{"id":"https://openalex.org/W4408399044","doi":"https://doi.org/10.1007/s11263-025-02398-3","title":"Parameter Efficient Fine-Tuning for Multi-modal Generative Vision Models with M\u00f6bius-Inspired Transformation","display_name":"Parameter Efficient Fine-Tuning for Multi-modal Generative Vision Models with M\u00f6bius-Inspired Transformation","publication_year":2025,"publication_date":"2025-03-13","ids":{"openalex":"https://openalex.org/W4408399044","doi":"https://doi.org/10.1007/s11263-025-02398-3"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02398-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02398-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02398-3.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02398-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083020611","display_name":"Haoran Duan","orcid":"https://orcid.org/0000-0001-9956-7020"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoran Duan","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101450937","display_name":"Shuai Shao","orcid":"https://orcid.org/0000-0003-2725-9955"},"institutions":[{"id":"https://openalex.org/I2799725268","display_name":"Manchester Academic Health Science Centre","ror":"https://ror.org/04rrkhs81","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2799725268"]},{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shuai Shao","raw_affiliation_strings":["School of Health Sciences, University of Manchester, Manchester, UK"],"affiliations":[{"raw_affiliation_string":"School of Health Sciences, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I2799725268","https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052525806","display_name":"Bing Zhai","orcid":null},"institutions":[{"id":"https://openalex.org/I32394136","display_name":"Northumbria University","ror":"https://ror.org/049e6bc10","country_code":"GB","type":"education","lineage":["https://openalex.org/I32394136"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bing Zhai","raw_affiliation_strings":["Department of Computer and Information Sciences, Northumbria University, Newcastle Upon Tyne, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Sciences, Northumbria University, Newcastle Upon Tyne, UK","institution_ids":["https://openalex.org/I32394136"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023485103","display_name":"Tejal Shah","orcid":"https://orcid.org/0000-0001-7060-4211"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tejal Shah","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110913124","display_name":"Jungong Han","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jungong Han","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072670483","display_name":"Rajiv Ranjan","orcid":"https://orcid.org/0000-0002-6610-1328"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rajiv Ranjan","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5083020611"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":23.2059,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.99582444,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"133","issue":"7","first_page":"4590","last_page":"4603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9995999932289124,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9980999827384949,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.996399998664856,"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/transformation","display_name":"Transformation (genetics)","score":0.7745014429092407},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7360279560089111},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6602883338928223},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5999761819839478},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5646187663078308},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5110388994216919},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.49590668082237244},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4530486762523651},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36173129081726074},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0853683352470398}],"concepts":[{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.7745014429092407},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7360279560089111},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6602883338928223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5999761819839478},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5646187663078308},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5110388994216919},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.49590668082237244},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4530486762523651},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36173129081726074},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0853683352470398},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-025-02398-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02398-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02398-3.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-025-02398-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02398-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02398-3.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408399044.pdf"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2129069237","https://openalex.org/W2132555007","https://openalex.org/W2423557781","https://openalex.org/W2606722458","https://openalex.org/W2618798060","https://openalex.org/W2619016545","https://openalex.org/W2737258237","https://openalex.org/W2964024144","https://openalex.org/W2964243274","https://openalex.org/W2990138404","https://openalex.org/W3034445277","https://openalex.org/W3034720584","https://openalex.org/W3035574324","https://openalex.org/W3041956526","https://openalex.org/W3096831136","https://openalex.org/W3174770825","https://openalex.org/W3180355996","https://openalex.org/W4205991051","https://openalex.org/W4232886157","https://openalex.org/W4281485151","https://openalex.org/W4285247752","https://openalex.org/W4312635677","https://openalex.org/W4312740349","https://openalex.org/W4312933868","https://openalex.org/W4318751661","https://openalex.org/W4319300158","https://openalex.org/W4380559233","https://openalex.org/W4382766104","https://openalex.org/W4386057725","https://openalex.org/W4386065887","https://openalex.org/W4386071957","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4386076425","https://openalex.org/W4386113271","https://openalex.org/W4386566659","https://openalex.org/W4387158652","https://openalex.org/W4390872477","https://openalex.org/W4390873054","https://openalex.org/W4390873331","https://openalex.org/W4391020683","https://openalex.org/W4393148714","https://openalex.org/W4393153655","https://openalex.org/W4403842319","https://openalex.org/W4404198594","https://openalex.org/W6735913928","https://openalex.org/W6739901393","https://openalex.org/W6743520202","https://openalex.org/W6752910514","https://openalex.org/W6759579507","https://openalex.org/W6762931180","https://openalex.org/W6765714711","https://openalex.org/W6778883912","https://openalex.org/W6779879114","https://openalex.org/W6795288823","https://openalex.org/W6797906067","https://openalex.org/W6851592950","https://openalex.org/W6853096648","https://openalex.org/W6853251322"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"rapid":[2],"development":[3,59],"of":[4,25,60,79],"multimodal":[5,27],"generative":[6,30,172],"vision":[7],"models":[8,35],"has":[9,103],"drawn":[10],"scientific":[11],"curiosity.":[12],"Notable":[13],"advancements,":[14],"such":[15,64],"as":[16,65,92],"OpenAI\u2019s":[17],"ChatGPT":[18],"and":[19,47,70,120,141,158],"Stable":[20],"Diffusion,":[21],"demonstrate":[22],"the":[23,58],"potential":[24],"combining":[26],"data":[28,48,148],"for":[29,170],"content.":[31],"Nonetheless,":[32],"customising":[33],"these":[34,112],"to":[36,44,145],"specific":[37],"domains":[38],"or":[39],"tasks":[40],"is":[41,153],"challenging":[42],"due":[43],"computational":[45],"costs":[46],"requirements.":[49],"Conventional":[50],"fine-tuning":[51,62],"methods":[52],"take":[53],"redundant":[54],"processing":[55],"resources,":[56],"motivating":[57],"parameter-efficient":[61,134],"technologies":[63],"adapter":[66],"module,":[67],"low-rank":[68],"factorization":[69],"orthogonal":[71,131],"fine-tuning.":[72,135],"These":[73],"solutions":[74],"selectively":[75],"change":[76],"a":[77,93,116],"subset":[78],"model":[80],"parameters,":[81],"reducing":[82],"learning":[83],"needs":[84],"while":[85],"maintaining":[86],"high-quality":[87],"results.":[88],"Orthogonal":[89],"fine-tuning,":[90],"regarded":[91],"reliable":[94],"technique,":[95],"preserves":[96],"semantic":[97],"linkages":[98],"in":[99,105,133,167],"weight":[100],"space":[101],"but":[102,118],"limitations":[104],"its":[106],"expressive":[107],"powers.":[108],"To":[109],"better":[110],"overcome":[111],"constraints,":[113],"we":[114],"provide":[115],"simple":[117],"innovative":[119],"effective":[121],"transformation":[122],"method":[123],"inspired":[124],"by":[125,155],"M\u00f6bius":[126],"geometry,":[127],"which":[128,152],"replaces":[129],"conventional":[130],"transformations":[132],"This":[136],"strategy":[137],"improved":[138],"fine-tuning\u2019s":[139],"adaptability":[140],"expressiveness,":[142],"allowing":[143],"it":[144],"capture":[146],"more":[147],"patterns.":[149],"Our":[150],"strategy,":[151],"supported":[154],"theoretical":[156],"understanding":[157],"empirical":[159],"validation,":[160],"outperforms":[161],"existing":[162],"approaches,":[163],"demonstrating":[164],"competitive":[165],"improvements":[166],"generation":[168],"quality":[169],"key":[171],"tasks.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}