{"id":"https://openalex.org/W7137923146","doi":"https://doi.org/10.1609/aaai.v40i4.37258","title":"AbductiveMLLM: Boosting Visual Abductive Reasoning Within MLLMs","display_name":"AbductiveMLLM: Boosting Visual Abductive Reasoning Within MLLMs","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137923146","doi":"https://doi.org/10.1609/aaai.v40i4.37258"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i4.37258","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37258","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37258/41220","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37258/41220","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067065591","display_name":"Boyu Chang","orcid":"https://orcid.org/0000-0002-8919-2808"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyu Chang","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129652127","display_name":"Qi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165204","display_name":"Zhuhai Institute of Advanced Technology","ror":"https://ror.org/05r1mzq61","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761","https://openalex.org/I4210165204"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["Beijing Institute of Technology\nBeijing Institute of Technology, Zhuhai"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology\nBeijing Institute of Technology, Zhuhai","institution_ids":["https://openalex.org/I4210165204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129715195","display_name":"Xi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Guo","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129735490","display_name":"Zhixiong Nan","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixiong Nan","raw_affiliation_strings":["Chongqing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027545344","display_name":"Yazhou Yao","orcid":"https://orcid.org/0000-0002-0337-9410"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yazhou Yao","raw_affiliation_strings":["Nanjing University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Science and Technology","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129742208","display_name":"Tianfei Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130296","display_name":"Detector Technology (United States)","ror":"https://ror.org/03j0tz946","country_code":"US","type":"company","lineage":["https://openalex.org/I4210130296"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianfei Zhou","raw_affiliation_strings":["Beijing Institute of Technology\nState Key Laboratory of Environment Characteristics and Effects for Near-space"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology\nState Key Laboratory of Environment Characteristics and Effects for Near-space","institution_ids":["https://openalex.org/I4210130296"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"4","first_page":"2698","last_page":"2706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8759999871253967,"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":0.8759999871253967,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.061500001698732376,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.01640000008046627,"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/abductive-reasoning","display_name":"Abductive reasoning","score":0.8309999704360962},{"id":"https://openalex.org/keywords/semantic-reasoner","display_name":"Semantic reasoner","score":0.8278999924659729},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6193000078201294},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6054999828338623},{"id":"https://openalex.org/keywords/causal-reasoning","display_name":"Causal reasoning","score":0.5026000142097473},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45669999718666077},{"id":"https://openalex.org/keywords/non-monotonic-logic","display_name":"Non-monotonic logic","score":0.39959999918937683},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.3441999852657318}],"concepts":[{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.8309999704360962},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.8278999924659729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6779999732971191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6751000285148621},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6193000078201294},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6054999828338623},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.5026000142097473},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C140843580","wikidata":"https://www.wikidata.org/wiki/Q840067","display_name":"Defeasible reasoning","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3043999969959259},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.30239999294281006},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.2612999975681305},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.258899986743927},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i4.37258","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37258","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37258/41220","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/37258","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37258","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/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i4.37258","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37258","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37258/41220","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":[],"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/W7137923146.pdf","grobid_xml":"https://content.openalex.org/works/W7137923146.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"abductive":[1,36],"reasoning":[2,29,129],"(VAR)":[3],"is":[4],"a":[5,95,102,150],"challenging":[6],"task":[7],"that":[8,169,195],"requires":[9],"AI":[10],"systems":[11],"to":[12,40,63,164,171],"infer":[13],"the":[14,51,89,122,137,156,160],"most":[15],"likely":[16],"explanation":[17],"for":[18],"incomplete":[19],"visual":[20,167],"observations.":[21],"While":[22],"recent":[23],"MLLMs":[24,67,142],"develop":[25],"strong":[26],"general-purpose":[27],"multimodal":[28],"capabilities,":[30],"they":[31],"remain":[32],"fall":[33],"short":[34],"in":[35,58,88,185],"inference,":[37],"as":[38,124],"compared":[39],"human":[41,59],"beings.":[42],"To":[43],"bridge":[44],"this":[45],"gap,":[46],"we":[47,74],"draw":[48],"inspiration":[49],"from":[50],"interplay":[52],"between":[53],"verbal":[54,90,172],"and":[55,61,83,105,159,204],"pictorial":[56,146],"abduction":[57,65],"cognition,":[60],"propose":[62],"strengthen":[64],"of":[66,78,98],"by":[68,143],"mimicking":[69],"such":[70],"dual-mode":[71],"behavior.":[72],"Concretely,":[73],"introduce":[75],"AbductiveMLLM":[76,196],"comprising":[77],"two":[79,180],"synergistic":[80],"components:":[81],"REASONER":[82,86],"IMAGINER.":[84],"The":[85,116,134,179],"operates":[87],"domain.":[91],"It":[92,148],"first":[93],"explores":[94],"broad":[96],"space":[97],"possible":[99],"explanations":[100],"using":[101],"blind":[103],"LLM":[104],"then":[106],"prunes":[107],"visually":[108],"incongruent":[109],"hypotheses":[110,118],"based":[111],"on":[112,136,154,190],"cross-modal":[113],"causal":[114],"alignment.":[115],"remaining":[117],"are":[119,182],"introduced":[120],"into":[121],"MLLM":[123],"targeted":[125],"priors,":[126],"steering":[127],"its":[128],"toward":[130],"causally":[131],"coherent":[132],"explanations.":[133],"IMAGINER,":[135],"other":[138],"hand,":[139],"further":[140],"guides":[141],"emulating":[144],"human-like":[145],"thinking.":[147],"conditions":[149],"text-to-image":[151],"diffusion":[152],"model":[153],"both":[155],"input":[157],"video":[158],"REASONER\u2019s":[161],"output":[162],"embeddings":[163],"\u201cimagine\u201d":[165],"plausible":[166],"scenes":[168],"correspond":[170],"explanation,":[173],"thereby":[174],"enriching":[175],"MLLMs'":[176],"contextual":[177],"grounding.":[178],"components":[181],"trained":[183],"jointly":[184],"an":[186],"end-to-end":[187],"manner.":[188],"Experiments":[189],"standard":[191],"VAR":[192],"benchmarks":[193],"show":[194],"achieves":[197],"state-of-the-art":[198],"performance,":[199],"consistently":[200],"outperforming":[201],"traditional":[202],"solutions":[203],"advanced":[205],"MLLMs.":[206]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}