{"id":"https://openalex.org/W7137910022","doi":"https://doi.org/10.1609/aaai.v40i8.37591","title":"Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning","display_name":"Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137910022","doi":"https://doi.org/10.1609/aaai.v40i8.37591"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i8.37591","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37591","pdf_url":null,"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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i8.37591","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031761785","display_name":"Yanshu Li","orcid":"https://orcid.org/0000-0001-7683-806X"},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanshu Li","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102954986","display_name":"Jianjiang Yang","orcid":"https://orcid.org/0000-0002-6061-4552"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianjiang Yang","raw_affiliation_strings":["University of Bristol"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bristol","institution_ids":["https://openalex.org/I36234482"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129693077","display_name":"Ziteng Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziteng Yang","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129708736","display_name":"Bozheng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bozheng Li","raw_affiliation_strings":["Brown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129746113","display_name":"Ligong Han","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ligong Han","raw_affiliation_strings":["MIT-IBM Watson AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT-IBM Watson AI Lab","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129698615","display_name":"hongyang he","orcid":null},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hongyang He","raw_affiliation_strings":["University of Warwick"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126419543","display_name":"Zhengtao Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengtao Yao","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409186","display_name":"Yingjie Chen","orcid":"https://orcid.org/0000-0001-6705-3535"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingjie Victor Chen","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032832468","display_name":"Songlin Fei","orcid":"https://orcid.org/0000-0003-2772-0166"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Songlin Fei","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129724115","display_name":"Dongfang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongfang Liu","raw_affiliation_strings":["Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129687573","display_name":"Ruixiang Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ruixiang Tang","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"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":0.12606838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"8","first_page":"6610","last_page":"6618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9286999702453613,"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":0.9286999702453613,"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":0.028200000524520874,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.006399999838322401,"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/process","display_name":"Process (computing)","score":0.6455000042915344},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6044999957084656},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.376800000667572},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.37610000371932983},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.31439998745918274},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3068000078201294},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.2904999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761900007724762},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6455000042915344},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6044999957084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4715000092983246},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46709999442100525},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.376800000667572},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i8.37591","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37591","pdf_url":null,"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/37591","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37591","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/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i8.37591","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i8.37591","pdf_url":null,"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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"in-context":[1,39,118],"learning":[2],"(ICL)":[3],"is":[4],"becoming":[5],"a":[6,104,122,183],"key":[7],"capability":[8],"that":[9,46,90,109,126],"allows":[10],"large":[11],"vision-language":[12],"models":[13,146],"(LVLMs)":[14],"to":[15,17,50,77,129],"adapt":[16],"novel":[18],"tasks":[19],"without":[20],"parameter":[21],"updates,":[22],"which":[23],"expands":[24],"their":[25,79,88],"usefulness":[26],"in":[27,87],"many":[28],"real-world":[29],"applications.":[30],"However,":[31],"ICL":[32],"performance":[33],"remains":[34,166],"unstable":[35],"even":[36],"when":[37],"the":[38,55,72,116,158],"demonstrations":[40],"(ICDs)":[41],"are":[42],"well":[43],"matched,":[44],"showing":[45,149],"LVLMs":[47,76,138],"still":[48],"struggle":[49],"make":[51],"full":[52],"use":[53],"of":[54,161,186],"provided":[56],"context.":[57],"While":[58],"existing":[59],"work":[60],"mainly":[61],"focuses":[62],"on":[63,115],"prompt":[64,162],"engineering":[65,163],"or":[66],"post-hoc":[67],"logit":[68],"calibration,":[69],"we":[70,98],"study":[71],"attention":[73,112,128,187],"mechanisms":[74],"inside":[75],"address":[78,95],"inherent":[80],"limitations.":[81],"We":[82],"identify":[83],"two":[84],"important":[85,131],"weaknesses":[86],"self-attention":[89],"hinder":[91],"effective":[92],"ICL.":[93],"To":[94],"these":[96],"weaknesses,":[97],"propose":[99],"Context-Aware":[100],"Modulated":[101],"Attention":[102],"(CAMA),":[103],"training-free":[105],"and":[106,139,147,152,165],"plug-and-play":[107],"method":[108],"dynamically":[110],"adjusts":[111],"logits":[113],"based":[114],"input":[117],"sequence.":[119],"CAMA":[120,142,173],"uses":[121],"two-stage":[123],"modulation":[124],"process":[125],"strengthens":[127],"semantically":[130],"tokens,":[132],"especially":[133],"visual":[134],"ones.":[135],"Across":[136],"four":[137],"seven":[140],"benchmarks,":[141],"consistently":[143],"outperforms":[144],"vanilla":[145],"baselines,":[148],"clear":[150],"effectiveness":[151],"generalization.":[153],"It":[154],"can":[155],"also":[156],"activate":[157],"intended":[159],"benefits":[160],"methods":[164],"robust":[167],"across":[168],"different":[169],"sequence":[170],"configurations.":[171],"Therefore,":[172],"opens":[174],"up":[175],"new":[176],"directions":[177],"for":[178],"improving":[179],"multimodal":[180],"reasoning":[181],"through":[182],"deeper":[184],"understanding":[185],"dynamics.":[188]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}