{"id":"https://openalex.org/W4386942429","doi":"https://doi.org/10.48550/arxiv.2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","display_name":"KOSMOS-2.5: A Multimodal Literate Model","publication_year":2023,"publication_date":"2023-09-20","ids":{"openalex":"https://openalex.org/W4386942429","doi":"https://doi.org/10.48550/arxiv.2309.11419"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.11419","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.11419","pdf_url":"https://arxiv.org/pdf/2309.11419","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.11419","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031963349","display_name":"Tengchao Lv","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Tengchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067298679","display_name":"Yupan Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yupan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006852343","display_name":"Jingye Chen","orcid":"https://orcid.org/0000-0003-3994-8934","observed_orcids":["https://orcid.org/0000-0003-3994-8934"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jingye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhao, Yuzhong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yuzhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jia, Yilin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Yilin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cui, Lei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113130010","display_name":"Shuming Ma","orcid":"https://orcid.org/0000-0003-1091-1206","observed_orcids":["https://orcid.org/0000-0003-1091-1206"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Shuming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123966441","display_name":"Yaoyao Chang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Yaoyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061624006","display_name":"Shaohan Huang","orcid":"https://orcid.org/0000-0003-4324-6337","observed_orcids":["https://orcid.org/0000-0003-4324-6337"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Shaohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370079","display_name":"Wenhui Wang","orcid":"https://orcid.org/0000-0002-9623-0489","observed_orcids":["https://orcid.org/0000-0002-9623-0489"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenhui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051688016","display_name":"Dong Li","orcid":"https://orcid.org/0000-0002-5815-5924","observed_orcids":["https://orcid.org/0000-0002-5815-5924","https://orcid.org/0000-0002-6202-3879"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034618643","display_name":"Weiyao Luo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Weiyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wu, Shaoxiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Shaoxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101457292","display_name":"Guoxin Wang","orcid":"https://orcid.org/0000-0003-2363-8595","observed_orcids":["https://orcid.org/0000-0003-2363-8595"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Guoxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103551927","display_name":"Cha Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Cha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852","observed_orcids":["https://orcid.org/0000-0002-7810-5852"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Furu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":119,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9785000085830688,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9785000085830688,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.019999999552965164,"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":0.000699999975040555,"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/document-understanding","display_name":"document understanding","score":0.6380000114440918},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.6940000057220459},{"id":"https://openalex.org/keywords/autoregressive-transformer","display_name":"autoregressive transformers","score":0.5849999785423279},{"id":"https://openalex.org/keywords/artificial-general-intelligence","display_name":"artificial general intelligence","score":0.5529999732971191}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433276176452637},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5906676054000854},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5720271468162537},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5305383801460266},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.5278273224830627},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5183828473091125},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4765118658542633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4720229506492615},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.47199347615242004},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4679129719734192},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4667136073112488},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.45560047030448914},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11751455068588257},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06894904375076294},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.11419","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.11419","pdf_url":"https://arxiv.org/pdf/2309.11419","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2309.11419","doi":"https://doi.org/10.48550/arxiv.2309.11419","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.11419","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.11419","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.11419","pdf_url":"https://arxiv.org/pdf/2309.11419","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386942429.pdf","grobid_xml":"https://content.openalex.org/works/W4386942429.