生成式语义通信——架构、技术与应用

工程（英文） ›› 2026, Vol. 56 ›› Issue (1) : 45 -61. DOI: 10.1016/j.eng.2025.07.022

生成式语义通信——架构、技术与应用

Jinke Ren ^a^,^b^,^c ,
Yaping Sun ^a^,^d^,^* ,
Hongyang Du ^e ,
Weiwen Yuan ^a^,^b^,^c ,
Chongjie Wang ^a^,^b^,^c ,
Xianda Wang ^a^,^b^,^c ,
Yingbin Zhou ^a^,^b^,^c ,
Ziwei Zhu ^a^,^b^,^c ,
Fangxin Wang ^a^,^b^,^c ,
Shuguang Cui ^a^,^b^,^c^,^*

作者信息 +

Generative Semantic Communication: Architectures, Technologies, and Applications

Jinke Ren ^a^,^b^,^c ,
Yaping Sun ^a^,^d^,^* ,
Hongyang Du ^e ,
Weiwen Yuan ^a^,^b^,^c ,
Chongjie Wang ^a^,^b^,^c ,
Xianda Wang ^a^,^b^,^c ,
Yingbin Zhou ^a^,^b^,^c ,
Ziwei Zhu ^a^,^b^,^c ,
Fangxin Wang ^a^,^b^,^c ,
Shuguang Cui ^a^,^b^,^c^,^*

Author information +

文章历史 +

Received	Accepted	Published
2024-11-30	2025-07-22
Issue Date
2025-07-28

PDF

Abstract

Semantic communication (SemCom) has emerged as a transformative paradigm for future wireless networks, aiming to improve communication efficiency by transmitting only the semantic meaning (or its encoded version) of the source data rather than the complete set of bits (symbols). However, traditional deep learning-based SemCom systems present challenges such as limited generalization, low robustness, and inadequate reasoning capabilities, primarily due to the inherently discriminative nature of deep neural networks. To address these limitations, generative artificial intelligence (GAI) is seen as a promising solution, offering notable advantages in learning complex data distributions, transforming data between high- and low-dimensional spaces, and generating high-quality content.

关键词

Key words

Semantic communication / Generative artificial intelligence / Large language model / Variational autoencoder / Generative adversarial network / Diffusion model

引用本文

引用格式 ▾

Jinke Ren,Yaping Sun,Hongyang Du,Weiwen Yuan,Chongjie Wang,Xianda Wang,Yingbin Zhou,Ziwei Zhu,Fangxin Wang,Shuguang Cui. 生成式语义通信——架构、技术与应用[J]. 工程（英文）, 2026, 56(1): 45-61 DOI:10.1016/j.eng.2025.07.022