AI RESEARCH
Learning to Wander: Improving the Global Image Geolocation Ability of LMMs via Actionable Reasoning
arXiv CS.CV
•
ArXi:2603.10463v1 Announce Type: new Geolocation, the task of identifying the geographic location of an image, requires abundant world knowledge and complex reasoning abilities. Though advanced large multimodal models (LMMs) have shown superior aforementioned capabilities, their performance on the geolocation task remains unexplored. To this end, we