{"id":"https://openalex.org/W7158321241","doi":"https://doi.org/10.1145/3805712.3809977","title":"Structural and Disentangled Adaptation of Large Vision Language Models for Multimodal Recommendation","display_name":"Structural and Disentangled Adaptation of Large Vision Language Models for Multimodal Recommendation","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7158321241","doi":"https://doi.org/10.1145/3805712.3809977"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809977","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809977","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/10.1145/3805712.3809977","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134831160","display_name":"Zhongtao Rao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongtao Rao","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-2113-5902","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134825421","display_name":"Peilin Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Peilin Zhou","raw_affiliation_strings":["New York University Abu Dhabi, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0001-6763-5236","affiliations":[{"raw_affiliation_string":"New York University Abu Dhabi, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I120250893"]}]},{"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":"https://openalex.org/A5134870769","display_name":"Zhiwei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiwei Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-1331-2827","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134843737","display_name":"Shoujin Wang","orcid":null},"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":"last","author":{"id":"https://openalex.org/A5134863298","display_name":"Nan Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Tang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2832-0295","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"4074","last_page":"4079"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7114999890327454,"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":0.7114999890327454,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.13950000703334808,"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":0.029200000688433647,"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/discriminative-model","display_name":"Discriminative model","score":0.710099995136261},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6345999836921692},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5899999737739563},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5619000196456909},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4973999857902527},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.48429998755455017},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4805000126361847},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4607999920845032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8482000231742859},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.710099995136261},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6345999836921692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5992000102996826},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5899999737739563},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5619000196456909},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.48429998755455017},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4372999966144562},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3813999891281128},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3805712.3809977","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809977","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:2512.06883","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2512.06883","pdf_url":"https://arxiv.org/pdf/2512.06883","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"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809977","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809977","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":[{"score":0.6956079602241516,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"recommendation":[1,41],"enhances":[2],"accuracy":[3],"by":[4],"leveraging":[5],"visual":[6],"and":[7,10,57,65,78,95,106,147,157,167,175],"textual":[8],"signals,":[9],"its":[11],"success":[12],"largely":[13],"depends":[14],"on":[15,135,170],"learning":[16],"high-quality":[17],"cross-modal":[18],"representations.":[19],"Recent":[20],"advances":[21],"in":[22,155,159],"Large":[23],"Vision-Language":[24],"Models":[25],"(LVLMs)":[26],"offer":[27],"unified":[28],"multimodal":[29,146],"representation":[30,49],"learning,":[31],"making":[32],"them":[33],"a":[34,79,90,117],"promising":[35],"backbone.":[36],"However,":[37],"applying":[38],"LVLMs":[39],"to":[40,45,61,130,165],"remains":[42],"challenging":[43],"due":[44],"(":[46,66],"i":[47],")":[48,68],"misalignment,":[50],"where":[51,73],"gaps":[52],"between":[53],"specific":[54],"domain":[55],"data":[56],"general":[58],"pre-training":[59],"lead":[60],"unaligned":[62],"embedding":[63],"spaces,":[64],"ii":[67],"gradient":[69,123,132],"conflicts":[70,124],"during":[71],"fine-tuning,":[72],"shared":[74],"adapters":[75],"cause":[76],"interference":[77],"lack":[80],"of":[81,153],"discriminative":[82],"power.":[83],"To":[84],"address":[85],"this,":[86],"we":[87],"propose":[88],"SDA,":[89],"lightweight":[91],"framework":[92],"for":[93],"Structural":[94,103],"Disentangled":[96],"Adaptation,":[97],"which":[98],"integrates":[99,142],"two":[100],"components:":[101],"Cross-Modal":[102],"Alignment":[104],"(CMSA)":[105],"Modality-Disentangled":[107],"Adaptation":[108],"(MoDA).":[109],"CMSA":[110],"aligns":[111],"embeddings":[112],"using":[113],"intra-modal":[114],"structures":[115],"as":[116],"soft":[118],"teacher,":[119],"while":[120],"MoDA":[121],"mitigates":[122],"via":[125],"expertized,":[126],"gated":[127],"low-rank":[128],"paths":[129],"disentangle":[131],"flows.":[133],"Experiments":[134],"three":[136],"public":[137],"Amazon":[138],"datasets":[139],"show":[140],"SDA":[141],"seamlessly":[143],"with":[144],"existing":[145],"sequential":[148],"recommenders,":[149],"yielding":[150],"average":[151],"gains":[152,169],"6.15%":[154],"Hit@10":[156],"8.64%":[158],"NDCG@10.":[160],"It":[161],"also":[162],"achieves":[163],"up":[164],"12.83%":[166],"18.70%":[168],"long-tail":[171],"items.":[172],"Our":[173],"code":[174],"full":[176],"experimental":[177],"results":[178],"are":[179],"available":[180],"at":[181],"https://github.com/RaoZhongtao/SDA.":[182]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-30T00:00:00"}