用轻量草案模型加速扩散型视觉语言动作模型推理，实现低延迟重规划。
Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
- 引入轻量草案模型与并行验证机制，减少全量推理调用。
- 在LIBERO上将平均推理延迟降至19.1毫秒（3.04倍加速），任务成功率基本保持。
- 适用于对延迟敏感的实体智能任务，如流水线分拣等实际场景。
基于扩散的视觉语言动作模型（dVLAs）在具身智能中具有潜力，但其全量推理的高延迟限制了实时部署。我们提出Realtime-VLA FLASH，一种推测性推理框架，通过引入轻量级草案模型，并利用主模型的行动专家进行并行验证，结合阶段感知回退机制，在需要时自动切换回全量推理流程。该设计实现了低延迟、高频次重规划，且不牺牲可靠性。实验表明，在LIBERO数据集上，FLASH将许多58.0毫秒的全量推理轮次替换为最快仅7.8毫秒的推测轮次，使任务级平均推理延迟降低至19.1毫秒（3.04倍加速）。此外，我们在真实流水线分拣任务中验证了其有效性，凸显其在延迟敏感的具身任务中的实际应用价值。
原文摘要 · Abstract (English)
Diffusion-based vision-language-action models (dVLAs) are promising for embodied intelligence but are fundamentally limited in real-time deployment by the high latency of full inference. We propose Realtime-VLA FLASH, a speculative inference framework that eliminates most full inference calls during replanning by introducing a lightweight draft model with parallel verification via the main model's Action Expert and a phase-aware fallback mechanism that reverts to the full inference pipeline when needed. This design enables low-latency, high-frequency replanning without sacrificing reliability. Experiments show that on LIBERO, FLASH largely preserves task performance by replacing many 58.0 ms full-inference rounds with speculative rounds as fast as 7.8 ms, lowering task-level average inference latency to 19.1 ms (3.04x speedup). We additionally demonstrate effectiveness on real-world conveyor-belt sorting, highlighting its practical impact for latency-critical embodied tasks.
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。