{"id":"https://openalex.org/W7126391042","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.105","title":"Unified Embeddings for Multimodal Retrieval via Frozen LLMs","display_name":"Unified Embeddings for Multimodal Retrieval via Frozen LLMs","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126391042","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.105"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.105","pdf_url":"https://aclanthology.org/2024.findings-eacl.105.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.105.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124521829","display_name":"Ziyang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077304103","display_name":"Heba Elfardy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heba Elfardy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079131136","display_name":"Markus Dreyer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Markus Dreyer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090984634","display_name":"Kevin Small","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Small","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124651137","display_name":"Mohit Bansal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohit Bansal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.572439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1537","last_page":"1547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.30809998512268066,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.30809998512268066,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.28189998865127563,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.12300000339746475,"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/key","display_name":"Key (lock)","score":0.33799999952316284},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28349998593330383},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.25450000166893005},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.23319999873638153},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.22949999570846558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5752999782562256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5267999768257141},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34950000047683716},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2531999945640564},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.23319999873638153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.22949999570846558},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.21940000355243683}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.105","pdf_url":"https://aclanthology.org/2024.findings-eacl.105.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.105","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.105","pdf_url":"https://aclanthology.org/2024.findings-eacl.105.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":"Findings of the Association for Computational Linguistics: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126391042.pdf","grobid_xml":"https://content.openalex.org/works/W7126391042.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"We":[3],"present":[4],"Unified":[5],"Embeddings":[6],"for":[7,48],"Multimodal":[8],"Retrieval":[9],"(UNIMUR),":[10],"a":[11],"simple":[12],"but":[13],"effective":[14],"approach":[15],"that":[16],"embeds":[17],"multimodal":[18,35,39,70,83,97,120],"inputs":[19],"and":[20,23,41,51,77,80,114,125,135],"retrieves":[21,34],"visual":[22,50,76],"textual":[24,52,78],"outputs":[25,36,79],"via":[26,37],"frozen":[27],"Large":[28],"Language":[29],"Models":[30],"(LLMs).Specifically,":[31],"UNIMUR":[32,57,85],"jointly":[33],"unified":[38,69],"embedding":[40,71],"applies":[42],"dual":[43],"alignment":[44],"training":[45],"to":[46,140],"account":[47],"both":[49],"semantics.Thus,":[53],"unlike":[54],"previous":[55,141],"approaches,":[56,142],"significantly":[58],"reduces":[59],"LLM's":[60],"modality":[61],"bias":[62],"towards":[63],"generating":[64],"text-only":[65],"outputs.Meanwhile,":[66],"the":[67,73,103,110],"proposed":[68],"mitigates":[72],"inconsistency":[74],"between":[75],"provides":[81],"coherent":[82],"outputs.Empirically,":[84],"also":[86,122],"achieves":[87,123],"strong":[88],"image/text":[89],"retrieval":[90,99,112,131],"ability":[91,146],"outperforming":[92],"existing":[93],"approaches":[94],"on":[95,100,119,128,133],"zeroshot":[96],"response":[98],"MMDialog,":[101],"improving":[102],"overall":[104],"R@1":[105],"by":[106],"6.5%":[107],"while":[108],"boosting":[109],"image":[111,130],"rate":[113],"having":[115],"better":[116],"cross-modal":[117],"consistency":[118],"outputs.UNIMUR":[121],"2.4%":[124],"3.9%":[126],"improvement":[127],"context-based":[129],"tasks":[132],"MMDialog":[134],"VisDial":[136],"respectively":[137],"when":[138],"compared":[139],"validating":[143],"its":[144],"generalization":[145],"across":[147],"multiple":[148],"tasks.":[149]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}