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1491389626","https://openalex.org/W2919502278","https://openalex.org/W3120043490","https://openalex.org/W3152774549","https://openalex.org/W3173325518","https://openalex.org/W3206324399","https://openalex.org/W3212748493","https://openalex.org/W4226020328","https://openalex.org/W4287077924","https://openalex.org/W4312233877","https://openalex.org/W4318718936","https://openalex.org/W4320855762","https://openalex.org/W4322718191","https://openalex.org/W4322832305","https://openalex.org/W4323717348","https://openalex.org/W4353113046","https://openalex.org/W4361229539","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4367628410","https://openalex.org/W4376309461","https://openalex.org/W4376312115","https://openalex.org/W4378711593","https://openalex.org/W4382202677","https://openalex.org/W4382490555","https://openalex.org/W4382491206","https://openalex.org/W4382766522","https://openalex.org/W4383604278","https://openalex.org/W4385574407","https://openalex.org/W4386185600","https://openalex.org/W4386228584","https://openalex.org/W4386395705","https://openalex.org/W4388626886","https://openalex.org/W4390137271","https://openalex.org/W4390872747","https://openalex.org/W4391212409","https://openalex.org/W4395022471","https://openalex.org/W4401024018","https://openalex.org/W4402716264","https://openalex.org/W4402716330","https://openalex.org/W4404782234","https://openalex.org/W4405416283","https://openalex.org/W4406489046","https://openalex.org/W4410536678","https://openalex.org/W7125812135","https://openalex.org/W7133185515","https://openalex.org/W7133190063","https://openalex.org/W7133202489","https://openalex.org/W7133231679"],"related_works":["https://openalex.org/W4412887761","https://openalex.org/W4402703998","https://openalex.org/W4387156669","https://openalex.org/W4402754014","https://openalex.org/W4396838021","https://openalex.org/W7118185822","https://openalex.org/W4414582701","https://openalex.org/W4416033858","https://openalex.org/W7169075743","https://openalex.org/W4309953147"],"abstract_inverted_index":{"The":[0],"automatic":[1],"reading":[2,28],"of":[3,29,37,57,121],"text-intensive":[4,30,38],"images":[5],"represents":[6],"a":[7,22,34,89,111,118],"significant":[8],"advancement":[9],"toward":[10],"achieving":[11],"Artificial":[12],"General":[13],"Intelligence":[14],"(AGI).":[15],"In":[16],"this":[17,100],"paper":[18],"we":[19,102],"present":[20],"KOSMOS-2.5,":[21],"multimodal":[23,83],"literate":[24,84,153],"model":[25],"for":[26,105,131,144],"machine":[27],"images.":[31],"Pre-trained":[32],"on":[33,99,136],"large-scale":[35],"corpus":[36,120],"images,":[39],"KOSMOS-2.5":[40,104,135],"excels":[41],"in":[42,78,110],"two":[43,137],"distinct":[44],"yet":[45],"complementary":[46],"transcription":[47],"tasks:":[48],"(1)":[49],"generating":[50],"spatially-aware":[51],"text":[52,58,70,146],"blocks,":[53],"where":[54],"each":[55],"block":[56],"is":[59,86],"assigned":[60],"spatial":[61],"coordinates":[62],"within":[63],"the":[64],"image,":[65],"and":[66,76,95,142,148,182],"(2)":[67],"producing":[68],"structured":[69],"output":[71],"that":[72,166],"captures":[73],"both":[74],"style":[75],"structure":[77],"markdown":[79],"format.":[80],"This":[81],"unified":[82],"capability":[85],"achieved":[87],"through":[88],"shared":[90],"decoder-only":[91],"autoregressive":[92],"Transformer":[93],"architecture":[94],"task-specific":[96],"prompts.":[97],"Building":[98],"foundation,":[101],"fine-tune":[103],"document":[106,112,124],"understanding":[107,113],"tasks,":[108],"resulting":[109],"generalist":[114],"named":[115],"KOSMOS-2.5-CHAT.":[116],"Additionally,":[117],"large":[119],"357.4":[122],"million":[123],"pages":[125],"spanning":[126],"diverse":[127],"domains":[128],"was":[129],"curated":[130],"pre-training.":[132],"We":[133],"evaluate":[134],"newly":[138],"proposed":[139],"benchmarks,":[140],"OCREval":[141],"MarkdownEval,":[143],"document-level":[145],"recognition":[147],"image-to-markdown":[149],"generation,":[150],"demonstrating":[151],"impressive":[152],"capabilities":[154],"comparable":[155,161],"to":[156,162],"GPT-4o.":[157],"KOSMOS-2.5-CHAT":[158],"achieves":[159],"performance":[160],"other":[163],"state-of-the-art":[164],"generalists":[165],"are":[167],"five":[168],"times":[169],"larger":[170],"(1.3B":[171],"vs.":[172],"7B)":[173],"across":[174],"nine":[175],"text-rich":[176],"visual":[177],"question":[178],"answering":[179],"benchmarks.":[180],"Models":[181],"code":[183],"have":[184],"been":[185],"available":[186],"at":[187],"\\url{https://aka.ms/kosmos25}.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":35},{"year":2025,"cited_by_count":46},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-09-22T00:00:00"}