{"id":"https://openalex.org/W4406139826","doi":"https://doi.org/10.1109/iccv51701.2025.02192","title":"FOLDER: Accelerating Multi-Modal Large Language Models with Enhanced Performance","display_name":"FOLDER: Accelerating Multi-Modal Large Language Models with Enhanced Performance","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4406139826","doi":"https://doi.org/10.1109/iccv51701.2025.02192"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.02430","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103098595","display_name":"Haicheng Wang","orcid":"https://orcid.org/0000-0001-8189-6424"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haicheng Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Paris Elite Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Paris Elite Institute of Technology","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027714533","display_name":"Zhipeng Yu","orcid":"https://orcid.org/0000-0002-1326-7789"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhemeng Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,Paris Elite Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Paris Elite Institute of Technology","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092741233","display_name":"Gabriele Spadaro","orcid":"https://orcid.org/0009-0008-4786-1074"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gabriele Spadaro","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100774573","display_name":"Ju Chen","orcid":"https://orcid.org/0000-0001-7674-4776"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"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":["KY","US"],"is_corresponding":false,"raw_author_name":"Chen Ju","raw_affiliation_strings":["Taobao &#x0026; Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao &#x0026; Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210086143","https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022572651","display_name":"Victor Qu\u00e9tu","orcid":"https://orcid.org/0009-0004-2795-3749"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Victor Qu\u00e9tu","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuai Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"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":["KY","US"],"is_corresponding":false,"raw_author_name":"Shuai Xiao","raw_affiliation_strings":["Taobao &#x0026; Tmall Group of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taobao &#x0026; Tmall Group of Alibaba","institution_ids":["https://openalex.org/I4210086143","https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":null,"display_name":"Enzo Tartaglione","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Enzo Tartaglione","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI, T&#x00E9;l&#x00E9;com Paris","institution_ids":["https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":4,"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":null,"issue":null,"first_page":"23614","last_page":"23625"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T10028","display_name":"Topic Modeling","score":0.9973999857902527,"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/T12031","display_name":"Speech and dialogue systems","score":0.9652000069618225,"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/modal","display_name":"Modal","score":0.7484808564186096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5559984445571899},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3874841332435608},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.09247443079948425},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08510473370552063}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7484808564186096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5559984445571899},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3874841332435608},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.09247443079948425},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08510473370552063},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.02192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.02430","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.02430","pdf_url":"https://arxiv.org/pdf/2501.02430","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},{"id":"pmh:oai:HAL:hal-05651244v1","is_oa":false,"landing_page_url":"https://telecom-paris.hal.science/hal-05651244","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV), Oct 2025, Honolulu, United States. IEEE, pp.23614-23625, 2026, &#x27E8;10.1109/ICCV51701.2025.02192&#x27E9;","raw_type":"Proceedings"},{"id":"doi:10.48550/arxiv.2501.02430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.02430","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.02430","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.02430","pdf_url":"https://arxiv.org/pdf/2501.02430","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406139826.pdf"},"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":{"Recently,":[0],"Multi-modal":[1],"Large":[2],"Language":[3],"Models":[4],"(MLLMs)":[5],"have":[6],"shown":[7],"remarkable":[8],"effectiveness":[9,108],"for":[10,37,139],"multi-modal":[11],"tasks":[12],"due":[13],"to":[14,17,56,97,162],"their":[15],"abilities":[16],"generate":[18],"and":[19,68,73,94],"understand":[20],"cross-modal":[21],"data.":[22],"However,":[23],"processing":[24],"long":[25],"sequences":[26],"of":[27,60,79,109,118,164],"visual":[28,32,62,103,116,165],"tokens":[29],"extracted":[30],"from":[31],"backbones":[33],"poses":[34],"a":[35,49,76,132],"challenge":[36],"deployment":[38],"in":[39],"real-time":[40],"applications.":[41],"To":[42],"address":[43],"this":[44],"issue,":[45],"we":[46,84,127],"introduce":[47],"FOLDER,":[48],"simple":[50],"yet":[51],"effective":[52],"plug-and-play":[53],"module":[54],"designed":[55],"reduce":[57],"the":[58,61,80,86,107,115,123,152],"length":[59],"token":[63,81],"sequence,":[64],"mitigating":[65],"both":[66,142],"computational":[67],"memory":[69],"demands":[70],"during":[71],"training":[72,133],"inference.":[74],"Through":[75],"comprehensive":[77],"analysis":[78],"reduction":[82,92],"process,":[83],"analyze":[85],"information":[87,100],"loss":[88],"introduced":[89],"by":[90,111,159],"different":[91],"strategies":[93],"develop":[95],"FOLDER":[96,110,144],"preserve":[98],"key":[99],"while":[101,155],"removing":[102,160],"redundancy.":[104],"We":[105],"showcase":[106],"integrating":[112],"it":[113],"into":[114],"backbone":[117],"several":[119],"MLLMs,":[120],"significantly":[121],"accelerating":[122],"inference":[124],"phase.":[125],"Furthermore,":[126],"evaluate":[128],"its":[129],"utility":[130],"as":[131],"accelerator":[134],"or":[135,147],"even":[136,148],"performance":[137,150],"booster":[138],"MLLMs.":[140],"In":[141],"contexts,":[143],"achieves":[145],"comparable":[146],"better":[149],"than":[151],"original":[153],"models,":[154],"dramatically":[156],"reducing":[157],"complexity":[158],"up":[161],"70%":[163],"tokens.":[166]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
