cs.LGFeb 4, 2026

AmbientFM: A Foundation Model for Ambient Sensing

Authors: Guozhen Zhu, Yuqian Hu, Sakila Jayaweera, Weihang Gao, Wei-Hsiang Wang, Jiaxuan Zhang, Beibei Wang, Chenshu Wu, 

Organizations: Origin Research, Rockville, USA · The University of Hong Kong, Hong Kong, China

Abstract

Ambient intelligence seeks to continuously understand human presence, activity, and physiology in physical spaces, enabling smart environments, health monitoring, and human-computer interaction. WiFi infrastructure offers a ubiquitous, always-on, and privacy-preserving sensing substrate across billions of IoT devices. Yet ambient sensing with WiFi remains largely fragmented, with most systems relying on task-specific models, labeled data collection, and customized training pipelines. We present AmbientFM, a foundation model for ambient sensing through ubiquitous WiFi signals. AmbientFM is pre-trained on 9.2 million unlabeled Channel State Information (CSI) samples collected over 439 days from 20 commercial device types deployed in real homes, the largest real-world WiFi CSI pre-training corpus reported to date. It learns transferable wireless representations through contrastive learning, masked reconstruction, and physics-informed objectives tailored to wireless signals. With lightweight adaptation, a single backbone transfers to 9 downstream tasks, achieving above 0.90 AUROC on all classification benchmarks and supporting dense spatial reconstruction. AmbientFM reduces the need for labeled data and task-specific design, enabling scalable ambient intelligence on existing wireless infrastructure.

Figures & tables

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. The Universal Language of CSI:Unifying Wireless Sensing Across Devices and Environments

    Jun 30, 2026Jiayi Chen, Weiting Ou, Guangxu ZhuWireless Foundation ModelsWi-Fi Sensing

  2. Zero-Fi: Zero-Shot Wi-Fi-Based Human Activity Recognition via Contrastive Signal-Language Alignment

    Jul 29, 2026Yitong Shen, Cheng Guo, Peiliang Wang +5Human Activity RecognitionZero-Shot Action Recognition