{"id":"https://openalex.org/W4408347338","doi":"https://doi.org/10.1109/icassp49660.2025.10888645","title":"Identical Human Preference Alignment Paradigm for Text-to-Image Models","display_name":"Identical Human Preference Alignment Paradigm for Text-to-Image Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408347338","doi":"https://doi.org/10.1109/icassp49660.2025.10888645"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5100538111","display_name":"Haoyuan Sun","orcid":"https://orcid.org/0000-0003-1719-8976"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyuan Sun","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044226655","display_name":"Bo Xia","orcid":"https://orcid.org/0000-0001-7694-4743"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xia","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076375643","display_name":"Yifei Zhao","orcid":"https://orcid.org/0000-0002-9614-4863"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Zhao","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026500154","display_name":"Yongzhe Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongzhe Chang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100737125","display_name":"Xueqian Wang","orcid":"https://orcid.org/0000-0003-3542-0593"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqian Wang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100538111"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.2092,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.84897334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"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/T12698","display_name":"3D Modeling in Geospatial Applications","score":0.878000020980835,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12698","display_name":"3D Modeling in Geospatial Applications","score":0.878000020980835,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6424561142921448},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5226795077323914},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48270416259765625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4774896800518036},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4003312587738037},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35256198048591614},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12129050493240356},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0719994306564331}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6424561142921448},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5226795077323914},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48270416259765625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4774896800518036},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4003312587738037},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35256198048591614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12129050493240356},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0719994306564331}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888645","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2763110165","https://openalex.org/W2962785568","https://openalex.org/W3153469116","https://openalex.org/W4312933868","https://openalex.org/W4386072096","https://openalex.org/W4390874002","https://openalex.org/W4390874530","https://openalex.org/W4402753770","https://openalex.org/W4402753790","https://openalex.org/W4409362098","https://openalex.org/W6779823529","https://openalex.org/W6846007759","https://openalex.org/W6852065897","https://openalex.org/W6852162230","https://openalex.org/W6852418670","https://openalex.org/W6852915159","https://openalex.org/W6853146131","https://openalex.org/W6856759744","https://openalex.org/W6857273126","https://openalex.org/W6857409505","https://openalex.org/W6861431061"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Implicit":[0],"reward":[1],"mechanism":[2],"of":[3,42,70,78,128],"Direct":[4],"Preference":[5,60],"Optimization":[6],"(DPO)":[7],"has":[8],"facilitated":[9],"its":[10],"recent":[11],"applications":[12],"beyond":[13],"large":[14],"language":[15],"models":[16,22],"(LLMs),":[17],"notably":[18],"in":[19,126,136],"aligning":[20],"text-to-image":[21,65],"with":[23,32],"human":[24,102],"preferences.":[25],"While":[26],"promising":[27],"results":[28,109],"have":[29],"been":[30],"achieved":[31],"algorithms":[33],"such":[34],"as":[35],"Diffusion-DPO,":[36,81],"their":[37],"reliance":[38],"on":[39,89,96],"the":[40,43,57,68,76,86,90,123],"assumptions":[41,69],"Bradley-Terry":[44,71],"model":[45,125],"could":[46],"potentially":[47],"lead":[48],"to":[49],"significant":[50],"overfitting.":[51,139],"In":[52],"this":[53],"paper,":[54],"we":[55],"propose":[56],"Step":[58],"Identical":[59],"Alignment":[61],"(SIPA)":[62],"method,":[63],"departing":[64],"alignment":[66,118,138],"from":[67],"preference":[72],"model.":[73],"We":[74],"assess":[75],"performance":[77],"four":[79],"models,":[80],"SPO,":[82],"and":[83,105,120],"SIPA,":[84],"alongside":[85],"original":[87,124],"model,":[88],"HPS-V2":[91],"test":[92],"set,":[93],"which":[94,131],"focus":[95],"three":[97],"key":[98],"aspects:":[99],"text-image":[100],"alignment,":[101,104],"value":[103],"generation":[106,129],"diversity.":[107],"Experimental":[108],"show":[110],"that":[111],"SIPA":[112],"matches":[113],"or":[114],"outperforms":[115],"existing":[116],"SOTA":[117],"methods,":[119],"even":[121],"exceeds":[122],"terms":[127],"diversity,":[130],"compellingly":[132],"demonstrates":[133],"SIPA\u2019s":[134],"superiority":[135],"mitigating":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}