过去塑造未来：自回归视频生成中的记忆机制综述
原标题：Paper page - The Past Frames the Future: Memory for Autoregressive Video Generation
AI 摘要
该论文针对自回归视频生成中因上下文窗口、存储和计算受限而导致历史信息（如实体身份、动态状态、干预引发的因果变化）过早丢失的问题，将记忆机制系统化为跨自回归步骤持久保存并能影响后续生成的历史信息。作者从形式、功能、操作、学习和评估五个互补视角综述了相关文献，并总结了可组合且资源感知的记忆架构、可信状态更新、自回归学习与标准化评估等开放挑战，为构建可靠的记忆条件视频生成系统提供了结构化基础。
正文节选
The Past Frames the Future: Memory for Autoregressive Video Generation Abstract Advances in generative models have improved video fidelity, enabling long-horizon generation, interactive world modeling, and evolving visual environments. Autoregressive (AR) video generation extends visual sequences through causal rollouts. However, a fundamental bottleneck emerges: as the generated sequence expands, practical models must operate under strictly bounded context windows, storage, and computational li