{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:07:30Z","timestamp":1784138850163,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":157,"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":"ACK Cyfronet AGH","award":["PLG\/2024\/017103"],"award-info":[{"award-number":["PLG\/2024\/017103"]}]},{"name":"ACK Cyfronet AGH","award":["PLG\/2025\/018259"],"award-info":[{"award-number":["PLG\/2025\/018259"]}]},{"name":"ETH Future Computing Laboratory","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]},{"name":"European Research Council","award":["101002047"],"award-info":[{"award-number":["101002047"]}]},{"name":"European Union’s HE research and innovation programme","award":["101070141"],"award-info":[{"award-number":["101070141"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809731","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"610-622","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Filtered Approximate Nearest Neighbor Search Algorithms on Transformer-based Embedding Vectors"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5979-4915","authenticated-orcid":false,"given":"Patrick","family":"Iff","sequence":"first","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1208-7320","authenticated-orcid":false,"given":"Paul","family":"Br\u00fcgger","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7654-6038","authenticated-orcid":false,"given":"Marcin","family":"Chrapek","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9420-6760","authenticated-orcid":false,"given":"David","family":"Kochergin","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6550-7916","authenticated-orcid":false,"given":"Maciej","family":"Besta","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1333-9797","authenticated-orcid":false,"given":"Torsten","family":"Hoefler","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2025. Tag-Filtered ANNS. https:\/\/github.com\/SpaceIshtar\/FilterGraph. Accessed: 2025-12-02."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/0734-189X(84)90079-3"},{"key":"e_1_3_2_1_3_1","volume-title":"George Toderici, Balakrishnan Varadarajan, Sudheendra Vijayanarasimhan, and Shoou-I Yu.","author":"Abu-El-Haija Sami","year":"2025","unstructured":"Sami Abu-El-Haija, Anja Hauth, Lu Jiang, Nisarg Kothari, Joonseok Lee, Hanhan Li, Paul Natsev, Joe Ng, Sobhan Naderi Parizi, George Toderici, Balakrishnan Varadarajan, Sudheendra Vijayanarasimhan, and Shoou-I Yu. 2025. YouTube 8M. https:\/\/research.google.com\/youtube8m\/download.html. Accessed: 2025-03-06."},{"key":"e_1_3_2_1_4_1","unstructured":"Alibaba-NLP. 2025. gte-Qwen2-7B-instruct. https:\/\/huggingface.co\/Alibaba-NLP\/gte-Qwen2-7B-instruct. Accessed: 2025-01-22."},{"key":"e_1_3_2_1_5_1","volume-title":"Pase: PostgreSQL Ultra-High Dimensional Approximate Nearest Neighbor Search Extension. https:\/\/github.com\/alipay\/PASE. Accessed: 2025-03-04.","year":"2025","unstructured":"Alipay. 2025. Pase: PostgreSQL Ultra-High Dimensional Approximate Nearest Neighbor Search Extension. https:\/\/github.com\/alipay\/PASE. Accessed: 2025-03-04."},{"key":"e_1_3_2_1_6_1","volume-title":"Practical and optimal LSH for angular distance. Advances in neural information processing systems 28","author":"Andoni Alexandr","year":"2015","unstructured":"Alexandr Andoni, Piotr Indyk, Thijs Laarhoven, Ilya Razenshteyn, and Ludwig Schmidt. 2015. Practical and optimal LSH for angular distance. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2746539.2746553"},{"key":"e_1_3_2_1_8_1","volume-title":"42nd International Conference on Very Large Data Bases","volume":"9","author":"Andr\u00e9 Fabien","year":"2016","unstructured":"Fabien Andr\u00e9, Anne-Marie Kermarrec, and Nicolas Le Scouarnec. 2016. Cache locality is not enough: High-performance nearest neighbor search with product quantization fast scan. In 42nd International Conference on Very Large Data Bases, Vol. 9. 12."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020576"},{"key":"e_1_3_2_1_10_1","unstructured":"Data Curation Lab at Rutgers University. 2025. ARKGraph: All-Range Approximate K-Nearest-Neighbor Graph. https:\/\/github.com\/rutgers-db\/ARKGraph. Accessed: 2025-02-25."},{"key":"e_1_3_2_1_11_1","unstructured":"Data Curation Lab at Rutgers University. 