{"id":"https://openalex.org/W7126074094","doi":"https://doi.org/10.48550/arxiv.2601.20430","title":"Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding","display_name":"Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7126074094","doi":"https://doi.org/10.48550/arxiv.2601.20430"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.20430","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.20430","pdf_url":"https://arxiv.org/pdf/2601.20430","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.20430","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068313625","display_name":"Haoyu Cao","orcid":"https://orcid.org/0000-0002-3789-9705","observed_orcids":["https://orcid.org/0000-0002-3789-9705"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Haoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022465137","display_name":"Kun Yin","orcid":"https://orcid.org/0000-0001-6300-6985","observed_orcids":["https://orcid.org/0000-0001-6300-6985"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124067625","display_name":"Yunfei Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yunfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124220501","display_name":"Bing Liu","orcid":"https://orcid.org/0000-0002-5965-5576","observed_orcids":["https://orcid.org/0000-0002-5965-5576"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Bing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120967337","display_name":"Zhongpeng Cai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Zhongpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127896979","display_name":"Xiaotian Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiaotian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124179725","display_name":"Huang Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124242226","display_name":"Xin Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084063805","display_name":"Yinsong Liu","orcid":"https://orcid.org/0000-0003-1073-3147","observed_orcids":["https://orcid.org/0000-0003-1073-3147","https://orcid.org/0009-0008-2842-7256"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yinsong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016912950","display_name":"Deqiang Jiang","orcid":"https://orcid.org/0000-0003-3987-2431","observed_orcids":["https://orcid.org/0000-0003-3987-2431"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Deqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140179585","display_name":"Xing Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124132676","display_name":"Yunsheng Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yunsheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124153656","display_name":"Qianyu Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Qianyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124161647","display_name":"Antai Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Antai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045688041","display_name":"Yanzhen Liao","orcid":"https://orcid.org/0009-0008-2872-6176","observed_orcids":["https://orcid.org/0009-0008-2872-6176"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Yanzhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051368188","display_name":"Yanqiu Qu","orcid":"https://orcid.org/0009-0001-2092-9031","observed_orcids":["https://orcid.org/0009-0001-2092-9031"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu, Yanqiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121778826","display_name":"Haodong Lin","orcid":"https://orcid.org/0009-0000-8976-1161","observed_orcids":["https://orcid.org/0009-0000-8976-1161","https://orcid.org/0009-0005-3200-190X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Haodong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017773875","display_name":"Chengxu He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Chengxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051181135","display_name":"Shuangyin Liu","orcid":"https://orcid.org/0000-0002-4068-1096","observed_orcids":["https://orcid.org/0000-0002-4068-1096"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shuangyin","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":false,"cited_by_count":0,"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":1.0,"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":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/document-parsing","display_name":"document parsing","score":0.9890000224113464},{"id":"https://openalex.org/keywords/layout-analysis","display_name":"layout analysis","score":0.5720000267028809},{"id":"https://openalex.org/keywords/table-recognition","display_name":"table recognition","score":0.5979999899864197},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.6639999747276306},{"id":"https://openalex.org/keywords/document-understanding","display_name":"document