AI RESEARCH
TagaVLM: Topology-Aware Global Action Reasoning for Vision-Language Navigation
arXiv CS.CV
•
ArXi:2603.02972v2 Announce Type: replace Vision-Language Navigation (VLN) presents a unique challenge for Large Vision-Language Models (VLMs) due to their inherent architectural mismatch: VLMs are primarily pretrained on static, disembodied vision-language tasks, which fundamentally clash with the dynamic, embodied, and spatially-structured nature of navigation. Existing large-model-based methods often resort to converting rich visual and spatial information into text, forcing models to implicitly infer complex visual-topological relationships or limiting their global action capabilities.