{"id":"https://openalex.org/W7126026301","doi":"https://doi.org/10.48550/arxiv.2601.20552","title":"DeepSeek-OCR 2: Visual Causal Flow","display_name":"DeepSeek-OCR 2: Visual Causal Flow","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7126026301","doi":"https://doi.org/10.48550/arxiv.2601.20552"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.20552","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.20552","pdf_url":"https://arxiv.org/pdf/2601.20552","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":"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/2601.20552","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134544722","display_name":"Haoran Wei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103400799","display_name":"Yaofeng Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yaofeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122952042","display_name":"Yukun Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yukun","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9750999808311462,"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":0.9750999808311462,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.021299999207258224,"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":0.00139999995008111,"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/causal-reasoning","display_name":"causal reasoning","score":0.5199999809265137},{"id":"https://openalex.org/keywords/visual-tokenization","display_name":"visual tokenization","score":0.4399999976158142},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.6679999828338623},{"id":"https://openalex.org/keywords/image-semantics","display_name":"image semantics","score":0.3970000147819519},{"id":"https://openalex.org/keywords/visual-perception","display_name":"visual perception","score":0.6420000195503235},{"id":"https://openalex.org/keywords/positional-encoding","display_name":"positional encoding","score":0.47999998927116394},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"optical character recognition","score":0.5839999914169312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275000214576721},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6748999953269958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6049000024795532},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.57669997215271},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.5591999888420105},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.45399999618530273},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44449999928474426},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4147000014781952},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.34279999136924744},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.31690001487731934},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2775999903678894},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2606000006198883},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.20552","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.20552","pdf_url":"https://arxiv.org/pdf/2601.20552","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.20552","doi":"https://doi.org/10.48550/arxiv.2601.20552","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.20552","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:2601.20552","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.20552","pdf_url":"https://arxiv.org/pdf/2601.20552","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126026301.pdf","grobid_xml":"https://content.openalex.org/works/W7126026301.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7134233028","https://openalex.org/W7080122087","https://openalex.org/W7213493810","https://openalex.org/W7119539169","https://openalex.org/W7202241531","https://openalex.org/W7161714222","https://openalex.org/W4405434026","https://openalex.org/W7160170738","https://openalex.org/W7213946933","https://openalex.org/W7147142768"],"abstract_inverted_index":{"We":[0],"present":[1],"DeepSeek-OCR":[2],"2":[3],"to":[4,35,85,95,101,134],"investigate":[5],"the":[6,87,132],"feasibility":[7],"of":[8,13],"a":[9,30,108,127],"novel":[10,109],"encoder-DeepEncoder":[11],"V2-capable":[12],"dynamically":[14],"reordering":[15],"visual":[16,27,49,98],"tokens":[17,28,99],"upon":[18],"image":[19,113],"semantics.":[20],"Conventional":[21],"vision-language":[22],"models":[23],"(VLMs)":[24],"invariably":[25],"process":[26],"in":[29],"rigid":[31],"raster-scan":[32],"order":[33],"(top-left":[34],"bottom-right)":[36],"with":[37,67,89,131],"fixed":[38],"positional":[39],"encoding":[40],"when":[41],"fed":[42],"into":[43],"LLMs.":[44],"However,":[45],"this":[46,78],"contradicts":[47],"human":[48,70],"perception,":[50],"which":[51],"follows":[52],"flexible":[53],"yet":[54],"semantically":[55],"coherent":[56],"scanning":[57],"patterns":[58],"driven":[59],"by":[60,77],"inherent":[61],"logical":[62],"structures.":[63],"Particularly":[64],"for":[65],"images":[66],"complex":[68],"layouts,":[69],"vision":[71],"exhibits":[72],"causally-informed":[73],"sequential":[74],"processing.":[75],"Inspired":[76],"cognitive":[79],"mechanism,":[80],"DeepEncoder":[81],"V2":[82],"is":[83],"designed":[84],"endow":[86],"encoder":[88],"causal":[90,122],"reasoning":[91,123],"capabilities,":[92],"enabling":[93],"it":[94],"intelligently":[96],"reorder":[97],"prior":[100],"LLM-based":[102],"content":[103],"interpretation.":[104],"This":[105],"work":[106],"explores":[107],"paradigm:":[110],"whether":[111],"2D":[112,137],"understanding":[114],"can":[115],"be":[116],"effectively":[117],"achieved":[118],"through":[119],"two-cascaded":[120],"1D":[121],"structures,":[124],"thereby":[125],"offering":[126],"new":[128],"architectural":[129],"approach":[130],"potential":[133],"achieve":[135],"genuine":[136],"reasoning.":[138],"Codes":[139],"and":[140],"model":[141],"weights":[142],"are":[143],"publicly":[144],"accessible":[145],"at":[146],"http://github.com/deepseek-ai/DeepSeek-OCR-2.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-30T00:00:00"}