2025. DynamicSegmentGraph. https:\/\/github.com\/rutgers-db\/DynamicSegmentGraph\/tree\/release_version. Accessed: 2025-12-02."},{"key":"e_1_3_2_1_12_1","unstructured":"Data Curation Lab at Rutgers University. 2025. SeRF. https:\/\/github.com\/rutgersdb\/ SeRF. Accessed: 2025-02-24."},{"key":"e_1_3_2_1_13_1","unstructured":"Database Group at The Chinese University of Hong Kong. 2025. DIGRA. https: \/\/github.com\/CUHK-DBGroup\/DIGRA. Accessed: 2025-12-02."},{"key":"e_1_3_2_1_14_1","volume-title":"SIGMOD 2026 (Round 2). https:\/\/github.com\/CUHKDBGroup\/ RangePQ. Accessed: 2025-12-04","author":"Database Group at The Chinese University of Hong Kong.","year":"2025","unstructured":"Database Group at The Chinese University of Hong Kong. 2025. WoW: A Window-to-Window Incremental Index for Range-Filtering Approximate Nearest Neighbor Search, SIGMOD 2026 (Round 2). https:\/\/github.com\/CUHKDBGroup\/ RangePQ. Accessed: 2025-12-04."},{"key":"e_1_3_2_1_15_1","unstructured":"Martin Aumueller Erik Bernhardsson and Alec Faitfull. 2025. ANN Benchmarks. https:\/\/ann-benchmarks.com\/index.html. Accessed: 2025-01-22."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2019.02.006"},{"key":"e_1_3_2_1_17_1","volume-title":"Soundnet: Learning sound representations from unlabeled video. Advances in neural information processing systems 29","author":"Aytar Yusuf","year":"2016","unstructured":"Yusuf Aytar, Carl Vondrick, and Antonio Torralba. 2016. Soundnet: Learning sound representations from unlabeled video. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.124"},{"key":"e_1_3_2_1_19_1","volume-title":"The inverted multi-index","author":"Babenko Artem","year":"2014","unstructured":"Artem Babenko and Victor Lempitsky. 2014. The inverted multi-index. IEEE transactions on pattern analysis and machine intelligence 37, 6 (2014), 1247-1260."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1734663.1734671"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1997.609451"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/361002.361007"},{"key":"e_1_3_2_1_23_1","volume-title":"Checkembed: Effective verification of llm solutions to open-ended tasks. arXiv preprint arXiv:2406.02524","author":"Besta Maciej","year":"2024","unstructured":"Maciej Besta, Lorenzo Paleari, Ales Kubicek, Piotr Nyczyk, Robert Gerstenberger, Patrick Iff, Tomasz Lehmann, Hubert Niewiadomski, and Torsten Hoefler. 2024. Checkembed: Effective verification of llm solutions to open-ended tasks. arXiv preprint arXiv:2406.02524 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143857"},{"key":"e_1_3_2_1_25_1","unstructured":"Yuzheng Cai. 2025. Unified Navigating Graph Algorithm for Filtered Approximate Nearest Neighbor Search. https:\/\/github.com\/YZ-Cai\/Unified-Navigating-Graph. Accessed: 2025-04-23."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3698822"},{"key":"e_1_3_2_1_27_1","volume-title":"Bge m3-embedding: Multi-lingual, multi-functionality, multigranularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216","author":"Chen Jianlv","year":"2024","unstructured":"Jianlv Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. Bge m3-embedding: Multi-lingual, multi-functionality, multigranularity text embeddings through self-knowledge distillation. arXiv preprint arXiv:2402.03216 (2024)."},{"key":"e_1_3_2_1_28_1","first-page":"5199","article-title":"Spann: Highly-efficient billion-scale approximate nearest neighborhood search","volume":"34","author":"Chen Qi","year":"2021","unstructured":"Qi Chen, Bing Zhao, Haidong Wang, Mingqin Li, Chuanjie Liu, Zengzhong Li, Mao Yang, and Jingdong Wang. 2021. Spann: Highly-efficient billion-scale approximate nearest neighborhood search. Advances in Neural Information Processing Systems 34 (2021), 5199-5212.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","first-page":"426","volume-title":"Vldb","volume":"97","author":"Ciaccia Paolo","year":"1997","unstructured":"Paolo Ciaccia, Marco Patella, Pavel Zezula, et al. 1997. M-tree: An efficient access method for similarity search in metric spaces. In Vldb, Vol. 97. Citeseer, 426-435."},{"key":"e_1_3_2_1_30_1","volume-title":"SIGMOD 2024 Programming Contest. 2025","author":"ACM","year":"2024","unstructured":"ACM SIGMOD 2024 Programming Contest. 2025. ACM SIGMOD Programming Contest 2024. https:\/\/dbgroup.cs.tsinghua.edu.cn\/sigmod2024\/index.shtml. Accessed: 2025-10-02."