{"id":"https://openalex.org/W7224122142","doi":"https://doi.org/10.48550/arxiv.2610.36793","title":"Visual Autoregressive Generation with Next Token Imagination","display_name":"Visual Autoregressive Generation with Next Token Imagination","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224122142","doi":"https://doi.org/10.48550/arxiv.2610.36793"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.36793","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36793","pdf_url":"https://arxiv.org/pdf/2610.36793","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.36793","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148893797","display_name":"Ruihang Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiang, Ruihang","raw_affiliation_strings":["University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160062236","display_name":"Zongyao Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhao, Zongyao","raw_affiliation_strings":["University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139621356","display_name":"Zhaolin Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wang, Zhaolin","raw_affiliation_strings":["University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160002703","display_name":"Yuanwei Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Liu, Yuanwei","raw_affiliation_strings":["University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160061077","display_name":"Xiatian Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhu, Xiatian","raw_affiliation_strings":["University of Surrey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey","institution_ids":["https://openalex.org/I28290843"]}]}],"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":true,"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":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/image-generation","display_name":"image generation","score":0.6209999918937683},{"id":"https://openalex.org/keywords/image-fidelity","display_name":"image fidelity","score":0.3499999940395355},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.47600001096725464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6575999855995178},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.652899980545044},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.61080002784729},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5321000218391418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5149000287055969},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4902999997138977},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43130001425743103},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C207363949","wikidata":"https://www.wikidata.org/wiki/Q462915","display_name":"Visual space","level":3,"score":0.3828999996185303},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33239999413490295},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.32829999923706055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3156999945640564},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26899999380111694},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.2662999927997589}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.36793","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36793","pdf_url":"https://arxiv.org/pdf/2610.36793","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.2610.36793","doi":"https://doi.org/10.48550/arxiv.2610.36793","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.36793","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:2610.36793","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36793","pdf_url":"https://arxiv.org/pdf/2610.36793","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224122142.pdf","grobid_xml":"https://content.openalex.org/works/W7224122142.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417148846","https://openalex.org/W4417077981","https://openalex.org/W7084907680","https://openalex.org/W4404345917","https://openalex.org/W4417280535","https://openalex.org/W7125419484","https://openalex.org/W4415796345","https://openalex.org/W4416052906","https://openalex.org/W7160095423","https://openalex.org/W7164007324"],"abstract_inverted_index":{"The":[0],"space":[1,124],"of":[2,22,74,117,180],"possible":[3],"visual":[4,39,76,99,111,165],"content":[5],"is":[6,47],"enormous,":[7],"and":[8,55,130,175,186,194],"arguably":[9],"unbounded.":[10],"Any":[11],"training":[12,94,196],"set,":[13],"however":[14],"large,":[15],"therefore":[16],"covers":[17],"only":[18,32],"a":[19,78,89,115,138,153,191],"tiny":[20],"fraction":[21],"it.":[23],"Yet":[24],"generative":[25],"models":[26,188],"are":[27,36],"typically":[28],"trained":[29],"to":[30,65,128,144,152],"fit":[31],"the":[33,50,59,75,142,147,163,178],"images":[34],"they":[35],"given.":[37],"In":[38,82],"autoregressive":[40],"(AR)":[41],"generation,":[42],"for":[43],"example,":[44],"each":[45],"token":[46,123],"predicted":[48],"from":[49],"preceding":[51],"ground-truth":[52],"(GT)":[53],"tokens":[54],"supervised":[56],"solely":[57],"by":[58,96,162],"GT":[60,148],"next":[61,149],"token.":[62],"Confining":[63],"learning":[64],"observed":[66],"data":[67],"in":[68],"this":[69,83,107,159],"way":[70],"limits":[71],"how":[72],"much":[73],"distribution":[77],"model":[79,90,143,193],"can":[80,105],"capture.":[81],"work,":[84],"we":[85],"hypothesize":[86],"that":[87,140,157,172],"letting":[88],"imagine":[91],"beyond":[92,146],"its":[93,120],"data,":[95],"exploring":[97],"plausible":[98],"realizations":[100],"it":[101],"has":[102],"never":[103],"observed,":[104],"ease":[106],"limitation.":[108],"We":[109,132],"use":[110],"AR":[112,187],"generation":[113],"as":[114],"proof":[116],"concept,":[118],"since":[119],"fixed,":[121],"discrete":[122],"makes":[125],"imagination":[126,160],"easier":[127],"steer":[129],"constrain.":[131],"propose":[133],"Next":[134],"Token":[135],"Imagination":[136],"(NTI),":[137],"method":[139],"allows":[141],"explore":[145],"token,":[150],"subject":[151],"carefully":[154],"designed":[155],"criterion":[156],"keeps":[158],"bounded":[161],"underlying":[164],"distribution.":[166],"Extensive":[167],"experiments":[168],"on":[169],"ImageNet":[170],"show":[171],"NTI":[173],"substantially":[174],"consistently":[176],"improves":[177],"fidelity":[179],"generated":[181],"images,":[182],"approaching":[183],"state-of-the-art":[184],"diffusion":[185],"while":[189],"using":[190],"smaller":[192],"lower":[195],"cost.":[197]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-29T00:00:00"}