{"id":"https://openalex.org/W7155015707","doi":"https://doi.org/10.48550/arxiv.2604.15622","title":"AdaVFM: Adaptive Vision Foundation Models for Edge Intelligence via LLM-Guided Execution","display_name":"AdaVFM: Adaptive Vision Foundation Models for Edge Intelligence via LLM-Guided Execution","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7155015707","doi":"https://doi.org/10.48550/arxiv.2604.15622"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.15622","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15622","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.15622","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134047367","display_name":"Yiwei Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhao, Yiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134035764","display_name":"Yi Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134067958","display_name":"Huapeng Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Huapeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102002494","display_name":"Jieyu Lin","orcid":"https://orcid.org/0000-0002-6875-658X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Jieyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028455655","display_name":"Stefano Ambrogio","orcid":"https://orcid.org/0000-0002-5475-4209"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ambrogio, Stefano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110511320","display_name":"Cijo Jose","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jose, Cijo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072078278","display_name":"Micha\u00ebl Ramamonjisoa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramamonjisoa, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067188801","display_name":"Patrick Labatut","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Labatut, Patrick","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053194542","display_name":"B. De Salvo","orcid":"https://orcid.org/0000-0002-0810-9903"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"De Salvo, Barbara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062792452","display_name":"Chiao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Chiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014824446","display_name":"Phillip B. Gibbons","orcid":"https://orcid.org/0000-0001-6967-2735"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gibbons, Phillip B.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134069122","display_name":"Ziyun Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ziyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5134047367"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7727000117301941,"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":0.7727000117301941,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07349999994039536,"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":0.05620000138878822,"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/context","display_name":"Context (archaeology)","score":0.5447999835014343},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5049999952316284},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49970000982284546},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4787999987602234},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4481000006198883},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4101000130176544},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.40540000796318054},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.3901999890804291}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6018999814987183},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5049999952316284},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4787999987602234},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4481000006198883},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3950999975204468},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.37700000405311584},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3077999949455261},{"id":"https://openalex.org/C21099817","wikidata":"https://www.wikidata.org/wiki/Q7631721","display_name":"Subnet","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.15622","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15622","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.15622","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15622","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Language-aligned":[0],"vision":[1,67],"foundation":[2],"models":[3,156,162],"(VFMs)":[4],"enable":[5,86],"versatile":[6],"visual":[7],"understanding":[8],"for":[9,33],"always-on":[10],"contextual":[11],"AI,":[12],"but":[13],"their":[14],"deployment":[15],"on":[16,45,62,99,124,146,151],"edge":[17],"devices":[18],"is":[19,54,64],"hindered":[20],"by":[21,140,171],"strict":[22],"latency":[23],"and":[24,48,127,148],"power":[25],"constraints.":[26],"We":[27],"present":[28],"AdaVFM,":[29],"an":[30],"adaptive":[31],"framework":[32],"efficient":[34,112],"on-device":[35],"inference":[36],"of":[37,58,157],"language-aligned":[38,82],"VFMs":[39],"that":[40,55,131],"dynamically":[41],"adjusts":[42],"computation":[43],"based":[44],"scene":[46],"context":[47],"task":[49],"complexity.":[50],"Our":[51],"key":[52],"insight":[53],"the":[56,81,100,154],"effect":[57],"model":[59,96,113],"size":[60],"reduction":[61],"performance":[63],"task-dependent":[65],"in":[66,144],"applications,":[68],"motivating":[69],"a":[70,106],"runtime-adaptive":[71],"execution":[72,89],"strategy.":[73],"AdaVFM":[74,132,166],"integrates":[75],"neural":[76],"architecture":[77],"search":[78],"(NAS)":[79],"into":[80],"VFM":[83,159],"backbone":[84],"to":[85,142,173],"lightweight":[87],"subnet":[88],"during":[90],"runtime.":[91],"A":[92],"multimodal":[93],"large":[94],"language":[95],"(LLM)":[97],"deployed":[98],"cloud":[101],"enables":[102],"runtime":[103],"control":[104],"with":[105,163],"context-aware":[107],"agent.":[108],"This":[109],"synergy":[110],"allows":[111],"adaptation":[114],"under":[115],"diverse":[116],"conditions":[117],"while":[118],"maintaining":[119],"strong":[120],"accuracy.":[121],"Extensive":[122],"experiments":[123],"zero-shot":[125],"classification":[126],"open-vocabulary":[128],"segmentation":[129],"demonstrate":[130],"achieves":[133],"state-of-the-art":[134],"accuracy-efficiency":[135],"trade-offs,":[136],"surpassing":[137],"prior":[138],"baselines":[139],"up":[141,172],"$7.9\\%$":[143],"acc@1":[145],"IN1K":[147],"$5.2\\%$":[149],"mIoU":[150],"ADE20K":[152],"over":[153],"best":[155],"comparable":[158],"sizes.":[160],"For":[161],"similar":[164],"accuracy,":[165],"further":[167],"reduces":[168],"average":[169],"FLOPs":[170],"$77.9\\%$.":[174]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2026-04-21T00:00:00"}