{"id":"https://openalex.org/W4415708206","doi":"https://doi.org/10.1109/icme59968.2025.11210235","title":"Elastic Architecture Search for Efficient Language Models","display_name":"Elastic Architecture Search for Efficient Language Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708206","doi":"https://doi.org/10.1109/icme59968.2025.11210235"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.27037","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100346376","display_name":"Shang Wang","orcid":"https://orcid.org/0000-0001-8176-9038"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100346376"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2867000102996826,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.2867000102996826,"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/T10028","display_name":"Topic Modeling","score":0.26409998536109924,"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":0.06599999964237213,"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/language-model","display_name":"Language model","score":0.6661999821662903},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5777000188827515},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5591999888420105},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4722000062465668},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4674000144004822},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.4657999873161316},{"id":"https://openalex.org/keywords/modeling-language","display_name":"Modeling language","score":0.3619999885559082},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.3411000072956085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831000089645386},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6661999821662903},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5777000188827515},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5199000239372253},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4722000062465668},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4674000144004822},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4657999873161316},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3747999966144562},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.3619999885559082},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C141218545","wikidata":"https://www.wikidata.org/wiki/Q7521336","display_name":"Simulation language","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.26010000705718994}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme59968.2025.11210235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.27037","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.27037","pdf_url":"https://arxiv.org/pdf/2510.27037","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.27037","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.27037","pdf_url":"https://arxiv.org/pdf/2510.27037","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W2923014074","https://openalex.org/W2963748441","https://openalex.org/W2970454332","https://openalex.org/W3034457371","https://openalex.org/W3034560159","https://openalex.org/W3096533519","https://openalex.org/W3105966348","https://openalex.org/W3167266074","https://openalex.org/W3180942591","https://openalex.org/W3198917403","https://openalex.org/W4385570984","https://openalex.org/W4385572634"],"related_works":[],"abstract_inverted_index":{"As":[0],"large":[1],"pre-trained":[2],"language":[3,10,48,126,130],"models":[4,135],"become":[5],"increasingly":[6],"critical":[7],"to":[8,112],"natural":[9],"understanding":[11],"(NLU)":[12],"tasks,":[13],"their":[14],"substantial":[15],"computational":[16],"and":[17,24,65,70,79,89,128],"memory":[18],"requirements":[19],"have":[20],"raised":[21],"significant":[22],"economic":[23],"environmental":[25],"concerns.":[26],"Addressing":[27],"these":[28],"challenges,":[29],"this":[30],"paper":[31],"introduces":[32],"the":[33,77,82,104,114,120],"Elastic":[34],"Language":[35],"Model":[36],"(ELM),":[37],"a":[38,57],"novel":[39,98],"neural":[40],"architecture":[41],"search":[42,59,83,121],"(NAS)":[43],"method":[44],"optimized":[45],"for":[46,68],"compact":[47],"models.":[49],"ELM":[50,138],"extends":[51],"existing":[52,141],"NAS":[53],"approaches":[54],"by":[55,137],"introducing":[56],"flexible":[58],"space":[60],"with":[61],"efficient":[62],"transformer":[63],"blocks":[64],"dynamic":[66],"modules":[67],"dimension":[69],"head":[71],"number":[72],"adjustment.":[73],"These":[74],"innovations":[75],"enhance":[76],"efficiency":[78],"flexibility":[80],"of":[81,92,107],"process,":[84],"which":[85],"facilitates":[86],"more":[87],"thorough":[88],"effective":[90],"exploration":[91],"model":[93],"architectures.":[94],"We":[95],"also":[96],"introduce":[97],"knowledge":[99],"distillation":[100],"losses":[101],"that":[102,134],"preserve":[103],"unique":[105],"characteristics":[106],"each":[108],"block,":[109],"in":[110],"order":[111],"improve":[113],"discrimination":[115],"between":[116],"architectural":[117],"choices":[118],"during":[119],"process.":[122],"Experiments":[123],"on":[124],"masked":[125],"modeling":[127,131],"causal":[129],"tasks":[132],"demonstrate":[133],"discovered":[136],"significantly":[139],"outperform":[140],"methods.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}