Bridging high-level semantic understanding with low-level physical control remains a persistent challenge in embodied intelligence, stemming from the fundamental spatiotemporal scale mismatch between cognition and action. Existing generative VLA policies typically adopt a "Generation-from-Noise" paradigm, which disregards this disparity, leading to representation inefficiency and weak condition alignment during optimization. In this work, we propose ResVLA, an architecture that shifts the paradigm to "Refinement-from-Intent." Recognizing that robotic motion naturally decomposes into global intent and local dynamics, ResVLA utilizes spectral analysis to decouple control into a deterministic low-frequency anchor and a stochastic high-frequency residual. By anchoring the generative process on the predicted intent, our model focuses strictly on refining local dynamics via a residual diffusion bridge. Extensive simulation experiments show that ResVLA achieves competitive performance, strong robustness to language and robot embodiment perturbations, and faster convergence than standard generative baselines. ResVLA also demonstrates strong performance in real-world robot experiments.

翻译：在具身智能中，弥合高层语义理解与低层物理控制之间的鸿沟仍是一项持续挑战，其根源在于认知与动作之间存在根本性的时空尺度失配。现有生成式VLA策略通常采用"从噪声生成"范式，该范式忽视了这一差异，导致优化过程中存在表征效率低下与条件对齐薄弱的问题。本文提出ResVLA架构，将范式转变为"从意图精炼"。考虑到机器人运动可自然分解为全局意图与局部动力学，ResVLA利用频谱分析将控制解耦为确定性低频锚点与随机性高频残差。通过将生成过程锚定于预测意图，我们的模型通过残差扩散桥接严格聚焦于局部动力学的精炼。大量仿真实验表明，ResVLA在性能、对语言及机器人形态扰动的强鲁棒性方面均表现出色，且收敛速度快于标准生成基线方法。真实世界机器人实验同样验证了ResVLA的优异性能。