ModelScope(@ModelScope2022):Xiaomi-Robotics-U0-4B packs unified embodied world generation into a compact 4B model. 📜 Apache 2.0. 🤖 https://t.co/t0lExTpGNf 📄 https://t.co/na6Pxa1bum 🏆 The full U0 system ranks #1 on World Arena and lifts π0.5’s real-world OOD success from 36.9% to 63.2% with generated data. 🌍 Generate or edit consistent multi-view scenes across robot embodiments. It also supports text-to-image and instruction-guided generation. 🛠 Change objects, layouts, robot bodies, and camera views while preserving task structure and cross-view consistency. 🧠 Text, images, and embodied observations share one token space and next-token objective. Inference code and Gradio are included.

ModelScope@ModelScope2022

2026.09.10 13:01

Xiaomi-Robotics-U0-4B packs unified embodied world generation into a compact 4B model. 📜 Apache 2.0. 🤖 📄 🏆 The full U0 system ranks #1# on World Arena and lifts π0.5’s real-world OOD success from 36.9% to 63.2% with generated data. 🌍 Generate or edit consistent multi-view scenes across robot embodiments. It also supports text-to-image and instruction-guided generation. 🛠 Change objects, layouts, robot bodies, and camera views while preserving task structure and cross-view consistency. 🧠 Text, images, and embodied observations share one token space and next-token objective. Inference code and Gradio are included.