Skip to content
Preprint

GuidedNav: Shaping Vision-Language Navigation Representations through Pre-action Attention and Spatial Guidance

Oct 2026 · 0 citations · 61 references
Computer Science

TL;DR

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.

Abstract

Vision-and-language navigation (VLN) requires an agent to track progress through an extended instruction, identify landmarks relevant to its current objective, and understand the surrounding spatial structure to act. End-to-end navigation policies typically rely on action supervision to implicitly learn these capabilities. Without explicit guidance on the evidence underlying each decision, however, policies can overfit to correlations predictive of training actions rather than learn the task-relevant grounding and geometry needed for generalization. Our insight is to guide the representations that connect instructions to actions: identifying what remains to be done determines which visual evidence matters, while understanding the geometry around that evidence informs how to move. We introduce GuidedNav, a unified framework that explicitly shapes these representations through training-time guidance. Subtask and landmark guidance steer native pre-action attention toward the active instruction segment and relevant visual regions, grounding action prediction in the current objective. Spatial guidance aligns the policy's internal representations with geometric features that capture long-horizon context and local spatial structure. Together, these objectives strengthen navigation capabilities while avoiding the inference overhead of intermediate textual reasoning and online geometric encoding. We also introduce Guided-R2R and Guided-RxR, two annotation-enriched navigation datasets that support more interpretable VLN research. GuidedNav establishes state-of-the-art performance among the compared monocular RGB policies, improving success rates by 8.1% and 13.1% relative to the strongest prior results on R2R-CE and RxR-CE val-unseen, respectively, while achieving faster inference. Extensive experiments further demonstrate the effectiveness and real-world transferability of our approach.

View source

Similar papers

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. · 0 citations
Sep 2026

What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior

This work uses intervention-based metrics that measure how visual observations, instructions, and visual memory causally influence navigation decisions and shows that these navigation policies are sensitive to all input modalities and do not depend on a single one.

Débora Oliveira Makowski, Samiran Gode, Abhijeet Nayak et al. · 0 citations

Seek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation

This work proposes SeekVLN, an evidence-seeking framework that couples semantic progress reasoning with active acquisition of task-relevant observations and introduces Counterfactual Contrastive Policy Optimization (C2PO) for reinforcement fine-tuning.

Zhi-Min Wang, Mei-Yuan Zhu, Duo Wu et al. · 0 citations
Review Sep 2026

GroundingVLN: Reasoning and Acting with Grounding for Vision-Language Navigation

This work proposes GroundingVLN, which uses visual grounding as a shared interface between reasoning and action, and introduces Grounded and Execution-Aware Reinforcement Learning (GEAR), which aligns grounded reasoning and spatial decisions with downstream execution.

Kailing Li, Yu Han, Tian-Wen Qian et al. · 0 citations
Conference Open access Sep 2026

FILD-Nav:Vision-and-Language Navigation with Instruction Landmark Features in Continuous Environments

FILD-Nav extracts task-relevant landmarks from instructions and incorporates landmark semantics into both waypoint prediction and topological planning, which improves waypoint relevance and enables more effective long-horizon navigation.

Chuan-Ye Hu, Lu-Lu Liu, Huai-Wei Si et al. · 0 citations
Preprint Oct 2026

StageVLN: Spatial and Trajectory Auxiliary Guidance for Efficient Vision-Language Navigation

Vision-and-Language Navigation (VLN) policies increasingly benefit from strong semantic priors provided by large vision-language models (VLMs). However, standard action supervision does not explicitly encourage intermediate representations to preserve scene geometry, relative orientation, or global episode progress. In...

Anh Dao, Q. Phạm, Le Danh Vinh et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.