{"id":"https://openalex.org/W4416750160","doi":"https://doi.org/10.1109/iros60139.2025.11246734","title":"STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation","display_name":"STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750160","doi":"https://doi.org/10.1109/iros60139.2025.11246734"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100321600","display_name":"Jiamin Wang","orcid":"https://orcid.org/0000-0003-1096-3727"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamin Wang","raw_affiliation_strings":["ShanghaiTech University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102699315","display_name":"Yichen Yao","orcid":"https://orcid.org/0009-0006-9319-9339"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Yao","raw_affiliation_strings":["ShanghaiTech University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638121","display_name":"Xiang Feng","orcid":"https://orcid.org/0000-0003-0807-2036"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Feng","raw_affiliation_strings":["ShanghaiTech University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100523757","display_name":"Hang Wu","orcid":"https://orcid.org/0009-0001-8485-629X"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hang Wu","raw_affiliation_strings":["Yinwang Intelligent Technology Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yinwang Intelligent Technology Co. Ltd","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079594358","display_name":"Yaming Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yaming Wang","raw_affiliation_strings":["Yinwang Intelligent Technology Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yinwang Intelligent Technology Co. Ltd","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005770588","display_name":"Qingqiu Huang","orcid":"https://orcid.org/0000-0002-6467-1634"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qingqiu Huang","raw_affiliation_strings":["Yinwang Intelligent Technology Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yinwang Intelligent Technology Co. Ltd","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102015139","display_name":"Yuexin Ma","orcid":"https://orcid.org/0000-0001-7237-988X"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexin Ma","raw_affiliation_strings":["ShanghaiTech University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005226727","display_name":"Xinge Zhu","orcid":"https://orcid.org/0000-0003-0107-8099"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xinge Zhu","raw_affiliation_strings":["Yinwang Intelligent Technology Co. Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yinwang Intelligent Technology Co. Ltd","institution_ids":["https://openalex.org/I4210153682"]}]}],"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":null,"issue":null,"first_page":"14163","last_page":"14169"},"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":0.9016000032424927,"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":0.9016000032424927,"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":0.023399999365210533,"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":0.008799999952316284,"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/feature","display_name":"Feature (linguistics)","score":0.5730000138282776},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.475600004196167},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.4706000089645386},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4659000039100647},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.40689998865127563},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.38920000195503235},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3612000048160553},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.3546999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7397000193595886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6100000143051147},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5730000138282776},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43540000915527344},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.38920000195503235},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C76956256","wikidata":"https://www.wikidata.org/wiki/Q27610560","display_name":"Process modeling","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246734","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2183341477","https://openalex.org/W4312933868","https://openalex.org/W4385571093","https://openalex.org/W4390872297","https://openalex.org/W4392016505","https://openalex.org/W4393148430","https://openalex.org/W4396754486","https://openalex.org/W4402716256","https://openalex.org/W4402727021","https://openalex.org/W4402778069","https://openalex.org/W4403706620","https://openalex.org/W4404722496","https://openalex.org/W4413157524"],"related_works":[],"abstract_inverted_index":{"The":[0,117],"generation":[1,101,163],"of":[2,34,181],"temporally":[3],"consistent,":[4],"high-fidelity":[5],"driving":[6,17,75,161,175,183],"videos":[7,184],"over":[8],"extended":[9],"horizons":[10],"presents":[11],"a":[12,55,86],"fundamental":[13],"challenge":[14],"in":[15,158],"autonomous":[16],"world":[18],"modeling.":[19],"Existing":[20],"approaches":[21],"often":[22],"suffer":[23],"from":[24],"error":[25,143],"accumulation":[26],"and":[27,37,64,85,107,111,132,141],"feature":[28,40,62],"misalignment":[29],"due":[30],"to":[31,122,172],"inadequate":[32],"decoupling":[33,131],"spatio-temporal":[35],"dynamics":[36],"limited":[38],"cross-frame":[39],"propagation":[41],"mechanisms.":[42],"To":[43,71],"address":[44],"these":[45],"limitations,":[46],"we":[47,78,167],"present":[48],"STAGE":[49,152],"(Streaming":[50],"Temporal":[51,81],"Attention":[52],"Generative":[53],"Engine),":[54],"novel":[56,87],"auto-regressive":[57,133],"framework":[58],"that":[59,151],"pioneers":[60],"hierarchical":[61],"coordination":[63],"multi-phase":[65],"optimization":[66],"for":[67],"sustainable":[68],"video":[69,76,96,100,162],"synthesis.":[70],"achieve":[72],"high-quality":[73,182],"long-horizon":[74,160],"generation,":[77],"introduce":[79],"Hierarchical":[80],"Feature":[82],"Transfer":[83],"(HTFT)":[84],"multi-stage":[88,118],"training":[89,119,125],"strategy.":[90],"HTFT":[91],"enhances":[92],"temporal":[93,106],"consistency":[94],"between":[95,115],"frames":[97,180],"throughout":[98],"the":[99,105,124,147,159,186,192],"process":[102,109,135],"by":[103,196],"modeling":[104],"denoising":[108,113],"separately":[110],"transferring":[112],"features":[114],"frames.":[116],"strategy":[120],"is":[121],"divide":[123],"into":[126],"three":[127],"stages,":[128],"through":[129],"model":[130,139],"inference":[134],"simulation,":[136],"thereby":[137],"accelerating":[138],"convergence":[140],"reducing":[142],"accumulation.":[144],"Experiments":[145],"on":[146,185],"Nuscenes":[148,187],"dataset":[149],"show":[150],"has":[153],"significantly":[154],"surpassed":[155],"existing":[156,197],"methods":[157],"task.":[164],"In":[165],"addition,":[166],"also":[168],"explored":[169],"STAGE\u2019s":[170],"ability":[171],"generate":[173],"unlimited-length":[174],"videos.":[176],"We":[177],"generated":[178],"600":[179],"dataset,":[188],"which":[189],"far":[190],"exceeds":[191],"maximum":[193],"length":[194],"achievable":[195],"methods.":[198],"Our":[199],"project":[200],"homepage:https://4dvlab.github.io/STAGE/":[201]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}