{"id":"https://openalex.org/W4401978690","doi":"https://doi.org/10.48550/arxiv.2408.01181","title":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling","display_name":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling","publication_year":2024,"publication_date":"2024-08-02","ids":{"openalex":"https://openalex.org/W4401978690","doi":"https://doi.org/10.48550/arxiv.2408.01181"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2408.01181","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.01181","pdf_url":"https://arxiv.org/pdf/2408.01181","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/2408.01181","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100401655","display_name":"Qian Zhang","orcid":"https://orcid.org/0000-0002-5712-0017","observed_orcids":["https://orcid.org/0000-0002-5712-0017"]},"institutions":[{"id":"https://openalex.org/I4210145278","display_name":"Institute of Applied Physics and Computational Mathematics","ror":"https://ror.org/03sxpbt26","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Qian","raw_affiliation_strings":["Institute of Applied Physics and Computational Mathematics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Applied Physics and Computational Mathematics","institution_ids":["https://openalex.org/I4210145278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108976173","display_name":"Xiangzi Dai","orcid":"https://orcid.org/0009-0009-3236-8380","observed_orcids":["https://orcid.org/0009-0009-3236-8380"]},"institutions":[{"id":"https://openalex.org/I4401726936","display_name":"Deepglint (China)","ror":"https://ror.org/0348v8v06","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726936"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dai, Xiangzi","raw_affiliation_strings":["DeepGlint"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepGlint","institution_ids":["https://openalex.org/I4401726936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077181557","display_name":"Ninghua Yang","orcid":"https://orcid.org/0009-0006-1643-194X","observed_orcids":["https://orcid.org/0009-0006-1643-194X"]},"institutions":[{"id":"https://openalex.org/I4401726936","display_name":"Deepglint (China)","ror":"https://ror.org/0348v8v06","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726936"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Ninghua","raw_affiliation_strings":["DeepGlint"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepGlint","institution_ids":["https://openalex.org/I4401726936"]}]},{"author_position":"middle","author":{"id":null,"display_name":"An, Xiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726936","display_name":"Deepglint (China)","ror":"https://ror.org/0348v8v06","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726936"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"An, Xiang","raw_affiliation_strings":["DeepGlint"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepGlint","institution_ids":["https://openalex.org/I4401726936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100531299","display_name":"Ziyong Feng","orcid":"https://orcid.org/0009-0007-8689-8366","observed_orcids":["https://orcid.org/0009-0007-8689-8366"]},"institutions":[{"id":"https://openalex.org/I4401726936","display_name":"Deepglint (China)","ror":"https://ror.org/0348v8v06","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726936"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng, Ziyong","raw_affiliation_strings":["DeepGlint"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepGlint","institution_ids":["https://openalex.org/I4401726936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080979886","display_name":"Xingyu Ren","orcid":"https://orcid.org/0000-0002-8543-8321","observed_orcids":["https://orcid.org/0000-0002-8543-8321"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ren, Xingyu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":48,"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":0.0006000000284984708,"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":0.0,"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/text-to-image-generation","display_name":"text-to-image generation","score":0.7900000214576721},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.8090000152587891},{"id":"https://openalex.org/keywords/image-text-dataset","display_name":"image-text dataset","score":0.8450000286102295}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7021684050559998},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6661719083786011},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5870033502578735},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5276269316673279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42421770095825195},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3611253499984741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34898847341537476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3239072263240814},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3064640164375305},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.18365684151649475},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10062199831008911},{"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2408.01181","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.01181","pdf_url":"https://arxiv.org/pdf/2408.01181","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.2408.01181","doi":"https://doi.org/10.48550/arxiv.2408.01181","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.01181","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:2408.01181","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.01181","pdf_url":"https://arxiv.org/pdf/2408.01181","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/W4401978690.pdf","grobid_xml":"https://content.openalex.org/works/W4401978690.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2173520492","https://openalex.org/W2893749619","https://openalex.org/W2896457183","https://openalex.org/W2963799213","https://openalex.org/W3092442149","https://openalex.org/W3094502228","https://openalex.org/W3135367836","https://openalex.org/W3206395542","https://openalex.org/W4221143397","https://openalex.org/W4224035735","https://openalex.org/W4226125322","https://openalex.org/W4288099666","https://openalex.org/W4289785045","https://openalex.org/W4311252447","https://openalex.org/W4327810158","https://openalex.org/W4378942574","https://openalex.org/W4384918448","https://openalex.org/W4399554455","https://openalex.org/W4399759049","https://openalex.org/W4399794526","https://openalex.org/W4403841197","https://openalex.org/W4415796345","https://openalex.org/W4415797571","https://openalex.org/W7133225605"],"related_works":["https://openalex.org/W4386076339","https://openalex.org/W4221143397","https://openalex.org/W4393178032","https://openalex.org/W4415796345","https://openalex.org/W6922489280","https://openalex.org/W7127185210","https://openalex.org/W4403556477","https://openalex.org/W4386065752","https://openalex.org/W4416150768","https://openalex.org/W4406857644"],"abstract_inverted_index":{"VAR":[0,34],"is":[1,36],"a":[2,54,98],"new":[3],"generation":[4],"paradigm":[5],"that":[6,58],"employs":[7],"'next-scale":[8],"prediction'":[9],"as":[10,80,93],"opposed":[11],"to":[12,22,38],"'next-token":[13],"prediction'.":[14],"This":[15],"innovative":[16],"transformation":[17],"enables":[18],"auto-regressive":[19],"(AR)":[20],"transformers":[21],"rapidly":[23],"learn":[24],"visual":[25],"distributions":[26],"and":[27,135],"achieve":[28],"robust":[29],"generalization.":[30],"However,":[31],"the":[32,64,108,116],"original":[33],"model":[35,57],"constrained":[37],"class-conditioned":[39],"synthesis,":[40],"relying":[41],"solely":[42],"on":[43,89],"textual":[44,81,133],"captions":[45,72],"for":[46,83,115],"guidance.":[47,120],"In":[48],"this":[49],"paper,":[50],"we":[51,95,105],"introduce":[52],"VAR-CLIP,":[53],"novel":[55],"text-to-image":[56],"integrates":[59],"Visual":[60],"Auto-Regressive":[61],"techniques":[62],"with":[63,130],"capabilities":[65],"of":[66,110,118],"CLIP.":[67],"The":[68],"VAR-CLIP":[69],"framework":[70],"encodes":[71],"into":[73,107],"text":[74],"embeddings,":[75],"which":[76],"are":[77,141],"then":[78],"utilized":[79],"conditions":[82],"image":[84],"generation.":[85],"To":[86],"facilitate":[87],"training":[88],"extensive":[90],"datasets,":[91],"such":[92],"ImageNet,":[94],"have":[96],"constructed":[97],"substantial":[99],"image-text":[100],"dataset":[101],"leveraging":[102],"BLIP2.":[103],"Furthermore,":[104],"delve":[106],"significance":[109],"word":[111],"positioning":[112],"within":[113],"CLIP":[114],"purpose":[117],"caption":[119],"Extensive":[121],"experiments":[122],"confirm":[123],"VAR-CLIP's":[124],"proficiency":[125],"in":[126],"generating":[127],"fantasy":[128],"images":[129],"high":[131],"fidelity,":[132],"congruence,":[134],"aesthetic":[136],"excellence.":[137],"Our":[138],"project":[139],"page":[140],"https://github.com/daixiangzi/VAR-CLIP":[142]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":31},{"year":2024,"cited_by_count":6}],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2024-08-29T00:00:00"}