{"id":"https://openalex.org/W4413146877","doi":"https://doi.org/10.1109/cvpr52734.2025.00382","title":"DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding","display_name":"DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413146877","doi":"https://doi.org/10.1109/cvpr52734.2025.00382"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079914128","display_name":"Wenhui Liao","orcid":null},"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":"Wenhui Liao","raw_affiliation_strings":["South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695120","display_name":"Jiapeng Wang","orcid":"https://orcid.org/0000-0003-1498-0305"},"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":"Jiapeng Wang","raw_affiliation_strings":["South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442422","display_name":"Hongliang Li","orcid":"https://orcid.org/0000-0002-9821-0297"},"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":"Hongliang Li","raw_affiliation_strings":["South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373451","display_name":"Chengyu Wang","orcid":"https://orcid.org/0000-0003-1010-9678"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyu Wang","raw_affiliation_strings":["Alibaba Cloud Computing,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054621636","display_name":"Jun Huang","orcid":"https://orcid.org/0000-0002-7706-7081"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Huang","raw_affiliation_strings":["Alibaba Cloud Computing,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Cloud Computing,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110244398","display_name":"Lianwen Jin","orcid":null},"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,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.7111,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98732265,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4038","last_page":"4049"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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":0.9975000023841858,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9527999758720398,"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/extension","display_name":"Extension (predicate logic)","score":0.7867993116378784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7842930555343628},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7526113986968994},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49965405464172363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4030842185020447},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2777824401855469}],"concepts":[{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.7867993116378784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842930555343628},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7526113986968994},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49965405464172363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4030842185020447},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2777824401855469},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00382","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00382","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2075768550","https://openalex.org/W3022218857","https://openalex.org/W2369178846","https://openalex.org/W2390279801","https://openalex.org/W2370289839","https://openalex.org/W4391913857","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Text-rich":[0],"document":[1,74,86],"understanding":[2],"(TDU)":[3],"requires":[4],"comprehensive":[5],"analysis":[6],"of":[7,52,84,89,95,105,113],"documents":[8],"containing":[9],"substantial":[10],"textual":[11],"content":[12,75],"and":[13,64,71,91,108,116,132,144,148],"complex":[14],"layouts.":[15],"While":[16],"Multimodal":[17],"Large":[18],"Language":[19],"Models":[20],"(MLLMs)":[21],"have":[22,99],"achieved":[23],"fast":[24],"progress":[25],"in":[26],"this":[27,43],"domain,":[28],"existing":[29,141],"approaches":[30],"either":[31],"demand":[32],"significant":[33],"computational":[34],"resources":[35],"or":[36],"struggle":[37],"with":[38,125],"effective":[39],"multi-modal":[40,50],"integration.":[41],"In":[42],"paper,":[44],"we":[45,80],"introduce":[46],"DocLayLLM,":[47],"an":[48],"efficient":[49],"extension":[51],"LLMs":[53,78,90],"specifically":[54],"designed":[55],"for":[56],"TDU.":[57],"By":[58],"lightly":[59],"integrating":[60],"visual":[61],"patch":[62],"tokens":[63,67],"2D":[65],"positional":[66],"into":[68],"LLMs\u2019":[69],"input":[70],"encoding":[72],"the":[73,77,85,103,111],"using":[76],"themselves,":[79],"fully":[81],"take":[82],"advantage":[83],"comprehension":[87],"capability":[88],"enhance":[92],"their":[93],"perception":[94],"OCR":[96],"information.":[97],"We":[98],"also":[100],"deeply":[101],"considered":[102],"role":[104],"chain-of-thought":[106],"(CoT)":[107],"innovatively":[109],"proposed":[110],"techniques":[112],"CoT":[114,117],"Pre-training":[115],"Annealing.":[118],"Our":[119],"DocLayLLM":[120,139],"can":[121],"achieve":[122],"remarkable":[123],"performances":[124],"lightweight":[126],"training":[127],"settings,":[128],"showcasing":[129],"its":[130],"efficiency":[131],"effectiveness.":[133],"Experimental":[134],"results":[135],"demonstrate":[136],"that":[137],"our":[138],"outperforms":[140],"OCR-dependent":[142],"methods":[143],"OCR-free":[145],"competitors.":[146],"Code":[147],"model":[149],"are":[150],"available":[151],"at":[152],"https://github.com/whlscut/DocLayLLM.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}