{"id":"https://openalex.org/W4409671560","doi":"https://doi.org/10.1145/3696410.3714764","title":"When Large Vision Language Models Meet Multimodal Sequential Recommendation: An Empirical Study","display_name":"When Large Vision Language Models Meet Multimodal Sequential Recommendation: An Empirical Study","publication_year":2025,"publication_date":"2025-04-22","ids":{"openalex":"https://openalex.org/W4409671560","doi":"https://doi.org/10.1145/3696410.3714764"},"language":"en","primary_location":{"id":"doi:10.1145/3696410.3714764","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696410.3714764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116559848","display_name":"Peilin Zhou","orcid":"https://orcid.org/0000-0001-6763-5236"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peilin Zhou","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6763-5236","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chao Liu","orcid":"https://orcid.org/0000-0001-5323-2209"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Liu","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5323-2209","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019910857","display_name":"Jing Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Ren","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-0301-1866","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105787661","display_name":"X. R. Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinfeng Zhou","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-6089-1657","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037356694","display_name":"Yueqi Xie","orcid":"https://orcid.org/0000-0002-5169-3180"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yueqi Xie","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-5169-3180","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067002890","display_name":"Meng Cao","orcid":"https://orcid.org/0000-0002-8946-4228"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Meng Cao","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0002-8946-4228","affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhongtao Rao","orcid":"https://orcid.org/0009-0005-2113-5902"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongtao Rao","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-2113-5902","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052366582","display_name":"You-Liang Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You-Liang Huang","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0587-9571","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083041690","display_name":"Dading Chong","orcid":"https://orcid.org/0000-0003-3495-522X"},"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":"Dading Chong","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3495-522X","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Junling Liu","orcid":"https://orcid.org/0009-0008-5513-8396"},"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":"Junling Liu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-5513-8396","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012882402","display_name":"Jae Boum Kim","orcid":"https://orcid.org/0000-0001-5451-6617"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jae Boum Kim","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-5451-6617","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082317196","display_name":"Shoujin Wang","orcid":"https://orcid.org/0000-0003-1133-9379"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shoujin Wang","raw_affiliation_strings":["University of Technology Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1133-9379","affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049858061","display_name":"Raymond Chi-Wing Wong","orcid":"https://orcid.org/0000-0001-7045-6503"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Raymond Chi-Wing Wong","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-7045-6503","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066599821","display_name":"Sung Hun Kim","orcid":"https://orcid.org/0000-0003-4478-9720"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sunghun Kim","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4478-9720","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"275","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9970999956130981,"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/T10028","display_name":"Topic Modeling","score":0.9968000054359436,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.989799976348877,"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/computer-science","display_name":"Computer science","score":0.7815147042274475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4886353611946106},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.47377490997314453},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42678114771842957},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0691893994808197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7815147042274475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4886353611946106},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.47377490997314453},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42678114771842957},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0691893994808197},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3696410.3714764","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696410.3714764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-148806","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-148806","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2900841426","https://openalex.org/W2963367478","https://openalex.org/W2971196067","https://openalex.org/W2990138404","https://openalex.org/W3212368439","https://openalex.org/W4214540501","https://openalex.org/W4224952158","https://openalex.org/W4306316975","https://openalex.org/W4309185982","https://openalex.org/W4322718576","https://openalex.org/W4328120750","https://openalex.org/W4367047350","https://openalex.org/W4368755500","https://openalex.org/W4378465281","https://openalex.org/W4384648324","https://openalex.org/W4387846171","https://openalex.org/W4387846851","https://openalex.org/W4393942911","https://openalex.org/W4396758653","https://openalex.org/W4409657429","https://openalex.org/W6600424091","https://openalex.org/W6603999813","https://openalex.org/W6604009900"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"As":[0],"multimedia":[1],"content":[2],"continues":[3],"to":[4,74,158,192],"grow":[5],"on":[6,96,156],"the":[7,9,69,97,103,147,170,183],"web,":[8],"integration":[10,79,121],"of":[11,133,186],"visual":[12],"and":[13,94,130,203],"textual":[14],"data":[15],"has":[16,57],"become":[17],"a":[18,180,189],"crucial":[19],"challenge":[20,40],"for":[21],"web":[22],"applications,":[23],"particularly":[24,176],"in":[25,37,52,81,196],"recommendation":[26,55,83,199],"systems.":[27,200],"Large":[28],"Vision":[29],"Language":[30],"Models":[31],"(LVLMs)":[32],"have":[33],"demonstrated":[34],"considerable":[35],"potential":[36],"addressing":[38],"this":[39,64],"across":[41,173],"various":[42,131],"tasks":[43],"that":[44,140,154],"require":[45],"such":[46],"multimodal":[47,53,198],"integration.":[48],"However,":[49],"their":[50,193],"application":[51],"sequential":[54],"(MSR)":[56],"not":[58],"been":[59],"extensively":[60],"studied.":[61],"To":[62],"bridge":[63],"gap,":[65],"we":[66],"introduce":[67],"MSRBench,":[68],"first":[70],"comprehensive":[71],"benchmark":[72,86,137],"designed":[73],"systematically":[75],"evaluate":[76],"different":[77],"LVLM":[78],"strategies":[80],"web-based":[82],"scenarios.":[84],"We":[85],"three":[87],"state-of-the-art":[88],"LVLMs,":[89],"i.e.,":[90],"GPT-4":[91],"Vision,":[92],"GPT-4o,":[93],"Claude-3-Opus,":[95],"next":[98],"item":[99,112,127],"prediction":[100],"task":[101],"using":[102,123,142],"constructed":[104],"Amazon":[105],"Review":[106],"Plus":[107],"dataset,":[108],"which":[109],"includes":[110],"additional":[111],"descriptions":[113],"generated":[114],"by":[115],"LVLMs.":[116],"Our":[117,201],"evaluation":[118],"examines":[119],"five":[120],"strategies:":[122],"LVLMs":[124,143,157,187],"as":[125,144,179],"recommender,":[126],"enhancer,":[128],"reranker,":[129],"combinations":[132],"these":[134],"roles.":[135],"The":[136],"results":[138],"reveal":[139],"1)":[141],"rerankers":[145],"is":[146],"most":[148,174],"effective":[149],"strategy,":[150],"significantly":[151],"outperforming":[152],"others":[153],"rely":[155],"directly":[159],"generate":[160],"recommendations":[161],"or":[162],"only":[163],"enhance":[164],"items;":[165],"2)":[166],"GPT-4o":[167],"consistently":[168],"achieves":[169],"best":[171],"performance":[172],"scenarios,":[175],"when":[177],"employed":[178],"reranker;":[181],"3)":[182],"computational":[184],"inefficiency":[185],"presents":[188],"major":[190],"barrier":[191],"widespread":[194],"adoption":[195],"real-time":[197],"code":[202],"datasets":[204],"are":[205],"available":[206],"at":[207],"https://github.com/PALIN2018/MSRBench.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
