Towards Ubiquitous Intelligence: Scaling Language Models Across Wireless Networks
暫譯: 邁向無所不在的智慧：在無線網絡中擴展語言模型

Du, Hongyang, Chen, Xianhao, Liu, Yuanwei

Towards Ubiquitous Intelligence: Scaling Language Models Across Wireless Networks
  • 出版商: Springer
  • 出版日期: 2026-05-19
  • 售價: $6,970
  • 貴賓價: 9.5 折 $6,621
  • 語言: 英文
  • 頁數: 163
  • 裝訂: Hardcover - also called cloth, retail trade, or trade
  • ISBN: 3032201934
  • ISBN-13: 9783032201935
  • 相關分類: Large language model

    • 海外代購書籍(需單獨結帳)

商品描述

This book systematically examines the integration of language models with wireless networks from both architectural and algorithmic perspectives. It begins with the evolution of language models and wireless network requirements, followed by core concepts such as model scaling, training, inference, and the resource constraints shaping their deployment. Building on this foundation, the book investigates LLMs in cloud environments and SLMs for edge computing, focusing on compression, distillation, and efficiency under constrained conditions. The central part of the book is structured around two complementary directions. The first, network-aided collaborative language models, explores how cloud and edge language models can jointly support distributed inference through model partitioning, collaborative training, and adaptive coordination, considering synchronization and communication constraints in wireless networks. The second, language model-aided network optimization, focuses on using language models as decision-making agents to improve network performance, covering protocol optimization, expert routing, and cross-layer integration. These technical developments are grounded through detailed application scenarios and case studies, analyzing trade-offs between accuracy, latency, and resource consumption. The book concludes with forward-looking discussions on architecture, deployment strategies, and research challenges, serving as a comprehensive reference for researchers and practitioners at the intersection of wireless networks and artificial intelligence.

商品描述(中文翻譯)

本書系統性地從架構和演算法的角度探討語言模型與無線網路的整合。內容首先介紹語言模型的演變及無線網路的需求，接著討論核心概念，如模型擴展、訓練、推理以及影響其部署的資源限制。在此基礎上，本書研究了雲端環境中的大型語言模型（LLMs）和邊緣計算中的小型語言模型（SLMs），重點關注在受限條件下的壓縮、蒸餾和效率。本書的核心部分圍繞兩個互補的方向進行結構化。第一個方向是網路輔助的協作語言模型，探討雲端和邊緣語言模型如何通過模型分割、協作訓練和自適應協調共同支持分散式推理，並考慮無線網路中的同步和通信限制。第二個方向是語言模型輔助的網路優化，專注於利用語言模型作為決策代理來改善網路性能，涵蓋協議優化、專家路由和跨層整合。這些技術發展通過詳細的應用場景和案例研究進行具體化，分析準確性、延遲和資源消耗之間的權衡。本書最後以前瞻性的討論結束，探討架構、部署策略和研究挑戰，為無線網路與人工智慧交集領域的研究者和實務工作者提供全面的參考。

作者簡介

Hongyang Du is an assistant professor at the Department of Electrical and Electronic Engineering, The University of Hong Kong, where he directs the Network Intelligence and Computing Ecosystem (NICE) Laboratory. He received the B.Eng. degree from the Beijing Jiaotong University, China, and the Ph.D. degree from the Nanyang Technological University, Singapore. He serves as the Editor of IEEE Communications Surveys & Tutorials, IEEE Transactions on Communications, IEEE Transactions on Vehicular Technology, and IEEE Open Journal of the Communications Society. He is the recipient of the IEEE ComSoc Young Professional Award for Best Early Career Researcher in 2024, the IEEE Signal Processing Society Scholarship from the IEEE Signal Processing Society in 2023, and IEEE Daniel E. Noble Fellowship Award from the IEEE Vehicular Technology Society in 2022. His research interests include edge intelligence, generative AI, and communication networks.

Xianhao Chen received the B.Eng. degree in electronic information from Southwest Jiaotong University, China, in 2017, and the Ph.D. degree in electrical and computer engineering from the University of Florida in 2022. He is currently an Assistant Professor at the Department of Electrical and Electronic Engineering, The University of Hong Kong, where he directs the Wireless Information and Intelligence (WILL) Laboratory. His research interests include wireless networking, edge intelligence, and machine learning.

