{"id":"https://openalex.org/W7204205586","doi":"https://doi.org/10.48550/arxiv.2608.23383","title":"Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds","display_name":"Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204205586","doi":"https://doi.org/10.48550/arxiv.2608.23383"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.23383","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23383","pdf_url":"https://arxiv.org/pdf/2608.23383","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.23383","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138266330","display_name":"Nan Duan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Nan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020769158","display_name":"Haoyang Huang","orcid":"https://orcid.org/0009-0009-1431-9112","observed_orcids":["https://orcid.org/0009-0009-1431-9112","https://orcid.org/0000-0002-3804-5437"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Haoyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101252846","display_name":"Weiyang Jin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Weiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138008566","display_name":"Haoran Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138211263","display_name":"Yaowei Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yaowei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138249487","display_name":"Yuming Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yuming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148053138","display_name":"Yijun Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148131597","display_name":"Xin Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121129672","display_name":"Xiaoxiao Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Xiaoxiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129462602","display_name":"Yanwen Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Yanwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129016858","display_name":"Yaofeng Su","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Yaofeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148121442","display_name":"Yilang Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yilang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148092807","display_name":"Haoyu Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040083129","display_name":"Zeyue Xue","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Zeyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059916557","display_name":"Songchun Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Songchun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110808792","display_name":"Junhao Zhuang","orcid":"https://orcid.org/0000-0002-1642-0750","observed_orcids":["https://orcid.org/0000-0002-1642-0750"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Junhao","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9609000086784363,"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":0.9609000086784363,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03700000047683716,"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/T10860","display_name":"Speech and Audio Processing","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/speaker-identity-preservation","display_name":"speaker identity preservation","score":0.5239999890327454},{"id":"https://openalex.org/keywords/world-modeling","display_name":"world modeling","score":0.5220000147819519},{"id":"https://openalex.org/keywords/image-text-alignment","display_name":"image-text alignment","score":0.36500000953674316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.739300012588501},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5938000082969666},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.5526999831199646},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5248000025749207},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44510000944137573},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4097999930381775},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30169999599456787},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C86297840","wikidata":"https://www.wikidata.org/wiki/Q6045397","display_name":"Interactive design","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C2781009140","wikidata":"https://www.wikidata.org/wiki/Q7170389","display_name":"Persistence (discontinuity)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2635999917984009},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23383","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23383","pdf_url":"https://arxiv.org/pdf/2608.23383","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.23383","doi":"https://doi.org/10.48550/arxiv.2608.23383","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23383","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.23383","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23383","pdf_url":"https://arxiv.org/pdf/2608.23383","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7215736923","https://openalex.org/W4417460464","https://openalex.org/W7170055304","https://openalex.org/W7220373354","https://openalex.org/W7161561000","https://openalex.org/W7119504059","https://openalex.org/W7117989537","https://openalex.org/W7214245996","https://openalex.org/W4405355504","https://openalex.org/W7117721277"],"abstract_inverted_index":{"Video":[0],"generation":[1,33],"is":[2],"progressing":[3],"beyond":[4],"isolated":[5],"clips":[6],"toward":[7],"long-form":[8],"narratives":[9],"and":[10,21,54,66,75,91,125,127,155,171,176,189,200],"interactive":[11,203],"worlds,":[12],"requiring":[13],"models":[14],"to":[15],"preserve":[16],"identities,":[17],"follow":[18],"user":[19],"controls,":[20],"remain":[22],"stable":[23],"over":[24,144],"extended":[25],"rollouts.":[26,133],"We":[27],"present":[28],"JoyAI-Echo-1.5,":[29],"a":[30,95,112,117,193],"unified":[31],"audio-visual":[32,114],"system":[34],"with":[35,165],"two":[36],"purpose-built":[37],"variants.":[38],"The":[39,78],"long-video":[40,146],"variant":[41,80,160],"introduces":[42],"composable":[43],"cross-shot":[44,149],"memory":[45,76],"that":[46,185],"aggregates":[47],"visual":[48,151,174],"evidence":[49],"across":[50,69,102],"multiple":[51],"prior":[52],"shots":[53],"speaker":[55],"cues":[56],"derived":[57],"from":[58],"speech-filtered":[59],"full-shot":[60],"audio,":[61],"enabling":[62,99],"persistent":[63],"character":[64],"appearance":[65],"voice":[67],"identity":[68],"flexible":[70,103],"combinations":[71],"of":[72,169],"text,":[73],"image,":[74],"conditioning.":[77],"world-model":[79,159],"converts":[81],"heterogeneous":[82],"navigation":[83],"inputs":[84],"into":[85,116],"calibrated":[86],"metric":[87],"6-DoF":[88],"camera":[89],"trajectories":[90],"injects":[92],"them":[93],"through":[94],"geometry-aware":[96],"conditioning":[97],"pathway,":[98],"controller-agnostic":[100],"interaction":[101],"viewpoints.":[104],"To":[105],"support":[106],"efficient":[107],"long-horizon":[108,128,177],"generation,":[109],"we":[110],"transform":[111],"bidirectional":[113],"backbone":[115],"causal":[118],"few-step":[119],"generator":[120],"using":[121],"progressive":[122],"teacher":[123],"forcing":[124],"short-":[126],"Self-Gradient":[129],"Forcing":[130],"on":[131,163,179],"self-generated":[132],"Experiments":[134],"demonstrate":[135],"strong":[136],"performance":[137],"in":[138,148],"both":[139],"settings.":[140],"JoyAI-Echo-1.5":[141],"achieves":[142,172],"improvements":[143],"existing":[145],"baselines":[147],"consistency,":[150],"quality,":[152],"text":[153],"alignment,":[154],"speech":[156],"fidelity.":[157],"Its":[158],"ranks":[161],"first":[162],"WBench,":[164],"an":[166],"average":[167],"score":[168],"81.7,":[170],"leading":[173],"quality":[175],"persistence":[178],"SANA-WM-Bench.":[180],"Together,":[181],"these":[182],"results":[183],"indicate":[184],"memory,":[186],"geometric":[187],"control,":[188],"rollout-aware":[190],"training":[191],"provide":[192],"practical":[194],"foundation":[195],"for":[196],"generating":[197],"coherent":[198],"stories":[199],"continuously":[201],"evolving":[202],"worlds.":[204],"Project":[205],"page:":[206],"https://echo-team-joy-future-academy-jd.github.io/Echo-1.5-Page/.":[207]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}