The field of research is moving towards the development of more accurate and efficient generative models and simulation techniques. This is evident in the increasing use of machine learning approaches, such as deep generative models and conditional generative adversarial networks, to simulate complex systems and phenomena. These models are being applied to a wide range of areas, including travel demand modeling, urban mobility flow generation, and radio map construction. The use of these models enables the simulation of dynamic network states, the generation of high-dimensional radio maps, and the prediction of complex phenomena such as climate extremes. Noteworthy papers in this area include the development of a Canada-wide morphology map for the ITU-R P.1411 propagation model and the proposal of MobiWorld, a generative world model for mobile wireless network planning and optimization. Additionally, the introduction of DeepX-GAN, a knowledge-informed deep generative model for capturing unseen spatial extremes, and the development of RadioDiff-3D, a diffusion-model-based generative framework for 3D radio map construction, are also significant contributions to the field.