CORAL-KV：用于自回归视频KV缓存的紧凑跨层预测与残差编码
CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches
AI总结：
该研究针对自回归视频扩散模型的KV缓存内存瓶颈，提出Coral-KV跨层预测残差编码框架，在HY-WorldPlay、MAGI-1等数据集上相比QVG系列方法，实现了PSNR提升与缓存内存减少的双重效果，还降低了时间不连续性。
摘要：
自回归视频扩散模型会维护不断增长的注意力键值（KV）缓存，这使得内存成为长视频生成的关键瓶颈。最近，基于聚类的量化方法成为压缩视频KV缓存的有效手段，该方法通过对相似的键向量和值向量进行分组，再对残差误差进行量化。然而，当后续帧关注压缩后的历史内容时，随着视频长度增加，微小的重建误差会不断累积。除了聚类所利用的层内相似性，我们还发现视频模型的缓存层之间存在强依赖关系。这一发现催生了Coral-KV——一种校准型离线、残差编码且局部适配的KV缓存压缩框架，该框架利用各层的缓存状态预测后续层的键和值，再对剩余的预测残差进行量化。我们构建了紧凑的块对角加低秩（block-DPLR）预测器：块对角分量对每个注意力头内的通道关系进行建模，而全局低秩项则对头之间的依赖关系进行建模。Coral-KV提供了灵活的保真度-内存权衡方案：它可以在不同视频间复用其预测器，也可以为当前视频适配轻量级块对角预测器以获得更高保真度。在HY-WorldPlay和MAGI-1两个数据集上的大量评估显示，我们的可复用配置相比QVG-4，PSNR分别提升了0.32 dB和4.95 dB，同时缓存内存分别减少了48%和37%；针对QVG-Pro，我们的视频适配配置使MAGI-1的PSNR提升了3.77 dB，同时缓存内存减少了33.7%。Coral-KV在扩展生成过程中保持了更高的重建保真度，减少了时间不连续性，同时保持了相当的生成延迟。
英文摘要：
Autoregressive video diffusion models maintain a growing attention key-value (KV) cache, making memory a key bottleneck for long video generation. Recently, clustering-based quantization has emerged as an effective method to compress video KV caches by grouping similar key and value vectors then quantizing residual errors. However, when later frames attend to the compressed history, small reconstruction errors can compound as the video grows. Beyond the within-layer similarity exploited by clustering, we find strong dependencies across cache layers in video models. This motivates Coral-KV - Calibrated Offline, Residual-coded, and Adapted Locally - a KV-cache compression framework that uses cache states in each layer to predict keys and values in subsequent layers, then quantizes the remaining prediction residuals. We construct compact block-diagonal-plus-low-rank (block-DPLR) predictors: block-diagonal components model channel relationships within each attention head, while a global low-rank term models dependencies between heads. Coral-KV exposes a flexible fidelity-memory trade-off: it can reuse its predictors across videos or refit lightweight block-diagonal predictors to the current video for higher fidelity. Across extensive evaluations on both HY-WorldPlay and MAGI-1, our reusable configuration improves PSNR over QVG-4 by 0.32 dB and 4.95 dB, respectively, while using 48% and 37% less cache memory. Against QVG-Pro, our video-adapted configuration improves MAGI-1 PSNR by 3.77 dB while using 33.7% less cache memory. Coral-KV also maintains higher reconstruction fidelity over extended generation and reduces temporal discontinuities while retaining comparable generation latency.
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。
