Open GVL

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

Official implementation of AMPLIFY: Actionless Motion Priors for Robot Learning from Videos

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo, and OpenVLA) in simulation under common setups (e.g., Google Robot, WidowX+Bridge)

EdgeVLA: An open-source edge vision-language-action model for robotics.

fastdup is a powerful, free tool designed to rapidly generate valuable insights from image and video datasets. It helps enhance the quality of both images and labels, while significantly reducing d…

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

Clean PyTorch implementations of imitation and reward learning algorithms

Really Fast End-to-End Jax RL Implementations

Official implementation of the DECKARD Agent from the paper "Do Embodied Agents Dream of Pixelated Sheep?"

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

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

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Fish-function `fish_ssh_agent` to start `ssh-agent` and export its environment variables to all fish instances: currently running and newly created.

Latex code for making neural networks diagrams

Google Drive direct download of big files