Search papers, labs, and topics across Lattice.
Institute of Marine Science and Technology, Shandong University, China
3
0
4
Using a large language model as an external trainer, LaT boosts multi-task neural solvers' performance on diverse Vehicle Routing Problems without the computational burden of traditional meta-learning.
VaFM outperforms traditional methods by effectively integrating visual semantics into vehicle routing, addressing complex constraints that were previously overlooked.
Neural routing solvers can now efficiently tackle hard constraints thanks to Construct-and-Refine (CaR), which slashes the refinement steps needed by 500x while boosting solution quality.
