SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Modern Vision-Language Navigation (VLN) models rely mostly on pre-trained large Vision-Language Models (VLMs) to predict navigation actions. While this fusion of language instructions and visual observations allows multimodal reasoning, it obscures how information is routed across modalities or what mechanisms drive navigation decisions. Thus, it remains unclear whether VLN models ground their predictions in relevant semantic cues or can track task progress. In this work, we study the interpretability and steerability of VLN models. We use intervention-based metrics that measure how visual obs

Read original source ↗ Open in workspace

recordType

paper

region

Global