{"id":"https://openalex.org/W7138423787","doi":"https://doi.org/10.1609/aaai.v40i7.37427","title":"LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation","display_name":"LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138423787","doi":"https://doi.org/10.1609/aaai.v40i7.37427"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i7.37427","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37427","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37427/41389","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37427/41389","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Weiquan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiquan Huang","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Aoqi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aoqi Wu","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yifan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xufang Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Xufang Luo","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuqing Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Yuqing Yang","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Usman Naseem","orcid":null},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Usman Naseem","raw_affiliation_strings":["Macquarie University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chunyu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Chunyu Wang","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qi Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Qi Dai","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiyang Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Xiyang Dai","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dongdong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Dongdong Chen","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chong Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Chong Luo","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lili Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Lili Qiu","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]},{"author_position":"last","author":{"id":null,"display_name":"Liang Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Hu","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":13,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.8252,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.97293447,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"40","issue":"7","first_page":"5131","last_page":"5139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9229000210762024,"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":0.9229000210762024,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.008799999952316284,"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/T10028","display_name":"Topic Modeling","score":0.008100000210106373,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6934999823570251},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6065999865531921},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.554099977016449},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45399999618530273},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4068000018596649},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.39309999346733093},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3407999873161316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807000279426575},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6934999823570251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6159999966621399},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6065999865531921},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5999000072479248},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.554099977016449},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4068000018596649},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.31279999017715454},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2890999913215637},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2547999918460846},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i7.37427","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37427","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37427/41389","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i7.37427","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i7.37427","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37427/41389","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6001151204109192}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138423787.pdf","grobid_xml":"https://content.openalex.org/works/W7138423787.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"CLIP":[0,69,79,89,97,123,132],"is":[1],"a":[2,12,67,101,107,137],"seminal":[3],"multimodal":[4,170],"model":[5],"that":[6,62],"maps":[7],"images":[8],"and":[9,41,128,152,157,165],"text":[10],"into":[11,66],"shared":[13],"representation":[14],"space":[15],"by":[16,25],"contrastive":[17],"learning":[18],"on":[19,105],"billions":[20],"of":[21,29,45,140],"image\u2013caption":[22,110],"pairs.":[23,111],"Inspired":[24],"the":[26,37,73,85,88,95],"rapid":[27],"progress":[28],"large":[30,117],"language":[31],"models":[32],"(LLMs),":[33],"we":[34,115],"investigate":[35],"how":[36],"superior":[38],"linguistic":[39],"understanding":[40],"broad":[42],"world":[43],"knowledge":[44],"LLMs":[46],"can":[47],"further":[48],"strengthen":[49],"CLIP\u2014particularly":[50],"in":[51],"handling":[52],"long,":[53],"complex":[54],"captions.":[55],"We":[56],"introduce":[57],"an":[58,64],"efficient":[59],"fine-tuning":[60],"framework":[61],"embeds":[63],"LLM":[65,86],"pretrained":[68,96],"while":[70],"incurring":[71],"almost":[72],"same":[74],"training":[75],"cost":[76],"as":[77,126,167],"regular":[78],"fine-tuning.":[80],"Our":[81],"method":[82],"first":[83],"\u201cembedding-izes\u201d":[84],"for":[87,169],"setting,":[90],"then":[91],"couples":[92],"it":[93],"to":[94],"vision":[98],"encoder":[99],"through":[100],"lightweight":[102],"adaptor":[103],"trained":[104],"only":[106],"few":[108],"million":[109],"With":[112],"this":[113],"strategy":[114],"achieve":[116],"performance":[118],"gains\u2014without":[119],"large-scale":[120],"retraining\u2014over":[121],"state-of-the-art":[122],"variants":[124],"such":[125],"EVA02":[127],"SigLIP-2.":[129],"The":[130],"LLM-enhanced":[131],"delivers":[133],"consistent":[134],"improvements":[135],"across":[136],"wide":[138],"spectrum":[139],"downstream":[141],"tasks,":[142],"including":[143],"linear-probe":[144],"classification,":[145],"zero-shot":[146],"image\u2013text":[147],"retrieval":[148],"with":[149],"both":[150],"short":[151],"long":[153],"captions":[154],"(in":[155],"English":[156],"other":[158],"languages),":[159],"zero-shot/supervised":[160],"image":[161],"segmentation,":[162],"object":[163],"detection,":[164],"used":[166],"tokenizer":[168],"large-model":[171],"benchmarks.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-28T00:00:00"}