{"id":"https://openalex.org/W4405355457","doi":"https://doi.org/10.1109/iccv51701.2025.01958","title":"V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding","display_name":"V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405355457","doi":"https://doi.org/10.1109/iccv51701.2025.01958"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01958","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.09616","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100758728","display_name":"Junbo Ge","orcid":"https://orcid.org/0000-0002-9360-7332"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junqi Ge","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368266","display_name":"Ziyi Chen","orcid":"https://orcid.org/0000-0002-8093-8466"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Chen","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925559","display_name":"Jintao Lin","orcid":"https://orcid.org/0000-0002-0009-8090"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jintao Lin","raw_affiliation_strings":["University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101417268","display_name":"Jinguo Zhu","orcid":"https://orcid.org/0000-0002-3616-4264"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinguo Zhu","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027234036","display_name":"Xihui Liu","orcid":"https://orcid.org/0000-0002-1791-8745"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xihui Liu","raw_affiliation_strings":["University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026944066","display_name":"Jifeng Dai","orcid":"https://orcid.org/0000-0002-6785-0785"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jifeng Dai","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xizhou Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xizhou Zhu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7946,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66885658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"21070","last_page":"21084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9958999752998352,"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":0.9958999752998352,"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":0.9395999908447266,"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/T12031","display_name":"Speech and dialogue systems","score":0.9254999756813049,"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/encoding","display_name":"Encoding (memory)","score":0.6886166930198669},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6539762020111084},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.6350478529930115},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6285585761070251},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.562890887260437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4272302985191345},{"id":"https://openalex.org/keywords/position-paper","display_name":"Position paper","score":0.4237651824951172},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3739575445652008},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09712257981300354},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09122097492218018},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.06386840343475342},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.05205643177032471}],"concepts":[{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6886166930198669},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6539762020111084},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.6350478529930115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6285585761070251},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.562890887260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4272302985191345},{"id":"https://openalex.org/C78780964","wikidata":"https://www.wikidata.org/wiki/Q7233193","display_name":"Position paper","level":2,"score":0.4237651824951172},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3739575445652008},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09712257981300354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09122097492218018},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.06386840343475342},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.05205643177032471},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.01958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01958","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:2412.09616","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.09616","pdf_url":"https://arxiv.org/pdf/2412.09616","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:hub.hku.hk:10722/359192","is_oa":false,"landing_page_url":"https://hub.hku.hk/handle/10722/359192","pdf_url":null,"source":{"id":"https://openalex.org/S4377196271","display_name":"The HKU Scholars Hub (University of Hong Kong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I889458895","host_organization_name":"University of Hong Kong","host_organization_lineage":["https://openalex.org/I889458895"],"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":"Conference_Paper"},{"id":"doi:10.48550/arxiv.2412.09616","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.09616","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.09616","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.09616","pdf_url":"https://arxiv.org/pdf/2412.09616","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4092911450","display_name":null,"funder_award_id":"62376134","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":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405355457.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2911039683","https://openalex.org/W2382416307","https://openalex.org/W2169127058","https://openalex.org/W1966415008","https://openalex.org/W3112644326","https://openalex.org/W4389316227","https://openalex.org/W2204729203","https://openalex.org/W2187575493","https://openalex.org/W2203842767","https://openalex.org/W2389520089"],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"shown":[4],"promising":[5],"capabilities":[6,41],"in":[7,15,19],"handling":[8],"various":[9],"multimodal":[10,48,113,133,143,162,184],"tasks,":[11],"yet":[12],"they":[13],"struggle":[14],"long-context":[16,40,47,142,161,195],"scenarios,":[17],"particularly":[18],"tasks":[20],"involving":[21],"videos,":[22],"high-resolution":[23],"images,":[24],"or":[25],"lengthy":[26],"image-text":[27],"documents.":[28],"In":[29],"our":[30,45,140],"work,":[31],"we":[32,86],"first":[33],"conduct":[34],"an":[35],"empirical":[36],"analysis":[37],"of":[38,42,111,120,169,182],"the":[39,56,75,79,118,147,166,170,178],"VLMs":[43],"using":[44],"augmented":[46,141],"datasets.":[49],"Our":[50,115],"findings":[51],"reveal":[52],"that":[53,98],"directly":[54],"applying":[55],"positional":[57,95],"encoding":[58,77,96],"mechanism":[59],"used":[60],"for":[61,104,193],"textual":[62],"tokens":[63,66],"to":[64,122,126,145,175,187],"visual":[65,105],"is":[67,173,180],"suboptimal,":[68],"and":[69,101,129,160],"VLM":[70],"performance":[71,156],"degrades":[72],"sharply":[73],"when":[74,165],"position":[76],"exceeds":[78],"model's":[80],"context":[81],"window.":[82],"To":[83],"address":[84],"this,":[85],"propose":[87],"Variable":[88],"Visual":[89],"Position":[90],"Encoding":[91],"(V2PE),":[92],"a":[93],"novel":[94],"approach":[97],"employs":[99],"variable":[100],"smaller":[102],"increments":[103],"tokens,":[106,177,189],"enabling":[107],"more":[108],"efficient":[109],"management":[110],"long":[112,132],"sequences.":[114],"experiments":[116],"demonstrate":[117],"effectiveness":[119],"V2PE":[121,138],"enhances":[123],"VLMs'":[124],"ability":[125],"effectively":[127],"understand":[128],"reason":[130],"over":[131],"contexts.":[134],"We":[135],"further":[136],"integrate":[137],"with":[139],"datasets":[144],"fine-tune":[146],"open-source":[148],"VLM,":[149],"InternVL2.":[150],"The":[151],"fine-tuned":[152],"model":[153,179],"achieves":[154],"strong":[155],"on":[157],"both":[158],"standard":[159],"tasks.":[163],"Notably,":[164],"sequence":[167],"length":[168],"training":[171],"dataset":[172],"increased":[174],"256K":[176],"capable":[181],"processing":[183],"sequences":[185],"up":[186],"1M":[188],"highlighting":[190],"its":[191],"potential":[192],"real-world":[194],"applications.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}