{"id":"https://openalex.org/W4415330791","doi":"https://doi.org/10.1109/tcsvt.2026.3663658","title":"Pyramid Token Pruning for High-Resolution Large Vision-Language Models via Region, Token, and Instruction-Guided Importance","display_name":"Pyramid Token Pruning for High-Resolution Large Vision-Language Models via Region, Token, and Instruction-Guided Importance","publication_year":2026,"publication_date":"2026-02-11","ids":{"openalex":"https://openalex.org/W4415330791","doi":"https://doi.org/10.1109/tcsvt.2026.3663658"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2026.3663658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3663658","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.15704","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuxuan Liang","orcid":"https://orcid.org/0009-0004-5039-7568"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Liang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-5039-7568","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xu Li","orcid":"https://orcid.org/0009-0001-2431-3410"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-2431-3410","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110235151","display_name":"Xiaolei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolei Chen","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-5700-9326","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114417932","display_name":"Haotian Chen","orcid":"https://orcid.org/0009-0009-7187-3523"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haotian Chen","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-0593-5281","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yi Zheng","orcid":"https://orcid.org/0009-0006-1549-6979"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zheng","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-1549-6979","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhe Liu","orcid":"https://orcid.org/0009-0003-3668-6518"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Liu","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-3668-6518","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rui Zhu","orcid":"https://orcid.org/0009-0007-7226-6923"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhu","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-7226-6923","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-9633-0033"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9633-0033","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003418019","display_name":"Xiangyang Xue","orcid":"https://orcid.org/0000-0002-4897-9209"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Xue","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4897-9209","affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01350393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"6","first_page":"8372","last_page":"8384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9951000213623047,"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":0.9951000213623047,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.987500011920929,"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/security-token","display_name":"Security token","score":0.6987000107765198},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6725999712944031},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5726000070571899},{"id":"https://openalex.org/keywords/subnetwork","display_name":"Subnetwork","score":0.5625},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5267000198364258},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5019000172615051},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4968999922275543},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4749999940395355},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.45829999446868896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907000184059143},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6987000107765198},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6725999712944031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6671000123023987},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5726000070571899},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.5625},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5019000172615051},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4968999922275543},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.4309000074863434},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.39410001039505005},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3765000104904175},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35920000076293945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2778251979","wikidata":"https://www.wikidata.org/wiki/Q7936617","display_name":"Visual processing","level":3,"score":0.27140000462532043},{"id":"https://openalex.org/C2779668609","wikidata":"https://www.wikidata.org/wiki/Q623092","display_name":"Rapid serial visual presentation","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.26420000195503235}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tcsvt.2026.3663658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3663658","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:2509.15704","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.15704","pdf_url":"https://arxiv.org/pdf/2509.15704","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:doi:10.48550/arxiv.2509.15704","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2509.15704","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.15704","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:2509.15704","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.15704","pdf_url":"https://arxiv.org/pdf/2509.15704","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":[{"id":"https://openalex.org/G2652456738","display_name":null,"funder_award_id":"62576110","funder_id":"https://openalex.org/F4320332588","funder_display_name":"Shanghai Key Laboratory of Intelligent Information Processing"}],"funders":[{"id":"https://openalex.org/F4320332588","display_name":"Shanghai Key Laboratory of Intelligent Information Processing","ror":"https://ror.org/013q1eq08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"recently":[5],"demonstrated":[6],"strong":[7],"multimodal":[8],"understanding,":[9],"yet":[10],"their":[11],"fine-grained":[12],"visual":[13,44,68,83],"perception":[14],"is":[15,25],"often":[16],"constrained":[17],"by":[18,81],"low":[19],"input":[20],"resolutions.":[21],"A":[22],"common":[23],"remedy":[24],"to":[26,99],"partition":[27],"high-resolution":[28],"images":[29],"into":[30],"multiple":[31],"sub-images":[32],"for":[33],"separate":[34],"encoding,":[35],"but":[36],"this":[37,53],"approach":[38],"drastically":[39],"inflates":[40],"the":[41],"number":[42],"of":[43],"tokens":[45,89],"and":[46,73,117],"introduces":[47],"prohibitive":[48],"inference":[49,118],"overhead.":[50],"To":[51],"overcome":[52],"challenge,":[54],"we":[55],"propose":[56],"Pyramid":[57],"Token":[58],"Pruning":[59],"(PTP),":[60],"a":[61],"training-free":[62],"strategy":[63],"that":[64,109],"hierarchically":[65],"integrates":[66],"bottom-up":[67],"saliency":[69],"at":[70],"both":[71],"region":[72],"token":[74],"levels":[75],"with":[76,120],"top-down":[77],"instruction-guided":[78],"relevance.":[79],"Inspired":[80],"human":[82],"cognition,":[84],"PTP":[85,110],"selectively":[86],"preserves":[87],"more":[88],"from":[90],"salient":[91],"regions":[92],"while":[93],"further":[94],"emphasizing":[95],"those":[96],"most":[97],"relevant":[98],"task":[100],"instructions.":[101],"Extensive":[102],"experiments":[103],"on":[104],"13":[105],"diverse":[106],"benchmarks":[107],"show":[108],"substantially":[111],"reduces":[112],"computational":[113],"cost,":[114],"memory":[115],"usage,":[116],"latency,":[119],"negligible":[121],"performance":[122],"degradation.":[123]},"counts_by_year":[],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-19T00:00:00"}