{"id":"https://openalex.org/W4417285901","doi":"https://doi.org/10.1109/iccv51701.2025.02040","title":"SmolDocling: An Ultra-Compact Vision-Language Model for End-To-End Multi-Modal Document Conversion","display_name":"SmolDocling: An Ultra-Compact Vision-Language Model for End-To-End Multi-Modal Document Conversion","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417285901","doi":"https://doi.org/10.1109/iccv51701.2025.02040"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.11576","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021157455","display_name":"Ahmed Nassar","orcid":"https://orcid.org/0000-0002-9468-0822"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed Nassar","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061511010","display_name":"Andr\u00e9s Marafioti","orcid":"https://orcid.org/0000-0001-8997-4925"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matteo Omenetti","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107628293","display_name":"Matteo Omenetti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maksym Lysak","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024178356","display_name":"Maksym Lysak","orcid":"https://orcid.org/0000-0002-3723-6960"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolaos Livathinos","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084933934","display_name":"Nikolaos Livathinos","orcid":"https://orcid.org/0000-0001-8513-3491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christoph Auer","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046722997","display_name":"Christoph Auer","orcid":"https://orcid.org/0000-0001-5761-0422"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucas Morin","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005557687","display_name":"Lucas Morin","orcid":"https://orcid.org/0000-0002-5829-5118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafael Teixeira de Lima","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114375423","display_name":"R. Teixeira De Lima","orcid":"https://orcid.org/0000-0001-5545-6513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusik Kim A. Said Gurbuz","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003257064","display_name":"Yusik Kim","orcid":"https://orcid.org/0000-0002-5366-9459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michele Dolfi","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119959084","display_name":"A. Said Gurbuz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter W. J. Staar","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37446071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21972","last_page":"21983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.4620000123977661,"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":0.4620000123977661,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.08229999989271164,"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/T10028","display_name":"Topic Modeling","score":0.06849999725818634,"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/markup-language","display_name":"Markup language","score":0.7538999915122986},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5640000104904175},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5508999824523926},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.510699987411499},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.43309998512268066},{"id":"https://openalex.org/keywords/document-type-definition","display_name":"Document type definition","score":0.3792000114917755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047999739646912},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.7538999915122986},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5640000104904175},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5508999824523926},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.510699987411499},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4823000133037567},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C84314905","wikidata":"https://www.wikidata.org/wiki/Q212327","display_name":"Document type definition","level":4,"score":0.3792000114917755},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34850001335144043},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2953999936580658},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C72773152","wikidata":"https://www.wikidata.org/wiki/Q5287629","display_name":"Document layout analysis","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.11576","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11576","pdf_url":"https://arxiv.org/pdf/2503.11576","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.11576","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.11576","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.11576","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11576","pdf_url":"https://arxiv.org/pdf/2503.11576","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"SmolDocling,":[2],"an":[3,59],"ultra-compact":[4],"vision-language":[5,77],"model":[6,12,166],"targeting":[7],"end-to-end":[8,60],"document":[9,71,86,103],"conversion.":[10],"Our":[11],"comprehensively":[13],"processes":[14],"entire":[15],"pages":[16],"by":[17],"generating":[18],"DocTags,":[19],"a":[20,74,99],"new":[21],"universal":[22],"markup":[23],"format":[24],"that":[25,39,48,143,151],"captures":[26],"all":[27],"page":[28],"elements":[29,72],"in":[30,73,83,158],"their":[31],"full":[32],"context":[33],"with":[34,146],"location.":[35],"Unlike":[36],"existing":[37],"approaches":[38],"rely":[40,49],"on":[41,50,123],"large":[42],"foundational":[43],"models,":[44,56],"or":[45],"ensemble":[46],"solutions":[47],"handcrafted":[51],"pipelines":[52],"of":[53,70,102],"multiple":[54],"specialized":[55],"SmolDocling":[57,79,144],"offers":[58],"conversion":[61],"for":[62,133],"accurately":[63],"capturing":[64],"content,":[65],"structure":[66],"and":[67,96,113,137],"spatial":[68],"location":[69],"256M":[75],"parameters":[76],"model.":[78],"exhibits":[80],"robust":[81],"performance":[82],"correctly":[84],"reproducing":[85],"features":[87],"such":[88],"as":[89],"code":[90,138],"listings,":[91],"tables,":[92,135],"equations,":[93,136],"charts,":[94,134],"lists,":[95],"more":[97],"across":[98],"diverse":[100],"range":[101],"types":[104],"including":[105],"business":[106],"documents,":[107],"academic":[108],"papers,":[109],"technical":[110],"reports,":[111],"patents,":[112],"forms":[114],"--":[115],"significantly":[116],"extending":[117],"beyond":[118],"the":[119],"commonly":[120],"observed":[121],"focus":[122],"scientific":[124],"papers.":[125],"Additionally,":[126],"we":[127],"contribute":[128],"novel":[129],"publicly":[130,173],"sourced":[131],"datasets":[132,170],"recognition.":[139],"Experimental":[140],"results":[141],"demonstrate":[142],"competes":[145],"other":[147],"Vision":[148],"Language":[149],"Models":[150],"are":[152],"up":[153],"to":[154],"27":[155],"times":[156],"larger":[157],"size,":[159],"while":[160],"reducing":[161],"computational":[162],"requirements":[163],"substantially.":[164],"The":[165],"is":[167],"currently":[168],"available,":[169],"will":[171],"be":[172],"available":[174],"soon.":[175]},"counts_by_year":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}