Tag
论文提出一种面向路网轨迹生成的图约束生成范式 Anticipatory Generative Modeling，并提出模型 Foresight，通过"anticipate–select–update–re-anticipate"循环解决路口转移选择问题，超越扩散模型等基线方法。
This paper proposes TraveL, a Transformer-based multi-view framework for learning distributional representations of paths in road networks, capturing varied traveler behaviors and regional correlations, and outperforming state-of-the-art methods in travel time estimation, path similarity, and destination prediction.
This paper introduces the edge-based contiguous p-median (ECpM) problem for partitioning road networks into compact territories, proposing two binary programming models with contiguity constraints and testing them on large road networks. The shortest-path constraint model achieves significant speedups over a cut set-based branch-and-cut approach, with connections to logistics districting.