Yuanwei Liu is a tenured full Professor in Department of Electrical and Electronic Engineering (EEE) at The University of Hong Kong (HKU), and also a visiting Professor in Queen Mary University of London. He is IEEE Fellow, AAIA Fellow, AIIA Fellow, web of Science Highly Cited Researcher (2021 to present), young member of the Hong Kong Academy of Engineering. His research interests include pinching antenna systems, next generation multiple access, integrated sensing and communications, reconfigurable intelligent surface, near-field communications and mobile edge generation. He is listed as one of 35 Innovators Under 35 China in 2022 by MIT Technology Review. He serves as an IEEE Communication Society Distinguished Lecturer, an IEEE Vehicular Technology Society Distinguished Lecturer, chair of IEEE Signal Processing and Computing for Communications (SPCC) Technical Committee, the academic Chair for the Next Generation Multiple Access Emerging Technology Initiative. He received IEEE ComSoc Outstanding Young Researcher Award for EMEA in 2020. He received the 2020 IEEE SPCC Technical Committee Early Achievement Award, IEEE Communication Theory Technical Committee (CTTC) 2021 Early Achievement Award. He received IEEE ComSoc Outstanding Nominee for Best Young Professionals Award in 2021. He received four IEEE best paper awards. He serves Co-Editor-in-Chief of IEEE ComSoc Technical Newsletter, Area Editor of IEEE TCOM/CL, Editor of IEEE COMST/TWC/TCCN /TVT/TNSE, (leading) guest editor of Proceedings of IEEE/IEEE JSAC/JSTSP etc., and the rapporteur of ETSI Industry Specification Group on RIS Industry Specification Group Work Item 6.

Kaibin Huang (Fellow, IEEE) received the B.Eng. and M.Eng. degrees from the National University of Singapore and the Ph.D. degree from The University of Texas at Austin, all in electrical engineering. He is the Philip K H Wong Wilson K L Wong Professor in Electrical Engineering and the Department Head at the Dept. of Electrical and Electronic Engineering, The University of Hong Kong (HKU), Hong Kong. His work was recognized with seven Best Paper awards from the IEEE Communication Society. He is a member of the Engineering Panel of Hong Kong Research Grants Council (RGC) and a Croucher Senior Research Fellow (2026 Class).

作者簡介(中文翻譯)

洪陽杜（Hongyang Du）是香港大學電機電子工程系的助理教授，並負責網絡智能與計算生態系統（NICE）實驗室。他於中國北京交通大學獲得工程學士學位，並於新加坡南洋理工大學獲得博士學位。他擔任《IEEE通訊調查與教程》、《IEEE通訊期刊》、《IEEE車輛技術期刊》和《IEEE通訊學會開放期刊》的編輯。他於2024年獲得IEEE通訊學會最佳早期職業研究者青年專業人士獎，2023年獲得IEEE信號處理學會獎學金，並於2022年獲得IEEE車輛技術學會的Daniel E. Noble獎學金。他的研究興趣包括邊緣智能、生成式人工智慧和通訊網絡。

陳先浩（Xianhao Chen）於2017年獲得中國西南交通大學電子信息工程學士學位，並於2022年獲得佛羅里達大學電氣與計算機工程博士學位。他目前是香港大學電機電子工程系的助理教授，並負責無線信息與智能（WILL）實驗室。他的研究興趣包括無線網絡、邊緣智能和機器學習。

劉元偉（Yuanwei Liu）是香港大學電機電子工程系的終身正教授，同時也是倫敦瑪麗女王大學的訪問教授。他是IEEE Fellow、AAIA Fellow、AIIA Fellow，並自2021年至今為科學網絡高被引研究者，還是香港工程學院的青年會員。他的研究興趣包括天線系統、下一代多重接入、集成感測與通訊、可重構智能表面、近場通訊和移動邊緣計算。他於2022年被《MIT Technology Review》列為35位35歲以下創新者之一。他擔任IEEE通訊學會傑出講者、IEEE車輛技術學會傑出講者、IEEE信號處理與通訊計算技術委員會（SPCC）主席，以及下一代多重接入新興技術倡議的學術主席。他於2020年獲得IEEE通訊學會EMEA傑出青年研究者獎，並於2020年獲得IEEE SPCC技術委員會早期成就獎、2021年IEEE通訊理論技術委員會（CTTC）早期成就獎。他於2021年獲得IEEE通訊學會最佳青年專業人士獎的傑出提名，並獲得四項IEEE最佳論文獎。他擔任IEEE通訊學會技術通訊的共同主編，IEEE TCOM/CL的區域編輯，以及IEEE COMST/TWC/TCCN/TVT/TNSE等期刊的編輯，並擔任ETSI行業規範小組RIS行業規範小組工作項目6的報告員。

黃凱彬（Kaibin Huang，IEEE Fellow）於新加坡國立大學獲得工程學士和碩士學位，並於德克薩斯大學奧斯汀分校獲得電氣工程博士學位。他是香港大學電機電子工程系的Philip K H Wong Wilson K L Wong電氣工程教授及系主任。他的工作曾獲得IEEE通訊學會七項最佳論文獎。他是香港研究資助局（RGC）工程小組的成員，並是2026班的Croucher高級研究員。

類似商品