Reproduction of the Walk These Ways low-level locomotion controller in a MuJoCo environment for the AlienGo quadruped, enabling sim-to-sim evaluation of policies originally trained in Isaac Gym.

A Python framework for AI-driven character animation using neural networks.

Torch-based library for ML problems with symmetry priors. It provides equivariant neural network modules, models, and utilities for leveraging group symmetries in data.

Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/

We write your reusable computer vision tools. 💜

Repository for Koopman based learning and nonlinear control

Nystroem-based Koopman operator regression for linear quadratic control.

Official PyTorch implementation of NeuralSVD (ICML 2024)

Extension of RSL-RL for using Morphological Symmetries in IsaacLab

A fast and differentiable QP solver for PyTorch.

Model Predictive Control in JAX

GPU-friendly, auto-differentiable LQR solver with JAX.

Clarity: A Minimalist Website Template for AI Research

Maros-Meszaros test set for QP solvers

A CLI that writes your git commit messages for you with AI

Geometric kernels on manifolds, meshes and graphs

A package to Learn Linear Operators

Affordance-based Robot Manipulation with Flow Matching

The first behavioral foundation model to control a virtual physics-based humanoid agent for a wide range of whole-body tasks.

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

A distributed whole-body model predictive control for quadruped robots

[ICRA 2025] We present a Morphology-Informed Heterogeneous Graph Neural Network (MI-HGNN) for learning-based contact perception. The architecture and connectivity of the MI-HGNN are constructed fro…

Codebase associated with paper "Memory-Efficient Learning of Stable Linear Dynamical Systems for Prediction and Control"

Machine learning with dataframes

Body Transformer: Leveraging Robot Embodiment for Policy Learning

A Multi-Task Dataset for Simulated Humanoid Control

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

Additional code for Stable-baselines3 to load and upload models from the Hub.

Inkscape extension to render text as Latex

Mujoco Gym environment for the control of quadruped robots