FrameFold：面向自回归长视频生成的响应引导式KV缓存整合
FrameFold: Response-Guided KV Cache Consolidation for Autoregressive Long Video Generation
AI总结：
FrameFold是一种无需训练的KV缓存整合方法，通过响应引导合并历史KV状态，在固定缓存预算下提升长视频生成的一致性与视觉质量，且长时间生成的质量下降程度低于基线。
摘要：
在自回归视频生成中，随着视频长度增加，保留所有历史键值（KV）状态会增大内存占用和每步注意力成本。固定的缓存预算虽能限制这些成本，但带来了保留支撑一致、高质量生成的历史内容的挑战。现有方法通过历史选择或整合控制缓存大小，然而决定保留什么以及如何限制有用内容的损失仍是共同挑战。我们的分析表明，空间查询依赖不同的历史内容，且当前注意力覆盖率更高并不一定能带来更好的长视频质量。我们提出FrameFold，一种无需训练的KV缓存整合方法，该方法通过比较合并前后相同近期历史查询检索到的内容，来指导代表性构造和合并选择。FrameFold利用相邻历史条目间的时间冗余，将它们的KV状态合并为共享代表性内容，同时保留完整的空间网格。它通过匹配条件注意力响应以闭式形式拟合值合并系数，随后选择剩余响应失真最低的合并方案。在相同KV缓存预算下，针对30秒和60秒的Self Forcing、Causal Forcing以及120秒的LongLive开展的实验表明，该方法提升了一致性和视觉质量；连续8分钟的Self Forcing滚动生成进一步显示，其质量下降程度小于基线方法。
英文摘要：
In autoregressive video generation, retaining all historical key-value (KV) states increases memory usage and per-step attention costs as videos grow longer. A fixed cache budget bounds these costs but raises the challenge of preserving historical content that supports consistent, high-quality generation. Existing methods control cache size through history selection or consolidation, yet deciding what to retain and how to limit the loss of useful content remains a shared challenge. Our analysis shows that spatial queries depend on different historical content and that higher current attention coverage does not necessarily yield better long-video quality. We introduce FrameFold, a training-free KV cache consolidation method that compares the content retrieved by the same recent historical queries before and after merging to guide both representative construction and merge selection. Exploiting temporal redundancy between adjacent historical entries, FrameFold merges their KV states into shared representatives while retaining complete spatial grids. It fits value-merging coefficients in closed form by matching conditional attention responses, then selects the merge with the lowest remaining response distortion. Under matched KV cache budgets, experiments on Self Forcing and Causal Forcing at 30 and 60 seconds and on LongLive at 120 seconds demonstrate improved consistency and visual quality. Continuous eight-minute Self Forcing rollouts further show less quality degradation than the baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
