activity
20242026
most citedWDMoE: Wireless Distributed Mixture of Experts for Large Language Models

1 citations · 1 across the 5 of their papers we have counts for

collaborators

7 papers

eess.SP2026

Towards Semantic-based Agent Communication Networks: Vision, Technologies, and Challenges

Ping Zhang, Rui Meng, Xiaodong Xu +24

The International Telecommunication Union (ITU) identifies "Artificial Intelligence (AI) and Communication" as one of six key usage scenarios for 6G. Agentic AI, characterized by i…

cs.IT2026

Unlocking High-Fidelity Analog Joint Source-Channel Coding on Standard Digital Transceivers

Shumin Yao, Hao Chen, Yaping Sun +4

Analog joint source-channel coding (JSCC) has demonstrated superior performance for semantic communications through graceful degradation across channel conditions. However, a funda…

cs.IT2025

CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems

Xuran Liu, Nan Xue, Rui Bao +5

While deploying large language models on edge devices promises low-latency and privacy-preserving AI services, it is hindered by limited device resources. Although pipeline paralle…

eess.SP2025

SCDM: Score-Based Channel Denoising Model for Digital Semantic Communications

Hao Mo, Yaping Sun, Shumin Yao +6

Score-based diffusion models represent a significant variant within the diffusion model family and have seen extensive application in the increasingly popular domain of generative…

cs.IT2024

Generative Semantic Communication: Architectures, Technologies, and Applications

Jinke Ren, Yaping Sun, Hongyang Du +7

This paper delves into the applications of generative artificial intelligence (GAI) in semantic communication (SemCom) and presents a thorough study. Three popular SemCom systems e…

cs.LG20241 cited

WDMoE: Wireless Distributed Mixture of Experts for Large Language Models

Nan Xue, Yaping Sun, Zhiyong Chen +6

Large Language Models (LLMs) have achieved significant success in various natural language processing tasks, but the role of wireless networks in supporting LLMs has not been thoro…