Tag
This paper introduces GranuVistaVQA, a multimodal benchmark with element-level annotations, and GranuRAG, a framework that treats visual elements as first-class retrieval units for verifiable multimodal RAG, achieving up to 29.2% improvement over baselines.
This paper presents KITE, a Retrieval-Augmented Generation (RAG)-based intelligent tutoring system for algorithmic reasoning and problem-solving in AI education. The system uses intent-aware Socratic response strategies and multimodal RAG to provide course-grounded, pedagogically appropriate feedback, and is evaluated through metrics, expert review, and simulated student interactions.