Repository for our paper Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries
The dataset repo have been move to: https://github.com/visual-rag/visual-rag Some queries are been removed or modified and result in slight different stats comparing to that reported in paper. We are working on another round of data revision and the arxiv paper will be updated later.