Khalifa University Launches RF-GPT for 6G AI Telecom
Khalifa University launches RF-GPT, a pioneering AI model for radio-frequency signals. Consequently, it overcomes key limitations in telecom AI by interpreting wireless data directly. Moreover, the model transforms signals into visual patterns for natural language analysis.
RF-GPT Delivers Superior Performance
RF-GPT excels in radio-frequency spectrogram tasks and outperforms baselines by up to 75.4 percent. For instance, it accurately counts signals in spectrograms nearly 98 percent of the time. Thus, it handles complex tasks like identifying signal types and detecting overlapping transmissions.
The model also recognizes wireless standards, estimates Wi-Fi device activity, and extracts 5G signal data. Trained on 625,000 synthetic samples, RF-GPT supports telecom operators and spectrum managers. Therefore, it aligns with UAE’s AI Strategy for smarter wireless networks.
Leadership Drives Innovation Forward
Researchers at Khalifa University, led by Professor Merouane Debbah, developed RF-GPT. Key team members include Hang Zou, Yu Tian, Dr. Lina Bariah, Dr. Samson Lasaulce, Dr. Chongwen Huang, and Bohao Wang. As a result, the project advances 6G-ready spectrum intelligence.
“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 Ahmed Al Durrah, Associate Provost for Research.
Professor Merouane Debbah stated that, “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 optimization and policy decisions, a crucial step towards future AI-native 6G networks.”