},{"key":"e_1_3_2_1_31_1","unstructured":"Cornell University Devrishi Joe Tricot Brian Maltzan Shamsi Brinn and Timo Bozsolik. 2025. arXiv Dataset. https:\/\/www.kaggle.com\/datasets\/Cornell-University\/arxiv. Accessed: 2025-03-13."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682475"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1374376.1374452"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/997817.997857"},{"key":"e_1_3_2_1_35_1","volume-title":"WIT : Wikipedia-based Image Text Dataset. https:\/\/github.com\/google-research-datasets\/wit. Accessed: 2025-03-06.","author":"Datasets Google Research","year":"2025","unstructured":"Google Research Datasets. 2025. WIT : Wikipedia-based Image Text Dataset. https:\/\/github.com\/google-research-datasets\/wit. Accessed: 2025-03-06."},{"key":"e_1_3_2_1_36_1","unstructured":"SJTU DBGroup. 2025. UNIFY - Unified Index for Range Filtered Approximate Nearest Neighbors Search. https:\/\/github.com\/sjtu-dbgroup\/UNIFY. Accessed: 2025-02-20."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04245-8"},{"key":"e_1_3_2_1_38_1","unstructured":"Karan Desai Gaurav Kaul Zubin Aysola and Justin Johnson. 2025. RedCaps: Web-curated image-text data created by the people for the people. https: \/\/redcaps.xyz\/. Accessed: 2025-03-06."},{"key":"e_1_3_2_1_39_1","unstructured":"Artem Babenko Dmitry Baranchuk. 2025. Benchmarks for Billion-Scale Similarity Search. https:\/\/research.yandex.com\/blog\/benchmarks-for-billion-scalesimilarity-search. Accessed: 2025-03-06."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1963405.1963487"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476407"},{"key":"e_1_3_2_1_42_1","unstructured":"Josh Engels. 2025. RangeFilteredANN. https:\/\/github.com\/JoshEngels\/ RangeFilteredANN. Accessed: 2025-02-25."},{"key":"e_1_3_2_1_43_1","volume-title":"Approximate Nearest Neighbor Search with Window Filters. arXiv preprint arXiv:2402.00943","author":"Engels Joshua","year":"2024","unstructured":"Joshua Engels, Benjamin Landrum, Shangdi Yu, Laxman Dhulipala, and Julian Shun. 2024. Approximate Nearest Neighbor Search with Window Filters. arXiv preprint arXiv:2402.00943 (2024)."},{"key":"e_1_3_2_1_44_1","unstructured":"Eric Yang Farrall. 2025. Word Embeddings. https:\/\/huggingface.co\/datasets\/ efarrall\/word_embeddings. Accessed: 2025-04-23."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2024.12.002"},{"key":"e_1_3_2_1_46_1","volume-title":"Satellite system graph: Towards the efficiency up-boundary of graph-based approximate nearest neighbor search. CoRR","author":"Fu Cong","year":"2019","unstructured":"Cong Fu, Changxu Wang, and Deng Cai. 2019. Satellite system graph: Towards the efficiency up-boundary of graph-based approximate nearest neighbor search. CoRR (2019)."},{"key":"e_1_3_2_1_47_1","first-page":"4139","article-title":"High dimensional similarity search with satellite system graph: Efficiency, scalability, and unindexed query compatibility","volume":"44","author":"Fu Cong","year":"2021","unstructured":"Cong Fu, Changxu Wang, and Deng Cai. 2021. High dimensional similarity search with satellite system graph: Efficiency, scalability, and unindexed query compatibility. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 8 (2021), 4139-4150.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_48_1","volume-title":"Fast approximate nearest neighbor search with the navigating spreading-out graph. arXiv preprint arXiv:1707.00143","author":"Fu Cong","year":"2017","unstructured":"Cong Fu, Chao Xiang, Changxu Wang, and Deng Cai. 2017. Fast approximate nearest neighbor search with the navigating spreading-out graph. arXiv preprint arXiv:1707.00143 (2017)."},{"key":"e_1_3_2_1_49_1","volume-title":"NHQ: Native Hybrid Query Framework for Vector Similarity Search with Attribute Constraint. https:\/\/github.com\/YujianFu97\/NHQ. Accessed: 2025-02-27.","author":"Fu Yujian","year":"2025","unstructured":"Yujian Fu. 2025. NHQ: Native Hybrid Query Framework for Vector Similarity Search with Attribute Constraint. https:\/\/github.com\/YujianFu97\/NHQ. Accessed: 2025-02-27."