LiMA：通过异步扩散弥合长期想象与实时灵巧操作之间的鸿沟
LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion
- Beijing Academy of Artificial Intelligence（北京人工智能研究院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对灵巧操作中意图规划与快速反应控制的时间错位问题，提出异步双系统生成框架LiMA，通过多尺度层次解耦慢速长期意图生成与快速高频运动细化，并引入潜在薛定谔桥耦合机制实现概率传输对齐，显著降低推理延迟并提升任务成功率。
AI中文摘要：
灵巧操作需要长期的前瞻性和快速的反应控制。视觉-语言-动作（VLA）模型虽然擅长高层推理，但往往缺乏对物理动力学和空间感知的细粒度理解。相反，世界-动作模型（WAMs）通常因迭代生成而面临高推理延迟。这些缺陷导致关键的时间错位，即模型的意图无法适应快速的物理接触变化。为克服这一根本瓶颈，我们提出LiMA，一种异步双系统生成框架，系统地将意图规划与反应执行解耦。LiMA将计算组织为多尺度层次结构：慢速系统处理稀疏的长期时空意图生成，而快速系统专注于密集的高频运动细化。为将稀疏的意图预测与密集的动作轨迹对齐，我们引入潜在薛定谔桥耦合机制，将细化形式化为熵正则化的概率传输过程。与Cosmos-Policy相比，LiMA通过异步解耦将推理延迟降低45.8%。在跨越多个时间跨度的六个双臂灵巧操作任务上进行评估，LiMA实现了70.8%的总体成功率和78.9%的平均子任务成功率，同时在未见场景中保持性能。项目网站可在https://ccdcs.github.io/LiMA_repo/获取。
英文摘要：
Dexterous manipulation demands long-term foresight and rapid reactive control. Vision-Language-Action (VLA) models, while proficient in high-level reasoning, often lack a fine-grained understanding of physical dynamics and spatial perception. Conversely, World-Action Models (WAMs) typically suffer from high inference latency due to iterative generation. These deficiencies result in a critical temporal misalignment where the model's intent fails to adapt to rapid physical contact changes. To overcome this fundamental bottleneck, we propose LiMA, an asynchronous dual-system generative framework that systematically decouples intent planning from reactive execution. LiMA organizes computation into a multi-scale hierarchy: a slow system handles sparse long-horizon spatiotemporal intent generation, while a fast system focuses on dense high-frequency motion refinement. To align sparse intent predictions with dense action trajectories, we introduce a Latent Schrödinger Bridge Coupling mechanism that formulates refinement as an entropy-regularized probabilistic transport process. LiMA reduces inference latency by 45.8% compared with Cosmos-Policy via asynchronous decoupling. Evaluated across six bimanual dexterous manipulation tasks spanning multiple horizons, LiMA achieves an overall success rate of 70.8% and an average subtask success rate of 78.9%, while maintaining performance in unseen scenarios. The project website is available at https://ccdcs.github.io/LiMA_repo/
