{"id":"https://openalex.org/W7152593955","doi":"https://doi.org/10.1145/3774904.3792793","title":"LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Multilingual Text-Centric VQA","display_name":"LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Multilingual Text-Centric VQA","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152593955","doi":"https://doi.org/10.1145/3774904.3792793"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792793","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792793","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792793","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101522204","display_name":"Jing Huang","orcid":"https://orcid.org/0009-0005-5651-9033"},"institutions":[{"id":"https://openalex.org/I4210135679","display_name":"Antea Group (France)","ror":"https://ror.org/03kfw6k71","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210101086","https://openalex.org/I4210135679"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jing Huang","raw_affiliation_strings":["Ant Digital Technologies, Ant Group, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0005-5651-9033","affiliations":[{"raw_affiliation_string":"Ant Digital Technologies, Ant Group, Singapore, Singapore","institution_ids":["https://openalex.org/I4210135679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111005874","display_name":"Zhiya Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiya Tan","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore and Ant Digital Technologies, Ant Group, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0004-2433-1389","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore and Ant Digital Technologies, Ant Group, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102585315","display_name":"Shutao Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135679","display_name":"Antea Group (France)","ror":"https://ror.org/03kfw6k71","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210101086","https://openalex.org/I4210135679"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Shutao Gong","raw_affiliation_strings":["Ant Digital Technologies, Ant Group, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0009-5643-0441","affiliations":[{"raw_affiliation_string":"Ant Digital Technologies, Ant Group, Changsha, Hunan, China","institution_ids":["https://openalex.org/I4210135679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101775134","display_name":"Fanwei Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135679","display_name":"Antea Group (France)","ror":"https://ror.org/03kfw6k71","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210101086","https://openalex.org/I4210135679"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fanwei Zeng","raw_affiliation_strings":["Ant Digital Technologies, Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-7872-8610","affiliations":[{"raw_affiliation_string":"Ant Digital Technologies, Ant Group, Hangzhou, China","institution_ids":["https://openalex.org/I4210135679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045125183","display_name":"Joey Tianyi Zhou","orcid":"https://orcid.org/0000-0002-4675-7055"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Joey Tianyi Zhou","raw_affiliation_strings":["CFAR, Agency for Science, Technology and Research, Singapore, Singapore and IHPC, Agency for Science, Technology and Research, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4675-7055","affiliations":[{"raw_affiliation_string":"CFAR, Agency for Science, Technology and Research, Singapore, Singapore and IHPC, Agency for Science, Technology and Research, Singapore, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077867418","display_name":"Changtao Miao","orcid":"https://orcid.org/0000-0002-7634-9992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changtao Miao","raw_affiliation_strings":["Ant Group, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-7634-9992","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, Zhejiang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121541012","display_name":"Huazhe Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093609","display_name":"Digital China Health (China)","ror":"https://ror.org/00n49pr77","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093609"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huazhe Tan","raw_affiliation_strings":["Ant Digital Technologies, Ant Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-2154-9679","affiliations":[{"raw_affiliation_string":"Ant Digital Technologies, Ant Group, Beijing, China","institution_ids":["https://openalex.org/I4210093609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081481835","display_name":"Weibin Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135679","display_name":"Antea Group (France)","ror":"https://ror.org/03kfw6k71","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210101086","https://openalex.org/I4210135679"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Weibin Yao","raw_affiliation_strings":["Ant Digital Technologies, Ant Group, Hangzhou, Singapore"],"raw_orcid":"https://orcid.org/0009-0004-1379-1830","affiliations":[{"raw_affiliation_string":"Ant Digital Technologies, Ant Group, Hangzhou, Singapore","institution_ids":["https://openalex.org/I4210135679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101478393","display_name":"Jianshu Li","orcid":"https://orcid.org/0000-0001-8554-6886"},"institutions":[{"id":"https://openalex.org/I4210135679","display_name":"Antea Group (France)","ror":"https://ror.org/03kfw6k71","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210101086","https://openalex.org/I4210135679"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jianshu Li","raw_affiliation_strings":["Ant Digital Technologies, Ant Group, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-8554-6886","affiliations":[{"raw_affiliation_string":"Ant Digital Technologies, Ant Group, Singapore, Singapore","institution_ids":["https://openalex.org/I4210135679"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.6816,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.98625693,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"8262","last_page":"8273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7141000032424927,"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":0.7141000032424927,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.07590000331401825,"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":0.042899999767541885,"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/visualization","display_name":"Visualization","score":0.3003000020980835},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.24740000069141388},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.24639999866485596},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.23899999260902405},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2361000031232834}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.542900025844574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5013999938964844},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3465999960899353},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.24740000069141388},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24639999866485596},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.23899999260902405},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2361000031232834},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2289000004529953},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.22869999706745148}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792793","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792793","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792793","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792793","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4955146312713623}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2979382951","https://openalex.org/W3004268082","https://openalex.org/W3120043490","https://openalex.org/W3205050305","https://openalex.org/W4313068342","https://openalex.org/W4386071687","https://openalex.org/W4390872747","https://openalex.org/W4403990523","https://openalex.org/W7133196460"],"related_works":[],"abstract_inverted_index":{"Multilingual":[0,133],"Text-Centric":[1],"Visual":[2,65],"Question":[3],"Answering":[4],"(TEC-VQA)":[5],"has":[6,169],"become":[7],"crucial":[8],"for":[9,51,118],"real-world":[10],"applications,":[11],"as":[12],"it":[13],"requires":[14],"fine-grained":[15],"understanding":[16],"and":[17,47,91,99,123,135,160,197],"reasoning":[18,77,97],"over":[19],"multilingual":[20,52],"scene":[21],"text.":[22],"Recent":[23],"advances":[24],"in":[25,33,110,188,194],"vision-language":[26],"models":[27,142,154],"(VLMs)":[28],"have":[29],"demonstrated":[30],"strong":[31],"potential":[32],"tackling":[34],"multimodal":[35,53],"tasks.":[36],"However,":[37],"most":[38],"existing":[39],"approaches":[40],"rely":[41],"primarily":[42],"on":[43,128],"textual":[44],"Chain-of-Thought":[45],"(CoT)":[46],"provide":[48],"limited":[49],"support":[50],"reasoning.":[54,94],"To":[55,95],"address":[56],"this":[57,205],"gap,":[58],"we":[59,102],"introduce":[60],"LaV-CoT,":[61],"the":[62],"first":[63],"Language-aware":[64],"CoT":[66],"framework":[67],"with":[68,83],"Multi-Aspect":[69,107],"Reward":[70,108],"Optimization.":[71],"LaV-CoT":[72,139,168],"incorporates":[73,116],"an":[74,185],"interpretable":[75],"multi-stage":[76],"pipeline":[78],"consisting":[79],"of":[80,143],"text":[81],"summary":[82],"bounding":[84],"box,":[85],"language":[86],"identification,":[87],"spatial":[88],"object-level":[89],"captioning,":[90],"step-by-step":[92],"logical":[93],"improve":[96],"accuracy":[98],"cross-lingual":[100],"generalization,":[101],"propose":[103],"a":[104],"novel":[105],"verifiable":[106],"Optimization":[109],"addition":[111],"to":[112,148],"supervised":[113],"fine-tuning":[114],"that":[115,138],"rewards":[117],"linguistic":[119],"consistency,":[120],"structural":[121],"fidelity,":[122],"response":[124],"accuracy.":[125],"Extensive":[126],"evaluations":[127],"public":[129],"datasets,":[130],"including":[131],"MMMB,":[132],"MMBench,":[134],"MTVQA,":[136],"show":[137],"outperforms":[140],"open-source":[141,153],"similar":[144],"size":[145],"by":[146],"up":[147],"~9.5%":[149],"accuracy,":[150],"even":[151],"surpassing":[152],"more":[155],"than":[156],"twice":[157],"its":[158,192],"size,":[159],"further":[161,180],"exceeding":[162],"several":[163],"state-of-the-art":[164],"proprietary":[165],"models.":[166],"Moreover,":[167],"been":[170],"integrated":[171],"into":[172],"our":[173],"online":[174,181],"Intelligent":[175],"Document":[176],"Processing":[177],"platform.":[178],"A":[179],"A/B":[182],"test":[183],"demonstrates":[184],"\\(\\sim\\)8.7%":[186],"improvement":[187],"acceptance":[189],"rate,":[190],"validating":[191],"effectiveness":[193],"industrial":[195],"deployment":[196],"commercial":[198],"applications.":[199],"Our":[200],"code":[201],"is":[202],"available":[203],"at":[204],"https://github.com/HJNVR/LaV-CoT":[206],"repository.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-04-10T00:00:00"}