Microwave modeling and simulation are two of the most fundamental steps in designing today’s and tomorrow’s wireless components and systems for new generations of communication networks, autonomous systems and IoT. However, the drive to higher frequencies, more functionality, higher performance, and tighter design margins of microwave circuits/systems have resulted in significantly increased design complexity and computational cost, defying the capabilities of existing modeling and simulation methods. In recent years, AI and machine learning have been a recognized vehicle for electromagnetic (EM) parameterized modeling and optimization to accelerate the microwave design. Researchers have investigated a variety of important applications utilizing the ability of AI and machine learning to perform the modeling and optimization of microwave components and circuits, such as high-speed very large-scale integration (VLSI) interconnects, spiral inductors, microwave field-effect transistors (FETs), heterojunction bipolar transistors, high-electron mobility transistors, filters, power amplifiers, microelectromechanical systems, and multi-physics design. This session focuses on recent research progress on a range of AI and machine learning based techniques for microwave modeling and optimization.