ABU DHABI, 6th April, 2026 (WAM) — Khalifa University of Science and Technology’s Digital Future Institute announced the launch of ‘RF-GPT’, a first-of-its-kind radio-frequency AI language model capable of interpreting wireless signals, overcoming a major limitation in telecommunications AI, where language models typically operate only on text and structured network data.
RF-GPT demonstrated consistent performance improvements in radio-frequency spectrogram tasks, outperforming existing baseline models by up to 75.4 percent, reflecting strong radio-frequency understanding. The model also correctly counted the number of signals in a spectrogram nearly 98 percent of the time, a capability that general-purpose AI models rarely achieve.
RF-GPT operates by converting radio signals into visual patterns that artificial intelligence systems can interpret. Once converted, these systems analyse the patterns and respond to queries about activity within the wireless spectrum using plain language. The foundation model directly supports the UAE National Artificial Intelligence Strategy, laying the groundwork for more autonomous and intelligent wireless networks.
The project was developed by Khalifa University researchers led by Professor Merouane Debbah, Senior Director of the Digital Future Institute, with contributions from postdoctoral fellows Hang Zou and Yu Tian, research scientists Dr. Lina Bariah of Khalifa University, Dr. Samson Lasaulce of Université de Lorraine, and Dr. Chongwen Huang, along with PhD student Bohao Wang from Zhejiang University.
Professor Ahmed Al Durrah, Associate Provost for Research at Khalifa University, said, “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 the UAE’s rapidly growing human capital and research capabilities necessary to support the country’s evolving digital ecosystem.”
Professor Merouane Debbah said, “RF-GPT represents a turning point for spectrum intelligence, moving from isolated, task-specific radio-frequency pipelines towards a unified RF-language interface. We gave a language model its first glimpse of the electromagnetic spectrum, and the view is already remarkable. By making the physical layer queryable in natural language, we open the door to AI-native radio systems, where RF perception can directly support network optimisation and policy decisions, a crucial step towards future AI-native 6G networks.”
RF-GPT was trained using approximately 625,000 computer-generated radio signal examples and is designed for telecommunications operators, network engineering teams, and spectrum authorities, supporting increasingly complex wireless environments. The model demonstrated strong performance across tasks such as identifying signal types, detecting overlapping transmissions, recognising wireless standards, estimating device usage in Wi-Fi networks, and extracting data from 5G signals.
