通过跨推理块复用残差，加速世界动作模型的推理
C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache
- 在不同推理块间复用相同去噪步骤的残差，减少重复计算
- 在Fast-WAM上实现最高2.5倍加速，成功率几乎不变
- 无需训练，可直接用于现有模型，适合部署优化
世界动作模型（WAMs）因基于视频建模目标，能从大量未标注视频中学习，泛化能力优于标准视觉-语言-动作（VLA）策略。但其泛化代价高昂：完成任务需多次推理块，每个块均需昂贵的去噪过程。现有加速方法仅缓存单个块内的计算，忽略跨块冗余。我们实证发现，当机器人执行平滑行为时，同一去噪步骤的残差在相邻块间高度相关。为此提出C³ache，一种无需训练的方法，可在相同去噪步骤下跨推理块缓存并重用残差。在Fast-WAM基准测试中，该方法使总墙钟推理时间最多提升2.5倍，任务成功率几乎无损。
原文摘要 · Abstract (English)
World Action Models (WAMs) generalize better than standard Vision-Language-Action (VLA) policies to novel motions and environments, because a video-modeling objective lets them learn from abundant unlabeled video rather than scarce labeled robot demonstrations. This generalization is computationally expensive. To complete a task, a WAM runs over multiple inference chunks, and each chunk requires a costly denoising process. Existing acceleration methods reduce this cost by caching and reusing computation within a single chunk's denoising trajectory. Our empirical analysis reveals a substantial source of redundancy they overlook: redundancy across chunks. When a robot executes a smooth behavior, the residuals computed at a given denoising step are strongly correlated from one chunk to the next. We introduce C$^3$ache, a training-free method that caches and reuses these residuals across inference chunks at the same denoising step. Experiments on benchmarks with a Fast-WAM backbone show that C$^3$ache achieves up to a $2.5\times$ speedup in total wall-clock inference time, with negligible degradation in task success rate.
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。