{"id":"https://openalex.org/W4417270342","doi":"https://doi.org/10.1109/iccv51701.2025.01803","title":"T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation","display_name":"T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417270342","doi":"https://doi.org/10.1109/iccv51701.2025.01803"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.20536","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034476012","display_name":"Chieh-Yun Chen","orcid":"https://orcid.org/0000-0002-7412-7894"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chieh-Yun Chen","raw_affiliation_strings":["SHI Labs @ Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SHI Labs @ Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112114160","display_name":"Min Shi","orcid":"https://orcid.org/0009-0001-5991-6545"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Shi","raw_affiliation_strings":["SHI Labs @ Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SHI Labs @ Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368308","display_name":"Gong Zhang","orcid":"https://orcid.org/0000-0002-7723-7538"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gong Zhang","raw_affiliation_strings":["SHI Labs @ Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SHI Labs @ Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002072267","display_name":"Humphrey Shi","orcid":"https://orcid.org/0000-0002-2922-5663"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Humphrey Shi","raw_affiliation_strings":["SHI Labs @ Georgia Tech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SHI Labs @ Georgia Tech","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034476012"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37873094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19396","last_page":"19405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.43459999561309814,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.43459999561309814,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.38350000977516174,"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/T10028","display_name":"Topic Modeling","score":0.03449999913573265,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/generalization","display_name":"Generalization","score":0.6086000204086304},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.5473999977111816},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5389000177383423},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.529699981212616},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5149999856948853},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47099998593330383},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.40630000829696655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7954000234603882},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6086000204086304},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5430999994277954},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5389000177383423},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.529699981212616},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47099998593330383},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.40630000829696655},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3695000112056732},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36480000615119934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33640000224113464},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C2988963302","wikidata":"https://www.wikidata.org/wiki/Q629206","display_name":"Program code","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30720001459121704},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3052999973297119},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01803","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.20536","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.20536","pdf_url":"https://arxiv.org/pdf/2507.20536","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2507.20536","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.20536","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:2507.20536","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.20536","pdf_url":"https://arxiv.org/pdf/2507.20536","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[],"awards":[{"id":"https://openalex.org/G2997156820","display_name":null,"funder_award_id":"2427478","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G962119475","display_name":null,"funder_award_id":"2229873","funder_id":"https://openalex.org/F4320306106","funder_display_name":"U.S. Department of Education"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306106","display_name":"U.S. Department of Education","ror":"https://ror.org/021adze67"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text-to-Image":[0],"(T2I)":[1],"generative":[2],"models":[3,133,188],"have":[4],"revolutionized":[5],"content":[6],"creation":[7],"but":[8],"remain":[9],"highly":[10],"sensitive":[11],"to":[12,18,73,96,140,186],"prompt":[13,32,75,86],"phrasing,":[14,76],"often":[15,49],"requiring":[16],"users":[17],"repeatedly":[19],"refine":[20],"prompts":[21,139],"multiple":[22],"times":[23],"without":[24],"clear":[25],"feedback.":[26],"While":[27],"techniques":[28],"such":[29],"as":[30],"automatic":[31],"engineering,":[33],"controlled":[34],"text":[35],"embeddings,":[36],"denoising,":[37],"and":[38,79,92,115,134,137,143,151,156,190,203,206,212],"multi-turn":[39],"generation":[40,90,178],"mitigate":[41],"these":[42],"issues,":[43],"they":[44],"offer":[45],"limited":[46],"controllability,":[47],"or":[48],"necessitate":[50],"additional":[51],"training,":[52],"restricting":[53],"the":[54,110,125],"generalization":[55],"abilities.":[56],"Thus,":[57],"we":[58],"introduce":[59],"T2I-Copilot,":[60],"a":[61,117,182],"training-free":[62],"multi-agent":[63],"system":[64],"that":[65],"leverages":[66],"collaboration":[67],"between":[68],"(Multimodal)":[69],"Large":[70,209],"Language":[71],"Models":[72],"automate":[74],"model":[77,127],"selection,":[78],"iterative":[80],"refinement.":[81],"This":[82],"approach":[83],"significantly":[84],"simplifies":[85],"engineering":[87],"while":[88,166],"enhancing":[89],"quality":[91,150],"text-image":[93,152],"alignment":[94],"compared":[95],"direct":[97],"generation.":[98],"Specifically,":[99],"T2I-Copilot":[100,161,180],"consists":[101],"of":[102,131,200],"three":[103],"agents:":[104],"(1)":[105],"Input":[106],"Interpreter,":[107],"which":[108,123,147],"parses":[109],"input":[111],"prompt,":[112],"resolves":[113],"ambiguities,":[114],"generates":[116],"standardized":[118],"report;":[119],"(2)":[120],"Generation":[121],"Engine,":[122],"selects":[124],"appropriate":[126],"from":[128],"different":[129],"types":[130],"T2I":[132],"organizes":[135],"visual":[136],"textual":[138],"initiate":[141],"generation;":[142],"(3)":[144],"Quality":[145],"Evaluator,":[146],"assesses":[148],"aesthetic":[149],"alignment,":[153],"providing":[154],"scores":[155],"feedback":[157],"for":[158,171],"potential":[159],"regeneration.":[160],"can":[162],"operate":[163],"fully":[164],"autonomously":[165],"also":[167],"supporting":[168],"human-in-the-loop":[169],"intervention":[170],"fine-grained":[172],"control.":[173],"On":[174],"GenAI-Bench,":[175],"using":[176],"open-source":[177],"models,":[179],"achieves":[181],"VQA":[183],"score":[184],"comparable":[185],"commercial":[187],"RecraftV3":[189],"Imagen":[191],"3,":[192],"surpasses":[193],"FLUX1.1-pro":[194],"by":[195,210],"6.17%":[196],"at":[197],"only":[198],"16.59%":[199],"its":[201],"cost,":[202],"outperforms":[204],"FLUX.1-dev":[205],"SD":[207],"3.5":[208],"9.11%":[211],"6.36%.":[213],"Code":[214],"will":[215],"be":[216],"released":[217],"at:":[218],"https://github.com/SHI-Labs/T2I-Copilot.":[219]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}