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

Yan Gao

3 indexed papers

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

Publications per year

3
26

Top categories

NLP×2ML×1AI×1Distributed×1Systems and Control×1

Frequent co-authors

Wangyi Mei2×
Zhouhong Gu2×
Zhenhan Bai2×
Yin Cai2×
Lefan Zhang2×
Zhenxin Ding2×

Research Timeline

2026
Deep Research as Rubric for Reinforcement Learning

The paper proposes Deep Research as Rubric (DR-rubric), a novel evidence-driven framework that treats rubric construction itself as a research problem to generate fine-grained, scalable reward signals for open-ended reasoning tasks.

Deep Research as Rubric for Reinforcement Learning

The paper proposes Deep Research as Rubric (DR-rubric), a novel evidence-driven framework that treats rubric construction itself as a research problem to generate fine-grained, scalable reward signals for open-ended reasoning tasks.

FoMoE: Breaking the Full-Replica Barrier with a Federation of MoEs

This paper introduces FoMoE, a system that reduces communication costs and achieves speedups in training large language models by partitioning expert layers across workers.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.DCEmpiricalRecentJun 17, 2026

FoMoE: Breaking the Full-Replica Barrier with a Federation of MoEs

Lorenzo Sani, Zeyu Cao, Meghdad Kurmanji, Alex Iacob +4 more

This paper introduces FoMoE, a system that reduces communication costs and achieves speedups in training large language models by partitioning expert layers across workers.

View →
cs.CLRecentMay 31, 2026

Deep Research as Rubric for Reinforcement Learning

Wangyi Mei, Zhouhong Gu, Zhenhan Bai, Yin Cai +8 more

The paper proposes Deep Research as Rubric (DR-rubric), a novel evidence-driven framework that treats rubric construction itself as a research problem to generate fine-grained, scalable reward signals…

View →
cs.CLRecentMay 31, 2026

Deep Research as Rubric for Reinforcement Learning

Wangyi Mei, Zhouhong Gu, Zhenhan Bai, Yin Cai +8 more

The paper proposes Deep Research as Rubric (DR-rubric), a novel evidence-driven framework that treats rubric construction itself as a research problem to generate fine-grained, scalable reward signals…

View →