HSAN integrates hierarchical semantic graphs, optimal transport-based goal selection, and graph-aware RL to claim SOTA results on VLN-CE tasks.
Shizhe Chen, Pierre-Luc Guhur, Makarand Tapaswi, Cordelia Schmid, and Ivan Laptev
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation
HSAN integrates hierarchical semantic graphs, optimal transport-based goal selection, and graph-aware RL to claim SOTA results on VLN-CE tasks.