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213898"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654970"},{"key":"e_1_3_2_1_52_1","volume-title":"Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997 2","author":"Gao Yunfan","year":"2023","unstructured":"Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Haofen Wang, and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997 2 (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.379"},{"key":"e_1_3_2_1_54_1","first-page":"518","article-title":"Similarity search in high dimensions via hashing","volume":"99","author":"Gionis Aristides","year":"1999","unstructured":"Aristides Gionis, Piotr Indyk, Rajeev Motwani, et al. 1999. Similarity search in high dimensions via hashing. In Vldb, Vol. 99. 518-529.","journal-title":"Vldb"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583552"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397243"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"crossref","unstructured":"Patrick Grother Patrick Grother Mei Ngan and Kayee Hanaoka. 2019. Face recognition vendor test (frvt) part 2: Identification.","DOI":"10.6028\/NIST.IR.8271"},{"key":"e_1_3_2_1_58_1","unstructured":"Department of Computer Science Guestrin Lab at Stanford University. 2025. ACORN. https:\/\/github.com\/guestrin-lab\/ACORN. Accessed: 2025-02-25."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.07.062"},{"key":"e_1_3_2_1_60_1","unstructured":"Gaurav Gupta. 2025. CAPS. https:\/\/github.com\/gaurav16gupta\/constrainedANN. Accessed: 2025-02-26."},{"key":"e_1_3_2_1_61_1","volume-title":"CAPS: A Practical Partition Index for Filtered Similarity Search. arXiv preprint arXiv:2308.15014","author":"Gupta Gaurav","year":"2023","unstructured":"Gaurav Gupta, Jonah Yi, Benjamin Coleman, Chen Luo, Vihan Lakshman, and Anshumali Shrivastava. 2023. CAPS: A Practical Partition Index for Filtered Similarity Search. arXiv preprint arXiv:2308.15014 (2023)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/602259.602266"},{"key":"e_1_3_2_1_63_1","volume-title":"A comprehensive survey on vector database: Storage and retrieval technique, challenge. arXiv preprint arXiv:2310.11703","author":"Han Yikun","year":"2023","unstructured":"Yikun Han, Chunjiang Liu, and Pengfei Wang. 2023. A comprehensive survey on vector database: Storage and retrieval technique, challenge. arXiv preprint arXiv:2310.11703 (2023)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.616"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807644"},{"key":"e_1_3_2_1_66_1","volume-title":"Rank-based similarity search: Reducing the dimensional dependence","author":"Houle Michael E","year":"2014","unstructured":"Michael E Houle and Michael Nett. 2014. Rank-based similarity search: Reducing the dimensional dependence. IEEE transactions on pattern analysis and machine intelligence 37, 1 (2014), 136-150."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850469.2850470"},{"key":"e_1_3_2_1_68_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46759-7_2"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60936-8_4"},{"key":"e_1_3_2_1_72_1","volume-title":"Ravishankar Krishnawamy, and Rohan Kadekodi.","author":"Subramanya Suhas Jayaram","year":"2019","unstructured":"Suhas Jayaram Subramanya, Fnu Devvrit, Harsha Vardhan Simhadri, Ravishankar Krishnawamy, and Rohan Kadekodi. 2019. Diskann: Fast accurate billion-point nearest neighbor search on a single node. Advances in neural information processing Systems 32 (2019)."},{"key":"e_1_3_2_1_73_1","volume-title":"Product quantization for nearest neighbor search","author":"Jegou Herve","year":"2010","unstructured":"Herve Jegou, Matthijs Douze, and Cordelia Schmid. 2010. Product quantization for nearest neighbor search. IEEE transactions on pattern analysis and machine intelligence 33, 1 (2010), 117-128."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3725399"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.298"},{"key":"e_1_3_2_1_76_1","volume-title":"Optimizing retrieval strategies for financial question answering documents in retrievalaugmented generation systems. arXiv preprint arXiv:2503.15191","author":"Kim Sejong","year":"2025","unstructured":"Sejong Kim, Hyunseo Song, Hyunwoo Seo, and Hyunjun Kim. 2025. Optimizing retrieval strategies for financial question answering documents in retrievalaugmented generation systems. arXiv preprint arXiv:2503.15191 (2025)."