{"id":"https://openalex.org/W4415744270","doi":"https://doi.org/10.1109/qrs-c65679.2025.00109","title":"Tiered-Precision Hybrid Computation: A Memory-Constrained Solution for Optimizing Word Embedding Search in Large-Scale AI Models","display_name":"Tiered-Precision Hybrid Computation: A Memory-Constrained Solution for Optimizing Word Embedding Search in Large-Scale AI Models","publication_year":2025,"publication_date":"2025-07-16","ids":{"openalex":"https://openalex.org/W4415744270","doi":"https://doi.org/10.1109/qrs-c65679.2025.00109"},"language":null,"primary_location":{"id":"doi:10.1109/qrs-c65679.2025.00109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qrs-c65679.2025.00109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 25th International Conference on Software Quality, Reliability, and Security Companion (QRS-C)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Dingshan Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210150405","display_name":"Hongzhiwei Technology (China)","ror":"https://ror.org/04bapa014","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150405"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dingshan Zhuang","raw_affiliation_strings":["Deedface AI Tech (Shanghai) Ltd.,China"],"affiliations":[{"raw_affiliation_string":"Deedface AI Tech (Shanghai) Ltd.,China","institution_ids":["https://openalex.org/I4210150405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112121529","display_name":"Yu Zeng","orcid":"https://orcid.org/0000-0001-5729-9320"},"institutions":[{"id":"https://openalex.org/I4210150405","display_name":"Hongzhiwei Technology (China)","ror":"https://ror.org/04bapa014","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150405"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You Zeng","raw_affiliation_strings":["Deedface AI Tech (Shanghai) Ltd.,China"],"affiliations":[{"raw_affiliation_string":"Deedface AI Tech (Shanghai) Ltd.,China","institution_ids":["https://openalex.org/I4210150405"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032979112","display_name":"Jianlong Li","orcid":"https://orcid.org/0009-0002-8267-8968"},"institutions":[{"id":"https://openalex.org/I4210150405","display_name":"Hongzhiwei Technology (China)","ror":"https://ror.org/04bapa014","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210150405"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxun Li","raw_affiliation_strings":["Deedface AI Tech (Shanghai) Ltd.,China"],"affiliations":[{"raw_affiliation_string":"Deedface AI Tech (Shanghai) Ltd.,China","institution_ids":["https://openalex.org/I4210150405"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210150405"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16257174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"788","last_page":"789"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3061000108718872,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10028","display_name":"Topic Modeling","score":0.3061000108718872,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.2198999971151352,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05900000035762787,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7023000121116638},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6793000102043152},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6208000183105469},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6144000291824341},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5740000009536743},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.42419999837875366},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41290000081062317},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.34139999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900000214576721},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7023000121116638},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6793000102043152},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6208000183105469},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6144000291824341},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5740000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5016000270843506},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.44839999079704285},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41290000081062317},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3366999924182892},{"id":"https://openalex.org/C184596265","wikidata":"https://www.wikidata.org/wiki/Q2651576","display_name":"Model of computation","level":3,"score":0.31369999051094055},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/qrs-c65679.2025.00109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/qrs-c65679.2025.00109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 25th International Conference on Software Quality, Reliability, and Security Companion (QRS-C)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2888269900","https://openalex.org/W4318186677","https://openalex.org/W4399768035"],"related_works":[],"abstract_inverted_index":{"Abstract:":[0],"Large-scale":[1],"AI":[2],"models":[3],"like":[4],"GPT-4":[5],"and":[6,68,82],"Llama":[7],"rely":[8],"on":[9,62],"GPU":[10,17],"computing":[11],"for":[12,50,74],"word":[13,38],"embedding":[14],"search,":[15],"but":[16],"memory":[18,33,45,66],"constraints":[19],"limit":[20],"scalability.":[21],"We":[22,77],"propose":[23],"Tiered-Precision":[24],"Hybrid":[25],"Computation":[26],"(TPHC),":[27],"a":[28,71],"two-stage":[29],"framework":[30],"to":[31,42,46],"optimize":[32],"usage.":[34],"In":[35,54],"Stage":[36,55],"1,":[37],"vectors":[39],"are":[40],"quantized":[41],"INT4,":[43],"reducing":[44],"25%":[47],"of":[48],"FP16,":[49],"coarse":[51],"candidate":[52],"selection.":[53],"2,":[56],"FP16":[57],"ensures":[58],"precise":[59],"similarity":[60],"computation":[61],"candidates.":[63],"TPHC":[64],"balances":[65],"efficiency":[67],"accuracy,":[69],"offering":[70],"scalable":[72],"solution":[73],"semantic":[75],"search.":[76],"analyze":[78],"its":[79],"theoretical":[80],"feasibility":[81],"suggest":[83],"future":[84],"evaluation":[85],"directions.":[86]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-31T00:00:00"}