Generative AI Meets Wireless Sensing: Towards Wireless Foundation Model

2025-09-18

AI Summary

This study addresses key bottlenecks in wireless sensing—including poor generalization across tasks (e.g., localization, activity recognition, environmental monitoring) and task fragmentation—by proposing a novel paradigm integrating generative AI deeply with wireless sensing. Methodologically, it introduces a dual-path framework: “plug-in enhancement” and “end-to-end solving,” systematically unifying GANs, VAEs, and diffusion models with synergistic data augmentation, domain adaptation, and signal denoising to enhance model robustness and cross-scenario transferability. Key contributions include: (1) the first articulation of a scalable, adaptive Wireless Foundation Model (WFM) vision; (2) a unified integration paradigm for generative models in wireless signal understanding, accompanied by theoretical analysis of applicability and limitations; and (3) the first technically sound, theoretically grounded, and engineering-practical pathway enabling multi-task unified modeling in wireless sensing.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Generation

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
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Generative Artificial Intelligence (GenAI) has made significant advancements in fields such as computer vision (CV) and natural language processing (NLP), demonstrating its capability to synthesize high-fidelity data and improve generalization. Recently, there has been growing interest in integrating GenAI into wireless sensing systems. By leveraging generative techniques such as data augmentation, domain adaptation, and denoising, wireless sensing applications, including device localization, human activity recognition, and environmental monitoring, can be significantly improved. This survey investigates the convergence of GenAI and wireless sensing from two complementary perspectives. First, we explore how GenAI can be integrated into wireless sensing pipelines, focusing on two modes of integration: as a plugin to augment task-specific models and as a solver to directly address sensing tasks. Second, we analyze the characteristics of mainstream generative models, such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and diffusion models, and discuss their applicability and unique advantages across various wireless sensing tasks. We further identify key challenges in applying GenAI to wireless sensing and outline a future direction toward a wireless foundation model: a unified, pre-trained design capable of scalable, adaptable, and efficient signal understanding across diverse sensing tasks.

Problem

• Integrating generative AI into wireless sensing systems
• Improving wireless sensing applications with generative techniques
• Developing unified wireless foundation model for sensing

Innovation

• Integrating generative AI as plugin and solver
• Applying GANs VAEs diffusion models to sensing
• Developing unified pre-trained wireless foundation model