{"id":"https://openalex.org/W7129065452","doi":"https://doi.org/10.1145/3773966.3777958","title":"MOON: Generative MLLM-based Multimodal Representation Learning for E-commerce Product Understanding","display_name":"MOON: Generative MLLM-based Multimodal Representation Learning for E-commerce Product Understanding","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129065452","doi":"https://doi.org/10.1145/3773966.3777958"},"language":null,"primary_location":{"id":"doi:10.1145/3773966.3777958","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777958","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3773966.3777958","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063777354","display_name":"Daoze Zhang","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":true,"raw_author_name":"Daoze Zhang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0001-0149-4220","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048683915","display_name":"Chenghan Fu","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":"Chenghan Fu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-1889-7732","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126089336","display_name":"Zhanheng Nie","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":"Zhanheng Nie","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-6313-3504","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126102790","display_name":"Jianyu Liu","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":"Jianyu Liu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-4772-6380","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076657105","display_name":"Wanxian Guan","orcid":"https://orcid.org/0000-0002-3774-886X"},"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":"Wanxian Guan","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3774-886X","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126092883","display_name":"Yuan Gao","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":"Yuan Gao","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0005-7781-1498","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126137285","display_name":"Jun Song","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":"Jun Song","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5778-6452","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126160107","display_name":"Pengjie Wang","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":"Pengjie Wang","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-4285-5033","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jian Xu","orcid":"https://orcid.org/0000-0003-3111-1005"},"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":"Jian Xu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3111-1005","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073856221","display_name":"Bo Zheng","orcid":"https://orcid.org/0000-0002-4037-6315"},"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":"Bo Zheng","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4037-6315","affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5063777354"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30809967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"924","last_page":"933"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.18080000579357147,"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":0.18080000579357147,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1444000005722046,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.11969999969005585,"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/generative-model","display_name":"Generative model","score":0.609499990940094},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5777000188827515},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5343000292778015},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.5152000188827515},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48170000314712524},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4099000096321106},{"id":"https://openalex.org/keywords/new-product-development","display_name":"New product development","score":0.3944000005722046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7032999992370605},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.609499990940094},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5777000188827515},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5343000292778015},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.5152000188827515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5055999755859375},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48170000314712524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42419999837875366},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C19351080","wikidata":"https://www.wikidata.org/wiki/Q1395034","display_name":"New product development","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31450000405311584},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C120823896","wikidata":"https://www.wikidata.org/wiki/Q1043226","display_name":"Product design","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27869999408721924}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773966.3777958","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777958","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"}],"best_oa_location":{"id":"doi:10.1145/3773966.3777958","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777958","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":[{"score":0.714093029499054,"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":24,"referenced_works":["https://openalex.org/W1486317198","https://openalex.org/W2194775991","https://openalex.org/W2893689064","https://openalex.org/W2920292591","https://openalex.org/W3034896171","https://openalex.org/W3035485997","https://openalex.org/W3107492437","https://openalex.org/W3158343399","https://openalex.org/W3200686557","https://openalex.org/W3202384916","https://openalex.org/W3207410886","https://openalex.org/W4224919569","https://openalex.org/W4226445989","https://openalex.org/W4290927857","https://openalex.org/W4308586874","https://openalex.org/W4312457846","https://openalex.org/W4321485547","https://openalex.org/W4324333799","https://openalex.org/W4386066596","https://openalex.org/W4387968297","https://openalex.org/W4402727764","https://openalex.org/W4403577831","https://openalex.org/W4409361147","https://openalex.org/W4412886676"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,36,76,87,97,111,151,162,169,202,221,227],"rapid":[2],"advancement":[3],"of":[4,44,78,90,99,134,173,229],"e-commerce,":[5],"exploring":[6],"general":[7],"representations":[8],"rather":[9],"than":[10],"task-specific":[11],"ones":[12],"has":[13],"attracted":[14],"increasing":[15],"research":[16],"attention.":[17],"For":[18],"product":[19,61,94,119,138,147,187,215,232],"understanding,":[20],"although":[21],"existing":[22],"discriminative":[23],"dual-flow":[24],"architectures":[25],"drive":[26],"progress":[27],"in":[28,84,93,146],"this":[29,66],"field,":[30],"they":[31],"inherently":[32],"struggle":[33],"to":[34,72,149,167],"model":[35,115,192],"many-to-one":[37],"alignment":[38],"between":[39],"multiple":[40],"images":[41,148],"and":[42,80,96,136,153,159,171,201,217,224],"texts":[43],"products.":[45],"Therefore,":[46],"we":[47,109,178],"argue":[48],"that":[49],"generative":[50,113],"Multimodal":[51],"Large":[52],"Language":[53],"Models":[54],"(MLLMs)":[55],"hold":[56],"significant":[57],"potential":[58],"for":[59,103,118,131,185,231],"improving":[60],"representation":[62,120],"learning.":[63,121],"Nevertheless,":[64],"achieving":[65],"goal":[67],"still":[68],"remains":[69],"non-trivial":[70],"due":[71],"several":[73],"key":[74],"challenges:":[75],"lack":[77],"multimodal":[79,135,182],"aspect-aware":[81],"modeling":[82,133],"modules":[83],"typical":[85],"LLMs;":[86],"common":[88],"presence":[89],"background":[91,157],"noise":[92],"images;":[95],"absence":[98],"a":[100,126,180],"standard":[101],"benchmark":[102,183,200],"evaluation.":[104],"To":[105],"address":[106],"these":[107],"issues,":[108],"propose":[110],"first":[112],"MLLM-based":[114],"named":[116],"MOON":[117,230],"Our":[122],"method":[123],"(1)":[124],"employs":[125],"guided":[127],"Mixture-of-Experts":[128],"(MoE)":[129],"module":[130],"targeted":[132],"aspect-specific":[137],"content;":[139],"(2)":[140],"effectively":[141],"detects":[142],"core":[143],"semantic":[144],"regions":[145],"mitigate":[150],"distraction":[152],"interference":[154],"caused":[155],"by":[156],"noise;":[158],"(3)":[160],"introduces":[161],"specialized":[163],"negative":[164,174],"sampling":[165],"strategy":[166],"increase":[168],"difficulty":[170],"diversity":[172],"samples.":[175],"In":[176],"addition,":[177],"release":[179],"large-scale":[181],"MBE":[184],"various":[186,209],"understanding":[188],"tasks.":[189],"Experimentally,":[190],"our":[191,199],"demonstrates":[193],"competitive":[194],"zero-shot":[195],"performance":[196],"on":[197],"both":[198],"public":[203],"dataset,":[204],"showcasing":[205],"strong":[206],"generalization":[207],"across":[208],"downstream":[210],"tasks,":[211],"including":[212],"cross-modal":[213],"retrieval,":[214],"classification,":[216],"attribute":[218],"prediction.":[219],"Furthermore,":[220],"case":[222],"study":[223],"visualization":[225],"illustrate":[226],"effectiveness":[228],"understanding.":[233]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-17T00:00:00"}