{"id":"https://openalex.org/W4393300306","doi":"https://doi.org/10.48550/arxiv.2403.18493","title":"VersaT2I: Improving Text-to-Image Models with Versatile Reward","display_name":"VersaT2I: Improving Text-to-Image Models with Versatile Reward","publication_year":2024,"publication_date":"2024-03-27","ids":{"openalex":"https://openalex.org/W4393300306","doi":"https://doi.org/10.48550/arxiv.2403.18493"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.18493","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.18493","pdf_url":"https://arxiv.org/pdf/2403.18493","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/2403.18493","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082287744","display_name":"Jianshu Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guo, Jianshu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103021774","display_name":"Wenhao Chai","orcid":"https://orcid.org/0000-0003-2611-0008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chai, Wenhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101454577","display_name":"Jie Deng","orcid":"https://orcid.org/0000-0002-2391-0782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Jie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101699930","display_name":"Hsiang-Wei Huang","orcid":"https://orcid.org/0000-0003-0373-9487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Hsiang-Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387912","display_name":"Ye Tian","orcid":"https://orcid.org/0000-0002-8255-2997"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Tian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705957","display_name":"Yichen Xu","orcid":"https://orcid.org/0009-0001-9557-3455"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yichen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462825","display_name":"Jiawei Zhang","orcid":"https://orcid.org/0000-0002-2292-4592"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiawei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101702810","display_name":"Jenq\u2013Neng Hwang","orcid":"https://orcid.org/0000-0002-8877-2421"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hwang, Jenq-Neng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089410490","display_name":"Gaoang Wang","orcid":"https://orcid.org/0000-0002-8403-1538"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Gaoang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5082287744"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9452999830245972,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9452999830245972,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9401000142097473,"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":0.9319999814033508,"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","display_name":"Image (mathematics)","score":0.5535891652107239},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5378566980361938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34254857897758484},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.33649328351020813}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5535891652107239},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5378566980361938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34254857897758484},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33649328351020813}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.18493","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.18493","pdf_url":"https://arxiv.org/pdf/2403.18493","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.2403.18493","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.18493","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:2403.18493","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.18493","pdf_url":"https://arxiv.org/pdf/2403.18493","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393300306.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Recent":[0],"text-to-image":[1],"(T2I)":[2],"models":[3,17],"have":[4],"benefited":[5],"from":[6],"large-scale":[7],"and":[8,32,130],"high-quality":[9,82],"data,":[10],"demonstrating":[11],"impressive":[12],"performance.":[13],"However,":[14],"these":[15],"T2I":[16,54,98],"still":[18],"struggle":[19],"to":[20,30,95,111,128],"produce":[21],"images":[22,83],"that":[23,44,146],"are":[24],"aesthetically":[25],"pleasing,":[26],"geometrically":[27],"accurate,":[28],"faithful":[29],"text,":[31],"of":[33,52,60],"good":[34],"low-level":[35,72],"quality.":[36],"We":[37,56],"present":[38],"VersaT2I,":[39],"a":[40,108],"versatile":[41],"training":[42,93],"framework":[43],"can":[45,117],"boost":[46],"the":[47,58,61,89,92,97,101,149],"performance":[48],"with":[49],"multiple":[50,113],"rewards":[51],"any":[53,134],"model.":[55],"decompose":[57],"quality":[59,78,114,122,154],"image":[62],"into":[63],"several":[64],"aspects":[65],"such":[66],"as":[67,91],"aesthetics,":[68],"text-image":[69],"alignment,":[70],"geometry,":[71],"quality,":[73],"etc.":[74],"Then,":[75],"for":[76],"every":[77],"aspect,":[79],"we":[80,106],"select":[81],"in":[84],"this":[85],"aspect":[86],"generated":[87],"by":[88],"model":[90,99,140],"set":[94],"finetune":[96],"using":[100],"Low-Rank":[102],"Adaptation":[103],"(LoRA).":[104],"Furthermore,":[105],"introduce":[107],"gating":[109],"function":[110],"combine":[112],"aspects,":[115],"which":[116],"avoid":[118],"conflicts":[119],"between":[120],"different":[121],"aspects.":[123],"Our":[124],"method":[125],"is":[126],"easy":[127],"extend":[129],"does":[131],"not":[132],"require":[133],"manual":[135],"annotation,":[136],"reinforcement":[137],"learning,":[138],"or":[139],"architecture":[141],"changes.":[142],"Extensive":[143],"experiments":[144],"demonstrate":[145],"VersaT2I":[147],"outperforms":[148],"baseline":[150],"methods":[151],"across":[152],"various":[153],"criteria.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}