{"id":"https://openalex.org/W7167928365","doi":"https://doi.org/10.1145/3805712.3809695","title":"Reconstructing Content with Collaborative Attention for Universal Multimodal Representation Learning","display_name":"Reconstructing Content with Collaborative Attention for Universal Multimodal Representation Learning","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7167928365","doi":"https://doi.org/10.1145/3805712.3809695"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809695","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809695","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809695","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140390061","display_name":"Jiahan Chen","orcid":"https://orcid.org/0009-0000-3768-714X"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahan Chen","raw_affiliation_strings":["State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-3768-714X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701873","display_name":"Da Li","orcid":"https://orcid.org/0009-0009-0345-7771"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Da Li","raw_affiliation_strings":["State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-0345-7771","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034939611","display_name":"Hengran Zhang","orcid":"https://orcid.org/0009-0004-1144-1298"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengran Zhang","raw_affiliation_strings":["State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-1144-1298","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084642830","display_name":"Yinqiong Cai","orcid":"https://orcid.org/0000-0002-7869-8213"},"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":"Yinqiong Cai","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7869-8213","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032745070","display_name":"Lixin Su","orcid":"https://orcid.org/0009-0008-1246-1740"},"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":"Lixin Su","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-1246-1740","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088621320","display_name":"Jiafeng Guo","orcid":"https://orcid.org/0000-0002-9509-8674"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Guo","raw_affiliation_strings":["State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9509-8674","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008762356","display_name":"Daiting Shi","orcid":"https://orcid.org/0000-0003-4926-3357"},"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":"Daiting Shi","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4926-3357","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101771060","display_name":"Dawei Yin","orcid":"https://orcid.org/0000-0002-0684-6205"},"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":"Dawei Yin","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0684-6205","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040708820","display_name":"Keping Bi","orcid":"https://orcid.org/0000-0001-5123-4999"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keping Bi","raw_affiliation_strings":["State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-4999","affiliations":[{"raw_affiliation_string":"State Key Laboratory of AI Safety, Beijing, China, Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China, and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94584566,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.30550000071525574,"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/T10028","display_name":"Topic Modeling","score":0.30550000071525574,"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":0.2700999975204468,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.20389999449253082,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.8190000057220459},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6200000047683716},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.5271999835968018},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.40880000591278076},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.3662000000476837},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.36169999837875366}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8190000057220459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459999918937683},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6200000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5674999952316284},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3569999933242798},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3377000093460083},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2779136372","wikidata":"https://www.wikidata.org/wiki/Q10283002","display_name":"Information flow","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809695","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809695","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"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809695","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809695","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47140803933143616}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W3120043490","https://openalex.org/W4312643954","https://openalex.org/W4312846625","https://openalex.org/W4400528754","https://openalex.org/W4404782013","https://openalex.org/W4412888456","https://openalex.org/W4413638510","https://openalex.org/W7133196460","https://openalex.org/W7160326358"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"embedding":[1,47,77,160,181],"models,":[2],"rooted":[3],"in":[4],"multimodal":[5,76,96,125,180],"large":[6],"language":[7],"models":[8,182],"(MLLMs),":[9],"have":[10],"yielded":[11],"significant":[12],"performance":[13,191],"improvements":[14],"across":[15],"diverse":[16],"tasks":[17],"such":[18],"as":[19,75,168],"retrieval":[20],"and":[21,33,41,56,105,156,186],"classification.":[22],"However,":[23],"most":[24],"existing":[25,177],"approaches":[26],"rely":[27],"heavily":[28],"on":[29,91,148],"large-scale":[30],"contrastive":[31,144],"learning":[32],"offer":[34],"limited":[35],"exploration":[36],"of":[37,44,60,68,132,176],"how":[38],"the":[39,53,66,102,112,118,124,129,133,136,140,174],"architectural":[40],"training":[42],"paradigms":[43],"MLLMs":[45,61],"affect":[46],"quality.":[48,161],"While":[49],"effective":[50,170],"for":[51,94,142],"generation,":[52],"causal":[54],"attention":[55,103],"next-token":[57],"prediction":[58],"paradigm":[59,89],"does":[62],"not":[63],"explicitly":[64],"encourage":[65],"formation":[67],"globally":[69],"compact":[70,185],"representations,":[71,188],"limiting":[72],"their":[73,190],"effectiveness":[74],"backbones.":[78],"To":[79],"address":[80],"this,":[81],"we":[82,100],"propose":[83],"CoCoA,":[84],"a":[85],"Content":[86],"reconstruction":[87,109,166],"pre-training":[88],"based":[90],"Collaborative":[92],"Attention":[93],"universal":[95],"representation":[97],"learning.":[98,145],"Specifically,":[99],"restructure":[101],"flow":[104],"introduce":[106],"an":[107,169],"EOS-based":[108],"task,":[110],"encouraging":[111],"model":[113,126],"to":[114,127,172,183],"reconstruct":[115],"input":[116,134],"from":[117],"corresponding":[119],"(EOS)":[120,137],"embeddings.":[121],"This":[122],"drives":[123],"compress":[128],"semantic":[130],"information":[131],"into":[135],"token,":[138],"laying":[139],"foundations":[141],"subsequent":[143],"Extensive":[146],"experiments":[147],"MMEB-V1":[149],"demonstrate":[150],"that":[151,164],"CoCoA":[152],"built":[153],"upon":[154],"Qwen2-VL":[155],"Qwen2.5-VL":[157],"significantly":[158],"improves":[159],"Results":[162],"validate":[163],"content":[165],"serves":[167],"strategy":[171],"maximize":[173],"value":[175],"data,":[178],"enabling":[179],"generate":[184],"informative":[187],"raising":[189],"ceiling.":[192],"Our":[193],"project":[194],"is":[195],"available":[196],"at":[197],"https://github.com/Trustworthy-Information-Access/CoCoA.":[198]},"counts_by_year":[],"updated_date":"2026-07-11T05:49:48.208612","created_date":"2026-07-11T00:00:00"}