},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/2396761.2396831"},{"key":"e_1_3_2_1_78_1","volume-title":"Datasets for approximate nearest neighbor search","author":"Laurent Amsaleg Herv\u00e9 J\u00e9gou","unstructured":"Herv\u00e9 J\u00e9gou Laurent Amsaleg. 2025. Datasets for approximate nearest neighbor search. http:\/\/corpus-texmex.irisa.fr\/. Accessed: 2025-03-06."},{"key":"e_1_3_2_1_79_1","unstructured":"Yann LeCun. 2025. mnist. https:\/\/huggingface.co\/datasets\/ylecun\/mnist\/viewer?views%5B%5D=train. Accessed: 2025-03-06."},{"key":"e_1_3_2_1_80_1","volume-title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models. arXiv preprint arXiv:2405.17428","author":"Lee Chankyu","year":"2024","unstructured":"Chankyu Lee, Rajarshi Roy, Mengyao Xu, Jonathan Raiman, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. 2024. NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models. arXiv preprint arXiv:2405.17428 (2024)."},{"key":"e_1_3_2_1_81_1","unstructured":"Yibin Lei. 2025. LENS-d8000. https:\/\/huggingface.co\/yibinlei\/LENS-d8000. Accessed: 2025-01-22."},{"key":"e_1_3_2_1_82_1","volume-title":"Enhancing Lexicon-Based Text Embeddings with Large Language Models. arXiv preprint arXiv:2501.09749","author":"Lei Yibin","year":"2025","unstructured":"Yibin Lei, Tao Shen, Yu Cao, and Andrew Yates. 2025. Enhancing Lexicon-Based Text Embeddings with Large Language Models. arXiv preprint arXiv:2501.09749 (2025)."},{"key":"e_1_3_2_1_83_1","first-page":"120","article-title":"Pytorch-biggraph: A large scale graph embedding system","volume":"1","author":"Lerer Adam","year":"2019","unstructured":"Adam Lerer, Ledell Wu, Jiajun Shen, Timothee Lacroix, Luca Wehrstedt, Abhijit Bose, and Alex Peysakhovich. 2019. Pytorch-biggraph: A large scale graph embedding system. Proceedings of Machine Learning and Systems 1 (2019), 120-131.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3284028.3284030"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00032"},{"key":"e_1_3_2_1_86_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_87_1","volume-title":"UNIFY: Unified Index for Range Filtered Approximate Nearest Neighbors Search. arXiv preprint arXiv:2412.02448","author":"Liang Anqi","year":"2024","unstructured":"Anqi Liang, Pengcheng Zhang, Bin Yao, Zhongpu Chen, Yitong Song, and Guangxu Cheng. 2024. UNIFY: Unified Index for Range Filtered Approximate Nearest Neighbors Search. arXiv preprint arXiv:2412.02448 (2024)."},{"key":"e_1_3_2_1_88_1","volume-title":"Survey of Filtered Approximate Nearest Neighbor Search over the Vector-Scalar Hybrid Data. arXiv preprint arXiv:2505.06501","author":"Lin Yanjun","year":"2025","unstructured":"Yanjun Lin, Kai Zhang, Zhenying He, Yinan Jing, and X SeanWang. 2025. Survey of Filtered Approximate Nearest Neighbor Search over the Vector-Scalar Hybrid Data. arXiv preprint arXiv:2505.06501 (2025)."},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.227"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-020-00635-4"},{"key":"e_1_3_2_1_91_1","volume-title":"2016 IEEE international conference on multimedia and expo (ICME). IEEE, 1-6.","author":"Liu Xinchen","year":"2016","unstructured":"Xinchen Liu,Wu Liu, Huadong Ma, and Huiyuan Fu. 2016. Large-scale vehicle reidentification in urban surveillance videos. In 2016 IEEE international conference on multimedia and expo (ICME). IEEE, 1-6."},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1145\/3686490.3686536"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00095"},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.14778\/3397230.3397240"},{"key":"e_1_3_2_1_95_1","volume-title":"Tag-Filtered Approximate Nearest Neighbor Search. In 2025 IEEE 41st International Conference on Data Engineering (ICDE). IEEE, 3642-3654","author":"Luo Jiarui","year":"2025","unstructured":"Jiarui Luo, Miao Qiao, Chaoji Zuo, and Dong Deng. 2025. Tag-Filtered Approximate Nearest Neighbor Search. In 2025 IEEE 41st International Conference on Data Engineering (ICDE). IEEE, 3642-3654."},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137765.3137836"},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2013.10.006"},{"key":"e_1_3_2_1_98_1","volume-title":"Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs","author":"Malkov Yu A","year":"2018","unstructured":"Yu A Malkov and Dmitry A Yashunin. 2018. Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence 42, 4 (2018), 824-836."