Training-only supervision of small geometry query tokens lets an RGB-only navigation policy outperform depth-sensor-based systems at a fraction of the latency.
Prospect: Unified streaming vision-language navigation via semantic–spatial fusion and latent predictive representation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 3roles
baseline 1polarities
baseline 1representative citing papers
WeldMamba achieves 74.63% mIoU for 500 ms lookahead segmentation of keyhole, wire, and molten pool using spatiotemporal state space modeling conditioned on welding signals and physics-based losses on a 43-sequence dataset.
StereoNav reaches new benchmark highs on R2R-CE and RxR-CE and improves real-robot reliability by supplying persistent target-location priors and stereo-derived geometry that stay stable under lighting changes and blur.
citing papers explorer
-
GeoScaffold: Learning Compact Geometric Latents via Reconstruction for Efficient Vision-Language Navigation
Training-only supervision of small geometry query tokens lets an RGB-only navigation policy outperform depth-sensor-based systems at a fraction of the latency.
-
Physics-Guided Spatiotemporal State Space Modeling for Lookahead Molten Pool Segmentation in Laser Wire-Feed Welding
WeldMamba achieves 74.63% mIoU for 500 ms lookahead segmentation of keyhole, wire, and molten pool using spatiotemporal state space modeling conditioned on welding signals and physics-based losses on a 43-sequence dataset.
-
What Limits Vision-and-Language Navigation ?
StereoNav reaches new benchmark highs on R2R-CE and RxR-CE and improves real-robot reliability by supplying persistent target-location priors and stereo-derived geometry that stay stable under lighting changes and blur.