{"id":"https://openalex.org/W4403582631","doi":"https://doi.org/10.1145/3627673.3680014","title":"Scaling Vison-Language Foundation Model to 12 Billion Parameters in Baidu Dynamic Image Advertising","display_name":"Scaling Vison-Language Foundation Model to 12 Billion Parameters in Baidu Dynamic Image Advertising","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403582631","doi":"https://doi.org/10.1145/3627673.3680014"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3680014","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3680014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","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/A5102734030","display_name":"Xinyu Zhao","orcid":"https://orcid.org/0009-0000-0253-5488"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Zhao","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-0253-5488","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103326213","display_name":"Kang Zhao","orcid":"https://orcid.org/0009-0000-3053-3965"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Zhao","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-3053-3965","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101725735","display_name":"Zhipeng Jin","orcid":"https://orcid.org/0009-0003-0863-2539"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Jin","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-0863-2539","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747784","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0001-5077-4782"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5077-4782","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325818","display_name":"Wen Tao","orcid":"https://orcid.org/0009-0002-5481-4512"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Tao","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-5481-4512","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088487947","display_name":"Xiaodong Chen","orcid":"https://orcid.org/0009-0006-8069-2845"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Chen","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-8069-2845","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011745550","display_name":"Cong Han","orcid":"https://orcid.org/0009-0003-6516-1139"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Han","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-6516-1139","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086810479","display_name":"Shuanglong Li","orcid":"https://orcid.org/0009-0002-7346-5258"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuanglong Li","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-7346-5258","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034880019","display_name":"Lin Liu","orcid":"https://orcid.org/0009-0003-7305-8940"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Liu","raw_affiliation_strings":["Baidu Search Ads, Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-7305-8940","affiliations":[{"raw_affiliation_string":"Baidu Search Ads, Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98301712"],"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":"5102","last_page":"5110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9208999872207642,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9208999872207642,"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/foundation","display_name":"Foundation (evidence)","score":0.6168017387390137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5996964573860168},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5247775912284851},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.44572579860687256},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.42338141798973083},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3681545555591583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3282463550567627},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3216797113418579},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.16546323895454407},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.12264183163642883},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10930684208869934}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.6168017387390137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5996964573860168},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5247775912284851},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.44572579860687256},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.42338141798973083},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3681545555591583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3282463550567627},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3216797113418579},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.16546323895454407},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.12264183163642883},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10930684208869934},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3680014","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627673.3680014","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2033101724","https://openalex.org/W2749708282","https://openalex.org/W2963527096","https://openalex.org/W3102566412","https://openalex.org/W3154430790","https://openalex.org/W4224308101","https://openalex.org/W4304014690","https://openalex.org/W4366344047","https://openalex.org/W4384652685","https://openalex.org/W6810081322"],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W2793937822","https://openalex.org/W2790817834","https://openalex.org/W2220552745","https://openalex.org/W2068840890"],"abstract_inverted_index":{"Dynamic":[0,86],"image":[1,20,50,167],"advertising":[2,9,111],"is":[3,127],"an":[4],"add-on":[5],"service":[6],"in":[7,16,48,73,85,134,145,156],"search":[8,14,208],"that":[10,99,171],"matches":[11],"visuals":[12],"to":[13,43,80,96,122,199],"ads":[15],"real-time.":[17],"However,":[18],"the":[19,30,44,69,128,140,188],"matching":[21],"system":[22,189],"encompasses":[23],"various":[24],"sub-tasks":[25],"with":[26,108,148],"different":[27],"objectives,":[28],"increasing":[29],"complexity":[31],"of":[32,63,143,192],"achieving":[33],"global":[34],"optimization.":[35],"Besides,":[36],"prevalent":[37],"long-tailed":[38],"data":[39,113],"poses":[40],"a":[41,61,91],"challenge":[42],"multimodal":[45,64,82,131],"representation":[46,71,132],"learning":[47],"dynamic":[49],"advertising.":[51],"Recently,":[52],"vision-language":[53],"pre-trained":[54],"models":[55,176],"have":[56],"achieved":[57],"remarkable":[58],"performance":[59,150],"across":[60,177],"variety":[62],"tasks,":[65],"and":[66,103,114,166,179,203,207],"implemented":[67,186],"as":[68,97],"foundational":[70],"model":[72,94,133],"electronic":[74],"business":[75,146],"scenarios.":[76],"In":[77],"this":[78],"paper,":[79],"improve":[81],"content":[83,168],"understanding":[84],"Image":[87],"adVERtising,":[88],"we":[89,119],"present":[90],"viSion-language":[92],"rEpresentation":[93],"(referred":[95],"DIVERSE)":[98],"learns":[100],"on":[101,151,187],"cross-view":[102],"cross-token":[104],"contrastive":[105],"loss.":[106],"Moreover,":[107,182],"large-scale":[109],"curated":[110],"image-text":[112],"extensive":[115],"efficient":[116],"training":[117],"techniques,":[118],"scale":[120],"DIVERSE":[121],"12":[123],"billion":[124],"parameters,":[125],"which":[126],"biggest":[129],"Chinese":[130],"industrial":[135],"practices.":[136],"Experiment":[137],"results":[138],"demonstrate":[139],"distinct":[141],"advantages":[142],"DIVERSE12B":[144,183],"datasets,":[147],"competitive":[149],"public":[152],"benchmarks.":[153],"Further":[154],"evaluation":[155],"downstream":[157],"applications":[158],"including":[159],"ad":[160],"text-image":[161,163],"retrieval,":[162],"relevance":[164],"modeling,":[165],"moderation,":[169],"shows":[170],"it":[172],"outperforms":[173],"previous":[174],"separately-trained":[175],"offline":[178],"online":[180],"metrics.":[181],"has":[184],"been":[185],"primary":[190],"traffic":[191],"Baidu":[193],"Search":[194],"Ads,":[195],"bringing":[196],"considerable":[197],"increase":[198],"both":[200],"user":[201],"experience,":[202],"revenue":[204],"for":[205],"advertisers":[206],"engine.":[209]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}