Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries.

@inproceedings{wu-2026-visualrag, author = {Yin Wu and Quanyu Long and Jing Li and Jianfei Yu and Wenya Wang}, editor = {Hannah Bast and Alistair Moffat and Falk Scholer and Marc Najork and Min Zhang and Hannah Bast and Marc Najork and Min Zhang}, title = {{Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {3473--3480}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3808615}, doi = {https://doi.org/10.1145/3805712.3808615} }