Wireless Large AI Model: Shaping the AI-Native Future of 6G and Beyond

2025-04-20

AI Summary

This paper addresses the intelligent evolution of 6G and beyond wireless networks by proposing the Wireless Large Artificial Intelligence Model (WLAM) paradigm to tackle core challenges—including channel dynamics, resource constraints, and distributed deployment—in the deep integration of AI and wireless communications. Methodologically, it establishes the first systematic theoretical framework for WLAM, uncovering bidirectional AI–wireless co-enabling mechanisms; designs a wireless-aware large model architecture integrating federated learning, model sparsification, semantic communication, over-the-air computation, and neural radiance field modeling to enable low-latency, robust, and energy-efficient AI-native operation. Contributions include: (i) identifying six representative application scenarios (e.g., intelligent reflecting surface control, integrated sensing and communication, and space-air-ground-sea ubiquitous coverage); (ii) distilling four implementation challenges and seven frontier research directions; and (iii) providing foundational theory and technical pathways for AI-native 6G networks.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Computer Vision: Large Vision Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

The emergence of sixth-generation and beyond communication systems is expected to fundamentally transform digital experiences through introducing unparalleled levels of intelligence, efficiency, and connectivity. A promising technology poised to enable this revolutionary vision is the wireless large AI model (WLAM), characterized by its exceptional capabilities in data processing, inference, and decision-making. In light of these remarkable capabilities, this paper provides a comprehensive survey of WLAM, elucidating its fundamental principles, diverse applications, critical challenges, and future research opportunities. We begin by introducing the background of WLAM and analyzing the key synergies with wireless networks, emphasizing the mutual benefits. Subsequently, we explore the foundational characteristics of WLAM, delving into their unique relevance in wireless environments. Then, the role of WLAM in optimizing wireless communication systems across various use cases and the reciprocal benefits are systematically investigated. Furthermore, we discuss the integration of WLAM with emerging technologies, highlighting their potential to enable transformative capabilities and breakthroughs in wireless communication. Finally, we thoroughly examine the high-level challenges hindering the practical implementation of WLAM and discuss pivotal future research directions.

Problem

• Surveying wireless large AI models for 6G intelligence and efficiency
• Exploring WLAM's role in optimizing wireless communication systems
• Addressing challenges in practical WLAM implementation and future research

Innovation

• Wireless large AI model enhances 6G intelligence
• WLAM optimizes wireless communication systems
• Integration with emerging technologies enables breakthroughs