{"id":"https://openalex.org/W7133300481","doi":"https://doi.org/10.48550/arxiv.2603.00511","title":"Multimodal Adaptive Retrieval Augmented Generation through Internal Representation Learning","display_name":"Multimodal Adaptive Retrieval Augmented Generation through Internal Representation Learning","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7133300481","doi":"https://doi.org/10.48550/arxiv.2603.00511"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00511","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00511","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00511","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100742779","display_name":"Runle Du","orcid":"https://orcid.org/0000-0002-2091-6062"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Ruoshuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128019297","display_name":"Xin Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128005271","display_name":"Qiang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Qiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127929493","display_name":"Bowen Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102157705","display_name":"Zhongqi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zhongqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127987625","display_name":"Weiqiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Weiqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127894660","display_name":"Liang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.961899995803833,"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":0.961899995803833,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.012299999594688416,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.004100000020116568,"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/robustness","display_name":"Robustness (evolution)","score":0.5486999750137329},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5385000109672546},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4620000123977661},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.44190001487731934},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.38530001044273376},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.37059998512268066},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.35269999504089355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8288999795913696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6122000217437744},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5486999750137329},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5385000109672546},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4320000112056732},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.37059998512268066},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.34869998693466187},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00511","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00511","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00511","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00511","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.44298863410949707}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Answering":[2],"systems":[3],"face":[4],"reliability":[5],"issues":[6],"due":[7],"to":[8,77,80,91,110],"hallucinations,":[9],"where":[10,46],"models":[11],"generate":[12],"answers":[13],"misaligned":[14],"with":[15],"visual":[16,43,106],"input":[17],"or":[18,38],"factual":[19],"knowledge.":[20],"While":[21],"Retrieval":[22],"Augmented":[23],"Generation":[24],"frameworks":[25],"mitigate":[26],"this":[27],"issue":[28],"by":[29],"incorporating":[30],"external":[31,84,157],"knowledge,":[32],"static":[33],"retrieval":[34,145],"often":[35],"introduces":[36],"irrelevant":[37],"conflicting":[39],"content,":[40],"particularly":[41],"in":[42,70,127,130,143,163],"RAG":[44,63],"settings":[45],"visually":[47],"similar":[48],"but":[49],"semantically":[50],"incorrect":[51],"evidence":[52],"may":[53],"be":[54],"retrieved.":[55],"To":[56],"address":[57],"this,":[58],"we":[59],"propose":[60],"Multimodal":[61],"Adaptive":[62],"(MMA-RAG),":[64],"which":[65,102],"dynamically":[66],"assesses":[67],"the":[68,71,75,82,87,112,121,138,149],"confidence":[69],"internal":[72,105,141],"knowledge":[73,158],"of":[74,114,140],"model":[76,122],"decide":[78],"whether":[79],"incorporate":[81],"retrieved":[83],"information":[85],"into":[86],"generation":[88],"process.":[89],"Central":[90],"MMA-RAG":[92,154],"is":[93],"a":[94,99,124],"decision":[95],"classifier":[96],"trained":[97],"through":[98],"layer-wise":[100],"analysis,":[101],"leverages":[103],"joint":[104],"and":[107,160],"textual":[108],"representations":[109,142],"guide":[111],"use":[113],"reverse":[115],"image":[116],"retrieval.":[117],"Experiments":[118],"demonstrated":[119,152],"that":[120,153],"achieves":[123],"significant":[125],"improvement":[126],"response":[128],"performance":[129],"three":[131],"VQA":[132],"datasets.":[133],"Meanwhile,":[134],"ablation":[135],"studies":[136],"highlighted":[137],"importance":[139],"adaptive":[144],"decisions.":[146],"In":[147],"general,":[148],"experimental":[150],"results":[151],"effectively":[155],"balances":[156],"utilization":[159],"inference":[161],"robustness":[162],"diverse":[164],"multimodal":[165],"scenarios.":[166]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-04T00:00:00"}