Vision-Language NavigationIntermediate
GeoScaffold: Learning Compact Geometric Latents via Reconstruction for Efficient Vision-Language Navigation
This preprint presents GeoScaffold, a training-only geometric supervision framework for streaming vision-language navigation. A 4B policy fine-tuned with eight geometry query tokens reaches 64.8% success rate on R2R-CE and 59.6% on RxR-CE while using only RGB at inference, and runs at 81 ms per frame on an RTX 4090. The approach avoids resident depth sensors or 3D encoders, making spatially aware navigation cheaper to deploy on edge robots.