{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:05:23Z","timestamp":1784138723059,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"NTU Start-Up Grant, Singapore","award":["NA"],"award-info":[{"award-number":["NA"]}]},{"name":"MOE AcRF Tier 1 Seed Funding Grant, Singapore","award":["RS37\/24"],"award-info":[{"award-number":["RS37\/24"]}]},{"name":"Natural Science Foundation of China","award":["62476132"],"award-info":[{"award-number":["62476132"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3808615","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:06:26Z","timestamp":1784135186000},"page":"3473-3480","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9041-5452","authenticated-orcid":false,"given":"Yin","family":"Wu","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4839-012X","authenticated-orcid":false,"given":"Quanyu","family":"Long","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3262-3734","authenticated-orcid":false,"given":"Jing","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8380-0609","authenticated-orcid":false,"given":"Jianfei","family":"Yu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5612-7818","authenticated-orcid":false,"given":"Wenya","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Anthropic. 2025. Introducing Claude 4. https:\/\/www.anthropic.com\/news\/claude-4. https:\/\/www.anthropic.com\/news\/claude-4 Accessed: 2025-07-25."},{"key":"e_1_3_2_1_2_1","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang Humen Zhong Yuanzhi Zhu Mingkun Yang Zhaohai Li Jianqiang Wan Pengfei Wang Wei Ding Zheren Fu Yiheng Xu Jiabo Ye Xi Zhang Tianbao Xie Zesen Cheng Hang Zhang Zhibo Yang Haiyang Xu and Junyang Lin. 2025. Qwen2.5-VL Technical Report. arXiv:2502.13923 [cs.CV] https:\/\/arxiv.org\/abs\/2502.13923"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01600"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Jaemin Cho Debanjan Mahata Ozan Irsoy Yujie He and Mohit Bansal. 2024. M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding. arXiv:2411.04952 [cs.CV] https:\/\/arxiv.org\/abs\/2411.04952","DOI":"10.1109\/ICCVW69036.2025.00649"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1576"},{"key":"e_1_3_2_1_7_1","unstructured":"Matthijs Douze Alexandr Guzhva Chengqi Deng Jeff Johnson Gergely Szilvasy Pierre-Emmanuel Mazar\u00e9 Maria Lomeli Lucas Hosseini and Herv\u00e9 J\u00e9gou. 2024. The Faiss library. arXiv:2401.08281 [cs.LG] https:\/\/arxiv.org\/abs\/2401.08281"},{"key":"e_1_3_2_1_8_1","unstructured":"Google. 2025. Gemini-2.5-Pro. https:\/\/deepmind.google\/models\/gemini\/pro\/. https:\/\/deepmind.google\/models\/gemini\/pro\/ Accessed: 2025-07-25."},{"key":"e_1_3_2_1_9_1","volume-title":"MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Usklli4gMc","author":"Hu Wenbo","year":"2025","unstructured":"Wenbo Hu, Jia-Chen Gu, Zi-Yi Dou, Mohsen Fayyaz, Pan Lu, Kai-Wei Chang, and Nanyun Peng. 2025. MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Usklli4gMc"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Hui Huang Yingqi Qu Xingyuan Bu Hongli Zhou Jing Liu Muyun Yang Bing Xu and Tiejun Zhao. 2024. An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4. arXiv:2403.02839 [cs.CL] https:\/\/arxiv.org\/abs\/2403.02839","DOI":"10.18653\/v1\/2025.findings-acl.306"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"e_1_3_2_1_12_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=TE0KOzWYAF","author":"Jiang Ziyan","year":"2025","unstructured":"Ziyan Jiang, Rui Meng, Xinyi Yang, Semih Yavuz, Yingbo Zhou, and Wenhu Chen. 2025. VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=TE0KOzWYAF"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.307"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531753"},{"key":"e_1_3_2_1_16_1","first-page":"9459","volume-title":"Lin (Eds.)","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 9459-9474. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/6b493230205f780e1bc26945df7481e5-Paper.pdf"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3041"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00289"},{"key":"e_1_3_2_1_20_1","unstructured":"Meta Llama Team. 2024. The Llama 3 Herd of Models. arXiv:2407.21783 [cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_1_21_1","unstructured":"Microsoft. 2025. Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs. arXiv:2503.01743 [cs.CL] https:\/\/arxiv.org\/abs\/2503.01743"},{"key":"e_1_3_2_1_22_1","unstructured":"Mistral AI. 2024. Announcing Pixtral 12B. https:\/\/mistral.ai\/news\/pixtral-12b\/. https:\/\/mistral.ai\/news\/pixtral-12b\/ Accessed: 2025-07-25."},{"key":"e_1_3_2_1_23_1","unstructured":"OpenAI. 2025. ChatGPT. https:\/\/openai.com\/chatgpt. https:\/\/openai.com\/chatgpt Accessed: 2025-07-25."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748-8763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"e_1_3_2_1_26_1","volume-title":"Forty-second International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=EVwMw2lVlw","author":"Su Xin","year":"2025","unstructured":"Xin Su, Man Luo, Kris W Pan, Tien Pei Chou, Vasudev Lal, and Phillip Howard. 2025. SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs. In Forty-second International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=EVwMw2lVlw"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.310"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01269"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00265"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.83"},{"key":"e_1_3_2_1_31_1","volume-title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track. https:\/\/openreview.net\/forum?id=uccHPGDlao","author":"Zheng Lianmin","year":"2023","unstructured":"Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track. https:\/\/openreview.net\/forum?id=uccHPGDlao"},{"key":"e_1_3_2_1_32_1","volume-title":"Defu Lian, and Yongping Xiong.","author":"Zhou Junjie","year":"2024","unstructured":"Junjie Zhou, Zheng Liu, Ze Liu, Shitao Xiao, Yueze Wang, Bo Zhao, Chen Jason Zhang, Defu Lian, and Yongping Xiong. 2024. MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval. arXiv preprint arXiv:2412.14475 (2024)."},{"key":"e_1_3_2_1_33_1","unstructured":"Jinguo Zhu Weiyun Wang Zhe Chen Zhaoyang Liu Shenglong Ye Lixin Gu Hao Tian Yuchen Duan Weijie Su Jie Shao Zhangwei Gao Erfei Cui Xuehui Wang Yue Cao Yangzhou Liu Xingguang Wei Hongjie Zhang Haomin Wang Weiye Xu Hao Li Jiahao Wang Nianchen Deng Songze Li Yinan He Tan Jiang Jiapeng Luo Yi Wang Conghui He Botian Shi Xingcheng Zhang Wenqi Shao Junjun He Yingtong Xiong Wenwen Qu Peng Sun Penglong Jiao Han Lv Lijun Wu Kaipeng Zhang Huipeng Deng Jiaye Ge Kai Chen Limin Wang Min Dou Lewei Lu Xizhou Zhu Tong Lu Dahua Lin Yu Qiao Jifeng Dai and Wenhai Wang. 2025. InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models. arXiv:2504.10479 [cs.CV] https:\/\/arxiv.org\/abs\/2504.10479"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:16:07Z","timestamp":1784135767000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3808615"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":33,"alternative-id":["10.1145\/3805712.3808615","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3808615","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}