{"id":"https://openalex.org/W7161029287","doi":"https://doi.org/10.1145/3805712.3808431","title":"A General Framework for Multimodal LLM-Based Multimedia Understanding in Large-Scale Recommendation Systems","display_name":"A General Framework for Multimodal LLM-Based Multimedia Understanding in Large-Scale Recommendation Systems","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7161029287","doi":"https://doi.org/10.1145/3805712.3808431"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808431","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808431","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3808431","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136015497","display_name":"Yiming Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Zhu","raw_affiliation_strings":["Meta Platforms, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0009-0009-8627-8778","affiliations":[{"raw_affiliation_string":"Meta Platforms, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136014804","display_name":"Xu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu Liu","raw_affiliation_strings":["Meta Platforms, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0009-0003-9531-5768","affiliations":[{"raw_affiliation_string":"Meta Platforms, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136070585","display_name":"Ziyun Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziyun Xu","raw_affiliation_strings":["Meta Platforms, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0009-0002-9184-135X","affiliations":[{"raw_affiliation_string":"Meta Platforms, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136068724","display_name":"Zheng Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng Wu","raw_affiliation_strings":["Meta Platforms, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0009-0001-5419-3325","affiliations":[{"raw_affiliation_string":"Meta Platforms, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136063958","display_name":"Joena Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joena Zhang","raw_affiliation_strings":["Meta Platforms, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0000-0002-5182-1234","affiliations":[{"raw_affiliation_string":"Meta Platforms, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019496981","display_name":"Sirius Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sirius Chen","raw_affiliation_strings":["Meta Platforms, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0000-0002-2756-5701","affiliations":[{"raw_affiliation_string":"Meta Platforms, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136015384","display_name":"Chenheli Hua","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenheli Hua","raw_affiliation_strings":["Meta Platforms, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0009-0000-7151-965X","affiliations":[{"raw_affiliation_string":"Meta Platforms, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136065975","display_name":"Silvester Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Silvester Yao","raw_affiliation_strings":["Meta Platforms, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0009-0004-1082-9055","affiliations":[{"raw_affiliation_string":"Meta Platforms, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041365728","display_name":"Qichao Que","orcid":"https://orcid.org/0000-0002-2676-1460"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qichao Que","raw_affiliation_strings":["Meta Platforms, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0000-0002-2676-1460","affiliations":[{"raw_affiliation_string":"Meta Platforms, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136018754","display_name":"Wentao Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092558","display_name":"BC Platforms (Finland)","ror":"https://ror.org/002fen565","country_code":"FI","type":"company","lineage":["https://openalex.org/I4210092558"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Wentao Shi","raw_affiliation_strings":["Meta Platforms, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-2616-6880","affiliations":[{"raw_affiliation_string":"Meta Platforms, Singapore, Singapore","institution_ids":["https://openalex.org/I4210092558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109935473","display_name":"Junfeng Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junfeng Pan","raw_affiliation_strings":["Meta Platforms, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0009-0003-3253-5157","affiliations":[{"raw_affiliation_string":"Meta Platforms, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022377869","display_name":"Linhong Zhu","orcid":"https://orcid.org/0000-0001-8350-392X"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Linhong Zhu","raw_affiliation_strings":["Meta Platforms, Menlo Park, USA"],"raw_orcid":"https://orcid.org/0000-0001-8350-392X","affiliations":[{"raw_affiliation_string":"Meta Platforms, Menlo Park, USA","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.57573434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5108","last_page":"5112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6783999800682068,"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":0.6783999800682068,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.060100000351667404,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.043800000101327896,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7491000294685364},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6983000040054321},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.64410001039505},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.57669997215271},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.48590001463890076},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4555000066757202},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.42750000953674316},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4223000109195709}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8461999893188477},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7491000294685364},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6983000040054321},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.64410001039505},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.57669997215271},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.48590001463890076},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42480000853538513},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4223000109195709},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33090001344680786},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3181999921798706},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.26269999146461487}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805712.3808431","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808431","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"},{"id":"pmh:oai:arXiv.org:2605.09338","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.09338","pdf_url":"https://arxiv.org/pdf/2605.09338","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,"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808431","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808431","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Conventional":[0],"recommendation":[1,124],"systems":[2],"frequently":[3],"fail":[4],"to":[5,121],"fully":[6],"exploit":[7],"the":[8,18,93,115],"high-dimensional":[9],"semantic":[10],"signals":[11],"inherent":[12],"in":[13,102,109],"multimedia":[14,58],"content,":[15],"thereby":[16],"limiting":[17],"fidelity":[19],"of":[20,95,118],"user":[21],"preference":[22],"modeling.":[23],"While":[24],"Multimodal":[25],"Large":[26],"Language":[27],"Models":[28],"(MM-LLMs)":[29],"offer":[30],"robust":[31],"mechanisms":[32],"for":[33,56],"interpreting":[34],"such":[35],"complex":[36],"data,":[37],"their":[38],"integration":[39],"into":[40],"latency-constrained,":[41],"industrial-scale":[42],"architectures":[43],"remains":[44],"a":[45,53,63,77,99,106],"significant":[46],"challenge.":[47],"To":[48],"address":[49],"this,":[50],"we":[51],"propose":[52],"generalized":[54],"framework":[55],"MM-LLM-driven":[57],"understanding.":[59],"Our":[60],"methodology":[61],"employs":[62],"tripartite":[64],"architecture":[65],"encompassing":[66],"content":[67],"interpretation,":[68],"representation":[69],"extraction,":[70],"and":[71,105],"systematic":[72],"pipeline":[73],"integration,":[74],"instantiated":[75],"via":[76],"LLaMA2-based":[78],"model":[79],"that":[80],"generates":[81],"descriptive":[82],"captions":[83],"subsequently":[84],"ingested":[85],"as":[86],"tokenized":[87],"categorical":[88],"features.":[89],"Empirical":[90],"evaluation":[91],"demonstrates":[92],"efficacy":[94],"this":[96],"approach,":[97],"yielding":[98],"0.35%":[100],"increase":[101],"offline":[103],"AUC":[104],"0.02%":[107],"improvement":[108],"online":[110],"metrics":[111],"at":[112],"scale,":[113],"substantiating":[114],"practical":[116],"viability":[117],"leveraging":[119],"MM-LLMs":[120],"enhance":[122],"large-scale":[123],"performance.":[125]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-14T00:00:00"}