什么让世界动作模型泛化？测试时未来建模实证研究
原标题：Paper page - What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
AI 摘要
该论文研究世界动作模型（WAMs）的泛化能力，发现隐式WAMs虽在分布内任务上与显式WAMs相当，但在环境扰动、数据效率和任务泛化三个维度上均出现退化。分析表明差距几乎完全来自第一个去噪步骤，收益源于“准备未来”而非“生成未来”。作者提出Simple-WAM，将未来建模简化为对完全加噪视频token的单次前向传播，并调整训练噪声调度，在仿真和真实任务中兼顾泛化性能与隐式WAM的效率。
正文节选
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling Abstract 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