{"id":"https://openalex.org/W4409366125","doi":"https://doi.org/10.1609/aaai.v39i9.33076","title":"DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming","display_name":"DocKylin: A Large Multimodal Model for Visual Document Understanding with Efficient Visual Slimming","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409366125","doi":"https://doi.org/10.1609/aaai.v39i9.33076"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i9.33076","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i9.33076","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/33076/35231","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/33076/35231","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115597371","display_name":"Jiaxin Zhang","orcid":"https://orcid.org/0000-0001-8585-9006"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaxin Zhang","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022094369","display_name":"Wentao Yang","orcid":"https://orcid.org/0000-0001-7712-822X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wentao Yang","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060021391","display_name":"Songxuan Lai","orcid":"https://orcid.org/0000-0002-0009-0566"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songxuan Lai","raw_affiliation_strings":["Huawei Cloud"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101236570","display_name":"Zecheng Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zecheng Xie","raw_affiliation_strings":["Huawei Cloud"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Cloud","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080674767","display_name":"Lianwen Jin","orcid":"https://orcid.org/0000-0002-5456-0957"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianwen Jin","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5115597371"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":1.9136,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85819071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"39","issue":"9","first_page":"9923","last_page":"9932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9904000163078308,"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":0.9904000163078308,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9585999846458435,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9373999834060669,"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/computer-science","display_name":"Computer science","score":0.5235036015510559},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3492389917373657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5235036015510559},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3492389917373657}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v39i9.33076","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i9.33076","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/33076/35231","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/33076","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/33076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i9.33076","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i9.33076","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/33076/35231","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5270964542","display_name":null,"funder_award_id":"62441604","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6561198578","display_name":null,"funder_award_id":"62476093","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409366125.pdf","grobid_xml":"https://content.openalex.org/works/W4409366125.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Current":[0],"multimodal":[1],"large":[2],"language":[3],"models":[4],"(MLLMs)":[5],"face":[6],"significant":[7],"challenges":[8],"in":[9,97],"visual":[10,56,82,145],"document":[11,27],"understanding":[12],"(VDU)":[13],"tasks":[14],"due":[15],"to":[16,52,66,109,129,139],"the":[17,63,87,114,157],"high":[18,33],"resolution,":[19],"dense":[20],"text,":[21],"and":[22,61,89,136,156],"complex":[23],"layouts":[24],"typical":[25],"of":[26,35,55,116,159],"images.":[28],"These":[29],"characteristics":[30],"demand":[31],"a":[32,77,122,142],"level":[34],"detail":[36,46],"perception":[37,47],"ability":[38,65],"from":[39],"MLLMs.":[40],"While":[41],"increasing":[42,58,113],"input":[43],"resolution":[44],"improves":[45],"capability,":[48],"it":[49],"also":[50],"leads":[51],"longer":[53],"sequences":[54],"tokens,":[57],"computational":[59],"costs":[60],"straining":[62],"models'":[64],"handle":[67],"long":[68],"contexts.":[69],"To":[70],"address":[71],"these":[72],"challenges,":[73],"we":[74,120],"introduce":[75,101],"DocKylin,":[76],"document-centric":[78],"MLLM":[79],"that":[80],"performs":[81],"content":[83],"slimming":[84],"at":[85],"both":[86],"pixel":[88],"token":[90,94],"levels,":[91],"thereby":[92],"reducing":[93],"sequence":[95],"length":[96],"VDU":[98,154],"scenarios.":[99],"We":[100],"an":[102],"Adaptive":[103],"Pixel":[104],"Slimming":[105,126],"(APS)":[106],"preprocessing":[107],"module":[108,128],"perform":[110],"pixel-level":[111],"slimming,":[112,132],"proportion":[115],"informative":[117],"pixels.":[118],"Moreover,":[119],"propose":[121],"novel":[123],"Dynamic":[124],"Token":[125],"(DTS)":[127],"conduct":[130],"token-level":[131],"filtering":[133],"essential":[134],"tokens":[135],"removing":[137],"others":[138],"adaptively":[140],"create":[141],"more":[143],"compact":[144],"sequence.":[146],"Experiments":[147],"demonstrate":[148],"DocKylin's":[149],"promising":[150],"performance":[151],"across":[152],"various":[153],"benchmarks":[155],"effectiveness":[158],"each":[160],"component.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}