EvoWorld：生成式视频模型中的视野外世界演化
原标题：Paper page - EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models
AI 摘要
该论文提出「视野外因果演化」（Out-of-Sight Causal Evolution）新问题，要求生成式视频模型在渲染事件后推理其对世界状态的影响，并给出因果合理的结果。作者提出 EvoWorld 框架，由视觉语言模型充当「世界大脑」维护世界状态并推理状态转移，配合分段自回归视频渲染器实现视觉呈现。团队还构建了 EvoWorld-Data 与 EvoWorld-Bench 用于训练和评测，实验显示其在事件条件因果演化上显著优于近期模型，同时保持视觉质量与一致性。
正文节选
EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models Abstract Generative video models are increasingly used as visual world simulators, yet their primary strength lies in rendering plausible pixels rather than reasoning about how a world should evolve. Coherent world evolution requires more than visual fidelity: when an event occurs, a model must infer its consequences for the entities in the world and then render the resulting state. For example, after a wild beast appears,