},{"key":"e_1_3_2_1_99_1","unstructured":"Yusuke Matsui. 2025. Reconfigurable Inverted Index (Rii): IVFPQ-based fast and memory efficient approximate nearest neighbor search method with a subsetsearch functionality. https:\/\/github.com\/matsui528\/rii. Accessed: 2025-04-23."},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240630"},{"key":"e_1_3_2_1_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.225"},{"key":"e_1_3_2_1_102_1","unstructured":"Microsoft. 2025. DiskANN. https:\/\/github.com\/microsoft\/DiskANN. Accessed: 2025-02-26."},{"key":"e_1_3_2_1_103_1","unstructured":"Microsoft. 2025. https:\/\/github.com\/microsoft\/MSVBASE. https:\/\/github.com\/microsoft\/MSVBASE. Accessed: 2025-02-26."},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589777"},{"key":"e_1_3_2_1_105_1","volume-title":"MTEB: Massive text embedding benchmark. arXiv preprint arXiv:2210.07316","author":"Muennighoff Niklas","year":"2022","unstructured":"Niklas Muennighoff, Nouamane Tazi, Lo\u00efc Magne, and Nils Reimers. 2022. MTEB: Massive text embedding benchmark. arXiv preprint arXiv:2210.07316 (2022)."},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2321376"},{"key":"e_1_3_2_1_107_1","unstructured":"NovaSearch. 2025. Stella_em_400M_v5. https:\/\/huggingface.co\/NovaSearch\/ stella_en_400M_v5. Accessed: 2025-03-11."},{"key":"e_1_3_2_1_108_1","doi-asserted-by":"crossref","unstructured":"NVIDIA. 2025. NV-Embed-v2. https:\/\/huggingface.co\/nvidia\/NV-Embed-v2. Accessed: 2025-01-22.","DOI":"10.46848\/actacientifica22122"},{"key":"e_1_3_2_1_109_1","unstructured":"Beijing Academy of Artificial Intelligence. 2025. bge-en-icl. https:\/\/huggingface. co\/BAAI\/bge-en-icl. Accessed: 2025-01-22."},{"key":"e_1_3_2_1_110_1","unstructured":"Stephen M Omohundro. 1989. Five balltree construction algorithms. (1989)."},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.14778\/2850583.2850589"},{"key":"e_1_3_2_1_112_1","doi-asserted-by":"publisher","DOI":"10.1145\/3654923"},{"key":"e_1_3_2_1_113_1","doi-asserted-by":"publisher","DOI":"10.14778\/3748191.3748193"},{"key":"e_1_3_2_1_114_1","volume-title":"Manning","author":"Pennington Jeffrey","year":"2025","unstructured":"Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2025. glove100_angular. https:\/\/www.tensorflow.org\/datasets\/catalog\/glove100_ angular. Accessed: 2025-03-06."},{"key":"e_1_3_2_1_115_1","volume-title":"Pinecone: The vector database to build knowledgeable AI. https:\/\/www.pinecone.io\/. Accessed: 2025-03-11.","year":"2025","unstructured":"Pinecone. 2025. Pinecone: The vector database to build knowledgeable AI. https:\/\/www.pinecone.io\/. Accessed: 2025-03-11."},{"key":"e_1_3_2_1_116_1","unstructured":"The Milvus Project. 2025. Milvus. https:\/\/github.com\/milvus-io\/milvus. Accessed: 2025-02-27."},{"key":"e_1_3_2_1_117_1","unstructured":"Navid Rekabsaz Oleg Lesota Markus Schedl Jon Brassey and Carsten Eickhoff. 2025. TripClick. https:\/\/tripdatabase.github.io\/tripclick\/. Accessed: 2025-07-28."},{"key":"e_1_3_2_1_118_1","volume-title":"A unified deep neural network for speaker and language recognition. arXiv preprint arXiv:1504.00923","author":"Richardson Fred","year":"2015","unstructured":"Fred Richardson, Douglas Reynolds, and Najim Dehak. 2015. A unified deep neural network for speaker and language recognition. arXiv preprint arXiv:1504.00923 (2015)."},{"key":"e_1_3_2_1_119_1","unstructured":"Christoph Schuhmann. 2025. LAION-400-MILLION OPEN DATASET. https: \/\/laion.ai\/blog\/laion-400-open-dataset\/. Accessed: 2025-03-06."},{"key":"e_1_3_2_1_120_1","volume-title":"Dynamic Retrieval-Augmented Generation. arXiv preprint arXiv:2312.08976","author":"Shapkin Anton","year":"2023","unstructured":"Anton Shapkin, Denis Litvinov, Yaroslav Zharov, Egor Bogomolov, Timur Galimzyanov, and Timofey Bryksin. 2023. Dynamic Retrieval-Augmented Generation. arXiv preprint arXiv:2312.08976 (2023)."},{"key":"e_1_3_2_1_121_1","volume-title":"Analysis & Benchmark]. arXiv preprint arXiv:2509.07789","author":"Shi Jiayang","year":"2025","unstructured":"Jiayang Shi, Yuzheng Cai, and Weiguo Zheng. 2025. Filtered Approximate Nearest Neighbor Search: A Unified Benchmark and Systematic Experimental Study [Experiment, Analysis & Benchmark]. arXiv preprint arXiv:2509.07789 (2025)."