{"id":"https://openalex.org/W4414360135","doi":"https://doi.org/10.24963/ijcai.2025/126","title":"Boosting Visual Knowledge-Intensive Training for LVLMs Through Causality-Driven Visual Object Completion","display_name":"Boosting Visual Knowledge-Intensive Training for LVLMs Through Causality-Driven Visual Object Completion","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360135","doi":"https://doi.org/10.24963/ijcai.2025/126"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/126","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5066354514","display_name":"Qingguo Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingguo Hu","raw_affiliation_strings":["Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China","School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087988578","display_name":"Ante Wang","orcid":"https://orcid.org/0000-0001-8438-554X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ante Wang","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003098857","display_name":"Jia Song","orcid":"https://orcid.org/0000-0002-0815-208X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Song","raw_affiliation_strings":["School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072824674","display_name":"Di Qiu","orcid":"https://orcid.org/0000-0001-9706-6302"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Delai Qiu","raw_affiliation_strings":["Xiamen Unisound Intelligence Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen Unisound Intelligence Technology Co., Ltd","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714477","display_name":"Qingsong Liu","orcid":"https://orcid.org/0000-0002-6689-6407"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingsong Liu","raw_affiliation_strings":["Xiamen Unisound Intelligence Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen Unisound Intelligence Technology Co., Ltd","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066326238","display_name":"Jinsong Su","orcid":"https://orcid.org/0000-0001-5606-7122"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Su","raw_affiliation_strings":["Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China","School of Informatics, Xiamen University, China","Shanghai Artificial Intelligence Laboratory, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1125","last_page":"1133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.957099974155426,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.957099974155426,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9556999802589417,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9538000226020813,"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/boosting","display_name":"Boosting (machine learning)","score":0.6855000257492065},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6157000064849854},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48910000920295715},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4733000099658966},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4584999978542328},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44620001316070557},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4381999969482422},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.43459999561309814},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.4097999930381775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741000056266785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6984000205993652},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6855000257492065},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6157000064849854},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48910000920295715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.476500004529953},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4733000099658966},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4584999978542328},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.4097999930381775},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.40869998931884766},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.38040000200271606},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35899999737739563},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3440000116825104},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3327000141143799},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/126","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"experienced":[5],"significant":[6],"advancements":[7],"in":[8,17,39,44,61,81],"recent":[9],"years.":[10],"However,":[11],"their":[12],"performance":[13],"still":[14],"falls":[15],"short":[16],"tasks":[18,138],"requiring":[19],"deep":[20],"visual":[21,37,46,64],"perception,":[22],"such":[23],"as":[24],"identifying":[25],"subtle":[26],"differences":[27],"between":[28],"images.":[29],"A":[30],"potential":[31],"cause":[32],"is":[33],"the":[34,78,90,160,171],"scarcity":[35],"of":[36,154],"knowledge":[38],"popular":[40],"instruction-tuning":[41],"corpora,":[42],"resulting":[43],"inadequate":[45],"perception":[47],"and":[48,122,139,156,166,170],"reasoning":[49],"capabilities.":[50],"To":[51],"address":[52],"this":[53],"challenge,":[54],"we":[55],"introduce":[56],"a":[57,62],"self-improvement":[58],"framework":[59],"grounded":[60],"novel":[63],"knowledge-intensive":[65],"task,":[66],"Causality-driven":[67],"Visual":[68],"object":[69,80],"Completion":[70],"(CVC).":[71],"This":[72],"task":[73],"requires":[74],"LVLMs":[75,110,117],"to":[76,159],"infer":[77],"masked":[79],"an":[82,151],"image":[83],"based":[84],"on":[85,108,145],"its":[86],"causal":[87],"relationships":[88],"with":[89],"other":[91],"visible":[92],"information.":[93],"We":[94],"first":[95],"obtain":[96],"rich":[97],"examples":[98],"cheaply":[99],"through":[100,120],"our":[101,148],"automated":[102],"instance":[103],"construction":[104],"pipeline,":[105],"without":[106],"relying":[107],"sophisticated":[109],"(e.g.,":[111],"GPT-4V)":[112],"or":[113],"human":[114],"assistance.":[115],"Then,":[116],"effectively":[118],"self-improve":[119],"trial":[121],"error":[123],"learning":[124],"using":[125],"these":[126],"created":[127],"instances.":[128],"Our":[129],"experiments":[130],"demonstrate":[131],"substantial":[132],"gains":[133],"across":[134],"four":[135,140],"challenging":[136],"specialized":[137,146],"widely-used":[141],"comprehensive":[142],"benchmarks.":[143],"Especially":[144],"tasks,":[147],"method":[149],"achieves":[150],"average":[152],"improvement":[153],"5.4%":[155],"4.0%":[157],"compared":[158],"corresponding":[161],"baselines":[162],"when":[163],"utilizing":[164],"LLaVA-1.5-7B":[165],"LLaVA-1.5-13B,":[167],"respectively.":[168],"Code":[169],"supplementary":[172],"file":[173],"are":[174],"available":[175],"at":[176],"https://github.com/XMUDeepLIT/CVC.":[177]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}