{"id":"https://openalex.org/W7166814076","doi":"https://doi.org/10.18653/v1/2026.acl-long.622","title":"Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks","display_name":"Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166814076","doi":"https://doi.org/10.18653/v1/2026.acl-long.622"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.622","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.622","pdf_url":"https://aclanthology.org/2026.acl-long.622.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.622.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139793138","display_name":"Yu Guang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Department of Computer Sciences , University of Wisconsin-Madison ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences , University of Wisconsin-Madison ,","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108422253","display_name":"Sharon Li","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharon Li","raw_affiliation_strings":["Department of Computer Sciences , University of Wisconsin-Madison ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences , University of Wisconsin-Madison ,","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86264706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13670","last_page":"13685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11516","display_name":"Visual and Cognitive Learning Processes","score":0.05689999833703041,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11516","display_name":"Visual and Cognitive Learning Processes","score":0.05689999833703041,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10656","display_name":"Child and Animal Learning Development","score":0.049300000071525574,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11285","display_name":"Hearing Impairment and Communication","score":0.03680000081658363,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2874000072479248},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2833000123500824},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.26910001039505005},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2572999894618988},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.25519999861717224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5534999966621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4088999927043915},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.24480000138282776},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.23980000615119934},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.22709999978542328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.622","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.622","pdf_url":"https://aclanthology.org/2026.acl-long.622.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.622","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.622","pdf_url":"https://aclanthology.org/2026.acl-long.622.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G4836357435","display_name":"SLES: Foundations of Safety-Aware Learning in the Wild","funder_award_id":"2331669","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6108913550","display_name":null,"funder_award_id":"FA9550-23-1-0184","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G6602531639","display_name":null,"funder_award_id":"N00014-23-1-2643","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7105599594","display_name":null,"funder_award_id":"N00014-23","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8760265284","display_name":"CAREER: Foundations of Human-Centered Machine Learning in the Wild","funder_award_id":"2237037","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320315389","display_name":"Open Philanthropy Project","ror":"https://ror.org/004d1k391"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166814076.pdf","grobid_xml":"https://content.openalex.org/works/W7166814076.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In-context":[0],"learning":[1],"(ICL)":[2],"enables":[3],"models":[4,98,115],"to":[5,7,23,68,106,126,132],"adapt":[6],"new":[8,152],"tasks":[9],"via":[10],"inference-time":[11],"demonstrations.Despite":[12],"its":[13,32],"success":[14],"in":[15,29,51,71],"large":[16,53],"language":[17,54],"models,":[18],"the":[19,155],"extension":[20],"of":[21,31,49,159],"ICL":[22,50,65,70,86,161],"multimodal":[24,52,64,85,160,168],"settings":[25,73],"remains":[26],"poorly":[27],"understood":[28],"terms":[30],"internal":[33],"mechanisms":[34,156],"and":[35,91,95,103,121,124,157,162],"how":[36,97],"it":[37],"differs":[38],"from":[39],"text-only":[40],"ICL.In":[41],"this":[42,81],"work,":[43],"we":[44,61,83,137],"conduct":[45],"a":[46,140],"systematic":[47],"analysis":[48,111],"models.Using":[55],"identical":[56],"task":[57,88,92,101,130,147],"formulations":[58],"across":[59,109],"modalities,":[60],"show":[62],"that":[63,113,145],"performs":[66],"comparably":[67],"textonly":[69],"zero-shot":[72],"but":[74],"degrades":[75],"significantly":[76],"under":[77],"few-shot":[78],"demonstrations.To":[79],"understand":[80],"gap,":[82],"decompose":[84],"into":[87,154],"mapping":[89,93,148],"construction":[90],"transfer,":[94],"analyze":[96],"establish":[99],"cross-modal":[100],"mappings,":[102],"transfer":[104,128],"them":[105],"query":[107],"samples":[108],"layers.Our":[110],"reveals":[112],"current":[114],"lack":[116],"reasoning-level":[117],"alignment":[118],"between":[119],"visual":[120],"textual":[122],"representations,":[123],"fail":[125],"reliably":[127],"learned":[129],"mappings":[131],"queries.Guided":[133],"by":[134],"these":[135],"findings,":[136],"further":[138],"propose":[139],"simple":[141],"inference-stage":[142],"enhancement":[143],"method":[144],"reinforces":[146],"transfer.Our":[149],"results":[150],"provide":[151],"insights":[153],"limitations":[158],"suggest":[163],"directions":[164],"for":[165],"more":[166],"effective":[167],"adaptation.Our":[169],"code":[170],"is":[171],"available":[172],"here.":[173]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-07-02T00:00:00"}