{"id":"https://openalex.org/W7127617461","doi":"https://doi.org/10.48550/arxiv.2602.03713","title":"Multimodal Generative Recommendation for Fusing Semantic and Collaborative Signals","display_name":"Multimodal Generative Recommendation for Fusing Semantic and Collaborative Signals","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7127617461","doi":"https://doi.org/10.48550/arxiv.2602.03713"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.03713","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.03713","pdf_url":"https://arxiv.org/pdf/2602.03713","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.03713","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001881723","display_name":"Moritz Vandenhirtz","orcid":"https://orcid.org/0000-0002-7137-8081","observed_orcids":["https://orcid.org/0000-0002-7137-8081"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Vandenhirtz, Moritz","raw_affiliation_strings":["Department of Computer Science , ETH Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , ETH Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072012496","display_name":"Kaveh Hassani","orcid":"https://orcid.org/0000-0001-9162-9442","observed_orcids":["https://orcid.org/0000-0001-9162-9442"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hassani, Kaveh","raw_affiliation_strings":["Department of Computer Science , ETH Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , ETH Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073757419","display_name":"Shervin Ghasemlou","orcid":"https://orcid.org/0009-0008-3242-2052","observed_orcids":["https://orcid.org/0009-0008-3242-2052"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ghasemlou, Shervin","raw_affiliation_strings":["Department of Computer Science , ETH Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , ETH Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144448633","display_name":"Shuai Shao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Shao, Shuai","raw_affiliation_strings":["Department of Computer Science , ETH Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , ETH Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123481042","display_name":"Hamid Eghbalzadeh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Eghbalzadeh, Hamid","raw_affiliation_strings":["Department of Computer Science , ETH Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , ETH Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047400593","display_name":"Fuchun Peng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Peng, Fuchun","raw_affiliation_strings":["Department of Computer Science , ETH Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , ETH Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124973203","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-2154-4037","observed_orcids":["https://orcid.org/0000-0002-2154-4037"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Liu, Jun","raw_affiliation_strings":["Department of Computer Science , ETH Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , ETH Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030257576","display_name":"Michael L. Iuzzolino","orcid":"https://orcid.org/0009-0006-6445-736X","observed_orcids":["https://orcid.org/0009-0006-6445-736X"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Iuzzolino, Michael Louis","raw_affiliation_strings":["Department of Computer Science , ETH Zurich , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , ETH Zurich , Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":1.0,"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":1.0,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generative-recommendation","display_name":"generative recommendation","score":0.9359999895095825},{"id":"https://openalex.org/keywords/sequential-recommendation","display_name":"sequential recommendation","score":0.7450000047683716},{"id":"https://openalex.org/keywords/multimodal-recommendation","display_name":"multimodal recommendation","score":0.8740000128746033},{"id":"https://openalex.org/keywords/collaborative-signals","display_name":"collaborative signals","score":0.7770000100135803},{"id":"https://openalex.org/keywords/dino","display_name":"DINO","score":0.9279999732971191}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5479999780654907},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5085999965667725},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5023999810218811},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5005999803543091},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40130001306533813},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.37459999322891235},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32350000739097595},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.26980000734329224},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.26589998602867126},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.03713","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.03713","pdf_url":"https://arxiv.org/pdf/2602.03713","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.2602.03713","doi":"https://doi.org/10.48550/arxiv.2602.03713","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.03713","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":"pmh:oai:arXiv.org:2602.03713","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.03713","pdf_url":"https://arxiv.org/pdf/2602.03713","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127617461.pdf","grobid_xml":"https://content.openalex.org/works/W7127617461.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7117553158","https://openalex.org/W4415535588","https://openalex.org/W6948010384","https://openalex.org/W7164669984","https://openalex.org/W4401863330","https://openalex.org/W4415622538","https://openalex.org/W4395687057","https://openalex.org/W7161808999","https://openalex.org/W7221363032","https://openalex.org/W7128500744"],"abstract_inverted_index":{"Sequential":[0],"recommender":[1],"systems":[2],"rank":[3],"relevant":[4],"items":[5],"by":[6,58,145],"modeling":[7],"a":[8,46,111,125,156],"user's":[9],"interaction":[10],"history":[11],"and":[12,22,114,123,142,152,192,196],"computing":[13],"the":[14,18,28,37,53,64,69,97,135,167,174,204],"inner":[15],"product":[16],"between":[17],"resulting":[19],"user":[20],"representation":[21],"stored":[23],"item":[24,35,44,55,91],"embeddings.":[25],"To":[26,105],"avoid":[27],"significant":[29],"memory":[30],"overhead":[31],"of":[32,48,176,206],"storing":[33],"large":[34,90,168,184],"sets,":[36,92],"generative":[38,193],"recommendation":[39,194],"paradigm":[40],"instead":[41],"models":[42],"each":[43,207],"as":[45,155],"series":[47],"discrete":[49],"semantic":[50,121,143],"codes.":[51],"Here,":[52],"next":[54],"is":[56],"predicted":[57,70],"an":[59,198],"autoregressive":[60],"model":[61],"that":[62,165,187],"generates":[63],"code":[65],"sequence":[66,163],"corresponding":[67],"to":[68,84,103,173,202],"item.":[71],"However,":[72],"despite":[73],"promising":[74],"ranking":[75],"capabilities":[76],"on":[77,89,134,182],"small":[78],"datasets,":[79],"these":[80],"methods":[81],"have":[82],"yet":[83],"surpass":[85],"traditional":[86],"sequential":[87,150,191],"recommenders":[88,151],"limiting":[93],"their":[94],"adoption":[95],"in":[96],"very":[98],"scenarios":[99],"they":[100],"were":[101],"designed":[102],"address.":[104],"resolve":[106],"this,":[107],"we":[108,160],"propose":[109,161],"MSCGRec,":[110],"Multimodal":[112],"Semantic":[113],"Collaborative":[115],"Generative":[116],"Recommender.":[117],"MSCGRec":[118,139,188],"incorporates":[119],"multiple":[120],"modalities":[122],"introduces":[124],"novel":[126],"self-supervised":[127],"quantization":[128],"learning":[129,164],"approach":[130],"for":[131],"images":[132],"based":[133],"DINO":[136],"framework.":[137],"Additionally,":[138],"fuses":[140],"collaborative":[141,147],"signals":[144],"extracting":[146],"features":[148],"from":[149],"treating":[153],"them":[154],"separate":[157],"modality.":[158],"Finally,":[159],"constrained":[162],"restricts":[166],"output":[169],"space":[170],"during":[171],"training":[172],"set":[175],"permissible":[177],"tokens.":[178],"We":[179],"empirically":[180],"demonstrate":[181],"three":[183],"real-world":[185],"datasets":[186],"outperforms":[189],"both":[190],"baselines":[195],"provide":[197],"extensive":[199],"ablation":[200],"study":[201],"validate":[203],"impact":[205],"component.":[208]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-06T00:00:00"}