ImageWAM：世界动作模型真的需要视频生成，还是只需要图像编辑？
ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?
AI总结：
提出ImageWAM框架，利用预训练图像编辑模型替代视频生成进行机器人动作预测，通过编辑去噪的KV缓存作为世界动作上下文，在多个模拟和真实实验中优于基线，计算量降至1/6，延迟降至1/4。
摘要：
世界动作模型（WAMs）通常依赖视频生成来桥接视觉世界建模和机器人控制。然而，基于视频的WAMs面临三个耦合的限制：密集的多帧未来令牌使得推理成本高昂，完整的视频预测将容量花费在与动作无关的时间和外观细节上，以及长期未来想象可能引入误导动作预测的错误。这些问题提出了一个简单的问题：世界动作模型真的需要视频生成吗？我们提出ImageWAM，一个简单的WAM框架，将预训练的图像编辑模型重新用于机器人动作预测。与视频生成相比，图像编辑提供了更匹配的先验：它只需要建模目标帧变换，关注与动作相关的当前到目标视觉差异，并通过编辑预训练将任务指令接地到局部视觉变化。在实践中，ImageWAM在推理时不解码目标帧；相反，它根据图像编辑去噪产生的KV缓存条件化一个流匹配动作专家，将其用作紧凑的世界动作上下文。ImageWAM在多个模拟和真实世界实验中优于标准VLA基线和匹配的竞争性WAM，且无需额外的策略预训练。它还将FLOPs降低到基于视频的WAMs的1/6，延迟降低到1/4。注意力分析进一步表明，编辑缓存聚焦于任务相关的变化区域，支持图像编辑作为基于视频的世界动作建模的有效替代方案。
英文摘要：
World Action Models (WAMs) commonly rely on video generation to bridge visual world modeling and robot control. However, video-based WAMs face three coupled limitations: dense multi-frame future tokens make inference costly, full video prediction spends capacity on action-irrelevant temporal and appearance details, and long-horizon future imagination may introduce errors that mislead action prediction. These issues raise a simple question: Does world action model really need video generation? We propose ImageWAM, a simple WAM framework that repurposes pretrained image editing models for robot action prediction. In contrast to video generation, image editing provides a better-matched prior: it only needs to model a target-frame transformation, focuses on action-relevant current-to-target visual differences, and grounds task instructions to localized visual changes through edit pretraining. In practice, ImageWAM does not decode the target frame at inference time; instead, it conditions a flow-matching action expert on the KV caches produced by image-editing denoising, using them as a compact world-action context. ImageWAM outperforms standard VLA baselines and matching competitive WAMs without additional policy pretraining across different simulator and real-world experiments. It also reduces FLOPs to 1/6 and latency to 1/4 of video-based WAMs. Attention analysis further shows that editing caches focus on task-relevant change regions, supporting image editing as an effective alternative to video-based world-action modeling.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
