Robot Navigation" (AAMAS-23)

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

prompt2model - Generate Deployable Models from Natural Language Instructions

Tight Learned Inertial Odometry

a Hassle-Free Python Experience

The Mojo Programming Language

RTAB-Map library and standalone application

Collection of tools, resources and sample code to use alongside the Sensor Logger app

Tight Learned Inertial Odometry

A high-performance, zero-overhead, extensible Python compiler using LLVM

Code for "Stochastic Optimization of Sorting Networks using Continuous Relaxations", ICLR 2019.

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

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

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Orbax provides common checkpointing and persistence utilities for JAX users

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Convolutional Neural Networks for Denoising Gyroscopes of Low-Cost IMUs

A benchmark environment for fully cooperative human-AI performance.

RoNIN: Robust Neural Inertial Navigation in the Wild