{"id":"https://openalex.org/W7138313380","doi":"https://doi.org/10.1609/aaai.v40i29.39594","title":"ViTCoP: Accelerating Large Vision-Language Models via Visual and Textual Semantic Collaborative Pruning","display_name":"ViTCoP: Accelerating Large Vision-Language Models via Visual and Textual Semantic Collaborative Pruning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138313380","doi":"https://doi.org/10.1609/aaai.v40i29.39594"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i29.39594","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i29.39594","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39594/43555","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/39594/43555","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129752915","display_name":"Wen Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Luo","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129747818","display_name":"Peng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Chen","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124001765","display_name":"Xiaotao Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotao Huang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129695799","display_name":"LiQun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"LiQun Huang","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47720641"],"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":"29","first_page":"24151","last_page":"24159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9735999703407288,"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":0.9735999703407288,"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":0.005400000140070915,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.003700000001117587,"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/redundancy","display_name":"Redundancy (engineering)","score":0.652899980545044},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6067000031471252},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5156999826431274},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5109000205993652},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46799999475479126},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.40880000591278076},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.37459999322891235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209999799728394},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.652899980545044},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6067000031471252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5748999714851379},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5109000205993652},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46799999475479126},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44530001282691956},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37459999322891235},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.305400013923645},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2538999915122986},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i29.39594","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i29.39594","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39594/43555","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/39594","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39594","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.v40i29.39594","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i29.39594","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39594/43555","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138313380.pdf","grobid_xml":"https://content.openalex.org/works/W7138313380.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0,62,137],"Vision-Language":[1,138],"Models":[2,64,139],"(LVLMs)":[3],"incur":[4],"high":[5],"computational":[6],"costs":[7],"due":[8,41,57],"to":[9,42,50,58,100,110],"significant":[10],"redundancy":[11,52,83],"in":[12,44,60,85,130],"their":[13],"visual":[14,25,38,107],"tokens.":[15,108],"To":[16,66],"effectively":[17],"reduce":[18],"this":[19],"cost,":[20],"researchers":[21],"have":[22],"proposed":[23],"various":[24,136],"token":[26,127],"pruning":[27,43,59,182],"methods.":[28],"However,":[29],"existing":[30,149],"methods":[31,150,175],"are":[32],"generally":[33],"limited,":[34],"either":[35],"losing":[36],"critical":[37,103],"information":[39,51],"prematurely":[40],"the":[45,54,61,86,93,120,126,131],"vision":[46,87],"encoder,":[47],"or":[48],"leading":[49],"among":[53],"selected":[55],"tokens":[56],"Language":[63],"(LLMs).":[65],"address":[67],"these":[68],"challenges,":[69],"we":[70,118],"propose":[71],"a":[72],"Visual":[73],"and":[74,104,154,165],"Textual":[75],"Semantic":[76],"Collaborative":[77],"Pruning":[78],"framework":[79],"(ViTCoP)":[80],"that":[81,141],"combines":[82],"filtering":[84],"encoder":[88],"with":[89,113],"step-wise":[90],"co-pruning":[91],"within":[92],"LLM":[94],"based":[95],"on":[96,135,151],"its":[97,170],"hierarchical":[98],"characteristics,":[99],"efficiently":[101],"preserve":[102],"informationally":[105],"diverse":[106],"Meanwhile,":[109],"ensure":[111],"compatibility":[112],"acceleration":[114],"techniques":[115],"like":[116],"FlashAttention,":[117],"introduce":[119],"L2":[121],"norm":[122],"of":[123],"K-vectors":[124],"as":[125],"saliency":[128],"metric":[129],"LLM.":[132],"Extensive":[133],"experiments":[134],"demonstrate":[140],"ViTCoP":[142],"not":[143],"only":[144],"achieves":[145],"state-of-the-art":[146],"performance":[147,171],"surpassing":[148],"both":[152],"image":[153],"video":[155],"understanding":[156],"tasks,":[157],"but":[158],"also":[159],"significantly":[160],"reduces":[161],"model":[162],"inference":[163],"latency":[164],"GPU":[166],"memory":[167],"consumption.":[168],"Notably,":[169],"advantage":[172],"over":[173],"other":[174],"becomes":[176],"even":[177],"more":[178],"pronounced":[179],"under":[180],"extreme":[181],"rates.":[183]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}