Preprint
Oct 2026
GuidedNav: Shaping Vision-Language Navigation Representations through Pre-action Attention and Spatial Guidance
GuidedNav is introduced, a unified framework that explicitly shapes representations that connect instructions to actions and establishes state-of-the-art performance among the compared monocular RGB policies, improving success rates and achieving faster inference.
Jing-Yu Guo, Jia-Xin Huang, Cheng-Xing Lin et al.
· 0 citations