🚀 Level up your GitHub profile readme with customizable cards including LOC statistics!

Train transformer language models with reinforcement learning.

DUSt3R: Geometric 3D Vision Made Easy

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

A library for scientific machine learning and physics-informed learning

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

Schedule-Free Optimization in PyTorch

A differentiable PDE solving framework for machine learning

[CVPR'22] NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

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

A library for differentiable robotics.

Computations and statistics on manifolds with geometric structures.

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

Command line toolkit for working with Arduino hardware

Model predictive control python toolbox

A modular framework for neural networks with Euclidean symmetry

A fast and differentiable model predictive control (MPC) solver for PyTorch.

Lightning fast data version control system for structured and unstructured machine learning datasets. We aim to make versioning datasets as easy as versioning code.

PythonLinearNonLinearControl is a library implementing the linear and nonlinear control theories in python.

High throughput synchronous and asynchronous reinforcement learning

BARF: Bundle-Adjusting Neural Radiance Fields 🤮 (ICCV 2021 oral)

PDEBench: An Extensive Benchmark for Scientific Machine Learning

[NeurIPS'19] Deep Equilibrium Models

A library for solving differential equations using neural networks based on PyTorch, used by multiple research groups around the world, including at Harvard IACS.

A fast and differentiable QP solver for PyTorch.

PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and RL

Geometric loss functions between point clouds, images and volumes