WorldMAP bootstraps reliable trajectory prediction in vision-language navigation by converting world-model-generated futures into structured supervision, cutting ADE by 18% and FDE by 42.1% on Target-Bench while making small VLMs competitive with large ones.
Cross-modal map learning for vision and language navigation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
LCGNav improves online topological VLN-CE by converting local depth views to physically truncated 3D point clouds and applying selective dimension-preserving fusion, yielding consistent gains on R2R-CE and RxR-CE benchmarks with open code.
citing papers explorer
-
WorldMAP: Bootstrapping Vision-Language Navigation Trajectory Prediction with Generative World Models
WorldMAP bootstraps reliable trajectory prediction in vision-language navigation by converting world-model-generated futures into structured supervision, cutting ADE by 18% and FDE by 42.1% on Target-Bench while making small VLMs competitive with large ones.
-
LCGNav: Local Candidate-Aware Geometric Enhancement for General Topological Planning in Vision-Language Navigation
LCGNav improves online topological VLN-CE by converting local depth views to physically truncated 3D point clouds and applying selective dimension-preserving fusion, yielding consistent gains on R2R-CE and RxR-CE benchmarks with open code.