{"id":"https://openalex.org/W4416040270","doi":"https://doi.org/10.1109/iccv51701.2025.01605","title":"Long Context Tuning for Video Generation","display_name":"Long Context Tuning for Video Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416040270","doi":"https://doi.org/10.1109/iccv51701.2025.01605"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01605","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.10589","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061091490","display_name":"Yuwei Guo","orcid":"https://orcid.org/0000-0002-2139-4489"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"YuweiGuo Guo","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025976462","display_name":"Ceyuan Yang","orcid":"https://orcid.org/0000-0003-1417-1938"},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Ceyuan Yang","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069660758","display_name":"Ziyan Yang","orcid":"https://orcid.org/0000-0002-9030-2074"},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Ziyan Yang","raw_affiliation_strings":["ByteDance","ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]},{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112510511","display_name":"Ziyao Ma","orcid":"https://orcid.org/0009-0006-7232-8648"},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Zhibei Ma","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111321227","display_name":"Zhijie Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Zhijie Lin","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062978510","display_name":"Zhenheng Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Zhenheng Yang","raw_affiliation_strings":["ByteDance","ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]},{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010087030","display_name":"Dahua Lin","orcid":"https://orcid.org/0000-0002-8865-7896"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dahua Lin","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101867141","display_name":"Lu Jiang","orcid":"https://orcid.org/0000-0002-8611-3828"},"institutions":[{"id":"https://openalex.org/I231086526","display_name":"University of Siedlce","ror":"https://ror.org/01wkb9987","country_code":"PL","type":"education","lineage":["https://openalex.org/I231086526"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Lu Jiang","raw_affiliation_strings":["ByteDance Seed"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance Seed","institution_ids":["https://openalex.org/I231086526"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5061091490"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30961045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17281","last_page":"17291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8508999943733215,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8508999943733215,"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/T11439","display_name":"Video Analysis and Summarization","score":0.0421999990940094,"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":0.01600000075995922,"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/context","display_name":"Context (archaeology)","score":0.6280999779701233},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.507099986076355},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.47519999742507935},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4659000039100647},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.44999998807907104},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4316999912261963},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4000000059604645},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.38909998536109924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8075000047683716},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6280999779701233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5317000150680542},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.507099986076355},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.47519999742507935},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47049999237060547},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4000000059604645},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.32580000162124634},{"id":"https://openalex.org/C19743564","wikidata":"https://www.wikidata.org/wiki/Q25378119","display_name":"Flicker","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3066999912261963},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2587999999523163}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01605","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:2503.10589","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10589","pdf_url":"https://arxiv.org/pdf/2503.10589","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"doi:10.48550/arxiv.2503.10589","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.10589","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.10589","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10589","pdf_url":"https://arxiv.org/pdf/2503.10589","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"video":[3,49],"generation":[4,91,110,131],"can":[5,101,120],"produce":[6,121],"realistic,":[7],"minute-long":[8],"single-shot":[9,48,116],"videos":[10,18],"with":[11,22,96,105,111],"scalable":[12],"diffusion":[13,50],"transformers.":[14],"However,":[15],"real-world":[16],"narrative":[17],"require":[19],"multi-shot":[20,123],"scenes":[21,124],"visual":[23,142],"and":[24,80,88,125,132],"dynamic":[25],"consistency":[26,55],"across":[27],"shots.":[28],"In":[29],"this":[30],"work,":[31],"we":[32],"introduce":[33],"Long":[34],"Context":[35],"Tuning":[36],"(LCT),":[37],"a":[38,73],"training":[39],"paradigm":[40],"that":[41],"expands":[42,61],"the":[43,137],"context":[44],"window":[45],"of":[46],"pre-trained":[47],"models":[51,117],"to":[52,68],"learn":[53],"scene-level":[54],"directly":[56],"from":[57,65],"data.":[58],"Our":[59],"method":[60],"full":[62],"attention":[63,98],"mechanisms":[64],"individual":[66],"shots":[67,71],"encompass":[69],"all":[70],"within":[72],"scene,":[74],"incorporating":[75],"interleaved":[76],"3D":[77],"position":[78],"embedding":[79],"an":[81],"asynchronous":[82],"noise":[83],"strategy,":[84],"enabling":[85],"both":[86],"joint":[87],"auto-regressive":[89,109],"shot":[90,134],"without":[92],"additional":[93],"parameters.":[94],"Models":[95],"bidirectional":[97],"after":[99,118],"LCT":[100,119],"further":[102],"be":[103],"fine-tuned":[104],"context-causal":[106],"attention,":[107],"facilitating":[108],"efficient":[112],"KV-cache.":[113],"Experiments":[114],"demonstrate":[115],"coherent":[122],"exhibit":[126],"emerging":[127],"capabilities,":[128],"including":[129],"compositional":[130],"interactive":[133],"extension,":[135],"paving":[136],"way":[138],"for":[139,147],"more":[140,148],"practical":[141],"content":[143],"creation.":[144],"See":[145],"https://guoyww.github.io/projects/long-context-video/":[146],"details.":[149]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}