边端部署具身大模型需系统级协同，突破内存与计算瓶颈。
Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies
- 构建八重耦合约束的部署挑战框架，覆盖资源与时序限制。
- 自回归视觉-语言-动作策略受内存带宽制约，扩散模型受限于计算延迟。
- 适合关注边端智能系统设计的研究者与工程师阅读。
在具身边缘系统中部署基础模型本质上是系统级问题，而非仅限于模型压缩。实时控制必须在严格的尺寸、重量和功耗约束下运行，其中内存流量、计算延迟、时序波动与安全余量直接相互影响。'部署考验'（Deployment Gauntlet）将这些约束归纳为八个相互关联的障碍，决定了具身基础模型能否可靠落地。在典型边缘工作负载中，自回归视觉-语言-动作策略主要受内存带宽限制，而基于扩散的控制器则更多受限于计算延迟与持续执行成本。因此，可靠部署依赖于内存、调度、通信与模型架构之间的系统级协同设计，包括将快速控制与慢速语义推理分离的分解策略。
原文摘要 · Abstract (English)
Deploying foundation models in embodied edge systems is fundamentally a systems problem, not just a problem of model compression. Real-time control must operate within strict size, weight, and power constraints, where memory traffic, compute latency, timing variability, and safety margins interact directly. The Deployment Gauntlet organizes these constraints into eight coupled barriers that determine whether embodied foundation models can run reliably in practice. Across representative edge workloads, autoregressive Vision-Language-Action policies are constrained primarily by memory bandwidth, whereas diffusion-based controllers are limited more by compute latency and sustained execution cost. Reliable deployment therefore depends on system-level co-design across memory, scheduling, communication, and model architecture, including decompositions that separate fast control from slower semantic reasoning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。