UAE university unveils AI model to interpret wireless signals

Khalifa University of Science and Technology’s Digital Future Institute has launched what it describes as the world’s first radio-frequency artificial intelligence language model capable of interpreting wireless signals, the Emirates News Agency (WAM) reported Monday.

The model, called RF-GPT, is designed to address a key limitation in telecommunications AI, where language models typically operate only on text and structured network data, according to WAM.

RF-GPT demonstrated consistent performance improvements in radio-frequency spectrogram tasks, outperforming existing baseline models by up to 75.4%, reflecting what the university described as strong radio-frequency understanding.

The model also correctly counted the number of signals in a spectrogram nearly 98% of the time, a capability that general-purpose AI models rarely achieve, WAM reported.

RF-GPT works by converting radio signals into visual patterns that artificial intelligence systems can interpret. Once converted, the systems analyze 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, the university said, adding that it lays 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. Contributors included 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; and Ph.D. student Bohao Wang from Zhejiang University.

Professor Ahmed Al Durrah, associate provost for research at Khalifa University, said the launch reflects the institution’s long-term focus on innovation in digital infrastructure to advance AI integration across strategic sectors and next-generation connectivity research.

“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,” Al Durrah said.

Debbah described RF-GPT as “a turning point for spectrum intelligence,” saying it moves 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,” Debbah said. “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 optimization 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.

The model demonstrated performance across tasks including identifying signal types, detecting overlapping transmissions, recognizing wireless standards, estimating device usage in Wi-Fi networks and extracting data from 5G signals, according to WAM.