发表机构
Tsinghua University; University of Science and Technology of China; Beijing Institute of Technology（清华大学; 中国科学技术大学; 北京理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过实证发现潜在世界动作模型在推理时丢弃未来表示会损失泛化能力，并提出Simple-WAM以单次前向传播准备未来，兼顾泛化与效率。
AI 中文摘要
世界动作模型（WAMs）在训练期间预测未来并伴随动作。由于视频去噪的计算成本高昂，推理期间是否仍必须生成未来存在争议：显式WAMs将未来去噪为与每个动作块相伴的干净帧，而潜在WAMs则完全丢弃未来以加速。我们发现，潜在WAMs虽然在分布内任务上与显式WAMs匹配，但未能保留最初促使WAMs发展的泛化优势。为证明这一点，我们沿三个轴评估泛化：环境扰动、数据效率和任务泛化。使用匹配的主干网络、训练数据和预算进行受控比较，当动作专家不再以未来表示为条件时，三个轴均出现一致的退化。进一步分析表明，差距几乎完全源于第一步去噪：收益来自“准备”未来，而非“生成”未来。因此，我们提出Simple-WAM，将未来建模简化为全噪声视频令牌的单次前向传播，并调整训练时噪声调度以适应此推理行为。在仿真和真实世界任务中，Simple-WAM兼具两者优势，在泛化性能上领先显式WAMs，同时效率与潜在WAMs相当。项目页面：此https URL。
英文摘要
World action models (WAMs) predict the future alongside actions during training. Due to the heavy computation cost of video denoising, whether the future must still be generated during inference is disputed: Explicit WAMs denoise it into clean frames along with every action chunk, whereas Latent WAMs discard it entirely for acceleration. We find that latent WAMs, despite matching explicit ones on in-distribution tasks, fail to retain the generalization benefits that originally motivated WAMs. To demonstrate this, we evaluate generalization along three axes: environmental perturbation, data efficiency, and task generalization. Controlled comparisons with a matched backbone, training data, and budget reveal consistent degradation across all three axes when the action expert no longer conditions on future representations. Further analysis shows that the gap arises almost entirely from the first denoising step: the benefit comes from preparing the future, not generating it. We therefore propose Simple-WAM, which simplifies future modeling into a single forward pass of fully noised video tokens and adapts the training-time noise schedule to this inference behavior. Across simulation and real-world tasks, Simple-WAM achieves the best of both worlds, leading explicit WAMs in generalization performance with efficiency comparable to Latent WAMs. Project Page: https://zrporz.github.io/Simple-WAM-Web/
