{"id":"https://openalex.org/W4416050722","doi":"https://doi.org/10.1145/3773966.3777923","title":"MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation","display_name":"MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W4416050722","doi":"https://doi.org/10.1145/3773966.3777923"},"language":"en","primary_location":{"id":"doi:10.1145/3773966.3777923","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777923","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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3773966.3777923","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yi Xu","orcid":"https://orcid.org/0009-0007-3571-8791"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Xu","raw_affiliation_strings":["Alibaba International Digital Commerce Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012930762","display_name":"Moyu Zhang","orcid":"https://orcid.org/0000-0002-9104-1881"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Moyu Zhang","raw_affiliation_strings":["Alibaba International Digital Commerce Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenxuan Li","orcid":"https://orcid.org/0009-0007-1022-6379"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxuan Li","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084755895","display_name":"Zhihao Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Liao","raw_affiliation_strings":["Beijing University of Aeronautics and Astronautics, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Aeronautics and Astronautics, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089731819","display_name":"Haibo Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Xing","raw_affiliation_strings":["Alibaba International Digital Commerce Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101891434","display_name":"Hao Deng","orcid":"https://orcid.org/0009-0002-6335-7405"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Deng","raw_affiliation_strings":["Alibaba International Digital Commerce Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032933252","display_name":"Jinxin Hu","orcid":"https://orcid.org/0000-0002-7252-5207"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxin Hu","raw_affiliation_strings":["Alibaba International Digital Commerce Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-6057-7886"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Alibaba International Digital Commerce Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082008486","display_name":"Xiaoyi Zeng","orcid":"https://orcid.org/0000-0002-3742-4910"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyi Zeng","raw_affiliation_strings":["Alibaba International Digital Commerce Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0001-6595-7661"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["Wuhan University, School of Computer Science, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University, School of Computer Science, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":66.5781,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.99174312,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"788","last_page":"797"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.48100000619888306,"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":0.48100000619888306,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.14180000126361847,"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/T10028","display_name":"Topic Modeling","score":0.09989999979734421,"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/bridging","display_name":"Bridging (networking)","score":0.5978999733924866},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5572999715805054},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.47450000047683716},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.39890000224113464},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.38960000872612},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.36230000853538513},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.3601999878883362},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.3447999954223633},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.334199994802475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8658999800682068},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5978999733924866},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5572999715805054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5009999871253967},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.47450000047683716},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44679999351501465},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3544999957084656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3515999913215637},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3447999954223633},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3447999954223633},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.3176000118255615},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3125},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C2778431730","wikidata":"https://www.wikidata.org/wiki/Q494291","display_name":"Folksonomy","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3773966.3777923","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777923","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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.15281","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.15281","pdf_url":"https://arxiv.org/pdf/2508.15281","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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","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.2508.15281","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.15281","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3773966.3777923","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777923","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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W4414034826","https://openalex.org/W2949465136","https://openalex.org/W2099419573","https://openalex.org/W3195061894","https://openalex.org/W4367047145","https://openalex.org/W4412377797","https://openalex.org/W4412877069","https://openalex.org/W4404783962","https://openalex.org/W4412394905","https://openalex.org/W4384648324","https://openalex.org/W4297971002","https://openalex.org/W3215615641","https://openalex.org/W4385568236"],"related_works":[],"abstract_inverted_index":{"Recommender":[0],"systems":[1],"traditionally":[2],"represent":[3],"items":[4,43],"using":[5,120],"unique":[6],"identifiers":[7],"(ItemIDs),":[8],"but":[9],"this":[10],"approach":[11],"struggles":[12],"with":[13,71,85,115],"large,":[14],"dynamic":[15],"item":[16],"corpora":[17],"and":[18,24,35,52,74,117,151,163,169,176],"sparse":[19],"long-tail":[20],"data,":[21],"limiting":[22],"scalability":[23],"generalization.":[25],"Semantic":[26],"IDs,":[27],"derived":[28],"from":[29],"multimodal":[30,105,126,145,160],"content":[31],"such":[32],"as":[33],"text":[34],"images,":[36],"offer":[37],"a":[38,45,98,103,108,112,144,167],"promising":[39],"alternative":[40],"by":[41],"mapping":[42],"into":[44],"shared":[46],"semantic":[47,81,133],"space,":[48],"enabling":[49],"knowledge":[50],"transfer":[51],"improving":[53],"recommendations":[54],"for":[55,172],"new":[56],"or":[57],"rare":[58],"items.":[59],"However,":[60],"existing":[61],"methods":[62],"face":[63],"two":[64],"key":[65],"challenges:":[66],"(1)":[67],"balancing":[68],"cross-modal":[69],"synergy":[70],"modality-specific":[72,116],"uniqueness,":[73],"(2)":[75],"bridging":[76],"the":[77],"semantic-behavioral":[78],"gap,":[79],"where":[80],"representations":[82],"may":[83],"misalign":[84],"actual":[86],"user":[87],"preferences.":[88],"To":[89],"address":[90],"these":[91],"challenges,":[92],"we":[93],"propose":[94],"Multimodal":[95],"Mixture-of-Quantization":[96],"(MMQ),":[97],"two-stage":[99],"framework":[100],"that":[101,156],"trains":[102],"novel":[104],"tokenizer.":[106],"First,":[107],"shared-specific":[109],"tokenizer":[110],"leverages":[111],"multi-expert":[113],"architecture":[114],"modality-shared":[118],"experts,":[119],"orthogonal":[121],"regularization":[122],"to":[123,135],"capture":[124],"comprehensive":[125],"information.":[127],"Second,":[128],"behavior-aware":[129],"fine-tuning":[130],"dynamically":[131],"adapts":[132],"IDs":[134],"downstream":[136],"recommendation":[137],"objectives":[138],"while":[139],"preserving":[140],"modality":[141],"information":[142],"through":[143],"reconstruction":[146],"loss.":[147],"Extensive":[148],"offline":[149],"experiments":[150],"online":[152],"A/B":[153],"tests":[154],"demonstrate":[155],"MMQ":[157],"effectively":[158],"unifies":[159],"synergy,":[161],"specificity,":[162],"behavioral":[164],"adaptation,":[165],"providing":[166],"scalable":[168],"versatile":[170],"solution":[171],"both":[173],"generative":[174],"retrieval":[175],"discriminative":[177],"ranking":[178],"tasks.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}