PAWBench：我们离概率对齐的世界建模还有多远？

中文摘要 AI 辅助

近期视频生成模型越来越多地被用作世界模型。许多物理过程可以以多种有效方式展开，因此世界模型不仅应生成合理轨迹，还应在相同初始观测和动作下复现可能行为的分布，我们将这一分布层面的要求称为概率对齐。然而，现有评估大多仅评估单视频合理性，未测试重复生成是否能恢复正确分布，这引出核心问题：当前视频生成器离概率对齐的世界建模还有多远？为回答该问题，我们将概率对齐形式化为世界模型的分布标准，并引入PAWBench——一个将视频生成器评估为世界动力学随机采样器的基准；还引入PAWEval，一种结果层面的协议，可将重复视频滚动转化为可能物理行为的经验分布。在50种场景和11个当前系统上，没有模型能在恢复有效行为范围的同时始终匹配参考概率。明确这一差距后，我们测试了语言提示、初始噪声采样或模型训练是否可重塑模型的预测分布。我们认为本研究可作为未来迈向概率对齐世界建模工作的基础。

英文摘要

Recent video generation models are increasingly framed as world models. Many physical processes can unfold in more than one valid way. Therefore, a world model should reproduce not only a plausible trajectory, but also the distribution of possible behaviors under the same initial observation and action. We call this distribution-level requirement probabilistic alignment. However, existing evaluations largely assess individual-video plausibility and do not test whether repeated generations recover the correct distribution. This raises a central question: how far are current video generators from probabilistically aligned world modeling? To answer it, we formalize probabilistic alignment as a distributional criterion for world models and introduce PAWBench, a benchmark for evaluating video generators as stochastic samplers of world dynamics. We further introduce PAWEval, an outcome-level protocol that converts repeated video rollouts into empirical distributions over possible physical behaviors. Across 50 scenarios and eleven current systems, no model consistently matches the reference probabilities while recovering the range of valid behaviors. Having established this gap, we test whether language prompts, initial noise sampling, or model training can reshape the model's predictive distribution. We believe our work can serve as a foundation for future efforts to move towards probabilistically aligned world modeling.

发表机构

• Shanghai Jiao Tong University（上海交通大学）
• Shanghai AI Laboratory（上海人工智能实验室）
• Krea AI
• Huggingface
• Shanghai Innovation Institute（上海创新研究院）
• Tongyi Lab（通义实验室）
• The University of Hong Kong（香港大学）

机构由 AI 辅助整理，请以论文原文为准。