3 papers
cs.LG2026
Continuous Cross-Domain Traffic State Prediction via Memory-Augmented Graph Liquid Time-Constant Networks
Jinrong Xiang, Ming Xu
Traffic state prediction is a fundamental task in intelligent transportation systems. In practical applications, some regions suffer from limited traffic observations due to insuff…
cs.LG2025
Learning to Rank Critical Road Segments via Heterogeneous Graphs with Origin-Destination Flow Integration
Ming Xu, Jinrong Xiang, Zilong Xie +1
Existing learning-to-rank methods for road networks often fail to incorporate origin-destination (OD) flows and route information, limiting their ability to model long-range spatia…
cs.CV2024
Hierarchical Spatial Proximity Reasoning for Vision-and-Language Navigation
Ming Xu, Zilong Xie
Most Vision-and-Language Navigation (VLN) algorithms are prone to making inaccurate decisions due to their lack of visual common sense and limited reasoning capabilities. To addres…