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

Guihai Chen

3 indexed papers

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

Publications per year

3
26

Top categories

Distributed×3ML×1AI×1Networking×1Crypto×1

Frequent co-authors

Fan Wu2×
Zhihao Xu1×
Hao Zhong1×
Zeting Zhou1×
Yuhang Xu1×
Haoyu Tong1×

Research Timeline

2026
An Efficient and Privacy-Preserving Architecture for Cross-Institutional Collaborative RAG

The paper introduces FedRAG, a novel federated RAG framework that enables privacy-preserving cross-institutional knowledge collaboration by decoupling the self-attention mechanism from data localization using a specialized scrambling protocol.

Scalable LLM Agent Tool Access in the Cloud

A cloud-scale gateway system for MCP services is presented, which breaks the direct-connect model and offloads legacy service integration, consolidates incompatible MCP variants, and reduces tool selection time and token usage.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs

This paper proposes Gleam, a framework for efficient GPU sharing across local-area CUDA devices, reducing bandwidth overhead, improving API call latency, and ensuring context consistency.

Highlighted terms show continued research focus across papers

Papers

cs.DCcs.LGEmpiricalRecentJul 25, 2026

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs

Zhihao Xu, Hao Zhong, Zeting Zhou, Yuhang Xu +8 more

This paper proposes Gleam, a framework for efficient GPU sharing across local-area CUDA devices, reducing bandwidth overhead, improving API call latency, and ensuring context consistency.

View →
cs.DCcs.AIcs.NIEmpirical
Recent
Jul 17, 2026

Scalable LLM Agent Tool Access in the Cloud

Mingxin Li, Enge Song, Yueshang Zuo, Xiaodong Liu +26 more

A cloud-scale gateway system for MCP services is presented, which breaks the direct-connect model and offloads legacy service integration, consolidates incompatible MCP variants, and reduces tool sele…

View →
cs.CRcs.DCRecentMay 25, 2026

An Efficient and Privacy-Preserving Architecture for Cross-Institutional Collaborative RAG

Chenxin Mao, Shangyu Liu, Zhenzhe Zheng, Fan Wu +2 more

The paper introduces FedRAG, a novel federated RAG framework that enables privacy-preserving cross-institutional knowledge collaboration by decoupling the self-attention mechanism from data localizati…

View →