通过密度感知机制压缩视频生成的键值缓存，提升长序列一致性。
DensityKV: Density-Guided KV Cache Compression for Long Video Generation
- 按注意力头分设键值库，用软里茨密度衡量局部冗余
- 在相同缓存上限下，显著提升长视频生成稳定性与连贯性
- 无需训练，适合长视频扩散模型部署应用
自回归视频扩散模型通过滑动窗口注意力实现流式生成，但每块生成内容依赖先前状态，导致外观和运动误差随时间递归传播。历史键值（KV）记忆保留早期主体与场景状态，有助于维持长时一致性。然而，保留所有生成状态会持续增长历史档案，而重复状态不断造成冗余覆盖。为此，我们提出DensityKV，一种免训练的历史KV库管理策略。DensityKV为每个注意力头维护独立的令牌级KV库，利用软里茨密度度量后RoPE键之间的局部冗余，这些键直接参数化注意力路由。通过约束状态进入库后邻域密度的增长，DensityKV抑制历史重复积累，同时保留每个完成生成块的连贯状态。在三个自回归视频生成主干网络及多种生成长度下的实验表明，在相同历史KV容量上限下，DensityKV提升了长时一致性与生成稳定性，且持久存储量独立于生成长度。
原文摘要 · Abstract (English)
Autoregressive video diffusion models enable streaming generation through sliding-window attention, but each generated block is conditioned on previously generated content, causing appearance and motion errors to propagate recursively over time. Historical key-value (KV) memory preserves earlier subject and scene states and helps maintain long-horizon consistency. However, retaining every generated state creates a historical archive that grows continuously with the rollout, while recurrent states repeatedly add redundant coverage. To address this problem, we propose DensityKV, a training-free historical KV bank management strategy. DensityKV maintains a separate token-level KV bank for each attention head and measures local redundancy among the post-RoPE keys that directly parameterize attention routing using Soft-Riesz density. By constraining neighborhood-density growth after states enter the bank, DensityKV limits repeated historical accumulation while preserving coherent states from each completed generation block. Experiments across three autoregressive video generation backbones and multiple generation lengths show that, at the same upper bound on historical KV capacity, DensityKV improves long-horizon consistency and generation stability while keeping persistent historical storage bounded independently of rollout length.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。