Multimodal AI

Performance Comparison of Multimodal Vision-Language Models in Classifying Turkish Dishes
Comprehensive zero-shot evaluation of open-source multimodal Vision-Language Models for culturally specific Turkish food classification.
DOI
From Video to Recipe: Leveraging Vision Language Models for Culinary Analysis
Investigates open-weight Vision-Language Models for automated recipe extraction, ingredient identification, and culinary video analysis.
Street-Level Geolocalization Using Multimodal Large Language Models and Retrieval-Augmented Generation
Proposes a multimodal framework integrating Vision-Language Models with RAG for street-level image geolocalization and interpretable spatial reasoning.
DOI