{"id":"https://openalex.org/W4283388932","doi":"https://doi.org/10.48550/arxiv.2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","display_name":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","publication_year":2022,"publication_date":"2022-06-22","ids":{"openalex":"https://openalex.org/W4283388932","doi":"https://doi.org/10.48550/arxiv.2206.10789"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2206.10789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.10789","pdf_url":"https://arxiv.org/pdf/2206.10789","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.10789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100745253","display_name":"Jiahui Yu","orcid":"https://orcid.org/0000-0002-1215-3851"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yu, Jiahui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059281265","display_name":"Yuanzhong Xu","orcid":"https://orcid.org/0000-0002-5264-5324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yuanzhong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009550511","display_name":"Jing Yu Koh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koh, Jing Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052977443","display_name":"Thang M. Luong","orcid":"https://orcid.org/0000-0003-2279-7164"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luong, Thang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043260617","display_name":"Gunjan Baid","orcid":"https://orcid.org/0000-0002-1339-2547"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baid, Gunjan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687845","display_name":"Zirui Wang","orcid":"https://orcid.org/0000-0002-5927-6322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zirui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064910671","display_name":"Vijay K. Vasudevan","orcid":"https://orcid.org/0000-0002-4509-0973"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasudevan, Vijay","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055207525","display_name":"Alexander Ku","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ku, Alexander","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112656212","display_name":"Yinfei Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yinfei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022200342","display_name":"Burcu Karagol Ayan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ayan, Burcu Karagol","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071599724","display_name":"Ben Hutchinson","orcid":"https://orcid.org/0000-0003-2253-6204"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hutchinson, Ben","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452646","display_name":"Wei Han","orcid":"https://orcid.org/0000-0001-6038-7911"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086908529","display_name":"Zarana Parekh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parekh, Zarana","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100353783","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-0144-9489"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399257","display_name":"Han Zhang","orcid":"https://orcid.org/0000-0001-7072-2189"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048931310","display_name":"Jason Baldridge","orcid":"https://orcid.org/0000-0002-4712-1841"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baldridge, Jason","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101011504","display_name":"Yonghui Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yonghui","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":17,"corresponding_author_ids":["https://openalex.org/A5100745253"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":340,"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":0.9731000065803528,"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":0.9731000065803528,"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":0.9589999914169312,"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":0.9381999969482422,"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/computer-science","display_name":"Computer science","score":0.8246384859085083},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6322305202484131},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6242959499359131},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5651986598968506},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5575411319732666},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4902387261390686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4863441586494446},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.47776782512664795},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.45287925004959106},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4445951581001282},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4434613287448883},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.43833622336387634},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4193955063819885},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4139610826969147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8246384859085083},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6322305202484131},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6242959499359131},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5651986598968506},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5575411319732666},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4902387261390686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4863441586494446},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.47776782512664795},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.45287925004959106},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4445951581001282},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4434613287448883},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.43833622336387634},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4193955063819885},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4139610826969147},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2206.10789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.10789","pdf_url":"https://arxiv.org/pdf/2206.10789","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2206.10789","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.10789","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.10789","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.10789","pdf_url":"https://arxiv.org/pdf/2206.10789","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2895525995","https://openalex.org/W2332512904","https://openalex.org/W2319626700","https://openalex.org/W4319589573"],"abstract_inverted_index":{"We":[0,170],"present":[1],"the":[2,42,58,111,157],"Pathways":[3],"Autoregressive":[4],"Text-to-Image":[5],"(Parti)":[6],"model,":[7],"which":[8,68],"generates":[9],"high-fidelity":[10],"photorealistic":[11],"images":[12,97],"and":[13,20,75,80,128,167,173,183],"supports":[14],"content-rich":[15],"synthesis":[16],"involving":[17],"complex":[18],"compositions":[19],"world":[21],"knowledge.":[22],"Parti":[23,88,160],"treats":[24],"text-to-image":[25],"generation":[26],"as":[27,41,98,142,144],"a":[28,90,120,147,162],"sequence-to-sequence":[29],"modeling":[30],"problem,":[31],"akin":[32],"to":[33,95,116,181],"machine":[34],"translation,":[35],"with":[36,119],"sequences":[37,99],"of":[38,61,100,126,132,151,159,165,176,187],"image":[39,92],"tokens":[40,48],"target":[43],"outputs":[44],"rather":[45],"than":[46],"text":[47],"in":[49,73,179],"another":[50],"language.":[51],"This":[52],"strategy":[53],"can":[54],"naturally":[55],"tap":[56],"into":[57],"rich":[59],"body":[60],"prior":[62],"work":[63],"on":[64,134,139],"large":[65],"language":[66],"models,":[67],"have":[69],"seen":[70],"continued":[71],"advances":[72],"capabilities":[74],"performance":[76],"through":[77],"scaling":[78,110],"data":[79],"model":[81,114],"sizes.":[82],"Our":[83,136],"approach":[84],"is":[85],"simple:":[86],"First,":[87],"uses":[89],"Transformer-based":[91],"tokenizer,":[93],"ViT-VQGAN,":[94],"encode":[96],"discrete":[101],"tokens.":[102],"Second,":[103],"we":[104],"achieve":[105],"consistent":[106],"quality":[107],"improvements":[108],"by":[109],"encoder-decoder":[112],"Transformer":[113],"up":[115],"20B":[117],"parameters,":[118],"new":[121,148],"state-of-the-art":[122],"zero-shot":[123],"FID":[124,130],"score":[125,131],"7.23":[127],"finetuned":[129],"3.22":[133],"MS-COCO.":[135],"detailed":[137],"analysis":[138],"Localized":[140],"Narratives":[141],"well":[143],"PartiPrompts":[145],"(P2),":[146],"holistic":[149],"benchmark":[150],"over":[152],"1600":[153],"English":[154],"prompts,":[155],"demonstrate":[156],"effectiveness":[158],"across":[161],"wide":[163],"variety":[164],"categories":[166],"difficulty":[168],"aspects.":[169],"also":[171],"explore":[172],"highlight":[174],"limitations":[175],"our":[177],"models":[178],"order":[180],"define":[182],"exemplify":[184],"key":[185],"areas":[186],"focus":[188],"for":[189,194],"further":[190],"improvements.":[191],"See":[192],"https://parti.research.google/":[193],"high-resolution":[195],"images.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":163},{"year":2023,"cited_by_count":137},{"year":2022,"cited_by_count":11}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}