{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:08:36Z","timestamp":1784138916694,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":61,"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":"National Science Foundation","award":["DGE2139757"],"award-info":[{"award-number":["DGE2139757"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809589","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"1519-1530","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Vector Index Compression in Any Modality"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7439-9653","authenticated-orcid":false,"given":"Hanxiang","family":"Qin","sequence":"first","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8863-4002","authenticated-orcid":false,"given":"Alexander","family":"Martin","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5008-4949","authenticated-orcid":false,"given":"Rohan","family":"Jha","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4988-2401","authenticated-orcid":false,"given":"Chunsheng","family":"Zuo","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0239-9989","authenticated-orcid":false,"given":"Reno","family":"Kriz","sequence":"additional","affiliation":[{"name":"Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4328-4288","authenticated-orcid":false,"given":"Benjamin","family":"Van Durme","sequence":"additional","affiliation":[{"name":"Microsoft, Baltimore, USA and Johns Hopkins University, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3573128.3604896"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1498853"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1611.09268"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/net.12.3.241.253"},{"key":"e_1_3_2_1_5_1","volume-title":"Token Merging: Your ViT But Faster. In The Eleventh International Conference, on Learning Representations.","author":"Bolya Daniel","year":"2022","unstructured":"Daniel Bolya, Cheng-Yang Fu, Xiaoliang Dai, Peizhao Zhang, Christoph Feichtenhofer, and Judy Hoffman. 2022. Token Merging: Your ViT But Faster. In The Eleventh International Conference, on Learning Representations."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2507.08143"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","unstructured":"Haonan Chen Sicheng Gao Radu Timofte Tetsuya Sakai and Zhicheng Dou. 2026. E5-Omni: Explicit Cross-modal Alignment for Omni-modal Embeddings. arXiv:2601.03666 [cs] doi:10.48550\/arXiv.2601.03666","DOI":"10.48550\/arXiv.2601.03666"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Benjamin Clavi\u00e9 Antoine Chaffin and Griffin Adams. 2024. Reducing the Footprint of Multi-Vector Retrieval with Minimal Performance Impact via Token Pooling. arXiv:2409.14683 [cs] doi:10.48550\/arXiv.2409.14683","DOI":"10.48550\/arXiv.2409.14683"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1576"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-17120-8_49"},{"key":"e_1_3_2_1_12_1","unstructured":"Manuel Faysse Hugues Sibille Tony Wu Bilel Omrani Gautier Viaud Celine Hudelot and Pierre Colombo. 2024. ColPali: Efficient Document Retrieval with Vision Language Models."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.mrl-main.36"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Georg Heigold Ehsan Variani Tom Bagby Cyril Allauzen Ji Ma Shankar Kumar and Michael Riley. 2026. Massive Sound Embedding Benchmark (MSEB ). arXiv:2602.07143 [cs] doi:10.48550\/arXiv.2602.07143","DOI":"10.48550\/arXiv.2602.07143"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557367"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1024"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.mrl-1.11"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","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.","DOI":"10.36227\/techrxiv.175624545.56457516\/v1"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401075"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02249"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2192"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Carlos Lassance Maroua Maachou Joohee Park and St\u00e9phane Clinchant. 2021. A Study on Token Pruning for ColBERT. arXiv:2112.06540 [cs] doi:10.48550\/arXiv.2112.06540","DOI":"10.48550\/arXiv.2112.06540"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103090"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","unstructured":"Mingxin Li Yanzhao Zhang Dingkun Long Keqin Chen Sibo Song Shuai Bai Zhibo Yang Pengjun Xie An Yang Dayiheng Liu Jingren Zhou and Junyang Lin. 2026. Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking. arXiv:2601.04720 [cs] doi:10.48550\/arXiv.2601.04720","DOI":"10.48550\/arXiv.2601.04720"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0722"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","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:2308.03281 [cs] doi:10.48550\/arXiv.2308.03281","DOI":"10.48550\/arXiv.2308.03281"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Ting Liu Liangtao Shi Richang Hong Yue Hu Quanjun Yin and Linfeng Zhang. 