{"id":"https://openalex.org/W4408353638","doi":"https://doi.org/10.1109/icassp49660.2025.10888279","title":"Aligning Text-to-Image Diffusion Models without Human Feedback","display_name":"Aligning Text-to-Image Diffusion Models without Human Feedback","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353638","doi":"https://doi.org/10.1109/icassp49660.2025.10888279"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888279","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/A5076597358","display_name":"Tao Liu","orcid":"https://orcid.org/0000-0001-5917-8311"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao Liu","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085883394","display_name":"Huafeng Kuang","orcid":"https://orcid.org/0000-0001-8888-512X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huafeng Kuang","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101445574","display_name":"Xianming Lin","orcid":"https://orcid.org/0000-0003-4739-8936"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianming Lin","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076597358"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":1.3688,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78232289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.30550000071525574,"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":0.30550000071525574,"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/computer-science","display_name":"Computer science","score":0.686418890953064},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5639451146125793},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5294299721717834},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5024149417877197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4571502208709717},{"id":"https://openalex.org/keywords/relevance-feedback","display_name":"Relevance feedback","score":0.4107985198497772},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.16607820987701416},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10314062237739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.686418890953064},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5639451146125793},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5294299721717834},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5024149417877197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4571502208709717},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.4107985198497772},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.16607820987701416},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10314062237739563},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888279","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/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W4312933868","https://openalex.org/W4384662964","https://openalex.org/W4385570204","https://openalex.org/W4385571411","https://openalex.org/W4390874002","https://openalex.org/W6782465632","https://openalex.org/W6791353385","https://openalex.org/W6810738896","https://openalex.org/W6811013733","https://openalex.org/W6839643428","https://openalex.org/W6844011046","https://openalex.org/W6846007759","https://openalex.org/W6847753483","https://openalex.org/W6850975553","https://openalex.org/W6852056849","https://openalex.org/W6852162230","https://openalex.org/W6852418670","https://openalex.org/W6853146131","https://openalex.org/W6856250771"],"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":{"Incorporating":[0],"human":[1,17,61,98,125],"feedback":[2,71,123,141],"to":[3,41,107],"optimize":[4],"text-to-image":[5,144],"models":[6],"has":[7],"demonstrated":[8],"significant":[9],"effectiveness.":[10],"However,":[11],"the":[12,46,79,117,148],"process":[13,54],"of":[14,69,97,104,120],"collecting":[15],"high-quality":[16],"preference":[18,82],"labels":[19,83],"is":[20],"both":[21],"resource-intensive":[22],"and":[23,110,146,153],"time-consuming.":[24],"To":[25],"address":[26],"this":[27],"challenge,":[28],"we":[29,115],"propose":[30],"a":[31,36,66,73,94,101],"novel":[32,67],"approach":[33,92],"that":[34,59,90],"leverages":[35],"large":[37],"language":[38],"model":[39,48,80],"(LLM)":[40],"generate":[42],"sophisticated":[43],"prompts,":[44],"guiding":[45],"diffusion":[47],"towards":[49],"enhanced":[50],"image":[51,132],"generation.":[52],"This":[53,134],"inherently":[55],"produces":[56],"ranking":[57],"pairs":[58],"approximate":[60],"preferences.":[62],"We":[63],"further":[64,129],"introduce":[65],"integration":[68],"AI":[70,122,140],"with":[72,81,124],"Supervised":[74],"Fine-Tuning":[75],"(SFT)":[76],"policy,":[77],"aligning":[78],"derived":[84],"from":[85],"AI.":[86],"Our":[87],"experiments":[88],"demonstrate":[89],"our":[91],"achieves":[93],"notable":[95],"approximation":[96],"preferences,":[99],"achieving":[100],"performance":[102],"level":[103],"68.13%":[105],"compared":[106],"human-level":[108],"benchmarks":[109],"delivering":[111],"competitive":[112],"results.":[113],"Furthermore,":[114],"showcase":[116],"synergistic":[118],"effects":[119],"combining":[121],"feedback,":[126],"resulting":[127],"in":[128,131],"improvements":[130],"quality.":[133],"research":[135],"offers":[136],"fresh":[137],"insights":[138],"into":[139],"learning":[142],"within":[143],"generation":[145],"lays":[147],"groundwork":[149],"for":[150],"more":[151],"efficient":[152],"cost-effective":[154],"training":[155],"methodologies.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}