UniteFormer: Unifying Node and Edge Modalities in Transformers for Vehicle Routing Problems

NeurIPSSpotlight2025

Authors
Dian Meng, Zhiguang Cao, Jie Gao, Yaoxin Wu, Yaqing Hou
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Neural solvers for the Vehicle Routing Problem (VRP) have typically relied on either node or edge inputs, limiting their flexibility and generalization in real-world scenarios…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

generalization transformer

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive