The field of control systems and diabetes management is rapidly evolving, with a focus on developing more accurate and personalized models for glucose-insulin dynamics. Recent research has explored the use of artificial intelligence, machine learning, and data-driven approaches to improve the precision and adaptability of insulin delivery systems. The integration of pramlintide, a hormone that delays gastric emptying, into automated insulin delivery systems has shown promising results in reducing postprandial glucose excursion. Additionally, the development of new control algorithms, such as the Koopman-Nemytskii operator, has enabled more accurate modeling of nonlinear controlled systems. Noteworthy papers include the introduction of the Invertible Koopman Neural Operator, which provides a novel data-driven modeling approach for partial differential equations, and the integration of biological-informed recurrent neural networks for glucose-insulin dynamics modeling, which has shown superior performance in capturing complex behaviors and control systems dynamics.