The paper introduces the Compositional Geometry Routing Problem and proposes DiCon, a differential-attention plus double-level contrastive learning solver that reports strong performance and generalization on mixed-geometry routing instances.
UDC: A unified neural divide-and-conquer framework for large-scale combinatorial optimization problems.Advances in Neural Information Processing Systems, 37:6081–6125
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning to Solve Compositional Geometry Routing Problems
The paper introduces the Compositional Geometry Routing Problem and proposes DiCon, a differential-attention plus double-level contrastive learning solver that reports strong performance and generalization on mixed-geometry routing instances.