{"id":"https://openalex.org/W7137902910","doi":"https://doi.org/10.1609/aaai.v40i9.37673","title":"Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models","display_name":"Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137902910","doi":"https://doi.org/10.1609/aaai.v40i9.37673"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i9.37673","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37673","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37673/41635","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37673/41635","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121190807","display_name":"Xuyang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuyang Liu","raw_affiliation_strings":["Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129722463","display_name":"Ziming Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziming Wang","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129704367","display_name":"Junjie Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Chen","raw_affiliation_strings":["Sichuan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University","institution_ids":["https://openalex.org/I24185976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129698110","display_name":"Yuhang Han","orcid":null},"institutions":[{"id":"https://openalex.org/I3133055985","display_name":"Westlake University","ror":"https://ror.org/05hfa4n20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3133055985"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Han","raw_affiliation_strings":["Westlake University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Westlake University","institution_ids":["https://openalex.org/I3133055985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129699287","display_name":"Yingyao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingyao Wang","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108249406","display_name":"J.Y. Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiale Yuan","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129653548","display_name":"Jun Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Song","raw_affiliation_strings":["Taobao & Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao & Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129689302","display_name":"Siteng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siteng Huang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129642857","display_name":"Honggang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honggang Chen","raw_affiliation_strings":["Sichuan University\nPolice Integration Computing Key Laboratory of Sichuan Province"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sichuan University\nPolice Integration Computing Key Laboratory of Sichuan Province","institution_ids":["https://openalex.org/I24185976"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":"40","issue":"9","first_page":"7350","last_page":"7358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6850000023841858,"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":0.6850000023841858,"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":0.04340000078082085,"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":0.042899999767541885,"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/thumbnail","display_name":"Thumbnail","score":0.756600022315979},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6305000185966492},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.6195999979972839},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5583999752998352},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4754999876022339},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.46700000762939453},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.46219998598098755},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.42160001397132874},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.41019999980926514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857000231742859},{"id":"https://openalex.org/C160174412","wikidata":"https://www.wikidata.org/wiki/Q873806","display_name":"Thumbnail","level":3,"score":0.756600022315979},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6305000185966492},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6195999979972839},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5583999752998352},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C509619924","wikidata":"https://www.wikidata.org/wiki/Q17130757","display_name":"Structural complexity","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.3370000123977661},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.3292999863624573},{"id":"https://openalex.org/C150178126","wikidata":"https://www.wikidata.org/wiki/Q18433212","display_name":"Dynamic range compression","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3212999999523163},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2888000011444092},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.2565999925136566}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i9.37673","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37673","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37673/41635","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37673","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37673","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i9.37673","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37673","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37673/41635","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5187113956","display_name":null,"funder_award_id":"2024-","funder_id":"https://openalex.org/F4320336736","funder_display_name":"Chengdu Science and Technology Program"}],"funders":[{"id":"https://openalex.org/F4320336736","display_name":"Chengdu Science and Technology Program","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137902910.pdf","grobid_xml":"https://content.openalex.org/works/W7137902910.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"vision-language":[1],"models":[2],"(LVLMs)":[3],"excel":[4],"at":[5],"visual":[6,160],"understanding":[7],"but":[8],"face":[9],"efficiency":[10],"challenges":[11],"due":[12],"to":[13,37,131,164,170],"quadratic":[14],"complexity":[15],"when":[16],"processing":[17],"long":[18],"multimodal":[19],"contexts.":[20],"While":[21],"token":[22,118],"compression":[23,68,119,135],"can":[24,64],"reduce":[25],"computational":[26],"costs,":[27],"existing":[28],"approaches":[29],"are":[30],"designed":[31],"for":[32,39,76,121],"single-view":[33],"LVLMs":[34,46],"and":[35,96,98,166],"fail":[36],"account":[38],"the":[40,67,85,91,99,126,134,173],"unique":[41],"multi-view":[42],"characteristics":[43,101],"of":[44,69,136,153,159,172],"high-resolution":[45,122],"that":[47,61,148],"use":[48],"dynamic":[49,86],"cropping.":[50],"Current":[51],"methods":[52],"treat":[53],"all":[54],"tokens":[55],"uniformly,":[56],"yet":[57],"our":[58],"analysis":[59],"shows":[60],"global":[62],"thumbnails":[63,95],"naturally":[65],"guide":[66,133],"local":[70,137],"crops":[71,97],"by":[72],"providing":[73],"holistic":[74],"context":[75],"evaluating":[77],"informativeness.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82,109],"first":[83],"analyze":[84],"cropping":[87],"strategy,":[88],"revealing":[89],"both":[90],"complementary":[92],"relationship":[93],"between":[94],"distinct":[100],"across":[102],"different":[103],"crops.":[104],"Based":[105],"on":[106],"these":[107],"insights,":[108],"propose":[110],"''Global":[111],"Compression":[112],"Commander''":[113],"(GlobalCom2),":[114],"a":[115,129],"novel":[116],"plug-and-play":[117],"framework":[120],"LVLMs.":[123],"GlobalCom2":[124,149],"uses":[125],"thumbnail":[127],"as":[128],"''commander''":[130],"adaptively":[132],"crops,":[138],"preserving":[139],"informative":[140],"details":[141],"while":[142,156],"removing":[143],"redundancy.":[144],"Extensive":[145],"experiments":[146],"demonstrate":[147],"maintains":[150],"over":[151],"90%":[152,158],"model":[154],"performance":[155],"compressing":[157],"tokens,":[161],"reducing":[162],"FLOPs":[163],"9.1%":[165],"peak":[167],"memory":[168],"usage":[169],"60%":[171],"original.":[174]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}