Vision-Language-Action (VLA) models generalize semantically well but often lack fine-grained modeling of world dynamics. We present MotuBrain, a unified World Action Model that jointly models video and action under a UniDiffuser formulation with a three-stream Mixture-of-Transformers architecture. A single model supports policy learning, world modeling, video generation, inverse dynamics, and joint video-action prediction, while scaling to heterogeneous multimodal data such as video-only, task-agnostic, and cross-embodiment robot data. Building on Motus, MotuBrain further introduces unified multiview modeling, an independent text stream for stronger language-action coupling, a shared cross-embodiment action representation, and an efficient post-training and deployment recipe for long-horizon real-world control. Our inference stack combines step reduction, compilation, FP8 quantization, DiT caching, V2A-style action-only inference, and real-time chunked closed-loop execution, achieving over 50x speedup over a naive baseline and up to 11 Hz inference. Experimentally, MotuBrain achieves 95.8% and 96.1% average success on RoboTwin 2.0 under clean and randomized settings, respectively, attains the strongest reported EWMScore in our WorldArena comparison, and adapts to new humanoid embodiments with only 50--100 trajectories. These results show that unified world action models can scale in generality, predictive accuracy, and real-world deployability.

翻译：视觉-语言-动作（VLA）模型在语义层面具有良好的泛化能力，但通常缺乏对世界动力学的精细建模。我们提出MotuBrain，一种统一的世界动作模型，该模型基于UniDiffuser框架与三流混合Transformer架构，联合建模视频与动作。单一模型支持策略学习、世界建模、视频生成、逆动力学以及联合视频-动作预测，同时可扩展至异构多模态数据，例如纯视频数据、任务无关数据以及跨具身机器人数据。在Motus基础上，MotuBrain进一步引入了统一多视角建模、用于增强语言-动作耦合的独立文本流、共享的跨具身动作表征，以及针对长时域真实世界控制的高效后训练与部署方案。我们的推理栈融合了步骤缩减、编译优化、FP8量化、DiT缓存、V2A式纯动作推理以及实时分块闭环执行，相比朴素基线实现了超过50倍的加速，推理频率高达11 Hz。实验表明，MotuBrain在RoboTwin 2.0的干净与随机化设定下分别达到平均95.8%与96.1%的成功率，在WorldArena对比中取得当前最强的EWMScore，且仅需50至100条轨迹即可适配新的类人具身形态。这些结果表明，统一世界动作模型能够在通用性、预测精度与真实世界可部署性方面实现扩展。