{"id":"https://openalex.org/W4404134026","doi":"https://doi.org/10.1145/3649329.3658473","title":"EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Unified Compression and Adaptive Layer Voting","display_name":"EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Unified Compression and Adaptive Layer Voting","publication_year":2024,"publication_date":"2024-06-23","ids":{"openalex":"https://openalex.org/W4404134026","doi":"https://doi.org/10.1145/3649329.3658473"},"language":"en","primary_location":{"id":"doi:10.1145/3649329.3658473","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3658473","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3649329.3658473","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034614246","display_name":"Zhongzhi Yu","orcid":"https://orcid.org/0000-0002-9981-4981"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhongzhi Yu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, United States"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100316060","display_name":"Zheng Wang","orcid":"https://orcid.org/0009-0000-2279-7506"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, United States"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004593702","display_name":"Yuhan Li","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhan Li","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, United States"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115600879","display_name":"Ruijie Gao","orcid":"https://orcid.org/0009-0002-8849-1643"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruijie Gao","raw_affiliation_strings":["Georgoa Institute of Technology, Atlanta, GA, United States"],"affiliations":[{"raw_affiliation_string":"Georgoa Institute of Technology, Atlanta, GA, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110128560","display_name":"Xiaoya Zhou","orcid":"https://orcid.org/0009-0007-7668-2561"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoya Zhou","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, United States"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, United States","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114554114","display_name":"Sreenidhi Reddy Bommu","orcid":"https://orcid.org/0009-0000-9756-7924"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sreenidhi Reddy Bommu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, United States"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107593559","display_name":"Yang Zhao","orcid":"https://orcid.org/0000-0001-8023-1551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang (Katie) Zhao","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, United States"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019582323","display_name":"Yingyan Lin","orcid":"https://orcid.org/0000-0001-5946-203X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingyan (Celine) Lin","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, United States"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, United States","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5034614246"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":12.8277,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.98989837,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"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/T10028","display_name":"Topic Modeling","score":0.9955000281333923,"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":0.9955000281333923,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9923999905586243,"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":0.9916999936103821,"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/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.7621909379959106},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7305552363395691},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7142926454544067},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6060784459114075},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5190535187721252},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.48233553767204285},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.41746607422828674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2080269455909729},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07914289832115173},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.07145649194717407},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06007105112075806}],"concepts":[{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.7621909379959106},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7305552363395691},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7142926454544067},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6060784459114075},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5190535187721252},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.48233553767204285},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.41746607422828674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2080269455909729},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07914289832115173},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.07145649194717407},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06007105112075806},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649329.3658473","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3658473","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3649329.3658473","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3658473","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8620029627","display_name":null,"funder_award_id":"2048183","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W3201628041","https://openalex.org/W3207000034","https://openalex.org/W4282961290","https://openalex.org/W4378446728","https://openalex.org/W4386736489","https://openalex.org/W4402670692","https://openalex.org/W6791858558","https://openalex.org/W6839562487","https://openalex.org/W6852686595"],"related_works":["https://openalex.org/W4313339048","https://openalex.org/W4386004629","https://openalex.org/W3176734149","https://openalex.org/W3201779876","https://openalex.org/W3113627641","https://openalex.org/W2918879532","https://openalex.org/W3083220997","https://openalex.org/W2885461866","https://openalex.org/W3162654428","https://openalex.org/W2901937988"],"abstract_inverted_index":{"Efficient":[0],"adaption":[1],"of":[2,28],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"on":[7,56],"edge":[8,57],"devices":[9],"is":[10,160],"essential":[11],"for":[12],"applications":[13],"requiring":[14],"continuous":[15],"and":[16,19,32,42,52,82,91,104,120,151],"privacy-preserving":[17],"adaptation":[18,55,137],"inference.":[20],"However,":[21],"existing":[22],"tuning":[23,45,90,144],"techniques":[24],"fall":[25],"short":[26],"because":[27],"the":[29,74,96,101,113],"high":[30],"computation":[31,75,115],"memory":[33,97,156],"overhead.":[34,157],"To":[35],"this":[36],"end,":[37],"we":[38],"introduce":[39],"a":[40,66,106,147,152],"computation-":[41],"memory-efficient":[43],"LLM":[44,54],"framework,":[46],"called":[47],"Edge-LLM,":[48],"to":[49,72,94,111],"facilitate":[50],"affordable":[51],"effective":[53],"devices.":[58],"Specifically,":[59],"Edge-LLM":[60,134],"features":[61],"three":[62],"core":[63],"components:":[64],"(1)":[65],"layer-wise":[67,79],"unified":[68],"compression":[69],"(LUC)":[70],"technique":[71],"reduce":[73,95],"overhead":[76,98],"by":[77,99,118],"generating":[78],"pruning":[80],"sparsity":[81],"quantization":[83],"bit-width":[84],"policies,":[85],"(2)":[86],"an":[87],"adaptive":[88,121],"layer":[89,122],"voting":[92],"scheme":[93],"reducing":[100],"backpropagation":[102],"depth,":[103],"(3)":[105],"complementary":[107],"hardware":[108,128],"scheduling":[109],"strategy":[110],"handle":[112],"irregular":[114],"patterns":[116],"introduced":[117],"LUC":[119],"tuning,":[123],"thereby":[124],"achieving":[125],"improved":[126],"real":[127],"efficiency.":[129],"Extensive":[130],"experiments":[131],"demonstrate":[132],"that":[133],"achieves":[135],"on-device":[136],"with":[138,146],"comparable":[139],"task":[140],"accuracy":[141],"as":[142],"vanilla":[143],"methods":[145],"2.92\u00d7":[148],"speed":[149],"up":[150],"4\u00d7":[153],"reduction":[154],"in":[155],"Our":[158],"code":[159],"available":[161],"at":[162],"https://github.com/GATECH-EIC/Edge-LLM":[163]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}