AI RESEARCH

Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization

arXiv CS.CV

ArXi:2604.16248v1 Announce Type: new Image geolocalization has traditionally been addressed through retrieval-based place recognition or geometry-based visual localization pipelines. Recent advances in Vision-Language Models (VLMs) have nstrated strong zero-shot reasoning capabilities across multimodal tasks, yet their performance in geographic inference remains underexplored. In this work, we present a systematic evaluation of multiple state-of-the-art VLMs for country-level image geolocalization using ground-view imagery only.