{"id":"https://openalex.org/W4388555312","doi":"https://doi.org/10.48550/arxiv.2311.04257","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","display_name":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","publication_year":2023,"publication_date":"2023-11-07","ids":{"openalex":"https://openalex.org/W4388555312","doi":"https://doi.org/10.48550/arxiv.2311.04257"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.04257","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.04257","pdf_url":"https://arxiv.org/pdf/2311.04257","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.04257","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005965903","display_name":"Qinghao Ye","orcid":"https://orcid.org/0000-0002-7977-5540"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ye, Qinghao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066544410","display_name":"Haiyang Xu","orcid":"https://orcid.org/0000-0001-9442-5912"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Haiyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091465907","display_name":"Jiabo Ye","orcid":"https://orcid.org/0009-0009-5451-8984"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Jiabo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452477","display_name":"Ming Yan","orcid":"https://orcid.org/0000-0003-4959-8878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Ming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hu, Anwen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Anwen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075202003","display_name":"Haowei Liu","orcid":"https://orcid.org/0000-0002-0439-2692"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Haowei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111800002","display_name":"Qi Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100329252","display_name":"Ji Zhang","orcid":"https://orcid.org/0000-0001-9544-9801"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ji","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620486","display_name":"Fei Huang","orcid":"https://orcid.org/0000-0001-9665-6642"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Fei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057864403","display_name":"Jingren Zhou","orcid":"https://orcid.org/0000-0002-4220-2634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jingren","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5005965903"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":29,"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/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9925000071525574,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.865468442440033},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7988622188568115},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7922009229660034},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6010363698005676},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5485284924507141},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.49020010232925415},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.48654595017433167},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.41140806674957275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35749173164367676},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2978976368904114}],"concepts":[{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.865468442440033},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7988622188568115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922009229660034},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6010363698005676},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5485284924507141},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.49020010232925415},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.48654595017433167},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.41140806674957275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35749173164367676},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2978976368904114},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2311.04257","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.04257","pdf_url":"https://arxiv.org/pdf/2311.04257","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.04257","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.04257","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.04257","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.04257","pdf_url":"https://arxiv.org/pdf/2311.04257","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388555312.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Multi-modal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"have":[5],"demonstrated":[6],"impressive":[7],"instruction":[8],"abilities":[9],"across":[10],"various":[11],"open-ended":[12],"tasks.":[13,48],"However,":[14],"previous":[15],"methods":[16],"primarily":[17],"focus":[18],"on":[19],"enhancing":[20],"multi-modal":[21,30,47,100,128,139],"capabilities.":[22],"In":[23],"this":[24],"work,":[25],"we":[26],"introduce":[27],"a":[28,51,61,80,107,131],"versatile":[29],"large":[31],"language":[32,57],"model,":[33],"mPLUG-Owl2,":[34],"which":[35],"effectively":[36],"leverages":[37],"modality":[38,76,121],"collaboration":[39,77,122],"to":[40,74],"improve":[41],"performance":[42],"in":[43,124,134],"both":[44,96,125],"text":[45,97],"and":[46,78,99,102,127],"mPLUG-Owl2":[49,69,91,112],"utilizes":[50],"modularized":[52],"network":[53],"design,":[54],"with":[55,106],"the":[56,114,120,135],"decoder":[58],"acting":[59],"as":[60],"universal":[62],"interface":[63],"for":[64],"managing":[65],"different":[66],"modalities.":[67],"Specifically,":[68],"incorporates":[70],"shared":[71],"functional":[72],"modules":[73],"facilitate":[75],"introduces":[79],"modality-adaptive":[81],"module":[82],"that":[83,90,118],"preserves":[84],"modality-specific":[85],"features.":[86],"Extensive":[87],"experiments":[88],"reveal":[89],"is":[92,113],"capable":[93],"of":[94,137],"generalizing":[95],"tasks":[98,101],"achieving":[103],"state-of-the-art":[104],"performances":[105],"single":[108],"generic":[109],"model.":[110],"Notably,":[111],"first":[115],"MLLM":[116],"model":[117],"demonstrates":[119],"phenomenon":[123],"pure-text":[126],"scenarios,":[129],"setting":[130],"pioneering":[132],"path":[133],"development":[136],"future":[138],"foundation":[140],"models.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":15}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2023-11-10T00:00:00"}