Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Dan Zhao

Dan Zhao

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

ML×2AI×2Vision×1

Frequent co-authors

Zhiyao Xu2×
Aoxue Liu2×
Zhanjie Ding2×
Yong Jiang2×
Qing Li2×
Zhiwen Yang1×

Research Timeline

2026
Beyond Task-Agnostic: Task-Aware Grouping for Communication-Efficient Multi-Task MoE Inference

The paper proposes Task-Aware Coactivation Grouping (TACG) to significantly reduce communication costs in multi-task MoE inference by grouping experts based on task-specific co-activation patterns, outperforming task-agnostic methods.

Beyond Task-Agnostic: Task-Aware Grouping for Communication-Efficient Multi-Task MoE Inference

The paper proposes Task-Aware Coactivation Grouping (TACG) to significantly reduce communication costs in multi-task MoE inference by grouping experts based on task-specific co-activation patterns, outperforming task-agnostic methods.

UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors

This paper proposes a universal PET image denoising network (UniPET) to adaptively recover different dose reduction factor styles and achieve high-quality PET image denoising across various dose reduction factors.

Highlighted terms show continued research focus across papers

Papers

cs.CVEmpiricalRecentJun 9, 2026

UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors

Zhiwen Yang, Yang Zhou, Haowei Chen, Hui Zhang +3 more

This paper proposes a universal PET image denoising network (UniPET) to adaptively recover different dose reduction factor styles and achieve high-quality PET image denoising across various dose reduc…

View →
cs.LGcs.AIRecentMay 31, 2026

Beyond Task-Agnostic: Task-Aware Grouping for Communication-Efficient Multi-Task MoE Inference

Zhiyao Xu, Aoxue Liu, Zhanjie Ding, Dan Zhao +2 more

The paper proposes Task-Aware Coactivation Grouping (TACG) to significantly reduce communication costs in multi-task MoE inference by grouping experts based on task-specific co-activation patterns, ou…

View →
cs.LGcs.AIRecentMay 31, 2026

Beyond Task-Agnostic: Task-Aware Grouping for Communication-Efficient Multi-Task MoE Inference

Zhiyao Xu, Aoxue Liu, Zhanjie Ding, Dan Zhao +2 more

The paper proposes Task-Aware Coactivation Grouping (TACG) to significantly reduce communication costs in multi-task MoE inference by grouping experts based on task-specific co-activation patterns, ou…

View →