},{"key":"e_1_3_2_1_122_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587638"},{"key":"e_1_3_2_1_123_1","volume-title":"Suhas Jayaram Subramanya, and Jingdong Wang","author":"Simhadri Harsha Vardhan","year":"2025","unstructured":"Harsha Vardhan Simhadri, George Williams, Martin Aum\u00fcller, Artem Babenko, Dmitry Baranchuk, Qi Chen, Matthijs Douze, Lucas Hosseini, Ravishankar Krishnaswamy, Gopal Srinivasa, Suhas Jayaram Subramanya, and Jingdong Wang. 2025. Billion-Scale Approximate Nearest Neighbor Search Challenge: NeurIPS'21 competition track. https:\/\/big-ann-benchmarks.com\/neurips21.html. Accessed: 2025-03-06."},{"key":"e_1_3_2_1_124_1","volume-title":"Ravishankar Krishnaswamy, and Harsha Vardhan Simhadri.","author":"Singh Aditi","year":"2021","unstructured":"Aditi Singh, Suhas Jayaram Subramanya, Ravishankar Krishnaswamy, and Harsha Vardhan Simhadri. 2021. Freshdiskann: A fast and accurate graph-based ann index for streaming similarity search. arXiv preprint arXiv:2105.09613 (2021)."},{"key":"e_1_3_2_1_125_1","volume-title":"Proceedings ninth IEEE international conference on computer vision. IEEE, 1470-1477","author":"Zisserman Sivic","year":"2003","unstructured":"Sivic and Zisserman. 2003. Video Google: A text retrieval approach to object matching in videos. In Proceedings ninth IEEE international conference on computer vision. IEEE, 1470-1477."},{"key":"e_1_3_2_1_126_1","volume-title":"Proceedings ninth IEEE international conference on computer vision. IEEE, 1470-1477","author":"Zisserman Sivic","year":"2003","unstructured":"Sivic and Zisserman. 2003. Video Google: A text retrieval approach to object matching in videos. In Proceedings ninth IEEE international conference on computer vision. IEEE, 1470-1477."},{"key":"e_1_3_2_1_127_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15286-3_16"},{"key":"e_1_3_2_1_128_1","doi-asserted-by":"publisher","DOI":"10.14778\/2556549.2556574"},{"key":"e_1_3_2_1_129_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_130_1","volume-title":"K-means tree: an optimal clustering tree for unsupervised learning. The journal of supercomputing 77, 5","author":"Tavallali Pooya","year":"2021","unstructured":"Pooya Tavallali, Peyman Tavallali, and Mukesh Singhal. 2021. K-means tree: an optimal clustering tree for unsupervised learning. The journal of supercomputing 77, 5 (2021), 5239-5266."},{"key":"e_1_3_2_1_131_1","unstructured":"Trevor. 2025. Mtg Scryfall Cropped Art Embeddings. https:\/\/huggingface.co\/datasets\/TrevorJS\/mtg-scryfall-cropped-art-embeddingsopen-clip-ViT-SO400M-14-SigLIP-384. Accessed: 2025-04-23."},{"key":"e_1_3_2_1_132_1","volume-title":"Vectara: The AI Agent and Assistant platform for enterprises. https:\/\/www.vectara.com\/. Accessed: 2025-03-11.","year":"2025","unstructured":"Vectara. 2025. Vectara: The AI Agent and Assistant platform for enterprises. https:\/\/www.vectara.com\/. Accessed: 2025-03-11."},{"key":"e_1_3_2_1_133_1","volume-title":"Vespa: We Make AI Work. https:\/\/vespa.ai\/. Accessed: 2025-03-11.","year":"2025","unstructured":"Vespa. 2025. Vespa: We Make AI Work. https:\/\/vespa.ai\/. Accessed: 2025-03-11."},{"key":"e_1_3_2_1_134_1","volume-title":"Proceedings of the 20th ACM international conference on Multimedia. 179-188","author":"Shipeng Li JingdongWang","year":"2012","unstructured":"JingdongWang and Shipeng Li. 2012. Query-driven iterated neighborhood graph search for large scale indexing. In Proceedings of the 20th ACM international conference on Multimedia. 179-188."},{"key":"e_1_3_2_1_135_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457550"},{"key":"e_1_3_2_1_136_1","volume-title":"Navigable proximity graph-driven native hybrid queries with structured and unstructured constraints. arXiv preprint arXiv:2203.13601","author":"Wang Mengzhao","year":"2022","unstructured":"Mengzhao Wang, Lingwei Lv, Xiaoliang Xu, Yuxiang Wang, Qiang Yue, and Jiongkang Ni. 2022. Navigable proximity graph-driven native hybrid queries with structured and unstructured constraints. arXiv preprint arXiv:2203.13601 (2022)."},{"key":"e_1_3_2_1_137_1","volume-title":"An efficient and robust framework for approximate nearest neighbor search with attribute constraint. Advances in Neural Information Processing Systems 36","author":"Wang Mengzhao","year":"2024","unstructured":"Mengzhao Wang, Lingwei Lv, Xiaoliang Xu, Yuxiang Wang, Qiang Yue, and Jiongkang Ni. 2024. An efficient and robust framework for approximate nearest neighbor search with attribute constraint. