The field of human mobility and transportation systems is witnessing significant advancements, driven by the integration of innovative technologies and methodologies. Researchers are focusing on developing more accurate and context-aware models to understand human movement patterns, detect anomalies, and predict trajectories. The incorporation of graph structures, semantic complexities, and spatio-temporal analysis is enabling more precise and interpretable results. Notably, the use of generative models, cognitive trajectory memories, and lifestyle concept banks is improving the analysis of human mobility data. Furthermore, the development of novel algorithms and frameworks, such as cooperative trajectory prediction and graph-enhanced anomaly detection, is enhancing the accuracy and robustness of transportation systems. Overall, these advancements are paving the way for more sustainable, efficient, and safe transportation systems. Noteworthy papers include: CoPAD, which proposes a novel framework for cooperative trajectory prediction, and GSTM-HMU, which introduces a generative spatio-temporal framework for human mobility understanding. Additionally, GETAD presents a graph-enhanced trajectory anomaly detection framework, and ATLAS introduces a spatio-temporal directed graph learning approach for account takeover fraud detection.