{"id":"https://openalex.org/W7203486548","doi":"https://doi.org/10.48550/arxiv.2608.13492","title":"AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)","display_name":"AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)","publication_year":2026,"publication_date":"2026-08-13","ids":{"openalex":"https://openalex.org/W7203486548","doi":"https://doi.org/10.48550/arxiv.2608.13492"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.13492","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.13492","pdf_url":"https://arxiv.org/pdf/2608.13492","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.13492","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140237199","display_name":"AlayaWorld Team","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"AlayaWorld Team","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114126140","display_name":"Kaipeng Zhang","orcid":"https://orcid.org/0000-0001-6105-6532","observed_orcids":["https://orcid.org/0000-0001-6105-6532"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kaipeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122091798","display_name":"Chuanhao Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chuanhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102729249","display_name":"Yifan Zhan","orcid":"https://orcid.org/0009-0002-3565-0508","observed_orcids":["https://orcid.org/0009-0002-3565-0508"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhan, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078980036","display_name":"Yongtao Ge","orcid":"https://orcid.org/0000-0003-1265-3204","observed_orcids":["https://orcid.org/0000-0003-1265-3204"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Yongtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111026732","display_name":"Yuanyang Yin","orcid":"https://orcid.org/0009-0003-1967-4638","observed_orcids":["https://orcid.org/0009-0003-1967-4638"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Yuanyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132862396","display_name":"Jiaming Tan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Jiaming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147216702","display_name":"Kang He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050298259","display_name":"Liaoyuan Fan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Liaoyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122198674","display_name":"Mingliang Zhai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhai, Mingliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068038722","display_name":"Ruicong Liu","orcid":"https://orcid.org/0000-0002-8460-8763","observed_orcids":["https://orcid.org/0000-0002-8460-8763"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ruicong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037481266","display_name":"Xiaojie Xu","orcid":"https://orcid.org/0000-0002-3614-1070","observed_orcids":["https://orcid.org/0000-0002-3614-1070"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Xiaojie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111115258","display_name":"Xuangeng Chu","orcid":"https://orcid.org/0009-0008-1925-7566","observed_orcids":["https://orcid.org/0009-0008-1925-7566"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu, Xuangeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140238873","display_name":"Zhen Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134554135","display_name":"Zhengyuan Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Zhengyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123486948","display_name":"Zhixiang Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102629811","display_name":"Zian Meng","orcid":"https://orcid.org/0009-0001-7965-0668","observed_orcids":["https://orcid.org/0009-0001-7965-0668"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Zian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5146530791","display_name":"Zihui Gao","orcid":"https://orcid.org/0000-0003-2980-1488","observed_orcids":["https://orcid.org/0000-0003-2980-1488"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Zihui","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":true,"cited_by_count":9,"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":0.9810000061988831,"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":0.9810000061988831,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.008899999782443047,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.006200000178068876,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/spatial-memory","display_name":"spatial memory","score":0.7310000061988831},{"id":"https://openalex.org/keywords/viewpoint-control","display_name":"viewpoint control","score":0.753000020980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709000110626221},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6948000192642212},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5834000110626221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4884999990463257},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4564000070095062},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.39149999618530273},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3476000130176544},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C2780412824","wikidata":"https://www.wikidata.org/wiki/Q3686420","display_name":"Signal conditioning","level":3,"score":0.3084999918937683},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3041999936103821},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3009999990463257},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.13492","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.13492","pdf_url":"https://arxiv.org/pdf/2608.13492","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.13492","doi":"https://doi.org/10.48550/arxiv.2608.13492","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.13492","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.13492","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.13492","pdf_url":"https://arxiv.org/pdf/2608.13492","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203486548.pdf","grobid_xml":"https://content.openalex.org/works/W7203486548.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W7105740705","https://openalex.org/W7162394427","https://openalex.org/W7162778655"],"related_works":["https://openalex.org/W7170055304","https://openalex.org/W7203471921","https://openalex.org/W7164883443","https://openalex.org/W7221766207","https://openalex.org/W4416047763","https://openalex.org/W7212275598","https://openalex.org/W4416138746","https://openalex.org/W4417460464","https://openalex.org/W7221804993","https://openalex.org/W4417036201"],"abstract_inverted_index":{"This":[0],"report":[1],"presents":[2],"an":[3],"improved":[4],"version":[5,118],"of":[6,111],"AlayaWorld.":[7],"While":[8],"the":[9,22,36,51,76,90,100,112,116,143,164,177,189],"backbone":[10],"architecture,":[11],"chunk-wise":[12],"autoregressive":[13],"generation":[14],"scheme,":[15],"and":[16,33,62,167,172,174],"training":[17,171],"data":[18],"remain":[19],"unchanged":[20],"from":[21],"previous":[23,77],"release,":[24],"we":[25,68,74,88],"substantially":[26],"revise":[27],"how":[28],"conditioning":[29,47,91,126],"signals":[30,48],"are":[31,97],"represented":[32],"integrated":[34],"into":[35],"model.":[37],"The":[38],"new":[39,117],"design":[40],"is":[41,185],"guided":[42],"by":[43],"a":[44,82,138],"simple":[45],"principle:":[46],"should":[49],"match":[50],"generated":[52,113],"content":[53],"as":[54,56,137],"closely":[55],"possible":[57],"in":[58,99,146],"both":[59],"latent":[60,103,129],"representation":[61],"temporal":[63,106],"structure.":[64],"To":[65],"this":[66],"end,":[67],"make":[69],"two":[70],"major":[71],"changes.":[72],"First,":[73],"replace":[75],"depth-warping-based":[78],"spatial":[79,135,191],"memory":[80,136,152,156],"with":[81,105,109,127],"streaming":[83],"3D":[84],"point-cache":[85],"renderer.":[86],"Second,":[87],"redesign":[89],"pipeline":[92],"so":[93],"that":[94,154,182],"visual":[95],"conditions":[96],"encoded":[98],"same":[101],"causal-VAE":[102],"space,":[104],"statistics":[107],"consistent":[108],"those":[110],"video.":[114],"Concretely,":[115],"introduces":[119],"six":[120],"modifications:":[121],"(1)":[122],"replacing":[123],"static-frame":[124],"image":[125],"motion-aware":[128],"conditioning;":[130],"(2)":[131],"causally":[132],"encoding":[133,166],"re-rendered":[134,190],"continuous":[139],"sequence;":[140],"(3)":[141],"aligning":[142],"temporal-memory":[144],"window":[145],"pixel":[147],"space;":[148],"(4)":[149],"adopting":[150],"hard":[151],"dropout":[153],"removes":[155],"tokens":[157],"rather":[158],"than":[159],"zeroing":[160],"them;":[161],"(5)":[162],"unifying":[163],"VAE":[165],"decoding":[168],"protocol":[169],"across":[170],"inference;":[173],"(6)":[175],"removing":[176],"camera":[178],"AdaLN":[179],"branch,":[180],"such":[181],"viewpoint":[183],"control":[184],"provided":[186],"entirely":[187],"through":[188],"condition.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":9}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-15T00:00:00"}