Chengru Song
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes OneReason, a framework that enhances the reasoning capability of generative recommendation models by focusing on improving item perception and structuring user behavior into coherent latent interests.
This paper introduces X-Stage, a software-visible post-issue pipeline stage to improve communication efficiency in distributed diffusion transformer (DiT) inference, leading to significant speedups for DeepGEMM MegaMoE and Ulysses sequence-parallel attention.
Papers
X-Stage: An Overlooked Pipeline Stage for Communication-Computation Overlap in DiT Inference
Jianwen Xian, Zhiyuan Xu, Yuchen Li, Ziliang Lai +7 more
This paper introduces X-Stage, a software-visible post-issue pipeline stage to improve communication efficiency in distributed diffusion transformer (DiT) inference, leading to significant speedups fo…