C3^3ache: Accelerating World Action Models with Cross Inference Chunk Cache

Abstract

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 C3^3ache, 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 C3^3ache achieves up to a 2.5×2.5\times speedup in total wall-clock inference time, with negligible degradation in task success rate.