# In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion > Source: > Published: 2026-09-29 07:30:11+00:00 Few-step autoregressive video diffusion generates a long video by splitting the video into temporal chunks and generating chunk-by-chunk, each through a short sequence of denoising stages. To memorize chunks that are already generated, previous methods reconstruct a clean or less-noisy key--value (K