{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T13:01:59Z","timestamp":1785502919726,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","funder":[{"name":"We thank the reviewers for their valuable comments and constructive suggestions.","award":["N\/A"],"award-info":[{"award-number":["N\/A"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780192","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"348-358","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PilotANN: Memory-Bounded GPU Acceleration for Vector Search"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3593-3447","authenticated-orcid":false,"given":"Yuntao","family":"Gui","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4081-913X","authenticated-orcid":false,"given":"Peiqi","family":"Yin","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2122-915X","authenticated-orcid":false,"given":"Xiao","family":"Yan","sequence":"additional","affiliation":[{"name":"Centre for Perceptual and Interactive Intelligence, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1530-2584","authenticated-orcid":false,"given":"Chaorui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Theory Lab, 2012 Labs of Huawei, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4769-2779","authenticated-orcid":false,"given":"Weixi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Theory Lab, 2012 Labs of Huawei, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6313-6288","authenticated-orcid":false,"given":"James","family":"Cheng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_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_2_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2361319"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.226"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlposs-1.24"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1114"},{"key":"e_1_3_2_2_7_1","volume-title":"SPANN: Highly-efficient Billion-scale Approximate Nearest Neighborhood Search. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","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. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 5199-5212. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/299dc35e747eb77177d9cea10a802da2-Abstract.html"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959190"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00128644"},{"key":"e_1_3_2_2_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1963405.1963487"},{"key":"e_1_3_2_2_12_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.08281"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00384"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/3303753.3303754"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/645925.671516"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3161156"},{"key":"e_1_3_2_2_19_1","volume-title":"Search-R3: Unifying Reasoning and Embedding Generation in Large Language Models. arXiv preprint arXiv:2510.07048","author":"Gui Yuntao","year":"2025","unstructured":"Yuntao Gui and James Cheng. 2025. Search-R3: Unifying Reasoning and Embedding Generation in Large Language Models. arXiv preprint arXiv:2510.07048 (2025)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.5591\/978-1-57735-516-8\/IJCAI11-222"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_2_2_22_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, Vol. 32 (2019)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5946540"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2022.EMNLP-MAIN.149"},{"key":"e_1_3_2_2_26_1","volume-title":"Harsha Vardhan Simhadri, and Jyothi Vedurada","author":"Karthik V","year":"2024","unstructured":"V Karthik, Saim Khan, Somesh Singh, Harsha Vardhan Simhadri, and Jyothi Vedurada. 2024. BANG: Billion-Scale Approximate Nearest Neighbor Search using a Single GPU. arXiv e-prints (2024), arXiv-2401."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459466"},{"key":"e_1_3_2_2_28_1","volume-title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Lewis Patrick S. H.","year":"2020","unstructured":"Patrick S. H. Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin (Eds.). https:\/\/proceedings.neurips.cc\/paper\/2020\/hash\/6b493230205f780e1bc26945df7481e5-Abstract.html"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2409.10516"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","unstructured":"Jerry Liu. 2022. LlamaIndex. doi:10.5281\/zenodo.1234","DOI":"10.5281\/zenodo.1234"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.14778\/3489496.3489506"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2013.10.006"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650200.3656601"},{"key":"e_1_3_2_2_35_1","volume-title":"Algorithms and data structures: The basic toolbox","author":"Mehlhorn Kurt","unstructured":"Kurt Mehlhorn, Peter Sanders, and Peter Sanders. 2008. Algorithms and data structures: The basic toolbox. Vol. 55. Springer."},{"key":"e_1_3_2_2_36_1","unstructured":"NVIDIA. 2020. Fast Flexible Allocation for NVIDIA CUDA with RAPIDS Memory Manager | NVIDIA Technical Blog -- developer.nvidia.com. https:\/\/developer.nvidia.com\/blog\/fast-flexible-allocation-for-cuda-with-rapids-memory-manager. [Accessed 15-10-2024]."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.15136"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3572848.3577527"},{"key":"e_1_3_2_2_39_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","volume":"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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748-8763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_2_40_1","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, Patrick Schramowski, Srivatsa Kundurthy, Katherine Crowson, Ludwig Schmidt, Robert Kaczmarczyk, and Jenia Jitsev. 2022. LAION-5B: An open large-scale dataset for training next generation image-text models. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/a1859debfb3b59d094f3504d5ebb6c25-Abstract-Datasets_and_Benchmarks.html"},{"key":"e_1_3_2_2_41_1","volume-title":"Introduction to information retrieval","author":"Sch\u00fctze Hinrich","unstructured":"Hinrich Sch\u00fctze, Christopher D Manning, and Prabhakar Raghavan. 2008. Introduction to information retrieval. Vol. 39. Cambridge University Press Cambridge."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587638"},{"key":"e_1_3_2_2_43_1","volume-title":"Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track (Proceedings of Machine Learning Research","volume":"189","author":"Simhadri Harsha Vardhan","year":"2022","unstructured":"Harsha Vardhan Simhadri, George Williams, Martin Aum\u00fcller, Matthijs Douze, Artem Babenko, Dmitry Baranchuk, Qi Chen, Lucas Hosseini, Ravishankar Krishnaswamny, Gopal Srinivasa, Suhas Jayaram Subramanya, and Jingdong Wang. 2022. Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search. In Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track (Proceedings of Machine Learning Research, Vol. 176), Douwe Kiela, Marco Ciccone, and Barbara Caputo (Eds.). PMLR, 177-189. https:\/\/proceedings.mlr.press\/v176\/simhadri22a.html"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2409.16576"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/1498765.1498785"},{"key":"e_1_3_2_2_46_1","unstructured":"Shitao Xiao Zheng Liu Peitian Zhang and Niklas Muennighoff. 2023. C-Pack: Packaged Resources To Advance General Chinese Embedding. arXiv:2309.07597 [cs.CL]"},{"key":"e_1_3_2_2_47_1","unstructured":"Yandex. 2021. Yandex -- research.yandex.com. https:\/\/research.yandex.com\/blog\/benchmarks-for-billion-scale-similarity-search. [Accessed 15-10-2024]."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366424.3386195"},{"key":"e_1_3_2_2_49_1","volume-title":"Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176","author":"Zhang Yanzhao","year":"2025","unstructured":"Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, et al., 2025. Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models. arXiv preprint arXiv:2506.05176 (2025)."},{"key":"e_1_3_2_2_50_1","first-page":"23","volume-title":"Fast Vector Query Processing for Large Datasets Beyond  Memory with Reordered Pipelining. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","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 Memory with Reordered Pipelining. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 23-40."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00094"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2393377"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503221.3508409"}],"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.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:11:06Z","timestamp":1785499866000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780192"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":53,"alternative-id":["10.1145\/3770854.3780192","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780192","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}