{"id":"https://openalex.org/W4416251433","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227736","title":"HyDRA: Hierarchical and Dynamic Rank Adaptation for Mobile Vision Language Model","display_name":"HyDRA: Hierarchical and Dynamic Rank Adaptation for Mobile Vision Language Model","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251433","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227736"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227736","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/A5050645206","display_name":"Yan Xi","orcid":"https://orcid.org/0000-0001-6143-3107"},"institutions":[{"id":"https://openalex.org/I176808543","display_name":"Liaoning Technical University","ror":"https://ror.org/01n2bd587","country_code":"CN","type":"education","lineage":["https://openalex.org/I176808543"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuanhao Xi","raw_affiliation_strings":["Liaoning Technical University,Huludao,China"],"affiliations":[{"raw_affiliation_string":"Liaoning Technical University,Huludao,China","institution_ids":["https://openalex.org/I176808543"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120403235","display_name":"Xiaohuan Bing","orcid":null},"institutions":[{"id":"https://openalex.org/I176808543","display_name":"Liaoning Technical University","ror":"https://ror.org/01n2bd587","country_code":"CN","type":"education","lineage":["https://openalex.org/I176808543"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohuan Bing","raw_affiliation_strings":["Liaoning Technical University,Huludao,China"],"affiliations":[{"raw_affiliation_string":"Liaoning Technical University,Huludao,China","institution_ids":["https://openalex.org/I176808543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010508067","display_name":"Ramin Yahyapour","orcid":"https://orcid.org/0000-0002-9057-4395"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramin Yahyapour","raw_affiliation_strings":["University of Göttingen,Göttingen,Germany"],"affiliations":[{"raw_affiliation_string":"University of Göttingen,Göttingen,Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050645206"],"corresponding_institution_ids":["https://openalex.org/I176808543"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34493861,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8912000060081482,"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":0.8912000060081482,"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":0.017999999225139618,"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":0.01080000028014183,"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/rank","display_name":"Rank (graph theory)","score":0.6079999804496765},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5656999945640564},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5396999716758728},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.5101000070571899},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5011000037193298},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4546999931335449},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.38760000467300415},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.37599998712539673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223999738693237},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6182000041007996},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6079999804496765},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5656999945640564},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5091999769210815},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2858999967575073},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227736","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/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1977556410","https://openalex.org/W2963518342","https://openalex.org/W2979382951","https://openalex.org/W4285294723","https://openalex.org/W4386566659","https://openalex.org/W4389523832","https://openalex.org/W4392172801","https://openalex.org/W4394966885","https://openalex.org/W4396680888","https://openalex.org/W4402670135","https://openalex.org/W4403081466","https://openalex.org/W4403793633","https://openalex.org/W4404356490"],"related_works":[],"abstract_inverted_index":{"Vision":[0],"Language":[1],"Models":[2],"(VLMs)":[3],"have":[4],"undergone":[5],"significant":[6,34],"advancements,":[7],"particularly":[8],"with":[9,54],"the":[10,24,51,148,162,174],"emergence":[11],"of":[12,20,176],"mobile-oriented":[13],"VLMs,":[14],"which":[15,103,131],"offer":[16],"a":[17,33,55,78,105,118,138,165],"wide":[18],"range":[19],"application":[21],"scenarios.":[22],"However,":[23],"substantial":[25],"computational":[26],"requirements":[27],"for":[28,61,90],"training":[29,62],"these":[30],"models":[31],"present":[32],"obstacle":[35],"to":[36,83,112,142],"their":[37],"practical":[38],"application.":[39],"To":[40],"address":[41],"this":[42,73],"issue,":[43],"Low-Rank":[44],"Adaptation":[45],"(LoRA)":[46],"has":[47],"been":[48],"proposed.":[49],"Nevertheless,":[50],"standard":[52],"LoRA":[53],"fixed":[56],"rank":[57,88],"lacks":[58],"sufficient":[59],"capability":[60],"mobile":[63,91],"VLMs":[64],"that":[65,108,121,158],"process":[66],"both":[67],"text":[68],"and":[69,86,127,144],"image":[70],"modalities.":[71],"In":[72,179],"work,":[74],"we":[75],"introduce":[76],"HyDRA,":[77],"parameter-efficient":[79],"fine-tuning":[80,149],"framework":[81,94],"designed":[82],"implement":[84],"hierarchical":[85,101],"dynamic":[87,129],"scheduling":[89],"VLMs.":[92],"This":[93],"incorporates":[95],"two":[96],"essential":[97],"optimization":[98,136],"strategies:":[99],"(1)":[100],"optimization,":[102],"involves":[104],"coarse-grained":[106],"approach":[107],"assigns":[109],"different":[110],"ranks":[111,123,146],"various":[113,169],"layers,":[114,126],"as":[115,117],"well":[116],"fine-grained":[119],"method":[120],"adjusts":[122],"within":[124],"individual":[125],"(2)":[128],"adjustment,":[130],"employs":[132],"an":[133],"end-to-end":[134],"automatic":[135],"using":[137],"lightweight":[139],"performance":[140],"model":[141,170],"determine":[143],"adjust":[145],"during":[147],"process.":[150],"Comprehensive":[151],"experiments":[152],"conducted":[153],"on":[154],"popular":[155],"benchmarks":[156],"demonstrate":[157],"HyDRA":[159],"consistently":[160],"outperforms":[161],"baseline,":[163],"achieving":[164],"4.7%":[166],"improvement":[167],"across":[168],"sizes":[171],"without":[172],"increasing":[173],"number":[175],"trainable":[177],"parameters.":[178],"some":[180],"tasks,":[181],"it":[182],"even":[183],"surpasses":[184],"full-parameter":[185],"fine-tuning.":[186]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}