LATIDIA · Robótica

Meituan-Robotics-0: A Vision-Language-Action Foundation Model for Desktop Manipulation

arXiv:2611.08577v1 Anuncio Tipo: nuevo Resumen: Presentamos Meituan-Robotics-0 (MR0), un modelo de base de visión-lenguaje-acción y un sistema de agente encarnado para la manipulación de escritorios de base estacionaria. MR0 combina 147 millones

La noticia

arXiv:2611.08577v1 Announce Type: new Abstract: We present Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for stationary-base desktop manipulation. MR0 combines 147 million vision-language samples with 15,060 hours of curated robot trajectories spanning 12 embodiments. A three-stage training recipe aligns multimodal representations with robot behavior through discrete action-token pre-training, transfers these priors to continuous cross-embodiment control through flow-matching mid-training, and adapts the policy through real-world post-training. We introduce Rollback, which pairs replaced policy segments with human corrections to provide positive and negative supervision for CFG-DAgger without value learning or advantage labeling. A unified end-effector interface supports heterogeneous embodiments, while asynchronous action-chunk merging maintains smooth execution under variable inference latency.