综述：以世界建模统一视频理解与生成
原标题：Paper page - Reading, Writing, Sharing, and Interacting with the World through Video
AI 摘要
一篇发表于 Hugging Face Daily Papers 的综述论文提出以「世界建模」为统一视角，整合视频理解与视频生成研究。作者将观测视频视为潜在时序世界的部分、有损投影，并围绕读取、写入、共享、交互四种操作组织文献，覆盖 600 余项工作。论文区分了时序连贯性与世界状态一致性，提出证据阶梯与分类体系，并总结长时一致性、物理因果等七项开放挑战。
正文节选
Reading, Writing, Sharing, and Interacting with the World through Video Abstract This survey unifies video understanding and generation through world modeling, organizing progress around inferring, synthesizing, sharing, and interacting with latent temporal states to emphasize persistent dynamics over clip-level perception. Video foundation models have advanced rapidly in understanding and generating visual sequences, while video world models seek to capture the underlying dynamics of the world