Robust perception and dynamics modeling are fundamental to real-world robotic policy learning. Recent methods employ video diffusion models (VDMs) to enhance robotic policies, improving their understanding and modeling of the physical world. However, existing approaches overlook the coherent and physically consistent motion representations inherently encoded across frames in VDMs. To this end, we propose Video2Act, a framework that efficiently guides robotic action learning by explicitly integrating spatial and motion-aware representations. Building on the inherent representations of VDMs, we extract foreground boundaries and inter-frame motion variations while filtering out background noise and task-irrelevant biases. These refined representations are then used as additional conditioning inputs to a diffusion transformer (DiT) action head, enabling it to reason about what to manipulate and how to move. To mitigate inference inefficiency, we propose an asynchronous dual-system design, where the VDM functions as the slow System 2 and the DiT head as the fast System 1, working collaboratively to generate adaptive actions. By providing motion-aware conditions to System 1, Video2Act maintains stable manipulation even with low-frequency updates from the VDM. For evaluation, Video2Act surpasses previous state-of-the-art VLA methods by 7.7% in simulation and 21.7% in real-world tasks in terms of average success rate, further exhibiting strong generalization capabilities.

翻译：鲁棒的感知与动力学建模是现实世界机器人策略学习的基础。近期方法采用视频扩散模型增强机器人策略，提升其对物理世界的理解与建模能力。然而现有方法忽略了视频扩散模型中帧间固有编码的连贯且物理一致的运动表征。为此，我们提出Video2Act框架，通过显式整合空间与运动感知表征高效引导机器人动作学习。基于视频扩散模型的固有表征，我们提取前景边界与帧间运动变化，同时过滤背景噪声及任务无关偏差。这些精炼表征被用作扩散Transformer动作头的额外条件输入，使其能够推理操作目标与运动方式。为解决推理效率低下的问题，我们提出异步双系统设计：将视频扩散模型作为慢速系统2、扩散Transformer头作为快速系统1协同生成自适应动作。通过向系统1提供运动感知条件，Video2Act即使在视频扩散模型低频更新下仍能保持稳定操作。在评估中，Video2Act在仿真与真实世界任务中的平均成功率分别超越此前最先进的视觉-语言-动作方法7.7%与21.7%，并展现出强泛化能力。