{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T02:20:33Z","timestamp":1790216433628,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Austrian Research Agency","award":["915229"],"award-info":[{"award-number":["915229"]}]},{"name":"Innovative Human Resource Development for Local Intellectualization program through the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT)","award":["IITP-2026-RS-2020-II201462, 50%"],"award-info":[{"award-number":["IITP-2026-RS-2020-II201462, 50%"]}]},{"name":"partly supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (Ministry of Science and ICT)","award":["RS-2023-NR076833"],"award-info":[{"award-number":["RS-2023-NR076833"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817457","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"8604-8612","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["MM-BRIGHT: A Multi-Task Multimodal Benchmark for Reasoning-Intensive Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8747-4927","authenticated-orcid":false,"given":"Abdelrahman","family":"Abdallah","sequence":"first","affiliation":[{"name":"University of Innsbruck, Innsbruck, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6750-3034","authenticated-orcid":false,"given":"Mohamed Darwish","family":"Mounis","sequence":"additional","affiliation":[{"name":"High Institute for Computer & IS, Alexandria, Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4270-2268","authenticated-orcid":false,"given":"Mahmoud","family":"Abdalla","sequence":"additional","affiliation":[{"name":"Chungbuk National University, Cheongju-si, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8513-570X","authenticated-orcid":false,"given":"Mahmoud SalahEldin","family":"Kasem","sequence":"additional","affiliation":[{"name":"Chungbuk National University, cheongju-si, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5890-0923","authenticated-orcid":false,"given":"Mostafa Farouk","family":"Senussi","sequence":"additional","affiliation":[{"name":"Chungbuk National University, Chungju-si, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6764-8969","authenticated-orcid":false,"given":"Mohamed","family":"Mahmoud","sequence":"additional","affiliation":[{"name":"Chungbuk National University, Chungju-si, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3600-0785","authenticated-orcid":false,"given":"Mohammed","family":"Ali","sequence":"additional","affiliation":[{"name":"University of Innsbruck, Innsbruck, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7235-0665","authenticated-orcid":false,"given":"Adam","family":"Jatowt","sequence":"additional","affiliation":[{"name":"University of Innsbruck, Innsbruck, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4333-2852","authenticated-orcid":false,"given":"Hyun Soo","family":"Kang","sequence":"additional","affiliation":[{"name":"Chungbuk National University, Chungju-si, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761484"},{"key":"e_1_3_2_1_2_1","volume-title":"Rankify: A comprehensive python toolkit for retrieval, re-ranking, and retrieval-augmented generation. arXiv preprint arXiv:2502.02464","author":"Abdallah Abdelrahman","year":"2025","unstructured":"Abdelrahman Abdallah, Bhawna Piryani, Jamshid Mozafari, Mohammed Ali, and Adam Jatowt. 2025b. Rankify: A comprehensive python toolkit for retrieval, re-ranking, and retrieval-augmented generation. arXiv preprint arXiv:2502.02464 (2025)."},{"key":"e_1_3_2_1_3_1","volume-title":"Tempretriever: Fusion-based temporal dense passage retrieval for time-sensitive questions. arXiv preprint arXiv:2502.21024","author":"Abdallah Abdelrahman","year":"2025","unstructured":"Abdelrahman Abdallah, Bhawna Piryani, Jonas Wallat, Avishek Anand, and Adam Jatowt. 