{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:37:41Z","timestamp":1780418261618,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62325201"],"award-info":[{"award-number":["62325201"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730115","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:41:01Z","timestamp":1752457261000},"page":"2483-2492","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["WebANNS: Fast and Efficient Approximate Nearest Neighbor Search in Web Browsers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7625-8721","authenticated-orcid":false,"given":"Mugeng","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0134-2683","authenticated-orcid":false,"given":"Siqi","family":"Zhong","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2057-3861","authenticated-orcid":false,"given":"Qi","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4846-5803","authenticated-orcid":false,"given":"Yudong","family":"Han","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7908-8484","authenticated-orcid":false,"given":"Xuanzhe","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7866-4075","authenticated-orcid":false,"given":"Yun","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2018. Total canvas memory use exceeds the maximum limit (Safari12). https:\/\/stackoverflow.com\/questions\/52532614\/total-canvas-memory-use-exceeds-the-maximum-limit-safari-12. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_2_1","unstructured":"2024. Wikipedia (en) embedded with cohere.ai multilingual-22-12 encoder. Cohere\/wikipedia-22-12-en-embeddings. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_3_1","unstructured":"2025. IndexedDB. https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/API\/IndexedDB_API. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_4_1","unstructured":"2025. MeMemo: RAG and Vector Search in Your Browser. https:\/\/poloclub.github. io\/mememo\/. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_5_1","unstructured":"2025. SemanticFinder: frontend-only live semantic search with transformers.js.-https:\/\/github.com\/do-me\/SemanticFinder. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_6_1","unstructured":"2025. Voy: A WASM vector similarity search written in Rust. https:\/\/github.com\/ tantaraio\/voy. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_7_1","unstructured":"2025. Why IndexedDB is slow and what to use instead. https:\/\/rxdb.info\/slow- indexeddb.html. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_8_1","volume-title":"Lempitsky","author":"Babenko Artem","year":"2015","unstructured":"Artem Babenko and Victor S. Lempitsky. 2015. The Inverted Multi-Index. IEEE Trans. Pattern Anal. Mach. Intell. (2015)."},{"key":"e_1_3_2_1_9_1","unstructured":"Erik Bernhardsson. 2017. Approximate Nearest Neighbors in C\/Python optimized for memory usage and loading\/saving to disk. https:\/\/github.com\/spotify\/annoy. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_10_1","unstructured":"Harrison Chase. 2022. LangChain. https:\/\/github.com\/langchain-ai\/langchain"},{"key":"e_1_3_2_1_11_1","volume-title":"Spann: Highly-efficient billion-scale approximate nearest neighborhood search. Advances in Neural Information Processing Systems","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 (2021)."},{"key":"e_1_3_2_1_12_1","volume-title":"Challenges of large language models for mental health counseling. arXiv preprint arXiv:2311.13857","author":"Chung Neo Christopher","year":"2023","unstructured":"Neo Christopher Chung, George Dyer, and Lennart Brocki. 2023. Challenges of large language models for mental health counseling. arXiv preprint arXiv:2311.13857 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"The faiss library. arXiv preprint arXiv:2401.08281","author":"Douze Matthijs","year":"2024","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 preprint arXiv:2401.08281 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"age, and technology education influence the adoption and appropriation of LLMs. arXiv preprint arXiv:2310.06556","author":"Draxler Fiona","year":"2023","unstructured":"Fiona Draxler, Daniel Buschek, Mikke Tavast, Perttu H\u00e4m\u00e4l\u00e4inen, Albrecht Schmidt, Juhi Kulshrestha, and Robin Welsch. 2023. Gender, age, and technology education influence the adoption and appropriation of LLMs. arXiv preprint arXiv:2310.06556 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"Optimized product quantization","author":"Ge Tiezheng","year":"2013","unstructured":"Tiezheng Ge, Kaiming He, Qifa Ke, and Jian Sun. 2013. Optimized product quantization. IEEE transactions on pattern analysis and machine intelligence (TPAMI) (2013), 744-755."},{"key":"e_1_3_2_1_16_1","first-page":"17","volume-title":"Proceedings of the International Conference on Service-Oriented Computing (ICSOC","author":"Ghodratnama Samira","year":"2023","unstructured":"Samira Ghodratnama and Mehrdad Zakershahrak. 2023. Adapting LLMs for Efficient, Personalized Information Retrieval: Methods and Implications. In Proceedings of the International Conference on Service-Oriented Computing (ICSOC 2023). 17-26."},{"key":"e_1_3_2_1_17_1","unstructured":"W3C Community Group. 2025. WebAssembly. https:\/\/webassembly.org\/. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"e_1_3_2_1_19_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 (TPAMI) (2010), 117-128."},{"key":"e_1_3_2_1_20_1","volume-title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation. arXiv preprint arXiv:2404.12457","author":"Jin Chao","year":"2024","unstructured":"Chao Jin, Zili Zhang, Xuanlin Jiang, Fangyue Liu, Xin Liu, Xuanzhe Liu, and Xin Jin. 2024. RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation. arXiv preprint arXiv:2404.12457 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_22_1","volume-title":"Pgvector: Open-source Vector Similarity Search for Postgres. https:\/\/github.com\/pgvector\/pgvector.","author":"Kane Andrew","year":"2021","unstructured":"Andrew Kane. 2021. Pgvector: Open-source Vector Similarity Search for Postgres. https:\/\/github.com\/pgvector\/pgvector."