Researchers introduced DeCoPrune, a KV-cache pruning method for autoregressive video diffusion that uses denoising consistency to compress the continuously growing cache. The work targets the memory cost of streaming video generation, where existing strategies either discard history with fixed windows or select tokens via local attention and similarity signals.
Autoregressive video diffusion supports streaming generation and interactive control, but its KV cache grows continuously with the generated history. Existing compression strategies either discard history using fixed windows or select tokens through local attention and similarity signals, which do n
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.