2025c. Tempretriever: Fusion-based temporal dense passage retrieval for time-sensitive questions. arXiv preprint arXiv:2502.21024 (2025)."},{"key":"e_1_3_2_1_4_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01600"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1011"},{"key":"e_1_3_2_1_7_1","volume-title":"Colpali: Efficient document retrieval with vision language models. arXiv preprint arXiv:2407.01449","author":"Faysse Manuel","year":"2024","unstructured":"Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, C\u00e9line Hudelot, and Pierre Colombo. 2024. Colpali: Efficient document retrieval with vision language models. arXiv preprint arXiv:2407.01449 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118 (2021)."},{"key":"e_1_3_2_1_9_1","volume-title":"Vlm2vec: Training vision-language models for massive multimodal embedding tasks. arXiv preprint arXiv:2410.05160","author":"Jiang Ziyan","year":"2024","unstructured":"Ziyan Jiang, Rui Meng, Xinyi Yang, Semih Yavuz, Yingbo Zhou, and Wenhu Chen. 2024. Vlm2vec: Training vision-language models for massive multimodal embedding tasks. arXiv preprint arXiv:2410.05160 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"Michael G\u00fcnther, Isabelle Mohr, Saba Sturua, Nan Wang, and Han Xiao.","author":"Koukounas Andreas","year":"2024","unstructured":"Andreas Koukounas, Georgios Mastrapas, Sedigheh Eslami, Bo Wang, Mohammad Kalim Akram, Michael G\u00fcnther, Isabelle Mohr, Saba Sturua, Nan Wang, and Han Xiao. 2024. jina-clip-v2: Multilingual multimodal embeddings for text and images. arXiv preprint arXiv:2412.08802 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281","author":"Li Zehan","year":"2023","unstructured":"Zehan Li, Xin Zhang, Yanzhao Zhang, Dingkun Long, Pengjun Xie, and Meishan Zhang. 2023. Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281 (2023)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"e_1_3_2_1_13_1","volume-title":"DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval. arXiv preprint arXiv:2508.07995","author":"Long Meixiu","year":"2025","unstructured":"Meixiu Long, Duolin Sun, Dan Yang, Junjie Wang, Yue Shen, Jian Wang, Peng Wei, Jinjie Gu, and Jiahai Wang. 2025. DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval. arXiv preprint arXiv:2508.07995 (2025)."},{"key":"e_1_3_2_1_14_1","volume-title":"ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval. arXiv preprint arXiv:2505.17166","author":"Mac\u00e9 Quentin","year":"2025","unstructured":"Quentin Mac\u00e9, Ant\u00f3nio Loison, and Manuel Faysse. 2025. ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval. arXiv preprint arXiv:2505.17166 (2025)."},{"key":"e_1_3_2_1_15_1","unstructured":"Rui Meng Ziyan Jiang Ye Liu Mingyi Su Xinyi Yang Yuepeng Fu Can Qin Zeyuan Chen Ran Xu Caiming Xiong et al. 2025. Vlm2vec-v2: Advancing multimodal embedding for videos images and visual documents. arXiv preprint arXiv:2507.04590 (2025)."},{"key":"e_1_3_2_1_16_1","first-page":"6","article-title":"Sfrembedding-mistral: enhance text retrieval with transfer learning","volume":"3","author":"Meng Rui","year":"2024","unstructured":"Rui Meng, Ye Liu, Shafiq Rayhan Joty, Caiming Xiong, Yingbo Zhou, and Semih Yavuz. 2024. Sfrembedding-mistral: enhance text retrieval with transfer learning. Salesforce AI Research Blog, Vol. 3 (2024), 6.","journal-title":"Salesforce AI Research Blog"},{"key":"e_1_3_2_1_17_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Muennighoff Niklas","year":"2024","unstructured":"Niklas Muennighoff, SU Hongjin, Liang Wang, Nan Yang, Furu Wei, Tao Yu, Amanpreet Singh, and Douwe Kiela. 2024. Generative representational instruction tuning. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"e_1_3_2_1_19_1","unstructured":"Tri Nguyen Mir Rosenberg Xia Song Jianfeng Gao Saurabh Tiwary Rangan Majumder and Li Deng. 2016. Ms marco: A human-generated machine reading comprehension dataset. (2016)."