{"id":"https://openalex.org/W4394769034","doi":"https://doi.org/10.1145/3597503.3639120","title":"When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference","display_name":"When Neural Code Completion Models Size up the Situation: Attaining Cheaper and Faster Completion through Dynamic Model Inference","publication_year":2024,"publication_date":"2024-04-12","ids":{"openalex":"https://openalex.org/W4394769034","doi":"https://doi.org/10.1145/3597503.3639120"},"language":"en","primary_location":{"id":"doi:10.1145/3597503.3639120","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597503.3639120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 46th International Conference on Software Engineering","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/A5078038118","display_name":"Zhensu Sun","orcid":"https://orcid.org/0000-0001-5393-7858"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhensu Sun","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102717874","display_name":"Xiaoning Du","orcid":"https://orcid.org/0000-0003-3728-9541"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaoning Du","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027425633","display_name":"Fu Song","orcid":"https://orcid.org/0000-0002-0581-2679"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Song","raw_affiliation_strings":["State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China","State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081197883","display_name":"Shangwen Wang","orcid":"https://orcid.org/0000-0003-1469-2063"},"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, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106407830","display_name":"Li Li","orcid":"https://orcid.org/0000-0003-2990-1614"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5078038118"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":9.7421,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.97916272,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9921000003814697,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9921000003814697,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9778000116348267,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9686999917030334,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.864741861820221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8269248008728027},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.75035560131073},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6618658900260925},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6554688811302185},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6070741415023804},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.48073744773864746},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4526408314704895},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42842257022857666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4064503312110901},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2712666094303131},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.175052672624588},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1661640703678131},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.1487051546573639},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.09089183807373047}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.864741861820221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8269248008728027},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.75035560131073},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6618658900260925},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6554688811302185},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6070741415023804},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.48073744773864746},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4526408314704895},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42842257022857666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4064503312110901},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2712666094303131},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.175052672624588},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1661640703678131},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.1487051546573639},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.09089183807373047},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3597503.3639120","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597503.3639120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2962677625","https://openalex.org/W3094307698","https://openalex.org/W3196295870","https://openalex.org/W4225108562","https://openalex.org/W4281669078","https://openalex.org/W4311887664","https://openalex.org/W4313547593","https://openalex.org/W4375859932","https://openalex.org/W4385481791"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2097707447","https://openalex.org/W2048831961","https://openalex.org/W1606349578"],"abstract_inverted_index":{"Leveraging":[0],"recent":[1],"advancements":[2],"in":[3,28,40,154,223,237],"large":[4],"language":[5],"models,":[6,225],"modern":[7],"neural":[8],"code":[9,20,73,92,155,185],"completion":[10,156,186],"models":[11],"have":[12],"demonstrated":[13],"the":[14,59,70,85,106,119,130,169,224],"capability":[15],"to":[16,123,160,193,203,227],"generate":[17],"highly":[18],"accurate":[19],"suggestions.":[21],"However,":[22],"their":[23,37],"massive":[24],"size":[25],"poses":[26],"challenges":[27],"terms":[29],"of":[30,72,88,98,126,151,171,220],"computational":[31,111],"costs":[32],"and":[33,129,157],"environmental":[34],"impact,":[35],"hindering":[36],"widespread":[38],"adoption":[39],"practical":[41],"scenarios.":[42],"Dynamic":[43],"inference":[44,56,68,86,153,180],"emerges":[45],"as":[46,50],"a":[47,142,164,177,233],"promising":[48],"solution,":[49],"it":[51,162,213],"allocates":[52],"minimal":[53],"computation":[54,200],"during":[55],"while":[57],"maintaining":[58],"model's":[60],"performance.":[61],"In":[62],"this":[63],"research,":[64],"we":[65,76],"explore":[66],"dynamic":[67,152,179],"within":[69],"context":[71],"completion.":[74,93],"Initially,":[75],"conducted":[77],"an":[78,228],"empirical":[79],"investigation":[80],"on":[81,84],"GPT-2,":[82],"focusing":[83],"capabilities":[87],"intermediate":[89],"layers":[90,218,222],"for":[91,184],"We":[94,174],"found":[95],"that":[96,167,212],"54.4%":[97],"tokens":[99,127],"can":[100,214],"be":[101],"accurately":[102],"generated":[103],"using":[104,116],"just":[105],"first":[107],"layer,":[108],"signifying":[109],"significant":[110],"savings":[112],"potential.":[113],"Moreover,":[114],"despite":[115],"all":[117],"layers,":[118],"model":[120],"still":[121],"fails":[122],"predict":[124],"14.5%":[125],"correctly,":[128],"subsequent":[131],"completions":[132],"continued":[133],"from":[134],"them":[135],"are":[136],"rarely":[137],"considered":[138],"helpful,":[139],"with":[140,163,197,231],"only":[141,192,232],"4.2%":[143],"Acceptance":[144],"Rate.":[145],"These":[146],"findings":[147],"motivate":[148],"our":[149],"exploration":[150],"inspire":[158],"us":[159],"enhance":[161],"decision-making":[165],"mechanism":[166],"stops":[168],"generation":[170],"incorrect":[172,205],"code.":[173],"thus":[175],"propose":[176],"novel":[178],"method":[181,189],"specifically":[182],"tailored":[183],"models.":[187],"This":[188],"aims":[190],"not":[191],"produce":[194],"correct":[195],"predictions":[196,206],"largely":[198],"reduced":[199],"but":[201],"also":[202],"prevent":[204],"proactively.":[207],"Our":[208],"extensive":[209],"evaluation":[210],"shows":[211],"averagely":[215],"skip":[216],"1.7":[217],"out":[219],"16":[221],"leading":[226],"11.2%":[229],"speedup":[230],"marginal":[234],"1.1%":[235],"reduction":[236],"ROUGE-L.":[238]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}