understanding","score":0.328000009059906},{"id":"https://openalex.org/keywords/multilingual-text-recognition","display_name":"multilingual text recognition","score":0.7179999947547913},{"id":"https://openalex.org/keywords/handwriting-recognition","display_name":"handwriting recognition","score":0.6629999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353000283241272},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7146999835968018},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6057999730110168},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5522000193595886},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5230000019073486},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4896000027656555},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3885999917984009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37279999256134033},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.30970001220703125},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25110000371932983},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.20430","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.20430","pdf_url":"https://arxiv.org/pdf/2601.20430","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.2601.20430","doi":"https://doi.org/10.48550/arxiv.2601.20430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.20430","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:2601.20430","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.20430","pdf_url":"https://arxiv.org/pdf/2601.20430","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7138414934","https://openalex.org/W7129180464","https://openalex.org/W7170068796","https://openalex.org/W7083843687","https://openalex.org/W7127910948","https://openalex.org/W7208714546","https://openalex.org/W4415854763","https://openalex.org/W7201878258","https://openalex.org/W7203447186","https://openalex.org/W7165729524"],"abstract_inverted_index":{"This":[0,90],"paper":[1],"presents":[2],"Youtu-Parsing,":[3],"an":[4,136],"efficient":[5],"and":[6,44,50,65,100,162,177,193,202],"versatile":[7],"document":[8,32,154,207],"parsing":[9],"model":[10,40,167],"designed":[11],"for":[12,41,104,128,205],"high-performance":[13],"content":[14,126],"extraction.":[15],"The":[16,68],"architecture":[17],"employs":[18],"a":[19,25,36,55,87,93,150],"native":[20],"Vision":[21],"Transformer":[22],"(ViT)":[23],"featuring":[24],"dynamic-resolution":[26],"visual":[27],"encoder":[28],"to":[29,75,133,145],"extract":[30],"shared":[31],"features,":[33],"coupled":[34],"with":[35],"prompt-guided":[37],"Youtu-LLM-2B":[38],"language":[39],"layout":[42],"analysis":[43],"region-prompted":[45,118],"decoding.":[46,147],"Leveraging":[47],"this":[48],"decoupled":[49],"feature-reusable":[51],"framework,":[52],"we":[53],"introduce":[54],"high-parallelism":[56],"decoding":[57,99],"strategy":[58,71,123],"comprising":[59],"two":[60],"core":[61],"components:":[62],"token":[63,69],"parallelism":[64,70,122],"query":[66,121],"parallelism.":[67],"concurrently":[72],"generates":[73],"up":[74],"64":[76],"candidate":[77],"tokens":[78],"per":[79],"inference":[80],"step,":[81],"which":[82],"are":[83],"subsequently":[84],"validated":[85],"through":[86],"verification":[88],"mechanism.":[89],"approach":[91],"yields":[92],"5--11x":[94],"speedup":[95],"over":[96],"traditional":[97],"autoregressive":[98],"is":[101],"particularly":[102],"well-suited":[103],"highly":[105],"structured":[106],"scenarios,":[107],"such":[108],"as":[109],"table":[110],"recognition.":[111],"To":[112],"further":[113],"exploit":[114],"the":[115,120,166,191],"advantages":[116],"of":[117,153],"decoding,":[119],"enables":[124],"simultaneous":[125],"prediction":[127],"multiple":[129],"bounding":[130],"boxes":[131],"(up":[132],"five),":[134],"providing":[135],"additional":[137],"2x":[138],"acceleration":[139],"while":[140],"maintaining":[141],"output":[142],"quality":[143],"equivalent":[144],"standard":[146],"Youtu-Parsing":[148,184,197],"encompasses":[149],"diverse":[151],"range":[152],"elements,":[155],"including":[156],"text,":[157,176],"formulas,":[158],"tables,":[159],"charts,":[160],"seals,":[161],"hierarchical":[163],"structures.":[164],"Furthermore,":[165],"exhibits":[168],"strong":[169],"robustness":[170],"when":[171],"handling":[172],"rare":[173],"characters,":[174],"multilingual":[175],"handwritten":[178],"content.":[179],"Extensive":[180],"evaluations":[181],"demonstrate":[182],"that":[183],"achieves":[185],"state-of-the-art":[186],"(SOTA)":[187],"performance":[188],"on":[189],"both":[190],"OmniDocBench":[192],"olmOCR-bench":[194],"benchmarks.":[195],"Overall,":[196],"demonstrates":[198],"significant":[199],"experimental":[200],"value":[201],"practical":[203],"utility":[204],"large-scale":[206],"intelligence":[208],"applications.":[209]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-30T00:00:00"}