{"id":"https://openalex.org/W7138140523","doi":"https://doi.org/10.1609/aaai.v40i9.37711","title":"FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion","display_name":"FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138140523","doi":"https://doi.org/10.1609/aaai.v40i9.37711"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i9.37711","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37711","pdf_url":null,"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://doi.org/10.1609/aaai.v40i9.37711","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129731263","display_name":"Xiangyang Luo","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":"Xiangyang Luo","raw_affiliation_strings":["Tsinghua University\nKling Team, Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University\nKling Team, Kuaishou Technology","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129691210","display_name":"Qingyu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I124391630","display_name":"Arab Open University","ror":"https://ror.org/04dqhen73","country_code":"OM","type":"education","lineage":["https://openalex.org/I124391630","https://openalex.org/I4210093932"]}],"countries":["OM"],"is_corresponding":false,"raw_author_name":"Qingyu Li","raw_affiliation_strings":["Kling Team, Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kling Team, Kuaishou Technology","institution_ids":["https://openalex.org/I124391630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125151232","display_name":"Xiaokun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I124391630","display_name":"Arab Open University","ror":"https://ror.org/04dqhen73","country_code":"OM","type":"education","lineage":["https://openalex.org/I124391630","https://openalex.org/I4210093932"]}],"countries":["OM"],"is_corresponding":false,"raw_author_name":"Xiaokun Liu","raw_affiliation_strings":["Kling Team, Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kling Team, Kuaishou Technology","institution_ids":["https://openalex.org/I124391630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129661553","display_name":"Wenyu Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I124391630","display_name":"Arab Open University","ror":"https://ror.org/04dqhen73","country_code":"OM","type":"education","lineage":["https://openalex.org/I124391630","https://openalex.org/I4210093932"]}],"countries":["OM"],"is_corresponding":false,"raw_author_name":"Wenyu Qin","raw_affiliation_strings":["Kling Team, Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kling Team, Kuaishou Technology","institution_ids":["https://openalex.org/I124391630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129723327","display_name":"Miao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I124391630","display_name":"Arab Open University","ror":"https://ror.org/04dqhen73","country_code":"OM","type":"education","lineage":["https://openalex.org/I124391630","https://openalex.org/I4210093932"]}],"countries":["OM"],"is_corresponding":false,"raw_author_name":"Miao Yang","raw_affiliation_strings":["Kling Team, Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kling Team, Kuaishou Technology","institution_ids":["https://openalex.org/I124391630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129698073","display_name":"Meng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I124391630","display_name":"Arab Open University","ror":"https://ror.org/04dqhen73","country_code":"OM","type":"education","lineage":["https://openalex.org/I124391630","https://openalex.org/I4210093932"]}],"countries":["OM"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["Kling Team, Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kling Team, Kuaishou Technology","institution_ids":["https://openalex.org/I124391630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129706888","display_name":"Pengfei Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I124391630","display_name":"Arab Open University","ror":"https://ror.org/04dqhen73","country_code":"OM","type":"education","lineage":["https://openalex.org/I124391630","https://openalex.org/I4210093932"]}],"countries":["OM"],"is_corresponding":false,"raw_author_name":"Pengfei Wan","raw_affiliation_strings":["Kling Team, Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kling Team, Kuaishou Technology","institution_ids":["https://openalex.org/I124391630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129718281","display_name":"Di ZHANG","orcid":null},"institutions":[{"id":"https://openalex.org/I124391630","display_name":"Arab Open University","ror":"https://ror.org/04dqhen73","country_code":"OM","type":"education","lineage":["https://openalex.org/I124391630","https://openalex.org/I4210093932"]}],"countries":["OM"],"is_corresponding":false,"raw_author_name":"Di Zhang","raw_affiliation_strings":["Kling Team, Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kling Team, Kuaishou Technology","institution_ids":["https://openalex.org/I124391630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129713375","display_name":"Kun Gai","orcid":null},"institutions":[{"id":"https://openalex.org/I124391630","display_name":"Arab Open University","ror":"https://ror.org/04dqhen73","country_code":"OM","type":"education","lineage":["https://openalex.org/I124391630","https://openalex.org/I4210093932"]}],"countries":["OM"],"is_corresponding":false,"raw_author_name":"Kun Gai","raw_affiliation_strings":["Kling Team, Kuaishou Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kling Team, Kuaishou Technology","institution_ids":["https://openalex.org/I124391630"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129739480","display_name":"Shao-Lun