{"id":"https://openalex.org/W7125812135","doi":"https://doi.org/10.1109/tpami.2026.3653415","title":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","display_name":"TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document","publication_year":2026,"publication_date":"2026-01-27","ids":{"openalex":"https://openalex.org/W7125812135","doi":"https://doi.org/10.1109/tpami.2026.3653415","pmid":"https://pubmed.ncbi.nlm.nih.gov/41587255"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3653415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3653415","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124013232","display_name":"Yuliang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuliang Liu","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3037-173X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123912629","display_name":"Biao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Yang","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-2621-2020","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124028528","display_name":"Qiang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108461","display_name":"Kingsoft (China)","ror":"https://ror.org/01stnfn33","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210108461"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Liu","raw_affiliation_strings":["Kingsoft, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0002-3786-6476","affiliations":[{"raw_affiliation_string":"Kingsoft, Wuhan, China","institution_ids":["https://openalex.org/I4210108461"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124050408","display_name":"Zhang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Li","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0008-7266-3950","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123910854","display_name":"Zhiyin Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyin Ma","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123918737","display_name":"Shuo Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0001-4491-2568","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123966366","display_name":"Xiang Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Bai","raw_affiliation_strings":["School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0002-3449-5940","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":46.458,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.99817901,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"48","issue":"5","first_page":"6008","last_page":"6019"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.43290001153945923,"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":0.43290001153945923,"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":0.31540000438690186,"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":0.0868000015616417,"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/spotting","display_name":"Spotting","score":0.6794999837875366},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.65829998254776},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6238999962806702},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6075000166893005},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5539000034332275},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4805000126361847},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4519999921321869},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.42100000381469727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8525999784469604},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6794999837875366},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.65829998254776},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6238999962806702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6133000254631042},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6075000166893005},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5539000034332275},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4805000126361847},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4519999921321869},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.42100000381469727},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36730000376701355},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.36230000853538513},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3176000118255615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.266400009393692},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3653415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3653415","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41587255","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41587255","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4189157326","display_name":null,"funder_award_id":"62225603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7708187557","display_name":null,"funder_award_id":"62576147","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,37],"present":[1],"TextMonkey,":[2],"a":[3,139,144,149,158],"large":[4,165],"multimodal":[5,166],"model":[6],"(LMM)":[7],"tailored":[8],"for":[9,168],"text-centric":[10],"tasks.":[11],"Our":[12],"approach":[13],"introduces":[14],"enhancement":[15],"across":[16],"several":[17],"dimensions:":[18],"By":[19],"adopting":[20],"Shifted":[21],"Window":[22],"Attention":[23],"layer,":[24],"we":[25,54,86],"achieve":[26],"cross-window":[27],"connectivity":[28],"at":[29],"higher":[30],"input":[31],"resolutions":[32],"and":[33,45,78,80,104,118,120,130,142],"stabilize":[34],"early":[35],"training;":[36],"hypothesize":[38],"that":[39],"images":[40],"may":[41],"contain":[42],"redundant":[43],"tokens,":[44,53],"by":[46,69],"using":[47],"similarity":[48],"to":[49,74],"filter":[50],"out":[51],"significant":[52],"can":[55],"not":[56],"only":[57],"streamline":[58],"the":[59,65],"token":[60],"length":[61],"but":[62],"also":[63],"enhance":[64,87],"model's":[66,72],"performance.":[67],"Moreover,":[68],"expanding":[70],"our":[71],"capabilities":[73],"encompass":[75],"text":[76,136],"spotting":[77,137],"grounding,":[79],"incorporating":[81],"positional":[82],"information":[83],"into":[84],"responses,":[85],"interpretability.":[88],"Evaluation":[89],"on":[90,147],"12":[91],"benchmarks":[92],"shows":[93],"notable":[94],"improvements:":[95],"5.2%":[96],"in":[97,107,122,134],"Scene":[98],"Text-Centric":[99],"tasks":[100,109,126],"(including":[101],"STVQA,":[102],"TextVQA,":[103],"OCRVQA),":[105],"6.9%":[106],"Document-Oriented":[108],"(such":[110],"as":[111],"DocVQA,":[112],"InfoVQA,":[113],"ChartVQA,":[114],"DeepForm,":[115],"Kleister":[116],"Charity,":[117],"WikiTableQuestions),":[119],"2.8%":[121],"Key":[123],"Information":[124],"Extraction":[125],"(comprising":[127],"FUNSD,":[128],"SROIE,":[129],"POIE).":[131],"It":[132],"outperforms":[133],"scene":[135],"with":[138,157],"10.9%":[140],"increase":[141],"sets":[143],"new":[145],"standard":[146],"OCRBench,":[148],"comprehensive":[150],"benchmark":[151],"consisting":[152],"of":[153,160],"29":[154],"OCR-related":[155],"assessments,":[156],"score":[159],"561,":[161],"surpassing":[162],"previous":[163],"open-sourced":[164],"models":[167],"document":[169],"understanding.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-01-28T00:00:00"}