thu-ml/RoboticsDiffusionTransformer

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

[ICML 2026] RoboTwin 2.0 Offical Code Repo

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

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

robomimic: A Modular Framework for Robot Learning from Demonstration

High-fidelity world models for general embodied intelligence, such as data engines and world simulators.

Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark