{"id":"https://openalex.org/W4412888477","doi":"https://doi.org/10.18653/v1/2025.findings-acl.383","title":"Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generation","display_name":"Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888477","doi":"https://doi.org/10.18653/v1/2025.findings-acl.383"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.383","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.383","pdf_url":"https://aclanthology.org/2025.findings-acl.383.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.383.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025568264","display_name":"Hongji Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Hongji Yang","raw_affiliation_strings":["SKL-IOTSC , CIS , University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SKL-IOTSC , CIS , University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012767739","display_name":"Yucheng Zhou","orcid":"https://orcid.org/0009-0006-9883-5621"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Yucheng Zhou","raw_affiliation_strings":["SKL-IOTSC , CIS , University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SKL-IOTSC , CIS , University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083325591","display_name":"Wencheng Han","orcid":null},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Wencheng Han","raw_affiliation_strings":["SKL-IOTSC , CIS , University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SKL-IOTSC , CIS , University of Macau","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101404956","display_name":"Jianbing Shen","orcid":"https://orcid.org/0000-0003-1883-2086"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Jianbing Shen","raw_affiliation_strings":["SKL-IOTSC , CIS , University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SKL-IOTSC , CIS , University of Macau","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204512498"],"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":"7332","last_page":"7349"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8259000182151794,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8259000182151794,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7928000092506409,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.7491999864578247,"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/computer-science","display_name":"Computer science","score":0.7349754571914673},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6172283291816711},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5590819716453552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5401427149772644},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48808062076568604},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3708110451698303},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33693867921829224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7349754571914673},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6172283291816711},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5590819716453552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5401427149772644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48808062076568604},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3708110451698303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33693867921829224}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.383","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.383","pdf_url":"https://aclanthology.org/2025.findings-acl.383.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.16763","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.16763","pdf_url":"https://arxiv.org/pdf/2505.16763","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.383","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.383","pdf_url":"https://aclanthology.org/2025.findings-acl.383.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1902999819","display_name":null,"funder_award_id":"0102/2023/RIA2","funder_id":"https://openalex.org/F4320323893","funder_display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia"},{"id":"https://openalex.org/G7895045165","display_name":null,"funder_award_id":"001/2024/SKL","funder_id":"https://openalex.org/F4320323893","funder_display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia"},{"id":"https://openalex.org/G865935055","display_name":null,"funder_award_id":"0154/2022/A3","funder_id":"https://openalex.org/F4320323893","funder_display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323893","display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia","ror":"https://ror.org/05vna4324"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888477.pdf","grobid_xml":"https://content.openalex.org/works/W4412888477.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2779427294","https://openalex.org/W2775347418","https://openalex.org/W2625805835","https://openalex.org/W2079911747","https://openalex.org/W3116076068","https://openalex.org/W3003936178","https://openalex.org/W2145652935","https://openalex.org/W2563206327","https://openalex.org/W2069885731"],"abstract_inverted_index":{"Text-to-image":[0],"models":[1,27,86],"are":[2,142],"powerful":[3],"for":[4,48],"producing":[5],"high-quality":[6],"images":[7,112],"based":[8],"on":[9,45,162],"given":[10],"text":[11],"prompts,":[12],"but":[13],"crafting":[14],"these":[15],"prompts":[16],"often":[17],"requires":[18],"specialized":[19],"vocabulary.To":[20],"address":[21],"this,":[22],"existing":[23],"methods":[24],"train":[25],"rewriting":[26],"with":[28],"supervision":[29],"from":[30],"large":[31,83],"amounts":[32],"of":[33,110,118,127],"manually":[34],"annotated":[35],"data":[36,46],"and":[37,51,96,108,138,147,159],"trained":[38,56],"aesthetic":[39],"assessment":[40],"models.To":[41],"alleviate":[42],"the":[43,52,82,89,93,106,111,115,124,128,136,139],"dependence":[44],"scale":[47],"model":[49,103,141,146],"training":[50],"biases":[53],"introduced":[54],"by":[55,114,155],"models,":[57],"we":[58,80,122],"propose":[59],"a":[60,68,73,77,101,157],"novel":[61],"prompt":[62,71,75],"optimization":[63],"framework,":[64],"designed":[65],"to":[66,76,91,104,130,152],"rephrase":[67],"simple":[69],"user":[70,94],"into":[72,144],"sophisticated":[74],"text-to-image":[78],"model.Specifically,":[79],"employ":[81,98],"vision":[84],"language":[85],"(LVLMs)":[87],"as":[88,100],"solver":[90,137],"rewrite":[92],"prompt,":[95],"concurrently,":[97],"LVLMs":[99],"reward":[102,140],"score":[105],"aesthetics":[107],"alignment":[109],"generated":[113],"optimized":[116],"prompt.Instead":[117],"laborious":[119],"human":[120],"feedback,":[121],"exploit":[123],"prior":[125],"knowledge":[126],"LVLM":[129],"provide":[131],"rewards,":[132],"i.e.,":[133],"AI":[134],"feedback.Simultaneously,":[135],"unified":[143],"one":[145],"iterated":[148],"in":[149],"reinforcement":[150],"learning":[151],"achieve":[153],"self-improvement":[154],"giving":[156],"solution":[158],"judging":[160],"itself.Results":[161],"two":[163],"popular":[164],"datasets":[165],"demonstrate":[166],"that":[167],"our":[168],"method":[169],"outperforms":[170],"other":[171],"strong":[172],"competitors.":[173]},"counts_by_year":[],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}