2024b. Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model. arXiv:2411.10803 [cs] doi:10.48550\/arXiv.2411.10803","DOI":"10.48550\/arXiv.2411.10803"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.191"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.800"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730135"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657951"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-88714-7_22"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","unstructured":"Quentin Mac\u00e9 Ant\u00f3nio Loison and Manuel Faysse. 2025. ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval. arXiv:2505.17166 [cs] doi:10.48550\/arXiv.2505.17166","DOI":"10.48550\/arXiv.2505.17166"},{"key":"e_1_3_2_1_37_1","volume-title":"What We Discovered on 'Deep YouTube'. The Atlantic (26","author":"McGrady Ryan","year":"2024","unstructured":"Ryan McGrady. 2024. What We Discovered on 'Deep YouTube'. The Atlantic (26 January 2024). https:\/\/www.theatlantic.com\/technology\/archive\/2024\/01\/how-many-videos-youtube-research\/677250\/ Accessed: 2025-01-11."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","unstructured":"Gabriel de Souza P. Moreira Ronay Ak Mengyao Xu Oliver Holworthy Benedikt Schifferer Zhiding Yu Yauhen Babakhin Radek Osmulski Jiarui Cai Ryan Chesler Bo Liu and Even Oldridge. 2026. Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document Retrieval. arXiv:2602.03992 [cs] doi:10.48550\/arXiv.2602.03992","DOI":"10.48550\/arXiv.2602.03992"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1098\/rspl.1895.0041"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the 40th International Conference, on Machine Learning. PMLR, 28337-28350","author":"Qin Guanghui","year":"2023","unstructured":"Guanghui Qin and Benjamin Van Durme. 2023. Nugget: Neural Agglomerative Embeddings, of Text. In Proceedings of the 40th International Conference, on Machine Learning. PMLR, 28337-28350."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01834"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557325"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.272"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2602.02444"},{"key":"e_1_3_2_1_46_1","unstructured":"Rapha\u00ebl Sourty. 2025. FastPlaid: A High-Performance Engine for Multi-Vector Search. https:\/\/github.com\/lightonai\/fast-plaid"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01769"},{"key":"e_1_3_2_1_48_1","volume-title":"BEIR: A Heterogenous Benchmark, for Zero-shot Evaluation, of Information Retrieval Models. NeurIPS Datasets and Benchmarks","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. NeurIPS Datasets and Benchmarks, Vol. abs\/2104.08663 (2021)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2505.11471"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","unstructured":"David Wan Han Wang Elias Stengel-Eskin Jaemin Cho and Mohit Bansal. 2025. CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval. arXiv:2506.06144 [cs] doi:10.48550\/arXiv.2506.06144","DOI":"10.48550\/arXiv.2506.06144"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500845"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2509.18095"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","unstructured":"Mengyao Xu Gabriel Moreira Ronay Ak Radek Osmulski Yauhen Babakhin Zhiding Yu Benedikt Schifferer and Even Oldridge. 2025. Llama Nemoretriever Colembed: Top-Performing Text-Image Retrieval Model. arXiv:2507.05513 [cs] doi:10.48550\/arXiv.2507.05513","DOI":"10.48550\/arXiv.2507.05513"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01843"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.103"},{"key":"e_1_3_2_1_58_1","volume-title":"Proceedings of the 42nd International Conference, on Machine Learning. PMLR, 74840-74857","author":"Zhang Yuan","year":"2025","unstructured":"Yuan Zhang, Chun-Kai Fan, Junpeng Ma, Wenzhao Zheng, Tao Huang, Kuan Cheng, Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, and Shanghang Zhang. 2025. SparseVLM: Visual Token Sparsification, for Efficient Vision-Language Model Inference. In Proceedings of the 42nd International Conference, on Machine Learning. PMLR, 74840-74857."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1506"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","unstructured":"Jiaying Zhu Yurui Zhu Xin Lu Wenrui Yan Dong Li Kunlin Liu Xueyang Fu and Zheng-Jun Zha. 2025. VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs. arXiv:2510.16598 [cs] doi:10.48550\/arXiv.2510.16598","DOI":"10.48550\/arXiv.2510.16598"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730100"}],"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":"2026-07-15T17:26:06Z","timestamp":1784136366000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809589"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":61,"alternative-id":["10.1145\/3805712.3809589","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809589","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"}}]}}