{"id":"https://openalex.org/W4411143519","doi":"https://doi.org/10.1109/tcsvt.2025.3578266","title":"Manager: Aggregating Insights From Unimodal Experts in Two-Tower VLMs and MLLMs","display_name":"Manager: Aggregating Insights From Unimodal Experts in Two-Tower VLMs and MLLMs","publication_year":2025,"publication_date":"2025-06-09","ids":{"openalex":"https://openalex.org/W4411143519","doi":"https://doi.org/10.1109/tcsvt.2025.3578266"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2025.3578266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3578266","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.11515","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100319784","display_name":"Xu Xiao\ue00b","orcid":"https://orcid.org/0000-0001-5774-1094"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiao Xu","raw_affiliation_strings":["Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, Heilongjiang, China","Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, Heilongjiang, China"],"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]},{"raw_affiliation_string":"Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029082837","display_name":"Libo Qin","orcid":"https://orcid.org/0000-0002-3619-675X"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Qin","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019108029","display_name":"Wanxiang Che","orcid":"https://orcid.org/0000-0002-3907-0335"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210161462","display_name":"Heilongjiang Institute of Technology","ror":"https://ror.org/05x0m9n95","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210161462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanxiang Che","raw_affiliation_strings":["Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, Heilongjiang, China","Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, Heilongjiang, China"],"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"]},{"raw_affiliation_string":"Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066305082","display_name":"Min\u2010Yen Kan","orcid":"https://orcid.org/0000-0001-8507-3716"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Min-Yen Kan","raw_affiliation_strings":["School of Computing, National University of Singapore, Queenstown, Singapore","School of Computing, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Queenstown, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100319784"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210161462"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21675584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":"12","first_page":"12278","last_page":"12291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11938","display_name":"ERP Systems Implementation and Impact","score":0.637499988079071,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11938","display_name":"ERP Systems Implementation and Impact","score":0.637499988079071,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12594","display_name":"Collaboration in agile enterprises","score":0.604200005531311,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11223","display_name":"Maritime Ports and Logistics","score":0.5392000079154968,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5497973561286926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44471126794815063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5497973561286926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44471126794815063}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcsvt.2025.3578266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3578266","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2506.11515","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11515","pdf_url":"https://arxiv.org/pdf/2506.11515","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.11515","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11515","pdf_url":"https://arxiv.org/pdf/2506.11515","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2565984771","display_name":null,"funder_award_id":"62236004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3596954764","display_name":null,"funder_award_id":"62476073","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4035621038","display_name":null,"funder_award_id":"62441603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4070007828","display_name":null,"funder_award_id":"62206078","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W4396696052"],"abstract_inverted_index":{"Two-Tower":[0,65,102],"Vision\u2013Language":[1],"Models":[2],"(VLMs)":[3],"have":[4],"demonstrated":[5],"strong":[6,128],"performance":[7,17,133,160],"across":[8,163],"various":[9],"downstream":[10,136,173],"VL":[11,95,123,137],"tasks.":[12,138],"While":[13],"BridgeTower":[14],"further":[15,231],"enhances":[16],"by":[18,205,226],"building":[19],"bridges":[20],"between":[21],"encoders,":[22],"it":[23],"<italic":[24,35,50],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[25,36,51],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">(i)</i>":[26],"suffers":[27],"from":[28,84,211],"ineffective":[29],"layer-by-layer":[30],"utilization":[31],"of":[32,42,45,87,161,166],"unimodal":[33,46,89],"representations,":[34],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">(ii)</i>":[37],"restricts":[38],"the":[39,56,64,101,113,145,158,176,191,202,222,227],"flexible":[40],"exploitation":[41],"different":[43,85,164],"levels":[44,86],"semantic":[47,223],"knowledge,":[48],"and":[49,77,97,130,169,190,216,230,235],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">(iii)</i>":[52],"is":[53,179],"limited":[54],"to":[55,91,144],"evaluation":[57],"on":[58,134,171],"traditional":[59],"low-resolution":[60],"datasets":[61],"only":[62],"with":[63,120],"VLM":[66,103,110],"architecture.":[67],"In":[68],"this":[69],"work,":[70],"we":[71,105,140],"propose":[72],"Manager,":[73],"a":[74,108,198],"lightweight,":[75],"efficient":[76],"effective":[78],"plugin":[79,199],"that":[80,111,154,186,200],"adaptively":[81],"aggregates":[82],"insights":[83],"pre-trained":[88],"experts":[90],"facilitate":[92],"more":[93,207],"comprehensive":[94],"alignment":[96],"fusion.":[98],"First,":[99],"under":[100],"architecture,":[104],"introduce":[106],"ManagerTower,":[107],"novel":[109],"introduces":[112],"manager":[114,189],"in":[115],"each":[116],"cross-modal":[117],"layer.":[118],"Whether":[119],"or":[121,181],"without":[122],"pre-training,":[124],"ManagerTower":[125],"outperforms":[126],"previous":[127],"baselines":[129],"achieves":[131],"superior":[132],"4":[135],"Moreover,":[139],"extend":[141],"our":[142,188],"exploration":[143],"latest":[146],"Multimodal":[147],"Large":[148],"Language":[149],"Model":[150],"(MLLM)":[151],"architecture.We":[152],"demonstrate":[153],"LLaVA-OV-Manager":[155],"significantly":[156],"boosts":[157],"zero-shot":[159],"LLaVA-OV":[162],"categories":[165],"capabilities,":[167],"images,":[168],"resolutions":[170],"20":[172],"datasets,":[174],"whether":[175],"multi-grid":[177,192,228],"algorithm":[178,193,229],"enabled":[180],"not.":[182],"In-depth":[183],"analysis":[184],"reveals":[185],"both":[187],"can":[194,220],"be":[195],"viewed":[196],"as":[197],"improves":[201],"visual":[203,209],"representation":[204],"capturing":[206],"diverse":[208],"details":[210],"two":[212],"orthogonal":[213],"perspectives":[214],"(depth":[215],"width).":[217],"Their":[218],"synergy":[219],"mitigate":[221],"ambiguity":[224],"caused":[225],"improve":[232],"performance.":[233],"Code":[234],"models":[236],"are":[237],"available":[238],"at":[239],"https://github.com/LooperXX/ManagerTower.":[240]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}