rytse

dust3r

DUSt3R: Geometric 3D Vision Made Easy

efficient-kan

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

mamba-minimal

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

schedule_free

Schedule-Free Optimization in PyTorch

dora

DORA (Dataflow-Oriented Robotic Architecture) is middleware designed to streamline and simplify the creation of AI-based robotic applications. It offers low latency, composable, and distributed dataflow capabilities. Applications are modeled as directed graphs, also referred to as pipelines.

torchtyping

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

frunk

Funktional generic type-level programming in Rust: HList, Coproduct, Generic, LabelledGeneric, Validated, Monoid and friends.

jaxtyping

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

mpc.pytorch

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

PythonLinearNonlinearControl

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

sample-factory

High throughput synchronous and asynchronous reinforcement learning

safe-control-gym

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

OBCA

Optimization-Based Collision Avoidance - a path planner for autonomous navigation

MRL

Code repository for the paper - "Matryoshka Representation Learning"

l4casadi

Use PyTorch Models with CasADi for data-driven optimization or learning-based optimal control. Supports Acados.

NeuralOperators.jl

DeepONets, (Fourier) Neural Operators, Physics-Informed Neural Operators, and more in Julia

egui-snarl

Customizable egui node-graph library

differentiable-mpc

mpc-reinforcement-learning

Reinforcement Learning with Model Predictive Control

PINNacle

Codebase for PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs.

trajax

movement_primitives

Dynamical movement primitives (DMPs), probabilistic movement primitives (ProMPs), and spatially coupled bimanual DMPs for imitation learning.

quax

Multiple dispatch over abstract array types in JAX.

BarrierNet

Safe robot learning

rotation-steerers

A steerer for D-dimensional keypoint descriptions is a DxD matrix that transforms the descriptions as if they were computed from a rotated image.

GPT-PINN

Generative Pre-Trained Physics-Informed Neural Networks Implementation

stereo_matching

stereo rectification and stereo matching for perspective camera and fisheye camera, based on opencv

ORCAgym

phase-based Observations, Rewards, Coupling Ablation

terra

A grid world environment for high-level earthworks planning in JAX for RL.

sb3-burn

Implementation of stable-baselines3 in rust with burn