OPTFM: A Scalable Multi-View Graph Transformer for Hierarchical Pre-Training in Combinatorial Optimization

NeurIPSSpotlight2025

Authors
Hao Yuan, Wenli Ouyang, Changwen Zhang, Congrui Li, Yong Sun
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Foundation Models (FMs) have demonstrated remarkable success in fields like computer vision and natural language processing, yet their application to combinatorial optimization remains underexplored…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

computer vision optimization pre-training transformer graph

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive