View article

Machine learning is a promising approach to explore the vast amount of wireless data with artificial intelligence (AI) to accomplish a wide variety of large-scale, computation or communication-oriented tasks in next-generation wireless networks, from intelligent computing to environment sensing and intelligent communication. Traditional approaches rely on each individual task having a specific AI model, which results in high hardware (HW)/software (SW) overheads and prevents the deep exploration of the inherent correlation within data and among tasks. The rapidly emerging big AI model or foundation model (FM) has received a lot of attention recently, which aims at building a unified machine learning system based on a generic class of AI models capable of accomplishing multiple natively interrelated tasks.