{"id":"https://openalex.org/W7134282924","doi":"https://doi.org/10.48550/arxiv.2603.06159","title":"Efficient Vector Search in the Wild: One Model for Multi-K Queries","display_name":"Efficient Vector Search in the Wild: One Model for Multi-K Queries","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7134282924","doi":"https://doi.org/10.48550/arxiv.2603.06159"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.06159","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101629182","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0003-0667-2599"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128520077","display_name":"Jiafei Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Jiafei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002957327","display_name":"Xingda Wei","orcid":"https://orcid.org/0000-0003-4983-6047"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Xingda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128497773","display_name":"Sijie Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Sijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128492326","display_name":"Rong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Rong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128393965","display_name":"Jianning Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jianning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128453158","display_name":"Xiaojian Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Xiaojian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018856303","display_name":"Wenyuan Yu","orcid":"https://orcid.org/0009-0006-5641-2452"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Wenyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128514356","display_name":"Jingren Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jingren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128456532","display_name":"Haibo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Haibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30062907,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.26840001344680786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.26840001344680786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.22689999639987946,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.12080000340938568,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7804999947547913},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6542999744415283},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44369998574256897},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.3573000133037567},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.33219999074935913},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.3312000036239624},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3262999951839447}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7804999947547913},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6956999897956848},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6542999744415283},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44369998574256897},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41749998927116394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3790999948978424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36399999260902405},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C21782646","wikidata":"https://www.wikidata.org/wiki/Q841666","display_name":"Search cost","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2985999882221222},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2639000117778778}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.06159","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.06159","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.06159","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.06159","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learned":[0],"top-K":[1,79,145],"search":[2,80,177],"is":[3,63,100],"a":[4,22,76,102,122],"promising":[5],"approach":[6],"for":[7,21,66,93],"serving":[8,67],"vector":[9,68,95],"queries":[10,69],"with":[11,109,121,129],"both":[12],"high":[13,85,87],"accuracy":[14,36],"and":[15,41,62,89,126,157],"performance.":[16],"However,":[17],"current":[18],"models":[19],"trained":[20,106],"specific":[23],"K":[24],"value":[25],"fail":[26],"to":[27,29,50,116,147,174],"generalize":[28,51],"real-world":[30],"multi-K":[31,94],"queries:":[32],"they":[33],"suffer":[34],"from":[35],"degradation":[37],"(for":[38,44],"larger":[39,119],"Ks)":[40],"performance":[42,131],"loss":[43],"smaller":[45,127],"Ks).":[46],"Training":[47],"the":[48,71,141,163,183,191,198],"model":[49,104,150],"on":[52,107,154],"different":[53],"Ks":[54,120,128],"requires":[55],"orders":[56],"of":[57,144,190,197,202],"magnitude":[58],"more":[59],"preprocessing":[60,91,165,192],"time":[61],"not":[64],"suitable":[65],"in":[70],"wild.":[72],"We":[73],"present":[74],"OMEGA,":[75],"K-generalizable":[77],"learned":[78,176],"method":[81],"that":[82,101],"simultaneously":[83],"achieves":[84,168],"accuracy,":[86],"performance,":[88],"low":[90],"cost":[92],"queries.":[96],"The":[97],"key":[98],"idea":[99],"base":[103],"properly":[105],"K=1":[108],"our":[110,135],"trajectory-based":[111],"features":[112],"can":[113],"be":[114],"used":[115],"accurately":[117],"predict":[118],"dynamic":[123],"refinement":[124],"procedure":[125],"minimal":[130],"loss.":[132],"To":[133],"make":[134],"refinements":[136],"efficient,":[137],"we":[138],"further":[139],"leverage":[140],"statistical":[142],"properties":[143],"searches":[146],"reduce":[148],"excessive":[149],"invocations.":[151],"Extensive":[152],"evaluations":[153],"multiple":[155],"public":[156],"production":[158],"datasets":[159],"show":[160],"that,":[161],"under":[162],"same":[164,184],"budgets,":[166],"OMEGA":[167,194],"6-33%":[169],"lower":[170],"average":[171,200],"latency":[172,201],"compared":[173],"state-of-the-art":[175],"methods,":[178],"while":[179],"all":[180],"systems":[181],"achieve":[182],"recall":[185],"target.":[186],"With":[187],"only":[188],"16-30%":[189],"time,":[193],"attains":[195],"1.01-1.28x":[196],"optimal":[199],"these":[203],"baselines.":[204]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-03-10T00:00:00"}