{"id":"https://openalex.org/W7138308281","doi":"https://doi.org/10.1609/aaai.v40i31.39860","title":"Fine-flow Distilling Coarse-flow Video Generation for Long-Term Driving World Model","display_name":"Fine-flow Distilling Coarse-flow Video Generation for Long-Term Driving World Model","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138308281","doi":"https://doi.org/10.1609/aaai.v40i31.39860"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i31.39860","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39860","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.v40i31.39860","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129726866","display_name":"Xiaodong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129743047","display_name":"Zhirong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhirong Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129641052","display_name":"Peixi Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peixi Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26737053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"31","first_page":"26526","last_page":"26534"},"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":0.891700029373169,"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":0.891700029373169,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.03480000048875809,"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/T12290","display_name":"Human Motion and Animation","score":0.0071000000461936,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5108000040054321},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44510000944137573},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3986000120639801},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.3474000096321106},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.34060001373291016},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3203999996185303},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.30820000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731000185012817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5281000137329102},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5108000040054321},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37790000438690186},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3253999948501587},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C106306483","wikidata":"https://www.wikidata.org/wiki/Q183984","display_name":"Futures contract","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i31.39860","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39860","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/39860","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/39860","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.v40i31.39860","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i31.39860","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":[],"awards":[{"id":"https://openalex.org/G1264567121","display_name":null,"funder_award_id":"62422602","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1947953275","display_name":null,"funder_award_id":"62425101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4011147796","display_name":null,"funder_award_id":"PCL2021A13","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5150481254","display_name":null,"funder_award_id":"PCL2021A13","funder_id":"https://openalex.org/F4320318558","funder_display_name":"Peng Cheng Laboratory"},{"id":"https://openalex.org/G5151253548","display_name":null,"funder_award_id":"62332002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6254270691","display_name":null,"funder_award_id":"62206281","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8687311786","display_name":null,"funder_award_id":"62372010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320318558","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Driving":[0],"world":[1,50,98,104],"models":[2,23,51,58],"are":[3,59,133,156],"used":[4],"to":[5,52,71,79,90,143,158],"simulate":[6],"futures":[7],"by":[8,177,183],"video":[9,64,131,149,187],"generation":[10],"based":[11],"on":[12,62],"the":[13,16,31,41,46,80,118,145,169,186],"condition":[14],"of":[15,48,120,147,189],"current":[17,22],"state":[18],"and":[19,66,74,111,153,161,179],"actions.":[20],"However,":[21,56],"often":[24],"suffer":[25],"serious":[26],"error":[27],"accumulations":[28],"when":[29],"predicting":[30],"long-term":[32,96,160],"future,":[33],"which":[34],"limits":[35],"practical":[36],"applications.":[37],"Recent":[38],"studies":[39],"utilize":[40],"Diffusion":[42],"Transformer":[43],"(DiT)":[44],"as":[45],"backbone":[47],"driving":[49,97,121],"improve":[53,144],"learning":[54,106,110],"flexibility.":[55],"these":[57],"always":[60],"trained":[61],"short":[63],"clips,":[65],"multiple":[67],"roll-out":[68],"generations":[69],"struggle":[70],"produce":[72],"consistent":[73],"reasonable":[75],"long":[76],"videos":[77],"due":[78],"training-inference":[81],"gap.":[82],"To":[83],"this":[84],"end,":[85],"we":[86,101,123],"propose":[87,124],"several":[88],"solutions":[89],"build":[91],"a":[92,125],"simple":[93,126],"yet":[94],"effective":[95],"model.":[99],"First,":[100],"hierarchically":[102],"decouple":[103],"model":[105,174],"into":[107],"large":[108],"motion":[109,114],"bidirectional":[112],"continuous":[113],"learning.":[115],"Then,":[116],"considering":[117],"continuity":[119],"scenes,":[122],"distillation":[127,140],"method":[128],"where":[129],"fine-grained":[130,154],"flows":[132],"self-supervised":[134],"signals":[135],"for":[136,185],"coarse-grained":[137,152],"flows.":[138],"The":[139,151],"is":[141],"designed":[142],"coherence":[146],"infinite":[148],"generation.":[150],"modules":[155],"coordinated":[157],"generate":[159],"temporally":[162],"coherent":[163],"videos.":[164],"On":[165],"NuScenes,":[166],"compared":[167],"with":[168],"state-of-the-art":[170],"front-view":[171],"models,":[172],"our":[173],"improves":[175],"FVD":[176],"27%":[178],"reduces":[180],"inference":[181],"time":[182],"85%":[184],"task":[188],"generating":[190],"110+":[191],"frames.":[192]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}