{"id":"https://openalex.org/W7214916581","doi":"https://doi.org/10.48550/arxiv.2609.36136","title":"Xiaomi-OCR-0 Technical Report","display_name":"Xiaomi-OCR-0 Technical Report","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214916581","doi":"https://doi.org/10.48550/arxiv.2609.36136"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.36136","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36136","pdf_url":"https://arxiv.org/pdf/2609.36136","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":"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/2609.36136","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153560752","display_name":"Xin Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153667290","display_name":"Anan Du","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Anan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132801349","display_name":"Feng Feng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153559135","display_name":"Pei Fu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Pei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153648274","display_name":"Jian Luan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luan, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031597824","display_name":"Longwei Xu","orcid":"https://orcid.org/0009-0005-6131-0015","observed_orcids":["https://orcid.org/0009-0005-6131-0015"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Longwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153566091","display_name":"Shaojie Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shaojie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153569890","display_name":"Hang Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153663191","display_name":"Heng Qu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu, Heng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5153667558","display_name":"Cheng Tan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Cheng","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":1,"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":0.9951000213623047,"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":0.9951000213623047,"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":0.004000000189989805,"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":0.00019999999494757503,"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-parsing","display_name":"document parsing","score":0.6959999799728394},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"optical character recognition","score":0.9200000166893005},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8970000147819519},{"id":"https://openalex.org/keywords/document-image-understanding","display_name":"document image understanding","score":0.4429999887943268}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.703499972820282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6686999797821045},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5831999778747559},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5462999939918518},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4943999946117401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48249998688697815},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.43230000138282776},{"id":"https://openalex.org/C182449105","wikidata":"https://www.wikidata.org/wiki/Q3099732","display_name":"Technical report","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37290000915527344},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3075999915599823},{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.26330000162124634}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.36136","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36136","pdf_url":"https://arxiv.org/pdf/2609.36136","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.36136","doi":"https://doi.org/10.48550/arxiv.2609.36136","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.36136","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.36136","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36136","pdf_url":"https://arxiv.org/pdf/2609.36136","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":"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/W7214916581.pdf","grobid_xml":"https://content.openalex.org/works/W7214916581.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W2936135081","https://openalex.org/W2997154779","https://openalex.org/W3109569233","https://openalex.org/W3120043490","https://openalex.org/W4213213306","https://openalex.org/W4285255856","https://openalex.org/W4312233877","https://openalex.org/W4391631327","https://openalex.org/W4395443875","https://openalex.org/W4403924796","https://openalex.org/W4404312770","https://openalex.org/W4405399726","https://openalex.org/W4407794264","https://openalex.org/W4413155934","https://openalex.org/W4414458387","https://openalex.org/W4415189326","https://openalex.org/W4415844479","https://openalex.org/W4415854763","https://openalex.org/W4416055645","https://openalex.org/W4416060568","https://openalex.org/W4416138682","https://openalex.org/W4416689650","https://openalex.org/W4416780398","https://openalex.org/W4417006752","https://openalex.org/W4417298651","https://openalex.org/W6891822422","https://openalex.org/W6948369276","https://openalex.org/W7077911270","https://openalex.org/W7083286904","https://openalex.org/W7106785538","https://openalex.org/W7117300705","https://openalex.org/W7119523234","https://openalex.org/W7120003758","https://openalex.org/W7125207973","https://openalex.org/W7126026301","https://openalex.org/W7126074094","https://openalex.org/W7126256595","https://openalex.org/W7126279814","https://openalex.org/W7127380112","https://openalex.org/W7127910948","https://openalex.org/W7133331632","https://openalex.org/W7135036919","https://openalex.org/W7138183912","https://openalex.org/W7140170375","https://openalex.org/W7148616083","https://openalex.org/W7151400241","https://openalex.org/W7161016653","https://openalex.org/W7162682230","https://openalex.org/W7163350220","https://openalex.org/W7165678383","https://openalex.org/W7165691354","https://openalex.org/W7166701728","https://openalex.org/W7166845830","https://openalex.org/W7167100696","https://openalex.org/W7167604932","https://openalex.org/W7167607154","https://openalex.org/W7168313909","https://openalex.org/W7168766369","https://openalex.org/W7203447186","https://openalex.org/W7213957640"],"related_works":["https://openalex.org/W7138183912","https://openalex.org/W7168766369","https://openalex.org/W7163350220","https://openalex.org/W7128395797","https://openalex.org/W7080122087","https://openalex.org/W7168313909","https://openalex.org/W7203761715","https://openalex.org/W4416138682","https://openalex.org/W7208714546","https://openalex.org/W7167607154"],"abstract_inverted_index":{"Compact":[0],"OCR-specific":[1],"vision-language":[2],"models":[3],"achieve":[4],"strong":[5],"document":[6,29,113],"parsing":[7,30,104],"performance,":[8],"but":[9],"often":[10],"rely":[11],"on":[12,18,76,79,84],"costly":[13],"supervision":[14,108],"and":[15,31,52,68,82],"focus":[16],"primarily":[17],"visual-text":[19],"reconstruction.":[20],"We":[21,34],"introduce":[22],"Xiaomi-OCR-0,":[23],"a":[24],"unified":[25],"0.8B":[26],"model":[27],"for":[28,112],"OCR-centric":[32,39,106],"understanding.":[33],"build":[35],"an":[36,42,88],"approximately":[37],"170M-sample":[38],"corpus":[40],"using":[41],"automated":[43],"data":[44],"engine":[45],"that":[46],"combines":[47,62],"expert":[48],"consensus,":[49],"render-based":[50],"verification,":[51],"targeted":[53],"synthesis.":[54],"Starting":[55],"from":[56],"Qwen3.5-0.8B,":[57],"our":[58],"progressive":[59],"training":[60],"recipe":[61],"Q-Mask-based":[63],"text":[64],"anchoring,":[65],"continued":[66],"pretraining,":[67],"mixed-task":[69],"reinforcement":[70],"learning":[71],"(Mix-RL).":[72],"Xiaomi-OCR-0":[73],"achieves":[74],"95.24":[75],"Real5-OmniDocBench,":[77],"96.83":[78],"OmniDocBench":[80],"v1.6,":[81],"87.94":[83],"Wild-OmniDocBench,":[85],"while":[86],"reaching":[87],"average":[89],"score":[90],"of":[91],"83.2":[92],"across":[93],"five":[94],"OCR-oriented":[95],"VQA":[96],"benchmarks.":[97],"Ablations":[98],"further":[99],"show":[100],"that,":[101],"with":[102],"sufficient":[103],"training,":[105],"understanding":[107],"provides":[109],"additional":[110],"gains":[111],"parsing.":[114],"Homepage:":[115],"https://huggingface.co/spaces/SeerRay-Lab/Xiaomi-OCR-0.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}