{"id":"https://openalex.org/W4416702660","doi":"https://doi.org/10.48550/arxiv.2509.02017","title":"Empowering Large Language Model for Sequential Recommendation via Multimodal Embeddings and Semantic IDs","display_name":"Empowering Large Language Model for Sequential Recommendation via Multimodal Embeddings and Semantic IDs","publication_year":2025,"publication_date":"2025-09-02","ids":{"openalex":"https://openalex.org/W4416702660","doi":"https://doi.org/10.48550/arxiv.2509.02017"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2509.02017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.02017","pdf_url":"https://arxiv.org/pdf/2509.02017","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.02017","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043861652","display_name":"Yuhao Wang","orcid":"https://orcid.org/0000-0002-6051-8659"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Yuhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024752665","display_name":"Junwei Pan","orcid":"https://orcid.org/0009-0003-2697-7012"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Junwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078263563","display_name":"Xinhang Li","orcid":"https://orcid.org/0000-0001-8294-0589"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xinhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021037797","display_name":"Maolin Wang","orcid":"https://orcid.org/0000-0002-0073-0172"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Maolin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092343466","display_name":"Yuan Wang","orcid":"https://orcid.org/0009-0009-4065-1717"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320057","display_name":"Yue Liu","orcid":"https://orcid.org/0000-0002-2595-4893"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325848","display_name":"Dapeng Liu","orcid":"https://orcid.org/0009-0003-2973-9167"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Dapeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037387576","display_name":"Jie Jiang","orcid":"https://orcid.org/0000-0001-9658-5127"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100645854","display_name":"Xiangyu Zhao","orcid":"https://orcid.org/0000-0003-2926-4416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Xiangyu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5043861652"],"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":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":0.7221999764442444,"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":0.7221999764442444,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.05530000105500221,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0414000004529953,"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/autoencoder","display_name":"Autoencoder","score":0.7425000071525574},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7247999906539917},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7049000263214111},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5098000168800354},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5087000131607056},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.4505000114440918},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.42879998683929443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997999787330627},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7425000071525574},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7247999906539917},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7049000263214111},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5098000168800354},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5087000131607056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5073000192642212},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.4505000114440918},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C204806902","wikidata":"https://www.wikidata.org/wiki/Q2333581","display_name":"Semantic security","level":5,"score":0.26579999923706055},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.251800000667572},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2509.02017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.02017","pdf_url":"https://arxiv.org/pdf/2509.02017","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.02017","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.02017","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.02017","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.02017","pdf_url":"https://arxiv.org/pdf/2509.02017","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Sequential":[0],"recommendation":[1,72],"(SR)":[2],"aims":[3],"to":[4,70,95,175,178],"capture":[5,129],"users'":[6],"dynamic":[7],"interests":[8],"and":[9,51,68,92,117,128,182,188],"sequential":[10],"patterns":[11],"based":[12,75],"on":[13,76,164],"their":[14,28],"historical":[15],"interactions.":[16],"Recently,":[17],"the":[18,65,114,140,143,151,169],"powerful":[19],"capabilities":[20],"of":[21,55,172],"large":[22],"language":[23],"models":[24],"(LLMs)":[25],"have":[26],"driven":[27],"adoption":[29],"in":[30,38,156],"SR.":[31],"However,":[32],"we":[33,80,100,138,149],"identify":[34],"two":[35],"critical":[36],"challenges":[37],"existing":[39],"LLM-based":[40],"SR":[41,84],"methods:":[42],"1)":[43],"embedding":[44,97,180],"collapse":[45,181],"when":[46,58],"incorporating":[47],"pre-trained":[48],"collaborative":[49],"embeddings":[50,57,91,94],"2)":[52],"catastrophic":[53,136,183],"forgetting":[54],"quantized":[56,93],"utilizing":[59],"semantic":[60],"IDs.":[61],"These":[62],"issues":[63],"dampen":[64],"model":[66,141],"scalability":[67],"lead":[69],"suboptimal":[71],"performance.":[73],"Therefore,":[74],"LLMs":[77],"like":[78],"Llama3-8B-instruct,":[79],"introduce":[81],"a":[82,102,157],"novel":[83],"framework":[85],"named":[86],"MME-SID,":[87],"which":[88,122],"integrates":[89],"multimodal":[90,145,158],"mitigate":[96,179],"collapse.":[98],"Additionally,":[99],"propose":[101],"Multimodal":[103],"Residual":[104],"Quantized":[105],"Variational":[106],"Autoencoder":[107],"(MM-RQ-VAE)":[108],"with":[109,142],"maximum":[110],"mean":[111],"discrepancy":[112],"as":[113],"reconstruction":[115],"loss":[116],"contrastive":[118],"learning":[119],"for":[120,193],"alignment,":[121],"effectively":[123],"preserve":[124],"intra-modal":[125],"distance":[126],"information":[127],"inter-modal":[130],"correlations,":[131],"respectively.":[132],"To":[133],"further":[134],"alleviate":[135],"forgetting,":[137],"initialize":[139],"trained":[144],"code":[146,187],"embeddings.":[147],"Finally,":[148],"fine-tune":[150],"LLM":[152],"efficiently":[153],"using":[154],"LoRA":[155],"frequency-aware":[159],"fusion":[160],"manner.":[161],"Extensive":[162],"experiments":[163],"three":[165],"public":[166],"datasets":[167,189],"validate":[168],"superior":[170],"performance":[171],"MME-SID":[173],"thanks":[174],"its":[176],"capability":[177],"forgetting.":[184],"The":[185],"implementation":[186],"are":[190],"publicly":[191],"available":[192],"reproduction:":[194],"https://github.com/Applied-Machine-Learning-Lab/MME-SID.":[195]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}