TLDR
长自回归视频生成面临一个根本性的记忆挑战：在注意力窗口有限的情况下，模型必须决定从不断增长的历史中保留哪些信息。现有方法按时间顺序组织记忆，保留近期帧并压缩或丢弃较旧帧。我们提出 RECAP-Forcing，按外观新颖度组织记忆。长视频不仅是一串帧，还是一组随时间演化、需保持身份一致的主体、物体与场景。我们通过保留与新出现外观对应的 KV cache 来组织记忆Long autoregressive video generation faces a fundamental memory challenge: with a finite attention window, a model must decide which information from an ever-expanding history to retain. Existing methods organize memory temporally, preserving recent frames while compressing or discarding older ones. We instead propose RECAP-Forcing, organizing memory by appearance novelty. A long video is not merely a sequence of frames, but an evolving cast of subjects, objects, and scenes whose identities must remain consistent over time. We organize memory by retaining the KV cache associated with newly app