Skip to content

Author

Ziliang Lai

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

HeadCast: Casting Attention Heads for Efficient Autoregressive Video Generation

HeadCast is proposed, a training-free, plug-and-play acceleration framework built on the observation that a pre-trained AR model's attention heads exhibit stable, heterogeneous behaviors that accelerates inference by up to 1.62x at 720P and 1.95x at 1080P, while keeping VBench quality on par with full attention and largely flicker-free.

Jinliang Shen, Li Su, Zheming Li et al. · 1 citation