Vision-and-Language Navigation (VLN) increasingly relies on large vision-language models, but their inference cost conflicts with real-time deployment. Token caching is a promising training-free strategy that avoids redundant computation by reusing stable visual tokens across frames. However, existing methods assume a static camera and fixed semantic focus, assumptions that VLN fundamentally violates. We identify two failure modes: (1) visual dynamics, where viewpoint shift displaces token positions across frames, causing position-wise matching to pair misaligned content; (2) semantic dynamics, where token relevance shifts across task stages as navigation progresses, making cached states stale. We propose VLN-Cache, a visual-dynamic-aware and semantic-dynamic-aware caching framework that introduces view-aligned remapping to recover geometric correspondences and a task-relevance saliency filter to veto reuse at semantic transitions. A layer-adaptive entropy policy further balances the per-layer reuse budget. Experiments on the R2R-CE simulation benchmark show up to 1.52x speedup while maintaining competitive navigation success rates.

翻译：视觉与语言导航（VLN）日益依赖大型视觉语言模型，但其推理成本与实时部署需求相冲突。令牌缓存是一种无需重新训练即可实施的策略，通过跨帧复用稳定的视觉令牌来避免冗余计算。然而，现有方法假设相机静止且语义焦点固定，这些假设在VLN任务中基本不成立。我们识别出两种失效模式：（1）视觉动态性：视角变化导致令牌在帧间位置偏移，使得基于位置的匹配关联到错误内容；（2）语义动态性：随着导航进程推进，令牌相关性在不同任务阶段发生转移，导致缓存状态过时。为此，我们提出VLN-Cache——一个兼具视觉动态感知与语义动态感知的缓存框架，其通过视图对齐重映射恢复几何对应关系，并引入任务相关显著性过滤器在语义转换时否决复用。此外，层级自适应熵策略进一步平衡了各层的复用预算。在R2R-CE仿真基准上的实验表明，该方法在保持导航成功率竞争力的同时，最高可实现1.52倍的加速。