{"id":"https://openalex.org/W4415540439","doi":"https://doi.org/10.1145/3746027.3761994","title":"LAVA Grand Challenge 2025: Benchmarking Japanese-English Document Understanding with Large Vision-Language Models","display_name":"LAVA Grand Challenge 2025: Benchmarking Japanese-English Document Understanding with Large Vision-Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540439","doi":"https://doi.org/10.1145/3746027.3761994"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3761994","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3761994","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3761994","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109625345","display_name":"Daichi Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daichi Sato","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0007-9194-4021","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043253670","display_name":"Duc Minh Vo","orcid":"https://orcid.org/0000-0003-4839-032X"},"institutions":[{"id":"https://openalex.org/I88773910","display_name":"Intuit (United States)","ror":"https://ror.org/049mrbr98","country_code":"US","type":"company","lineage":["https://openalex.org/I88773910"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Duc Minh Vo","raw_affiliation_strings":["SB Intuitions, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4839-032X","affiliations":[{"raw_affiliation_string":"SB Intuitions, Tokyo, Japan","institution_ids":["https://openalex.org/I88773910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063438958","display_name":"Khan Md. Anwarus Salam","orcid":"https://orcid.org/0000-0002-4579-6992"},"institutions":[{"id":"https://openalex.org/I4210120159","display_name":"SoftBank Group (Japan)","ror":"https://ror.org/02ew2ks20","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210120159"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Khan Md. Anwarus Salam","raw_affiliation_strings":["SoftBank Corp., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4579-6992","affiliations":[{"raw_affiliation_string":"SoftBank Corp., Tokyo, Japan","institution_ids":["https://openalex.org/I4210120159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100915709","display_name":"Hidenori Shoji","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120159","display_name":"SoftBank Group (Japan)","ror":"https://ror.org/02ew2ks20","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210120159"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hidenori Shoji","raw_affiliation_strings":["SoftBank Corp., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0004-8506-2442","affiliations":[{"raw_affiliation_string":"SoftBank Corp., Tokyo, Japan","institution_ids":["https://openalex.org/I4210120159"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuma Matsuoka","orcid":"https://orcid.org/0009-0001-3945-1437"},"institutions":[{"id":"https://openalex.org/I4210120159","display_name":"SoftBank Group (Japan)","ror":"https://ror.org/02ew2ks20","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210120159"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuma Matsuoka","raw_affiliation_strings":["SoftBank Corp., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0001-3945-1437","affiliations":[{"raw_affiliation_string":"SoftBank Corp., Tokyo, Japan","institution_ids":["https://openalex.org/I4210120159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113436628","display_name":"T. Taniguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takara Taniguchi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0002-0546-2178","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaito Baba","orcid":"https://orcid.org/0009-0004-1351-6097"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaito Baba","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0009-0004-1351-6097","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050229964","display_name":"Hideki Nakayama","orcid":"https://orcid.org/0000-0001-8726-2780"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Nakayama","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8726-2780","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"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":0.14512956,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13771","last_page":"13776"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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/benchmarking","display_name":"Benchmarking","score":0.7434999942779541},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6420999765396118},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5224999785423279},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5092999935150146},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4758000075817108},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4551999866962433},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4032000005245209}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7434999942779541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257000207901001},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6420999765396118},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5843999981880188},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5224999785423279},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4551999866962433},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36809998750686646},{"id":"https://openalex.org/C113754120","wikidata":"https://www.wikidata.org/wiki/Q40157","display_name":"Lava","level":3,"score":0.36169999837875366},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C2777362162","wikidata":"https://www.wikidata.org/wiki/Q5594431","display_name":"Grand Challenges","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3761994","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3761994","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3761994","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3761994","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W3120043490","https://openalex.org/W4213213306","https://openalex.org/W4285255856","https://openalex.org/W4382202558","https://openalex.org/W4402716477","https://openalex.org/W4411120511","https://openalex.org/W4412945260","https://openalex.org/W4412945734"],"related_works":[],"abstract_inverted_index":{"The":[0,84,137],"advent":[1],"of":[2,35,62,126,134,148],"Large":[3],"Vision-Language":[4],"Models":[5],"(LVLMs)":[6],"has":[7],"demonstrated":[8],"significant":[9,29],"capabilities":[10,145],"in":[11,22,150,164],"multimodal":[12],"understanding.":[13],"However,":[14],"their":[15],"application":[16],"to":[17,32,109],"complex,":[18],"multi-page":[19,80],"documents,":[20],"particularly":[21],"non-English":[23],"languages":[24],"like":[25],"Japanese,":[26],"remains":[27],"a":[28,67,71,161],"challenge":[30],"due":[31],"the":[33,44,63,99,120,127,131,143],"scarcity":[34],"suitable":[36],"benchmarks.":[37],"To":[38],"address":[39],"this":[40,165],"gap,":[41],"we":[42],"organized":[43],"''Large":[45],"Vision---Language":[46],"Model":[47],"Learning":[48],"and":[49,95,105,115,129,146,159],"Applications":[50],"(LAVA)":[51],"Grand":[52,139],"Challenge''":[53],"at":[54],"ACM":[55],"MultiMedia":[56],"2025.":[57],"We":[58,65,97,117],"present":[59,119],"an":[60,103,124],"overview":[61],"competition.":[64],"designed":[66,108],"novel,":[68],"challenging":[69],"task:":[70],"10-way":[72],"multiple-choice":[73],"Visual":[74],"Question":[75],"Answering":[76],"(VQA)":[77],"task":[78,85],"on":[79],"Japanese":[81],"PDF":[82],"documents.":[83],"demands":[86],"that":[87],"models":[88],"integrate":[89],"information":[90],"across":[91],"multiple":[92],"pages,":[93],"text,":[94],"figures.":[96],"detail":[98],"dataset":[100],"construction,":[101],"including":[102,123],"annotation":[104],"filtering":[106],"process":[107],"ensure":[110],"questions":[111],"are":[112],"visually":[113],"grounded":[114],"non-trivial.":[116],"also":[118],"competition":[121],"results,":[122],"analysis":[125],"leaderboard,":[128],"discuss":[130],"baseline":[132],"performance":[133],"representative":[135],"models.":[136],"LAVA":[138],"Challenge":[140],"highlighted":[141],"both":[142],"current":[144],"limitations":[147],"LVLMs":[149],"practical":[151],"document":[152],"understanding":[153],"scenarios,":[154],"thereby":[155],"stimulating":[156],"future":[157],"research":[158],"providing":[160],"robust":[162],"benchmark":[163],"important":[166],"domain.":[167]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}
