{"id":"https://openalex.org/W4414943736","doi":"https://doi.org/10.1109/iccv51701.2025.01738","title":"Sparse Fine-Tuning of Transformers for Generative Tasks","display_name":"Sparse Fine-Tuning of Transformers for Generative Tasks","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414943736","doi":"https://doi.org/10.1109/iccv51701.2025.01738"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.10855","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100344463","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0002-6857-7696"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Chen","raw_affiliation_strings":["Purdue University,IN,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,IN,USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001511524","display_name":"Jingxi Yu","orcid":"https://orcid.org/0000-0001-8772-9299"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingxi Yu","raw_affiliation_strings":["Purdue University,IN,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,IN,USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063383026","display_name":"Zichen Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zichen Miao","raw_affiliation_strings":["Purdue University,IN,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,IN,USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101992408","display_name":"Qiang Qiu","orcid":"https://orcid.org/0000-0003-2610-3502"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Qiu","raw_affiliation_strings":["Purdue University,IN,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,IN,USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27173913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18703","last_page":"18713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9272000193595886,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9272000193595886,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/transformer","display_name":"Transformer","score":0.6144000291824341},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48899999260902405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43549999594688416},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.43070000410079956},{"id":"https://openalex.org/keywords/k-svd","display_name":"K-SVD","score":0.41940000653266907},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.40459999442100525},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.3968000113964081},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.37860000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7479000091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6288999915122986},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6144000291824341},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.43070000410079956},{"id":"https://openalex.org/C154771677","wikidata":"https://www.wikidata.org/wiki/Q17098361","display_name":"K-SVD","level":3,"score":0.41940000653266907},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3621000051498413},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.36070001125335693},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.29159998893737793},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2720000147819519}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.10855","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.10855","pdf_url":"https://arxiv.org/pdf/2507.10855","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"},{"id":"doi:10.48550/arxiv.2507.10855","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.10855","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.10855","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.10855","pdf_url":"https://arxiv.org/pdf/2507.10855","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"pre-trained":[1],"transformers":[2],"have":[3],"revolutionized":[4],"artificial":[5],"intelligence":[6],"across":[7],"various":[8,194],"domains,":[9],"and":[10,55,104],"fine-tuning":[11,34,70,196],"remains":[12],"the":[13,25,36,58,102,124,130,134,156,166,172,182],"dominant":[14],"approach":[15,170],"for":[16,108],"adapting":[17],"these":[18],"models":[19],"to":[20,24,51,61,111,129],"downstream":[21,112],"tasks":[22],"due":[23],"cost":[26],"of":[27,45,85,101,120,126,138,158,168,189],"training":[28],"from":[29],"scratch.":[30],"However,":[31],"in":[32,171],"existing":[33],"methods,":[35],"updated":[37,131],"representations":[38],"are":[39,79],"formed":[40],"as":[41,81,97,118],"a":[42,69,82,186],"dense":[43],"combination":[44,84,188],"modified":[46],"parameters,":[47],"making":[48],"it":[49],"challenging":[50],"interpret":[52],"their":[53],"contributions":[54],"understand":[56],"how":[57],"model":[59],"adapts":[60],"new":[62],"tasks.":[63,113],"In":[64],"this":[65],"work,":[66],"we":[67,141,164],"introduce":[68],"framework":[71],"inspired":[72],"by":[73,151],"sparse":[74,83,139,187],"coding,":[75],"where":[76,177],"fine-tuned":[77],"features":[78],"represented":[80],"basic":[86],"elements,":[87],"i.e.,":[88],"feature":[89,93,160,190],"dictionary":[90,94,161,191],"atoms.":[91,162],"The":[92],"atoms":[95,106],"function":[96],"fundamental":[98],"building":[99],"blocks":[100],"representation,":[103],"tuning":[105],"allows":[107],"seamless":[109],"adaptation":[110],"Sparse":[114],"coefficients":[115],"then":[116],"serve":[117],"indicators":[119],"atom":[121,128,135],"importance,":[122],"identifying":[123],"contribution":[125],"each":[127],"representation.":[132],"Leveraging":[133],"selection":[136],"capability":[137],"coefficients,":[140],"first":[142],"demonstrate":[143],"that":[144],"our":[145,169,178],"method":[146,179],"enhances":[147],"image":[148],"editing":[149],"performance":[150],"improving":[152],"text":[153],"alignment":[154],"through":[155],"removal":[157],"unimportant":[159],"Additionally,":[163],"validate":[165],"effectiveness":[167],"text-to-image":[173],"concept":[174,184],"customization":[175],"task,":[176],"efficiently":[180],"constructs":[181],"target":[183],"using":[185],"atoms,":[192],"outperforming":[193],"baseline":[195],"methods.":[197]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}