{"id":"https://openalex.org/W4402671850","doi":"https://doi.org/10.18653/v1/2024.acl-long.223","title":"CaMML: Context-Aware Multimodal Learner for Large Models","display_name":"CaMML: Context-Aware Multimodal Learner for Large Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402671850","doi":"https://doi.org/10.18653/v1/2024.acl-long.223"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.acl-long.223","doi":"https://doi.org/10.18653/v1/2024.acl-long.223","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.acl-long.223","pdf_url":"https://aclanthology.org/2024.acl-long.223.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2024.acl-long.223.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100393447","display_name":"Yixin Chen","orcid":"https://orcid.org/0000-0002-6605-1615","observed_orcids":["https://orcid.org/0000-0002-6605-1615","https://orcid.org/0009-0000-6853-5915","https://orcid.org/0009-0000-8465-851X"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yixin Chen","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328904","display_name":"Shuai Zhang","orcid":"https://orcid.org/0000-0002-7866-4611","observed_orcids":["https://orcid.org/0000-0002-7866-4611","https://orcid.org/0009-0009-1288-5460"]},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["The University of Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041872681","display_name":"Boran Han","orcid":"https://orcid.org/0000-0001-9567-7062","observed_orcids":["https://orcid.org/0000-0001-9567-7062"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Boran Han","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091543199","display_name":"Tong He","orcid":"https://orcid.org/0000-0002-2388-8618","observed_orcids":["https://orcid.org/0000-0002-2388-8618"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tong He","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bo Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["The University of Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1212,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84841718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4056","last_page":"4071"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.0,"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":0.0,"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/large-multimodal-models","display_name":"large multimodal models","score":0.7739999890327454},{"id":"https://openalex.org/keywords/context-aware-learning","display_name":"context-aware learning","score":0.5590000152587891},{"id":"https://openalex.org/keywords/multimodal-fine-tuning","display_name":"multimodal fine-tuning","score":0.7089999914169312},{"id":"https://openalex.org/keywords/multimodal-benchmark","display_name":"multimodal benchmark","score":0.546999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7687942385673523},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.557910680770874},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.44984978437423706},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41366544365882874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.279886931180954},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.acl-long.223","doi":"https://doi.org/10.18653/v1/2024.acl-long.223","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.acl-long.223","pdf_url":"https://aclanthology.org/2024.acl-long.223.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2401.03149","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.03149","pdf_url":"https://arxiv.org/pdf/2401.03149","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2401.03149","doi":"https://doi.org/10.48550/arxiv.2401.03149","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.03149","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.acl-long.223","doi":"https://doi.org/10.18653/v1/2024.acl-long.223","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.acl-long.223","pdf_url":"https://aclanthology.org/2024.acl-long.223.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402671850.pdf","grobid_xml":"https://content.openalex.org/works/W4402671850.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W4307079201","https://openalex.org/W4319165821","https://openalex.org/W4320343008","https://openalex.org/W4361229539","https://openalex.org/W4366850747","https://openalex.org/W4382142077","https://openalex.org/W4382491206","https://openalex.org/W4386185600","https://openalex.org/W4386794522","https://openalex.org/W4402727764","https://openalex.org/W4403081466"],"related_works":["https://openalex.org/W4402727536","https://openalex.org/W4407036905","https://openalex.org/W7171672204","https://openalex.org/W4409369440","https://openalex.org/W4387323789","https://openalex.org/W4402672008","https://openalex.org/W7166885695","https://openalex.org/W7220898152","https://openalex.org/W4402903971","https://openalex.org/W7135416617"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,64,113],"introduce":[4],"Context-Aware":[5],"MultiModal":[6],"Learner":[7],"(CaMML),":[8],"for":[9,84],"tuning":[10],"large":[11,27],"multimodal":[12,23,54,68,85,97],"models":[13,140],"(LMMs).CaMML,":[14],"a":[15,104],"lightweight":[16],"module,":[17],"is":[18,46],"crafted":[19],"to":[20,33,58,119,130],"seamlessly":[21],"integrate":[22],"contextual":[24],"samples":[25],"into":[26],"models,":[28,69],"thereby":[29],"empowering":[30],"the":[31,89,121],"model":[32],"derive":[34],"knowledge":[35],"from":[36],"analogous,":[37],"domain-specific,":[38],"up-to-date":[39],"information":[40],"and":[41,49,71,126,139],"make":[42],"grounded":[43],"inferences.Importantly,":[44],"CaMML":[45,125],"highly":[47],"scalable":[48],"can":[50],"efficiently":[51],"handle":[52],"lengthy":[53],"context":[55],"examples":[56],"owing":[57],"its":[59,132],"hierarchical":[60],"design.Based":[61],"on":[62,92],"CaMML,":[63],"have":[65,74,114],"developed":[66],"two":[67],"CaMML-7B":[70],"CaMML-13B,":[72],"that":[73],"shown":[75],"exceptional":[76],"performance":[77,91],"across":[78],"an":[79],"array":[80],"of":[81,109,124],"benchmark":[82,98],"datasets":[83],"tasks.Remarkably,":[86],"CaMML-13B":[87],"achieves":[88],"state-of-the-art":[90],"over":[93],"ten":[94],"widely":[95],"recognized":[96],"datasets,":[99],"surpassing":[100],"LLaVA-1.5":[101],"(13B)":[102],"with":[103],"noticeable":[105],"margin,":[106],"without":[107],"integration":[108],"any":[110],"external":[111],"resources.Moreover,":[112],"conducted":[115],"extensive":[116],"ablative":[117],"studies":[118],"inspect":[120],"inner":[122],"workings":[123],"performed":[127],"qualitative":[128],"analyses":[129],"showcase":[131],"effectiveness":[133],"in":[134],"handling":[135],"real-world":[136],"challenging":[137],"cases.Code":[138],"are":[141],"available":[142],"at:":[143],"https://github.":[144],"com/amazon-science/camml.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-09-21T00:00:00"}