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591651"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463238"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Yu A. Malkov and D. A. Yashunin. 2020. Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2020) 824-836.","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_1_26_1","unstructured":"mdn web docs. 2024. Service Worker API. https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/API\/Service_Worker_API. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_27_1","unstructured":"mdn web docs. 2025 a. Storage quotas and eviction criteria. https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/API\/Storage_API\/Storage_quotas_and_eviction_criteria. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_28_1","unstructured":"mdn web docs. 2025 b. Wasm currently only allows 32-bit addressing. https:\/\/developer.mozilla.org\/en-US\/docs\/WebAssembly\/JavaScript_interface\/Memory\/Memory. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_29_1","unstructured":"OpenAI. 2025. ChatGPT. https:\/\/chatgpt.com\/. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_30_1","first-page":"31186","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS 2022)","author":"Pham Ninh","year":"2022","unstructured":"Ninh Pham and Tao Liu. 2022. Falconn: A locality-sensitive filtering approach for approximate nearest neighbor search. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS 2022) (2022), 31186-31198."},{"key":"e_1_3_2_1_31_1","unstructured":"LinQ AI Research. 2024. FinDER: Financial Document Retrieval Dataset. https:\/\/huggingface.co\/datasets\/Linq-AI-Research\/FinanceRAG. Accessed: 2025-01-01."},{"key":"e_1_3_2_1_32_1","volume-title":"EdgeRAG: Online-Indexed RAG for Edge Devices. arXiv preprint arXiv:2412.21023","author":"Seemakhupt Korakit","year":"2024","unstructured":"Korakit Seemakhupt, Sihang Liu, and Samira Khan. 2024. EdgeRAG: Online-Indexed RAG for Edge Devices. arXiv preprint arXiv:2412.21023 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.157"},{"key":"e_1_3_2_1_34_1","volume-title":"Improving the domain adaptation of retrieval augmented generation (RAG) models for open domain question answering. Transactions of the Association for Computational Linguistics (TACL)","author":"Siriwardhana Shamane","year":"2023","unstructured":"Shamane Siriwardhana, Rivindu Weerasekera, Elliott Wen, Tharindu Kaluarachchi, Rajib Rana, and Suranga Nanayakkara. 2023. Improving the domain adaptation of retrieval augmented generation (RAG) models for open domain question answering. Transactions of the Association for Computational Linguistics (TACL) (2023), 1-17."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3097987"},{"key":"e_1_3_2_1_36_1","volume-title":"FusionANNS: An Efficient CPU\/GPU Cooperative Processing Architecture for Billion-scale Approximate Nearest Neighbor Search. arXiv preprint arXiv:2409.16576","author":"Tian Bing","year":"2024","unstructured":"Bing Tian, Haikun Liu, Yuhang Tang, Shihai Xiao, Zhuohui Duan, Xiaofei Liao, Xuecang Zhang, Junhua Zhu, and Yu Zhang. 2024. FusionANNS: An Efficient CPU\/GPU Cooperative Processing Architecture for Billion-scale Approximate Nearest Neighbor Search. arXiv preprint arXiv:2409.16576 (2024)."},{"key":"e_1_3_2_1_37_1","first-page":"2765","volume-title":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR","author":"Zijie","year":"2024","unstructured":"Zijie J. Wang and Duen Horng Chau. 2024. MeMemo: On-device Retrieval Augmentation for Private and Personalized Text Generation. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2024). 2765-2770."},{"key":"e_1_3_2_1_38_1","volume-title":"Rethinking privacy in machine learning pipelines from an information flow control perspective. arXiv preprint arXiv:2311.15792","author":"Wutschitz Lukas","year":"2023","unstructured":"Lukas Wutschitz, Boris K\u00f6pf, Andrew Paverd, Saravan Rajmohan, Ahmed Salem, Shruti Tople, Santiago Zanella-B\u00e9guelin, Menglin Xia, and Victor R\u00fchle. 2023. Rethinking privacy in machine learning pipelines from an information flow control perspective. arXiv preprint arXiv:2311.15792 (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581388"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539212"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219820"},{"key":"e_1_3_2_1_42_1","first-page":"995","volume-title":"Approximate Vector Queries on Very Large Unstructured Datasets. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23)","author":"Zhang Zili","year":"2023","unstructured":"Zili Zhang, Chao Jin, Linpeng Tang, Xuanzhe Liu, and Xin Jin. 2023. Fast, Approximate Vector Queries on Very Large Unstructured Datasets. In 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 995-1011."},{"key":"e_1_3_2_1_43_1","first-page":"23","volume-title":"Fast Vector Query Processing for Large Datasets Beyond GPU Memory with Reordered Pipelining. In 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024","author":"Zhang Zili","year":"2024","unstructured":"Zili Zhang, Fangyue Liu, Gang Huang, Xuanzhe Liu, and Xin Jin. 2024. Fast Vector Query Processing for Large Datasets Beyond GPU Memory with Reordered Pipelining. In 21st USENIX Symposium on Networked Systems Design and Implementation, NSDI 2024, Santa Clara, CA, April 15-17, 2024. 23-40."},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the Eleventh International Conference on Learning Representations (ICLR","author":"Zhou Shuyan","year":"2023","unstructured":"Shuyan Zhou, Uri Alon, Frank F Xu, Zhengbao Jiang, and Graham Neubig. 2023. DocPrompting: Generating Code by Retrieving the Docs. In Proceedings of the Eleventh International Conference on Learning Representations (ICLR 2023)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730115","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:22:31Z","timestamp":1755868951000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730115"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":44,"alternative-id":["10.1145\/3726302.3730115","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730115","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}