Dall-EM: Generative AI with Diffusion Models for New Design Space Discovery and Target-to-Electromagnetic Structure Synthesis

Design of RF and mmWave circuits and electromagnetic (EM) structures is typically a designer experience-driven process, aided with time and resource-intensive simulations, iterative design methods, and ad-hoc optimization. The starting points of this process are preselected parameterized templates that not only limit the design space and achievable performance, but the entire design iterative and optimization process can be extremely time-consuming. Further, while there are templates that exist for simpler EM structures operable over a narrow range of frequencies, for many structures that require complex spectral responses, there are no set templates. We present a generative AI approach toward rapid synthesis of arbitrary shaped EM structures with designer scattering-parameters utilizing a directed diffusion approach. While these models have been extremely successful in generating complex images from text, we show for the first time the diffusion model for synthesis of EM structures (represented as images), allowing search space of arbitrary shaped structures.