{"id":"https://openalex.org/W4415329328","doi":"https://doi.org/10.48550/arxiv.2505.15779","title":"IA-T2I: Internet-Augmented Text-to-Image Generation","display_name":"IA-T2I: Internet-Augmented Text-to-Image Generation","publication_year":2025,"publication_date":"2025-05-21","ids":{"openalex":"https://openalex.org/W4415329328","doi":"https://doi.org/10.48550/arxiv.2505.15779"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.15779","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15779","pdf_url":"https://arxiv.org/pdf/2505.15779","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/2505.15779","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057986563","display_name":"Chuanhao Li","orcid":"https://orcid.org/0009-0006-2440-0596","observed_orcids":["https://orcid.org/0009-0006-2440-0596","https://orcid.org/0000-0002-5769-3739"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Chuanhao","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sun, Jianwen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Jianwen","raw_affiliation_strings":["Nankai University","Shanghai Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Shanghai Innovation Institute","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050688781","display_name":"Yulong Feng","orcid":"https://orcid.org/0000-0001-8877-5027","observed_orcids":["https://orcid.org/0000-0001-8877-5027","https://orcid.org/0009-0000-5594-3629"]},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng, Yukang","raw_affiliation_strings":["Nankai University","Shanghai Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Shanghai Innovation Institute","institution_ids":["https://openalex.org/I4405279436"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhai, Mingliang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhai, Mingliang","raw_affiliation_strings":["Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010151006","display_name":"Yifan Chang","orcid":"https://orcid.org/0000-0003-2820-0840","observed_orcids":["https://orcid.org/0000-0003-2820-0840"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang, Yifan","raw_affiliation_strings":["Shanghai Innovation Institute","University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Innovation Institute","institution_ids":["https://openalex.org/I4405279436"]},{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036606244","display_name":"Kaipeng Zhang","orcid":"https://orcid.org/0000-0001-6105-6532","observed_orcids":["https://orcid.org/0000-0001-6105-6532"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I4405279436","display_name":"Shanghai Innovation Institute","ror":"https://ror.org/01fatbw66","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279436"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Kaipeng","raw_affiliation_strings":["Shanghai AI Laboratory","Shanghai Innovation Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Innovation Institute","institution_ids":["https://openalex.org/I4405279436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.9984999895095825,"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":0.9984999895095825,"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":0.00139999995008111,"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":0.9990000128746033},{"id":"https://openalex.org/keywords/reference-images","display_name":"reference images","score":0.7910000085830688},{"id":"https://openalex.org/keywords/self-reflection","display_name":"self-reflection","score":0.6830000281333923},{"id":"https://openalex.org/keywords/prompt-alignment","display_name":"prompt alignment","score":0.5419999957084656},{"id":"https://openalex.org/keywords/image-search","display_name":"image search","score":0.4359999895095825},{"id":"https://openalex.org/keywords/gpt-4o","display_name":"GPT-4o","score":0.7820000052452087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7335000038146973},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6577000021934509},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5576000213623047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5386999845504761},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4756999909877777},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3935000002384186},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.365200012922287},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3303000032901764},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3163999915122986},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C2779732396","wikidata":"https://www.wikidata.org/wiki/Q2207288","display_name":"Craft","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.25589999556541443}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.15779","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15779","pdf_url":"https://arxiv.org/pdf/2505.15779","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.2505.15779","doi":"https://doi.org/10.48550/arxiv.2505.15779","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.15779","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.15779","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15779","pdf_url":"https://arxiv.org/pdf/2505.15779","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415329328.pdf","grobid_xml":"https://content.openalex.org/works/W4415329328.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"text-to-image":[1,64],"(T2I)":[2],"generation":[3,65],"models":[4,71],"achieve":[5],"promising":[6],"results,":[7],"but":[8,172],"they":[9],"fail":[10],"on":[11,99],"the":[12,15,19,46,54,100,113,125,138,146,151,211],"scenarios":[13],"where":[14,161],"knowledge":[16,76],"implied":[17],"in":[18,30,43,188,221],"text":[20,102,147,162],"prompt":[21,184],"is":[22,88,96,109,131],"uncertain.":[23],"For":[24],"example,":[25],"a":[26,36,40,93,104,128,157,182],"T2I":[27,70,126],"model":[28],"released":[29],"February":[31],"would":[32],"struggle":[33],"to":[34,53,68,90,111,123,133,141,185,196,202],"generate":[35],"suitable":[37,115],"poster":[38],"for":[39],"movie":[41],"premiering":[42],"April,":[44],"because":[45],"character":[47],"designs":[48],"and":[49,136],"styles":[50],"are":[51],"uncertain":[52,75,168],"model.":[55],"To":[56,149],"solve":[57],"this":[58],"problem,":[59],"we":[60,155,179],"propose":[61],"an":[62,84,119,198],"Internet-Augmented":[63],"(IA-T2I)":[66],"framework":[67],"compel":[69],"clear":[72],"about":[73,219],"such":[74],"by":[77,118,218],"providing":[78],"them":[79],"with":[80,145],"reference":[81,94],"images.":[82],"Specifically,":[83],"active":[85],"retrieval":[86],"module":[87,108],"designed":[89],"determine":[91],"whether":[92],"image":[95,106,116,120,140],"needed":[97],"based":[98],"given":[101],"prompt;":[103],"hierarchical":[105],"selection":[107],"introduced":[110],"find":[112],"most":[114],"returned":[117],"search":[121],"engine":[122],"enhance":[124],"model;":[127],"self-reflection":[129],"mechanism":[130],"presented":[132],"continuously":[134],"evaluate":[135,150],"refine":[137],"generated":[139],"ensure":[142],"faithful":[143],"alignment":[144],"prompt.":[148],"proposed":[152],"framework's":[153],"performance,":[154],"collect":[156],"dataset":[158],"named":[159],"Img-Ref-T2I,":[160],"prompts":[163],"include":[164],"three":[165],"types":[166],"of":[167,204,213],"knowledge:":[169],"(1)":[170],"known":[171],"rare.":[173],"(2)":[174],"unknown.":[175],"(3)":[176],"ambiguous.":[177],"Moreover,":[178],"carefully":[180],"craft":[181],"complex":[183],"guide":[186],"GPT-4o":[187,217],"making":[189],"preference":[190,206],"evaluation,":[191],"which":[192],"has":[193],"been":[194],"shown":[195],"have":[197],"evaluation":[199],"accuracy":[200],"similar":[201],"that":[203],"human":[205,222],"evaluation.":[207,223],"Experimental":[208],"results":[209],"demonstrate":[210],"effectiveness":[212],"our":[214],"framework,":[215],"outperforming":[216],"30%":[220]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-19T00:00:00"}