{"id":"https://openalex.org/W4387559735","doi":"https://doi.org/10.48550/arxiv.2310.05126","title":"UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model","display_name":"UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model","publication_year":2023,"publication_date":"2023-10-08","ids":{"openalex":"https://openalex.org/W4387559735","doi":"https://doi.org/10.48550/arxiv.2310.05126"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.05126","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.05126","pdf_url":"https://arxiv.org/pdf/2310.05126","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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.05126","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091465907","display_name":"Jiabo Ye","orcid":"https://orcid.org/0009-0009-5451-8984"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ye, Jiabo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019498452","display_name":"Anwen Hu","orcid":"https://orcid.org/0000-0001-8839-4996"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Anwen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078053186","display_name":"Haiyang Xu","orcid":"https://orcid.org/0000-0002-9457-4552"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Haiyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005965903","display_name":"Qinghao Ye","orcid":"https://orcid.org/0000-0002-7977-5540"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Qinghao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000844861","display_name":"Ming Yan","orcid":"https://orcid.org/0000-0002-4388-6708"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Ming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656763","display_name":"Guohai Xu","orcid":"https://orcid.org/0000-0002-0063-7410"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Guohai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734065","display_name":"Chenliang Li","orcid":"https://orcid.org/0000-0001-9077-3928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chenliang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102413215","display_name":"Junfeng Tian","orcid":"https://orcid.org/0000-0001-6638-6418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Junfeng","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/A5100329266","display_name":"Ji Zhang","orcid":"https://orcid.org/0000-0002-3835-7975"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ji","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Qin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100507059","display_name":"Liang He","orcid":"https://orcid.org/0000-0001-8032-8767"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Liang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100735835","display_name":"Xin Lin","orcid":"https://orcid.org/0000-0003-3067-4746"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Xin Alex","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","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":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5091465907"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9779000282287598,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9575999975204468,"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/computer-science","display_name":"Computer science","score":0.8850922584533691},{"id":"https://openalex.org/keywords/situated","display_name":"Situated","score":0.786449670791626},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5981602072715759},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5471287965774536},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4991486072540283},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.485566109418869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46661701798439026},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.41499030590057373},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41442549228668213},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3843157887458801},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33171945810317993}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8850922584533691},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.786449670791626},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5981602072715759},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5471287965774536},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4991486072540283},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.485566109418869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46661701798439026},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.41499030590057373},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41442549228668213},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3843157887458801},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33171945810317993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.05126","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.05126","pdf_url":"https://arxiv.org/pdf/2310.05126","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.05126","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.05126","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.05126","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.05126","pdf_url":"https://arxiv.org/pdf/2310.05126","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":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.8700000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387559735.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2066060456","https://openalex.org/W2978017171","https://openalex.org/W4387929264","https://openalex.org/W3105220303","https://openalex.org/W4287903637","https://openalex.org/W2999168658","https://openalex.org/W69308499","https://openalex.org/W3016473712","https://openalex.org/W2901701848","https://openalex.org/W2936497627"],"abstract_inverted_index":{"Text":[0],"is":[1,60,74],"ubiquitous":[2],"in":[3,12,150],"our":[4,143],"visual":[5,94],"world,":[6],"conveying":[7],"crucial":[8],"information,":[9],"such":[10],"as":[11],"documents,":[13,162],"websites,":[14],"and":[15,56,69,96,112,167,171],"everyday":[16],"photographs.":[17],"In":[18],"this":[19],"work,":[20],"we":[21,51,99],"propose":[22],"UReader,":[23],"a":[24,78,87,119],"first":[25],"exploration":[26],"of":[27,48,81,127,153],"universal":[28],"OCR-free":[29],"visually-situated":[30,155],"language":[31,156],"understanding":[32,157],"based":[33],"on":[34,77],"the":[35,43,49,57,93,106,124,131],"Multimodal":[36],"Large":[37],"Language":[38,83],"Model":[39],"(MLLM).":[40],"By":[41],"leveraging":[42],"shallow":[44],"text":[45,95,110],"recognition":[46],"ability":[47],"MLLM,":[50],"only":[52],"finetuned":[53,76],"1.2%":[54],"parameters":[55],"training":[58],"cost":[59],"much":[61],"lower":[62],"than":[63],"previous":[64],"work":[65],"following":[66],"domain-specific":[67],"pretraining":[68],"finetuning":[70],"paradigms.":[71],"Concretely,":[72],"UReader":[73],"jointly":[75],"wide":[79],"range":[80],"Visually-situated":[82],"Understanding":[84],"tasks":[85,104],"via":[86],"unified":[88],"instruction":[89],"format.":[90],"To":[91],"enhance":[92],"semantic":[97],"understanding,":[98],"further":[100],"apply":[101],"two":[102],"auxiliary":[103],"with":[105],"same":[107],"format,":[108],"namely":[109],"reading":[111],"key":[113],"points":[114],"generation":[115],"tasks.":[116],"We":[117],"design":[118],"shape-adaptive":[120],"cropping":[121],"module":[122],"before":[123],"encoder-decoder":[125],"architecture":[126],"MLLM":[128],"to":[129],"leverage":[130],"frozen":[132],"low-resolution":[133],"vision":[134],"encoder":[135],"for":[136],"processing":[137],"high-resolution":[138],"images.":[139],"Without":[140],"downstream":[141],"finetuning,":[142],"single":[144],"model":[145],"achieves":[146],"state-of-the-art":[147],"ocr-free":[148],"performance":[149],"8":[151],"out":[152],"10":[154],"tasks,":[158],"across":[159],"5":[160],"domains:":[161],"tables,":[163],"charts,":[164],"natural":[165],"images,":[166],"webpage":[168],"screenshots.":[169],"Codes":[170],"instruction-tuning":[172],"datasets":[173],"will":[174],"be":[175],"released.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-20T07:46:08.049788","created_date":"2023-10-12T00:00:00"}