{"id":"https://openalex.org/W7167924592","doi":"https://doi.org/10.1145/3805712.3809844","title":"Beyond Unimodal Perspectives: Generative Retrieval with Multimodal Semantics","display_name":"Beyond Unimodal Perspectives: Generative Retrieval with Multimodal Semantics","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167924592","doi":"https://doi.org/10.1145/3805712.3809844"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809844","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809844","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809844","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100317533","display_name":"Jing Zhu","orcid":"https://orcid.org/0000-0002-5364-151X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Zhu","raw_affiliation_strings":["University of Michigan, Ann Arbor, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0000-0002-5364-151X","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118969340","display_name":"Clark Mingxuan Ju","orcid":"https://orcid.org/0009-0008-9054-3856"},"institutions":[{"id":"https://openalex.org/I174135032","display_name":"Bellevue College","ror":"https://ror.org/05gr4yv49","country_code":"US","type":"education","lineage":["https://openalex.org/I174135032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingxuan Ju","raw_affiliation_strings":["Snap Inc., Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0009-0008-9054-3856","affiliations":[{"raw_affiliation_string":"Snap Inc., Bellevue, WA, USA","institution_ids":["https://openalex.org/I174135032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016839661","display_name":"Yozen Liu","orcid":"https://orcid.org/0000-0002-2107-504X"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yozen Liu","raw_affiliation_strings":["Snap Inc., Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2107-504X","affiliations":[{"raw_affiliation_string":"Snap Inc., Seattle, WA, USA","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046017316","display_name":"Shubham Vij","orcid":"https://orcid.org/0009-0002-5524-4232"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shubham Vij","raw_affiliation_strings":["Snap Inc., Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0009-0002-5524-4232","affiliations":[{"raw_affiliation_string":"Snap Inc., Seattle, WA, USA","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015996266","display_name":"Danai Koutra","orcid":"https://orcid.org/0000-0002-3206-8179"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danai Koutra","raw_affiliation_strings":["University of Michigan, Ann Arbor, Ann Arbor, MI, USA"],"raw_orcid":"https://orcid.org/0000-0002-3206-8179","affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101799872","display_name":"Neil Shah","orcid":"https://orcid.org/0000-0003-3261-8430"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil Shah","raw_affiliation_strings":["Snap Inc., Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3261-8430","affiliations":[{"raw_affiliation_string":"Snap Inc., Seattle, WA, USA","institution_ids":["https://openalex.org/I4210142583"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035766567","display_name":"Tong Zhao","orcid":"https://orcid.org/0000-0001-7660-1732"},"institutions":[{"id":"https://openalex.org/I4210142583","display_name":"Snap (United States)","ror":"https://ror.org/04dgkhg68","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142583"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Zhao","raw_affiliation_strings":["Snap Inc., Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7660-1732","affiliations":[{"raw_affiliation_string":"Snap Inc., Seattle, WA, USA","institution_ids":["https://openalex.org/I4210142583"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"4414","last_page":"4418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.263700008392334,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.263700008392334,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.24639999866485596,"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":0.18690000474452972,"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/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7189000248908997},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.670799970626831},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6685000061988831},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5619999766349792},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.48010000586509705},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.46140000224113464},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.40299999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7466999888420105},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7189000248908997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6736999750137329},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.670799970626831},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6685000061988831},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5879999995231628},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5619999766349792},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.46140000224113464},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2994999885559082},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.2937999963760376},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.26510000228881836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809844","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809844","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809844","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809844","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1652763299","https://openalex.org/W2171279286","https://openalex.org/W2512971201","https://openalex.org/W2963367478","https://openalex.org/W2971196067","https://openalex.org/W2984100107","https://openalex.org/W4296591867","https://openalex.org/W4312910992","https://openalex.org/W4396734745","https://openalex.org/W4400909953","https://openalex.org/W4401857430","https://openalex.org/W4401863553","https://openalex.org/W4403577940"],"related_works":[],"abstract_inverted_index":{"Generative":[0,44],"retrieval":[1],"(GR)":[2],"has":[3],"revolutionized":[4],"recommendation":[5],"systems":[6],"by":[7],"integrating":[8],"the":[9,12,29,39,74,80],"content":[10],"of":[11,33,42,51,127],"items":[13],"into":[14],"semantic":[15,86],"identifiers.":[16],"However,":[17],"existing":[18],"frameworks":[19],"predominantly":[20],"isolate":[21],"modalities":[22],"(e.g.,":[23],"relying":[24],"solely":[25],"on":[26],"text),":[27],"overlooking":[28],"inherently":[30],"multimodal":[31,135],"nature":[32],"real-world":[34],"items.":[35],"This":[36],"work":[37],"addresses":[38],"underexplored":[40],"challenge":[41],"Multimodal":[43],"Retrieval":[45],"(MGR).":[46],"Through":[47],"a":[48],"systematic":[49],"analysis":[50],"Early":[52],"and":[53,76,111,133],"Late":[54],"Fusion":[55],"strategies,":[56],"we":[57,94],"reveal":[58],"that":[59,122],"naive":[60,134],"integration":[61],"fails":[62,82],"due":[63],"to":[64,83,107,115,131],"two":[65],"critical":[66],"limitations:":[67],"modality":[68,72,77,105],"sensitivity,":[69],"where":[70,79],"one":[71],"dominates":[73],"representation,":[75],"correspondence,":[78],"model":[81],"align":[84],"distinct":[85],"IDs":[87],"across":[88],"modalities.":[89],"To":[90],"overcome":[91],"these":[92],"challenges,":[93],"introduce":[95],"MGR-LF++,":[96],"an":[97],"enhanced":[98],"late":[99],"fusion":[100],"framework.":[101],"MGR-LF++":[102,123],"employs":[103],"contrastive":[104],"alignment":[106],"enforce":[108],"cross-modal":[109],"consistency":[110],"incorporates":[112],"special":[113],"tokens":[114],"preserve":[116],"autoregressive":[117],"integrity.":[118],"Extensive":[119],"experiments":[120],"demonstrate":[121],"achieves":[124],"performance":[125],"improvements":[126],"over":[128],"20%":[129],"compared":[130],"unimodal":[132],"alternatives.":[136]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-11T00:00:00"}