Write PyTorch controllers, test them in simulation, and seamlessly transfer to real-time hardware.

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

🔥 SpatialVLA: a spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes. Accepted at RSS 2025.

Paper list in the survey: A Survey on Vision-Language-Action Models: An Action Tokenization Perspective

Intel® RealSense™ SDK

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

Kronos: A Foundation Model for the Language of Financial Markets

Bitcoin Core integration/staging tree

Let us control diffusion models!

Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environments.

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)

Benchmarking Knowledge Transfer in Lifelong Robot Learning

OpenVLA: An open-source vision-language-action model for robotic manipulation.

[TPAMI 2025] Towards Visual Grounding: A Survey

[ICCV 2025] DyWA:Dynamics-adaptive World Action Model for Generalizable Non-prehensile Manipulation

Unified framework for robot learning built on NVIDIA Isaac Sim

[IROS 2025 Award Finalist] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Official implementation of OpenWBT.

[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video