The first open-source unified world model for scalable robot manipulation:

5B-parameter open-source unified video-action world model that combines policy and world modeling to generate robot actions, predict future visuals, and evaluate task progress from observations, language, and state.

The model is trained on 27.3K hours of heterogeneous data (17.8K real-robot teleop, 6.5K UMI demos, 3K egocentric human videos), enabling it to perform complex manipulation tasks like faucet connecting, bag packing, and toolbox storing as shown in demo videos.

The approach supports test-time action refinement and points toward deployment-driven continuous improvement via fleet data.

Thanks for sharing, Jianlan Luo (@jianlanluo)!

📌 Resource links for τ0-WM:

• Project page: https://finch.agibot.com/research/tau0-wm • GitHub (code): https://github.com/sii-research/tau-0-wm • Hugging Face (model weights): https://huggingface.co/sii-research/tau-0-wm • Paper (PDF): https://finch-static.agibot.com/VAM/blog/tau_0_wm.pdf

——-

Weekly robotics and AI insights. Subscribe free: http://22astronauts.com