{"id":"https://openalex.org/W4416252384","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228461","title":"LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment","display_name":"LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252384","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228461"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":"https://openalex.org/A5101416003","display_name":"Bo Zeng","orcid":"https://orcid.org/0000-0002-4681-6828"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Binrui Zeng","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002881194","display_name":"Bin Ji","orcid":"https://orcid.org/0000-0002-5508-5051"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Ji","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374809","display_name":"Xiaodong Liu","orcid":"https://orcid.org/0009-0000-2114-5784"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Liu","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624238","display_name":"Jie Yu","orcid":"https://orcid.org/0000-0002-0007-6211"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Yu","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376021","display_name":"Shasha Li","orcid":"https://orcid.org/0000-0003-4198-2314"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shasha Li","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037788039","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0001-6232-1254"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100355083","display_name":"Xiaopeng Li","orcid":"https://orcid.org/0000-0002-5264-3775"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Li","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000548793","display_name":"Shangwen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangwen Wang","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102002672","display_name":"Xiaoyan Hong","orcid":"https://orcid.org/0000-0002-0745-5038"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinran Hong","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050772360","display_name":"Yongtao Tang","orcid":"https://orcid.org/0000-0002-9012-6373"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongtao Tang","raw_affiliation_strings":["National University of Defense Technology,College of Computer Science and Technology,Changsha,China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5101416003"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18339999,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.14480000734329224,"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":0.14480000734329224,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.10890000313520432,"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/T14347","display_name":"Big Data and Digital Economy","score":0.09849999845027924,"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/quantization","display_name":"Quantization (signal processing)","score":0.8525999784469604},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6187999844551086},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6176000237464905},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5182999968528748},{"id":"https://openalex.org/keywords/stochastic-quantization","display_name":"Stochastic quantization","score":0.41589999198913574},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.3822999894618988}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.8525999784469604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7044000029563904},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6187999844551086},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6176000237464905},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5182999968528748},{"id":"https://openalex.org/C2780288589","wikidata":"https://www.wikidata.org/wiki/Q7617833","display_name":"Stochastic quantization","level":4,"score":0.41589999198913574},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C186108316","wikidata":"https://www.wikidata.org/wiki/Q352530","display_name":"Adaptive neuro fuzzy inference system","level":4,"score":0.311599999666214},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30329999327659607},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2858999967575073},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228461","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228461","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2946609015","https://openalex.org/W2998617917","https://openalex.org/W3194676777","https://openalex.org/W4393147125","https://openalex.org/W4401042327","https://openalex.org/W4404781961","https://openalex.org/W4404782134","https://openalex.org/W4412887764"],"related_works":[],"abstract_inverted_index":{"As":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"demonstrate":[5],"exceptional":[6],"performance":[7],"across":[8],"various":[9,65],"domains,":[10],"deploying":[11,36],"LLMs":[12,37,87],"on":[13,38,89,120],"edge":[14,40,62,138],"devices":[15,63],"has":[16],"emerged":[17],"as":[18],"a":[19,78],"new":[20],"trend.":[21],"Quantization":[22,76],"techniques,":[23],"which":[24,140],"reduce":[25],"the":[26,52,95,107,134,160,184],"size":[27],"and":[28,83,109,114,150,168],"memory":[29,53],"requirements":[30,54],"of":[31,55,86,97,111,137,166,186],"LLMs,":[32,56],"are":[33],"effective":[34],"for":[35,80,178],"resource-limited":[39],"devices.":[41],"However,":[42],"existing":[43],"one-size-fits-all":[44],"quantization":[45,82,127,143,162,176],"methods":[46],"often":[47],"fail":[48],"to":[49,60,133,145,182],"dynamically":[50],"adjust":[51],"limiting":[57],"their":[58,116],"applications":[59],"practical":[61],"with":[64,147],"computation":[66,135],"resources.":[67],"To":[68],"tackle":[69],"this":[70],"issue,":[71],"we":[72],"propose":[73],"Layer-Specific":[74],"Adaptive":[75],"(LSAQ),":[77],"system":[79,124],"adaptive":[81],"dynamic":[84],"deployment":[85,185],"based":[88],"layer":[90,113,121],"importance.":[91],"Specifically,":[92],"LSAQ":[93,157],"evaluates":[94],"importance":[96],"LLMs\u2019":[98],"neural":[99],"layers":[100,146],"by":[101],"constructing":[102],"top-k":[103],"token":[104],"sets":[105],"from":[106],"inputs":[108],"outputs":[110],"each":[112],"calculating":[115],"Jaccard":[117],"similarity.":[118],"Based":[119],"importance,":[122,149],"our":[123],"adaptively":[125],"adjusts":[126],"strategies":[128],"in":[129,164],"real":[130],"time":[131],"according":[132],"resource":[136],"devices,":[139],"applies":[141],"higher":[142,148],"precision":[144],"vice":[151],"versa.":[152],"Experimental":[153],"results":[154],"show":[155],"that":[156],"consistently":[158],"outperforms":[159],"selected":[161],"baselines":[163],"terms":[165],"perplexity":[167],"zero-shot":[169],"tasks.":[170],"Additionally,":[171],"it":[172],"can":[173],"devise":[174],"appropriate":[175],"schemes":[177],"different":[179],"usage":[180],"scenarios":[181],"facilitate":[183],"LLMs.":[187]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}
