Author

Ziliang Lai

h-index 4 View on Semantic Scholar

We have 2 of 8 papers

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.

Jul 2026

X-Stage: An Overlooked Pipeline Stage for Communication-Computation Overlap in DiT Inference

A lightweight Burst-Gap model parameterized by backpressure-free issue time, effective drain rate, and outstanding capacity predicts issue overhead, recovery between bursts, and the onset of backpressure, and two communication-computation fused kernels are redesigned.

Jianwen Xian, Zhiyuan Xu, Yucheng Li et al. · arXiv.org · 0 citations

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 lar...

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