Xiaomi introduces Xiaomi-Robotics-U0, a 38-billion-parameter multimodal autoregressive model that unifies text-to-image generation, image editing, embodied scene synthesis, embodied transfer, and embodied video generation. The paper frames embodied generation as an extension of foundation image and video generation, aiming to preserve broad visual knowledge while enforcing multi-view consistency, geometry, and robot-specific constraints. According to the supplied abstract, U0 outperforms GPT-Image-2.0 in human evaluations for embodied scene generation and transfer, ranks first on World Arena for embodied video generation, and raises pi_0.5’s out-of-distribution manipulation success rate from 36.9% to 63.2%.
No heat snapshots are available in the last 24 hours.