The basis mannequin straight contributes to the UAE National Artificial Intelligence Strategy, laying the groundwork for extra autonomous and clever wi-fi networks.
Khalifa University of Science and Technology ’s Digital Future Institute introduced the launch of ‘RF-GPT’ a first-of-its-kind radio-frequency AI language mannequin succesful of decoding wi-fi alerts, overcoming a significant limitation in telecom AI the place language fashions usually function solely on textual content and structured community information.
RF-GPT confirmed constant efficiency enhancements in radio frequency spectrogram duties, outperforming current baseline fashions by up to 75.4%, demonstrating robust radio frequency understanding. RF-GPT additionally accurately counted the quantity of alerts in a spectrogram ~98% of the time, which general-purpose AI fashions virtually by no means obtain.
RF-GPT works by turning radio alerts into visible patterns that synthetic intelligence can perceive. Once transformed, AI programs can analyze these patterns and reply questions on what is occurring within the wi-fi spectrum utilizing plain language. The basis mannequin straight contributes to the UAE National Artificial Intelligence Strategy, laying the groundwork for extra autonomous and clever wi-fi networks.
The mission was developed by Khalifa University researchers led by Professor Merouane Debbah, Senior Director, Digital Future Institute, and consists of Post Doctoral Fellows Hang Zou, Yu Tian, Research Scientists Dr. Lina Bariah, Khalifa University, Dr. Samson Lasaulce, Universit´ e de Lorraine, and Dr. Chongwen Huang and PhD pupil Bohao Wang from Zhejiang University.
“The launch of ‘RF-GPT’ reflects Khalifa University’s long-term focus on innovation in digital infrastructure to advance AI integration across strategic sectors, and next-generation connectivity research, aligned with national priorities. Initiatives such as this model contribute to UAE’s fast growing human capital and research capabilities necessary to support the UAE’s evolving digital ecosystem.”
– Professor Ahmed Al Durrah, Associate Provost for Research, Khalifa University
“RF-GPT represents a turning point for spectrum intelligence, moving from isolated, task-specific radio frequency pipelines toward a unified RF-language interface. We gave a language model its first glimpse of the electromagnetic spectrum and the view is already remarkable. Imagine what it will see next. By making the physical layer quarriable in natural language, we open the door to AI-native radio systems where RF perception can directly support network optimization and policy decisions, a crucial step toward future AI-native 6G networks.”
– Professor Merouane Debbah, Senior Director, Digital Future Institute
RF-GPT was educated utilizing roughly 625,000 computer-generated radio sign examples, and is designed for telecom operators, community engineering groups, and spectrum authorities, supporting more and more complicated wi-fi environments. The mannequin carried out strongly throughout duties reminiscent of figuring out sign sorts, detecting overlapping transmissions, recognizing wi-fi requirements, estimating gadget utilization in Wi-Fi networks, and extracting information from 5G alerts.