GC-VLN decomposes a navigation instruction into a graph of spatial constraints, solves the constraints with an optimizer, and beats prior zero-shot methods on VLN-CE benchmarks without any training.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GC-VLN: Instruction as Graph Constraints for Training-free Vision-and-Language Navigation
GC-VLN decomposes a navigation instruction into a graph of spatial constraints, solves the constraints with an optimizer, and beats prior zero-shot methods on VLN-CE benchmarks without any training.