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_138_1","volume-title":"A comprehensive survey and experimental comparison of graph-based approximate nearest neighbor search. arXiv preprint arXiv:2101.12631","author":"Wang Mengzhao","year":"2021","unstructured":"Mengzhao Wang, Xiaoliang Xu, Qiang Yue, and Yuxiang Wang. 2021. A comprehensive survey and experimental comparison of graph-based approximate nearest neighbor search. arXiv preprint arXiv:2101.12631 (2021)."},{"key":"e_1_3_2_1_139_1","doi-asserted-by":"publisher","DOI":"10.14778\/3424573.3424580"},{"key":"e_1_3_2_1_140_1","volume-title":"WoW: A Window-to-Window Incremental Index for Range-Filtering Approximate Nearest Neighbor Search. arXiv preprint arXiv:2508.18617","author":"Wang Ziqi","year":"2025","unstructured":"Ziqi Wang, Jingzhe Zhang, and Wei Hu. 2025. WoW: A Window-to-Window Incremental Index for Range-Filtering Approximate Nearest Neighbor Search. arXiv preprint arXiv:2508.18617 (2025)."},{"key":"e_1_3_2_1_141_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415541"},{"key":"e_1_3_2_1_142_1","volume-title":"Spectral hashing. Advances in neural information processing systems 21","author":"Torralba Antonio","year":"2008","unstructured":"YairWeiss, Antonio Torralba, and Rob Fergus. 2008. Spectral hashing. Advances in neural information processing systems 21 (2008)."},{"key":"e_1_3_2_1_143_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557610"},{"key":"e_1_3_2_1_144_1","volume-title":"Beyond goldfish memory: Long-term opendomain conversation. arXiv","author":"Xu J","year":"2021","unstructured":"J Xu, A Szlam, and J Weston. 2021. Beyond goldfish memory: Long-term opendomain conversation. arXiv 2021. arXiv preprint arXiv:2107.07567 (2021)."},{"key":"e_1_3_2_1_145_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5970"},{"key":"e_1_3_2_1_146_1","unstructured":"Yuexuan Xu. 2025. iRangeGraph. https:\/\/github.com\/YuexuanXu7\/iRangeGraph. Accessed: 2025-02-21."},{"key":"e_1_3_2_1_147_1","doi-asserted-by":"publisher","DOI":"10.1145\/3698814"},{"key":"e_1_3_2_1_148_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3386131"},{"key":"e_1_3_2_1_149_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389770"},{"key":"e_1_3_2_1_150_1","volume-title":"Jasper and Stella: distillation of SOTA embedding models. arXiv preprint arXiv:2412.19048","author":"Zhang Dun","year":"2024","unstructured":"Dun Zhang, Jiacheng Li, Ziyang Zeng, and FulongWang. 2024. Jasper and Stella: distillation of SOTA embedding models. arXiv preprint arXiv:2412.19048 (2024)."},{"key":"e_1_3_2_1_151_1","doi-asserted-by":"publisher","DOI":"10.1145\/3725401"},{"key":"e_1_3_2_1_152_1","first-page":"377","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Zhang Qianxi","year":"2023","unstructured":"Qianxi Zhang, Shuotao Xu, Qi Chen, Guoxin Sui, Jiadong Xie, Zhizhen Cai, Yaoqi Chen, Yinxuan He, Yuqing Yang, Fan Yang, et al. 2023. {VBASE}: Unifying Online Vector Similarity Search and Relational Queries via Relaxed Monotonicity. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23). 377-395."},{"key":"e_1_3_2_1_153_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00094"},{"key":"e_1_3_2_1_154_1","volume-title":"Constrained approximate similarity search on proximity graph. arXiv preprint arXiv:2210.14958","author":"Zhao Weijie","year":"2022","unstructured":"Weijie Zhao, Shulong Tan, and Ping Li. 2022. Constrained approximate similarity search on proximity graph. arXiv preprint arXiv:2210.14958 (2022)."},{"key":"e_1_3_2_1_155_1","doi-asserted-by":"publisher","DOI":"10.14778\/3377369.3377374"},{"key":"e_1_3_2_1_156_1","doi-asserted-by":"publisher","DOI":"10.14778\/3603581.3603601"},{"key":"e_1_3_2_1_157_1","doi-asserted-by":"publisher","DOI":"10.1145\/3639324"}],"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":"2026-07-15T17:19:26Z","timestamp":1784135966000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809731"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":157,"alternative-id":["10.1145\/3805712.3809731","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809731","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"}}]}}