Wireless Sensing AI: Machine Intelligence Beyond Vision and Language

YECL Seminar

Abstract:
Can machines perceive without cameras or sensors? While computer vision allows machines to "see", its capabilities based on cameras are fundamentally limited by specific fields of view, lighting conditions, and the inability to see through obstacles. In this talk, I will introduce Wireless AI Perception, a paradigm that endows machines with a new sense to understand the physical world using ambient wireless signals-seeing through walls and in absolute darkness. Wireless AI reimagines Wi-Fi, transforming everyday wireless devices from a pure communication medium into a ubiquitous all-in-one sensing platform. We will first introduce the concepts, principles, and grand challenges of wireless sensing, then present our unique Wireless AI solution, which has been commercialized and deployed across millions of real-world devices. The talk will conclude with an exploration of other modalities like mmWave, acoustics, and thermal, and a preliminary investigation into open benchmarks and frameworks for "sensing foundation models".
 
Biography:
Dr. Chenshu Wu is an Assistant Professor in the Department of Computer Science at the University of Hong Kong, where he leads the HKU AIoT Lab. Prior to joining HKU, he served as Chief Scientist at Origin AI and conducted research at the University of Maryland, Princeton University, and Tsinghua University. His research focuses on wireless and mobile AIoT systems at the intersection of wireless sensing, ubiquitous computing, and the Internet of Things. He has authored three books and over 100 papers in top-tier venues such as SIGCOMM, NSDI, OSDI, MobiCom, MobiSys, and UbiComp. He holds over 90 filed or granted patents, and his work on Wi-Fi sensing has been deployed globally in award-winning commercial products. He is the recipient of NSF China Excellent Young Scientists Fund, NAM Healthy Longevity Catalyst Award, and CCF Outstanding Doctoral Dissertation Award. He serves as an associate editor of ACM IMWUT and ACM TIoT, the Journal Track Co-Chair of EWSN 2025 and the TPC Co-Chair of IEEE ICPADS 2024. He co-organized workshops including HotSense 2025, RFCom 2024, Wireless AI Perception 2022, and regularly serves on the TPC of MobiSys, SenSys, MobiHoc, ICDCS, INFOCOM, and others. He received his B.S. and Ph.D. degrees from Tsinghua University. More information at https://cswu.me.