AM-FM: A Foundation Model for Ambient Intelligence Through WiFi

2026-02-04

AI Summary

This work addresses the limitations of existing wireless sensing approaches, which rely on task-specific models and large amounts of labeled data, hindering scalable ambient intelligence on ubiquitous Wi-Fi infrastructure. To overcome this, the authors propose AM-FM—the first foundation model for Wi-Fi-based ambient intelligence—that learns generalizable wireless signal representations through self-supervised pretraining. AM-FM integrates contrastive learning, masked reconstruction, and physics-informed self-supervision, and is pretrained on 9.2 million channel state information (CSI) samples. Extensive experiments across nine downstream tasks demonstrate that AM-FM substantially improves data efficiency and generalization capability, thereby validating the feasibility of achieving scalable ambient intelligence using existing Wi-Fi devices.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Planning, Routing, and Scheduling: Planning with Language 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
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Ambient intelligence, continuously understanding human presence, activity, and physiology in physical spaces, is fundamental to smart environments, health monitoring, and human-computer interaction. WiFi infrastructure provides a ubiquitous, always-on, privacy-preserving substrate for this capability across billions of IoT devices. Yet this potential remains largely untapped, as wireless sensing has typically relied on task-specific models that require substantial labeled data and limit practical deployment. We present AM-FM, the first foundation model for ambient intelligence and sensing through WiFi. AM-FM is pre-trained on 9.2 million unlabeled Channel State Information (CSI) samples collected over 439 days from 20 commercial device types deployed worldwide, learning general-purpose representations via contrastive learning, masked reconstruction, and physics-informed objectives tailored to wireless signals. Evaluated on public benchmarks spanning nine downstream tasks, AM-FM shows strong cross-task performance with improved data efficiency, demonstrating that foundation models can enable scalable ambient intelligence using existing wireless infrastructure.

Problem

• ambient intelligence
• WiFi sensing
• foundation model
• wireless sensing
• task-specific models

Innovation

• foundation model
• ambient intelligence
• WiFi sensing
• Channel State Information
• contrastive learning