{"id":"https://openalex.org/W7131263071","doi":"https://doi.org/10.1109/vcip67698.2025.11396865","title":"MGM-DPO: Multi-Generative-Model Guided Preference Optimization for Advanced Text-to-Image Models","display_name":"MGM-DPO: Multi-Generative-Model Guided Preference Optimization for Advanced Text-to-Image Models","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7131263071","doi":"https://doi.org/10.1109/vcip67698.2025.11396865"},"language":null,"primary_location":{"id":"doi:10.1109/vcip67698.2025.11396865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102001682","display_name":"Yu Zhao","orcid":"https://orcid.org/0000-0002-5164-9446"},"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":"Yu Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126713264","display_name":"Jiarui Wang","orcid":null},"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":"Jiarui Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126679174","display_name":"Huiyu Duan","orcid":null},"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":"Huiyu Duan","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126740280","display_name":"Guangtao Zhai","orcid":null},"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":"Guangtao Zhai","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126660745","display_name":"Xiongkuo Min","orcid":null},"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":"Xiongkuo Min","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.11969999969005585,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.11969999969005585,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.08980000019073486,"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":0.08299999684095383,"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/preference","display_name":"Preference","score":0.7728000283241272},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4767000079154968},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4627000093460083},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3749000132083893},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3359000086784363},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.3082999885082245}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7728000283241272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117999792098999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.603600025177002},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45989999175071716},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3749000132083893},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.3082999885082245},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip67698.2025.11396865","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396865","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5098257660865784}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2109169869","https://openalex.org/W2948175577","https://openalex.org/W3153469116","https://openalex.org/W4312933868","https://openalex.org/W4386211581","https://openalex.org/W4390874002","https://openalex.org/W4390874566","https://openalex.org/W4392902675","https://openalex.org/W4402753790","https://openalex.org/W4402754104","https://openalex.org/W4402916399","https://openalex.org/W4406610920","https://openalex.org/W4413145497","https://openalex.org/W4413145894"],"related_works":[],"abstract_inverted_index":{"Text-to-image":[0],"generation":[1,119],"has":[2],"rapidly":[3],"progressed":[4],"with":[5,95],"autoregressive,":[6],"diffusion,":[7],"and":[8,13,34,65,107,125,140,162],"distillation-based":[9],"models,":[10],"enabling":[11],"high-fidelity":[12],"semantically":[14],"relevant":[15],"image":[16,102],"synthesis":[17],"from":[18,29,112],"natural":[19],"language":[20],"prompts.":[21],"Despite":[22],"their":[23,72],"success,":[24],"these":[25,50],"models":[26,58,76],"still":[27],"suffer":[28],"text\u2013image":[30],"misalignment,":[31],"limited":[32],"detail,":[33],"outputs":[35,139],"that":[36],"may":[37],"violate":[38],"human":[39,96,163],"commonsense":[40],"or":[41,69],"aesthetic":[42],"preferences.":[43],"Existing":[44],"human-feedback-based":[45],"fine-tuning":[46],"approaches":[47],"partially":[48],"alleviate":[49],"issues":[51],"but":[52],"primarily":[53],"focus":[54],"on":[55,74],"earlier":[56],"diffusion":[57,148],"(e.g.,":[59],"Stable":[60,152],"Diffusion":[61,132,153],"v1.4,":[62],"v2.0,":[63],"SDXL)":[64],"often":[66],"exhibit":[67],"over-optimization":[68],"under-optimization,":[70],"leaving":[71],"effectiveness":[73],"state-of-the-art":[75,170],"unclear.":[77],"In":[78],"this":[79],"work,":[80],"we":[81,128],"advance":[82],"preference":[83,97,164],"alignment":[84,165],"for":[85],"modern":[86],"text-to-image":[87],"models.":[88,149,174],"We":[89],"utilize":[90],"EvalMi-50K,":[91],"a":[92,141],"large-scale":[93],"dataset":[94,124],"scores,":[98],"to":[99,116,145,151],"train":[100],"our":[101],"quality":[103],"assessment":[104],"(IQA)":[105],"model":[106,115,138],"use":[108],"the":[109,113,118,123],"predicted":[110],"scores":[111],"IQA":[114,126],"reward":[117],"model.":[120],"Building":[121],"upon":[122],"model,":[127],"propose":[129],"Multi-Generative-Model":[130],"Guided":[131],"Preference":[133],"Optimization(MGM-DPO),":[134],"which":[135],"leverages":[136],"diverse":[137],"stable":[142],"optimization":[143],"strategy":[144],"align":[146],"advanced":[147],"Applied":[150],"3.5":[154],"Large,":[155],"MGM-DPO":[156],"significantly":[157],"improves":[158],"fidelity,":[159],"prompt":[160],"alignment,":[161],"across":[166],"multiple":[167],"benchmarks,":[168],"achieving":[169],"results":[171],"among":[172],"human-feedback-tuned":[173],"Code":[175],"is":[176],"available":[177],"at":[178],"https://github.com/IntMeGroup/MGM-DPO.":[179]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-25T00:00:00"}