FutureNav proposes a 4B-scale VLM that jointly optimizes action prediction, inverse/forward dynamics, and future state generation for VLN and reports SOTA results on multiple benchmarks.
Pathdreamer: A world model for indoor navigation.arXiv preprint arXiv:2105.08756, 2021
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
-
FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation
FutureNav proposes a 4B-scale VLM that jointly optimizes action prediction, inverse/forward dynamics, and future state generation for VLN and reports SOTA results on multiple benchmarks.