Huang","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":"Shao-Lun Huang","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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"9","first_page":"7689","last_page":"7697"},"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":0.7182999849319458,"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":0.7182999849319458,"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":0.11900000274181366,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.027699999511241913,"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/pipeline","display_name":"Pipeline (software)","score":0.6984000205993652},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6554999947547913},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6128000020980835},{"id":"https://openalex.org/keywords/weaving","display_name":"Weaving","score":0.5705000162124634},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5304999947547913},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5257999897003174},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.49639999866485596},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4449999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8037999868392944},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6984000205993652},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6554999947547913},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6128000020980835},{"id":"https://openalex.org/C54525549","wikidata":"https://www.wikidata.org/wiki/Q2553445","display_name":"Weaving","level":2,"score":0.5705000162124634},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5257999897003174},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48420000076293945},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4424999952316284},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.37560001015663147},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3149999976158142},{"id":"https://openalex.org/C2778307483","wikidata":"https://www.wikidata.org/wiki/Q5149038","display_name":"Colored","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.2815999984741211},{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.27399998903274536},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27000001072883606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26919999718666077},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i9.37711","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37711","pdf_url":null,"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/37711","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37711","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.v40i9.37711","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37711","pdf_url":null,"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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6258983016014099}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"video":[1,64,159,180,211],"generation":[2],"models":[3],"perform":[4],"well":[5],"at":[6],"single-shot":[7],"synthesis":[8],"but":[9],"struggle":[10],"with":[11],"multi-shot":[12,49,137,179],"videos,":[13],"facing":[14],"critical":[15],"challenges":[16],"in":[17],"maintaining":[18],"character":[19,104],"and":[20,25,32,83,105,158,197,209],"background":[21],"consistency":[22,82,196],"across":[23],"shots":[24,101],"flexibly":[26],"generating":[27],"videos":[28,50],"of":[29,51,70,115,165],"arbitrary":[30,52],"length":[31],"shot":[33,95,120],"count.":[34],"To":[35,66,161],"address":[36,67],"these":[37],"limitations,":[38],"we":[39,169],"introduce":[40],"\\textbf{FilmWeaver},":[41],"a":[42,90,94,109,113,172,177],"novel":[43],"framework":[44,128],"designed":[45],"to":[46,61,76,102,121,135,141,175],"generate":[47],"consistent,":[48,207],"length.":[53],"First,":[54],"it":[55],"employs":[56],"an":[57],"autoregressive":[58],"diffusion":[59],"paradigm":[60],"achieve":[62,87],"arbitrary-length":[63],"generation.":[65],"the":[68,78,118,163],"challenge":[69],"consistency,":[71],"our":[72,145,166,187],"key":[73],"insight":[74],"is":[75],"decouple":[77],"problem":[79],"into":[80],"inter-shot":[81],"intra-shot":[84],"coherence.":[85],"We":[86],"this":[88,142],"through":[89],"dual-level":[91],"cache":[92],"mechanism:":[93],"memory":[96,111],"caches":[97],"keyframes":[98],"from":[99,117],"preceding":[100],"maintain":[103],"scene":[106],"identity,":[107],"while":[108],"temporal":[110],"retains":[112],"history":[114],"frames":[116],"current":[119],"ensure":[122],"smooth,":[123],"continuous":[124],"motion.":[125],"The":[126],"proposed":[127],"allows":[129],"for":[130,194,204],"flexible,":[131],"multi-round":[132],"user":[133],"interaction":[134],"create":[136],"videos.":[138],"Furthermore,":[139],"due":[140],"decoupled":[143],"design,":[144],"method":[146,188],"demonstrates":[147],"high":[148],"versatility":[149],"by":[150],"supporting":[151],"downstream":[152],"tasks":[153],"such":[154],"as":[155],"multi-concept":[156],"injection":[157],"extension.":[160],"facilitate":[162],"training":[164],"consistency-aware":[167],"method,":[168],"also":[170],"developed":[171],"comprehensive":[173],"pipeline":[174],"construct":[176],"high-quality":[178],"dataset.":[181],"Extensive":[182],"experimental":[183],"results":[184],"demonstrate":[185],"that":[186],"surpasses":[189],"existing":[190],"approaches":[191],"on":[192],"metrics":[193],"both":[195],"aesthetic":[198],"quality,":[199],"opening":[200],"up":[201],"new":[202],"possibilities":[203],"creating":[205],"more":[206],"controllable,":[208],"narrative-driven":[210],"content.":[212]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}
