# WAM-Cache：面向高效 World Action Models 的陈旧度有界 KV 复用

> 原文链接：https://robotics.hellobike.com/papers/2026-10-08-2610-11401
> 频道：papers | 更新日期：2026-10-08 | 标签：arxiv, cs.RO
> 核心摘要：针对WAM闭环控制中视频DiT预填充开销，WAM-Cache以陈旧度有界KV复用加速，并在仿真和真机验证。

# WAM-Cache：面向高效 World Action Models 的陈旧度有界 KV 复用

::: v-pre
> 原文链接：[WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models](https://arxiv.org/abs/2610.11401)（arXiv 2610.11401 · 发布日期：2026-10-08）

**WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models**

针对WAM闭环控制中视频DiT预填充开销，WAM-Cache以陈旧度有界KV复用加速，并在仿真和真机验证。

## 核心要点

- WAM闭环控制每个动作块运行视频DiT，预填充KV成为主要计算开销。
- 方法跨动作块保留分层KV，仅重算稀疏刷新token，且无需训练。
- 刷新集合结合动作专家交叉注意力与视觉潜在惊讶，并加入严格年龄上界。
- 在Fast-WAM上，视频DiT预填充FLOPs降低32-42%，精度接近密集策略。

**验证范围与局限**：验证范围包括RoboTwin 2.0、LIBERO仿真和真实机器人实验。

## 英文摘要 (Abstract)

World Action Models (WAMs) enable generalist robot manipulation by conditioning an action expert on representations from a pretrained video Diffusion Transformer (DiT). In closed-loop control, the video DiT runs at every chunk to encode the current observation into layerwise key-value (KV) pairs that the action expert queries. This prefill dominates the per-chunk computational cost, yet existing training-free accelerations leave it fully dense. We present WAM-Cache, a training-free framework that retains layerwise key-value representations across chunks and recomputes only a sparse refresh set of tokens. Crucially, we find that the intuitive heuristic of refreshing visually drifted tokens plateaus far below the dense baseline, even with an oracle predicting ground-truth KV drift. Downstream action accuracy is instead governed by where the action expert attends, not by what moved. WAM-Cache therefore selects the refresh set by uniting the action expert's cross-attention with visual latent surprise, complemented by a strict age bound that suppresses compounding error. On Fast-WAM, WAM-Cache cuts video DiT prefill FLOPs by 32-42% across RoboTwin 2.0, LIBERO, and real-world experiments, while staying within 0.7-1.8 percentage points of the dense policy in simulation and 2.5 points on a real robot.

作者：Kai Ding, Yang He, Ruijie Quan, Yi Yang
:::

## 原始参考来源 (Sources)

- [arXiv 2610.11401：WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models](https://arxiv.org/abs/2610.11401)