AI RESEARCH
DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation
arXiv CS.CV
•
ArXi:2606.04432v1 Announce Type: new Video diffusion transformers have achieved state-of-the-art visual quality, but their high inference cost remains a major bottleneck for real-time applications. Recent distillation frameworks produce autoregressive video diffusion models with reduced latency, yet these models still use a fixed number of denoising steps per frame, wasting computation on predictable frames and under-refining challenging ones. We present DSA, a confidence-guided adaptive computation framework for AR video diffusion.