},{"key":"e_1_3_2_1_20_1","volume-title":"Nomic embed vision: Expanding the latent space. arXiv preprint arXiv:2406.18587","author":"Nussbaum Zach","year":"2024","unstructured":"Zach Nussbaum, Brandon Duderstadt, and Andriy Mulyar. 2024. Nomic embed vision: Expanding the latent space. arXiv preprint arXiv:2406.18587 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","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, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"e_1_3_2_1_23_1","volume-title":"Daniela Rus, Bryan Kian Hsiang Low, Sewon Min, Wen-tau Yih, Pang Wei Koh, et al.","author":"Shao Rulin","year":"2025","unstructured":"Rulin Shao, Rui Qiao, Varsha Kishore, Niklas Muennighoff, Xi Victoria Lin, Daniela Rus, Bryan Kian Hsiang Low, Sewon Min, Wen-tau Yih, Pang Wei Koh, et al., 2025. ReasonIR: Training Retrievers for Reasoning Tasks. arXiv preprint arXiv:2504.20595 (2025)."},{"key":"e_1_3_2_1_24_1","volume-title":"Bright: A realistic and challenging benchmark for reasoning-intensive retrieval. arXiv preprint arXiv:2407.12883","author":"Su Hongjin","year":"2024","unstructured":"Hongjin Su, Howard Yen, Mengzhou Xia, Weijia Shi, Niklas Muennighoff, Han-yu Wang, Haisu Liu, Quan Shi, Zachary S Siegel, Michael Tang, et al., 2024. Bright: A realistic and challenging benchmark for reasoning-intensive retrieval. arXiv preprint arXiv:2407.12883 (2024)."},{"key":"e_1_3_2_1_25_1","volume-title":"Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663 (2021)."},{"key":"e_1_3_2_1_26_1","volume-title":"Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533","author":"Wang Liang","year":"2022","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. Text embeddings by weakly-supervised contrastive pre-training. arXiv preprint arXiv:2212.03533 (2022)."},{"key":"e_1_3_2_1_27_1","volume-title":"European Conference on Computer Vision. Springer, 387-404","author":"Wei Cong","year":"2024","unstructured":"Cong Wei, Yang Chen, Haonan Chen, Hexiang Hu, Ge Zhang, Jie Fu, Alan Ritter, and Wenhu Chen. 2024. Uniir: Training and benchmarking universal multimodal information retrievers. In European Conference on Computer Vision. Springer, 387-404."},{"key":"e_1_3_2_1_28_1","volume-title":"Rar-b: Reasoning as retrieval benchmark. arXiv preprint arXiv:2404.06347","author":"Xiao Chenghao","year":"2024","unstructured":"Chenghao Xiao, G Thomas Hudson, and Noura Al Moubayed. 2024. Rar-b: Reasoning as retrieval benchmark. arXiv preprint arXiv:2404.06347 (2024)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"e_1_3_2_1_30_1","volume-title":"Anh Tuan Luu, and Chen Zhao","author":"Zhang Siyue","year":"2025","unstructured":"Siyue Zhang, Yuan Gao, Xiao Zhou, Yilun Zhao, Tingyu Song, Arman Cohan, Anh Tuan Luu, and Chen Zhao. 2025. MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrieval. arXiv preprint arXiv:2510.09510 (2025)."},{"key":"e_1_3_2_1_31_1","volume-title":"GME: Improving Universal Multimodal Retrieval by Multimodal LLMs. arXiv preprint arXiv:2412.16855","author":"Zhang Xin","year":"2024","unstructured":"Xin Zhang, Yanzhao Zhang, Wen Xie, Mingxin Li, Ziqi Dai, Dingkun Long, Pengjun Xie, Meishan Zhang, Wenjie Li, and Min Zhang. 2024. GME: Improving Universal Multimodal Retrieval by Multimodal LLMs. arXiv preprint arXiv:2412.16855 (2024)."},{"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)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:23:44Z","timestamp":1786065824000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":32,"alternative-id":["10.1145\/3770855.3817457","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817457","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}