The field of intelligent transportation systems is moving towards more accurate and efficient models for predicting human mobility, traffic flow, and bus trajectories. Researchers are focusing on developing unified models that can handle multiple cities and heterogeneous data, as well as improving the robustness of existing models to uncertainties and variations in traffic patterns. Noteworthy papers in this area include: Zero-Shot Cellular Trajectory Map Matching, which proposes a pixel-based trajectory calibration assistant for zero-shot CTMM, outperforming existing methods by 16.8%. UniMove, a unified model for multi-city human mobility prediction, which improves mobility prediction accuracy by over 10.2% through joint training on multi-city data. M3-Net, a cost-effective graph-free MLP-based model for traffic prediction, which achieves superior performance in terms of prediction accuracy and lightweight deployment. UQGNN, a novel Graph Neural Network with Uncertainty Quantification for multivariate spatiotemporal prediction, which consistently outperforms state-of-the-art baselines in both prediction accuracy and uncertainty quantification. GSMT, a hybrid model for multi-bus trajectory prediction, which significantly outperforms existing approaches in both short-term and long-term trajectory prediction tasks. Efficient Methods for Accurate Sparse Trajectory Recovery and Map Matching, which presents efficient methods TRMMA and MMA for accurate trajectory recovery and map matching, respectively, achieving the best result quality on 4 large real-world datasets.