Sep 2026
FINE: Future-Informed Navigation Encoding for Data-Efficient Vision-Language Navigation
FINE is introduced, a Future-Informed Navigation Encoding framework that extracts this latent supervision from existing demonstrations and improves success rate on R2R-CE and RxR-CE val-unseen, recovering roughly one-third of the performance lost by reducing the training demonstrations.
Khang Nguyen, Hoang Pham Quang Nguyen, Ha Phuong Nguyen et al.
· arXiv.org · 0 citations