{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:14:11Z","timestamp":1765340051607,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"name":"Key Laboratory of Target Cognition and Application Technology","award":["2023-CXPT-LC-005"],"award-info":[{"award-number":["2023-CXPT-LC-005"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755390","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:38:54Z","timestamp":1761377934000},"page":"4329-4338","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5673-3729","authenticated-orcid":false,"given":"Hui","family":"Wu","sequence":"first","affiliation":[{"name":"Key Laboratory of Target Cognition and Application Technology(TCAT), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China and School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6991-9097","authenticated-orcid":false,"given":"Haoquan","family":"Zhai","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3869-7881","authenticated-orcid":false,"given":"Yuchen","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7147-5666","authenticated-orcid":false,"given":"Hengyi","family":"Cai","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4171-3234","authenticated-orcid":false,"given":"Peirong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7466-0234","authenticated-orcid":false,"given":"Yidan","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of the Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2414-9642","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2612-3364","authenticated-orcid":false,"given":"Chunle","family":"Wang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2789-8581","authenticated-orcid":false,"given":"Yingyan","family":"Hou","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9212-1947","authenticated-orcid":false,"given":"Shuaiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0684-6205","authenticated-orcid":false,"given":"Dawei","family":"Yin","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01600"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.708"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1076"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657834"},{"key":"e_1_3_2_1_6_1","volume-title":"From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130","author":"Edge Darren","year":"2024","unstructured":"Darren Edge, Ha Trinh, Newman Cheng, Joshua Bradley, Alex Chao, Apurva Mody, Steven Truitt, and Jonathan Larson. 2024. From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"The Thirteenth International Conference on Learning Representations.","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. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.398"},{"key":"e_1_3_2_1_9_1","unstructured":"Shengding Hu Yuge Tu Xu Han Chaoqun He Ganqu Cui Xiang Long Zhi Zheng Yewei Fang Yuxiang Huang Weilin Zhao et al. 2024. MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies. arXiv preprint arXiv:2404.06395 (2024)."},{"key":"e_1_3_2_1_10_1","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin et al. 2024. A survey on hallucination in large language models: Principles taxonomy challenges and open questions. ACM Transactions on Information Systems (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"e_1_3_2_1_12_1","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","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, et al., 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, Vol. 33 (2020), 9459-9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.493"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.775"},{"key":"e_1_3_2_1_15_1","unstructured":"Yuchen Li Hengyi Cai Rui Kong Xinran Chen Jiamin Chen Jun Yang Haojie Zhang Jiayi Li Jiayi Wu Yiqun Chen et al. 2025a. Towards AI Search Paradigm. arXiv preprint arXiv:2506.17188 (2025)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599935"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709395"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737258"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE65448.2025.00333"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.478"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.322"},{"key":"e_1_3_2_1_22_1","volume-title":"Unifying multimodal retrieval via document screenshot embedding. arXiv preprint arXiv:2406.11251","author":"Ma Xueguang","year":"2024","unstructured":"Xueguang Ma, Sheng-Chieh Lin, Minghan Li, Wenhu Chen, and Jimmy Lin. 2024a. Unifying multimodal retrieval via document screenshot embedding. arXiv preprint arXiv:2406.11251 (2024)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_2_1_24_1","volume-title":"Infographicvqa. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 1697-1706","author":"Mathew Minesh","year":"2022","unstructured":"Minesh Mathew, Viraj Bagal, Rub\u00e8n Tito, Dimosthenis Karatzas, Ernest Valveny, and CV Jawahar. 2022. Infographicvqa. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. 1697-1706."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00605"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3677052.3698671"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.463"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26598"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109834"},{"key":"e_1_3_2_1_31_1","unstructured":"Cunxiang Wang Xiaoze Liu Yuanhao Yue Xiangru Tang Tianhang Zhang Cheng Jiayang Yunzhi Yao Wenyang Gao Xuming Hu Zehan Qi et al. 2023b. Survey on factuality in large language models: Knowledge retrieval and domain-specificity. arXiv preprint arXiv:2310.07521 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.691"},{"key":"e_1_3_2_1_33_1","volume-title":"When search engine services meet large language models: visions and challenges","author":"Xiong Haoyi","year":"2024","unstructured":"Haoyi Xiong, Jiang Bian, Yuchen Li, Xuhong Li, Mengnan Du, Shuaiqiang Wang, Dawei Yin, and Sumi Helal. 2024. When search engine services meet large language models: visions and challenges. IEEE Transactions on Services Computing (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Xu Fangyuan","year":"2024","unstructured":"Fangyuan Xu, Weijia Shi, and Eunsol Choi. 2024. RECOMP: Improving retrieval-augmented LMs with context compression and selective augmentation. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"e_1_3_2_1_37_1","volume-title":"Chartbench: A benchmark for complex visual reasoning in charts. arXiv preprint arXiv:2312.15915","author":"Xu Zhengzhuo","year":"2023","unstructured":"Zhengzhuo Xu, Sinan Du, Yiyan Qi, Chengjin Xu, Chun Yuan, and Jian Guo. 2023. Chartbench: A benchmark for complex visual reasoning in charts. arXiv preprint arXiv:2312.15915 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3620067"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1194"},{"key":"e_1_3_2_1_40_1","volume-title":"Visrag: Vision-based retrieval-augmented generation on multi-modality documents. arXiv preprint arXiv:2410.10594","author":"Yu Shi","year":"2024","unstructured":"Shi Yu, Chaoyue Tang, Bokai Xu, Junbo Cui, Junhao Ran, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, et al., 2024b. Visrag: Vision-based retrieval-augmented generation on multi-modality documents. arXiv preprint arXiv:2410.10594 (2024)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-srw.7"},{"key":"e_1_3_2_1_42_1","first-page":"121156","article-title":"Rankrag: Unifying context ranking with retrieval-augmented generation in llms","volume":"37","author":"Yu Yue","year":"2024","unstructured":"Yue Yu, Wei Ping, Zihan Liu, Boxin Wang, Jiaxuan You, Chao Zhang, Mohammad Shoeybi, and Bryan Catanzaro. 2024a. Rankrag: Unifying context ranking with retrieval-augmented generation in llms. Advances in Neural Information Processing Systems, Vol. 37 (2024), 121156-121184.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"e_1_3_2_1_44_1","volume-title":"Mm-llms: Recent advances in multimodal large language models. arXiv preprint arXiv:2401.13601","author":"Zhang Duzhen","year":"2024","unstructured":"Duzhen Zhang, Yahan Yu, Jiahua Dong, Chenxing Li, Dan Su, Chenhui Chu, and Dong Yu. 2024. Mm-llms: Recent advances in multimodal large language models. arXiv preprint arXiv:2401.13601 (2024)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755390","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:09:08Z","timestamp":1765339748000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755390"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":44,"alternative-id":["10.1145\/3746027.3755390","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755390","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}