{"id":"https://openalex.org/W4403580361","doi":"https://doi.org/10.1145/3664647.3681652","title":"Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value Optimization","display_name":"Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value Optimization","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403580361","doi":"https://doi.org/10.1145/3664647.3681652"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681652","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.12700","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xingqi Wang","orcid":"https://orcid.org/0009-0001-0017-6415"},"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":"Xingqi Wang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026595284","display_name":"Xiaoyuan Yi","orcid":"https://orcid.org/0000-0003-2710-1613"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyuan Yi","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044651577","display_name":"Xing Xie","orcid":"https://orcid.org/0000-0002-8608-8482"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Xie","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039477812","display_name":"Jia Jia","orcid":"https://orcid.org/0009-0005-8449-278X"},"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":"Jia Jia","raw_affiliation_strings":["DCST, BNRist, Tsinghua University & Key Laboratory of Pervasive Computing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, BNRist, Tsinghua University & Key Laboratory of Pervasive Computing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.245,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53874327,"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":"3558","last_page":"3567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9966999888420105,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9966999888420105,"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/T10028","display_name":"Topic Modeling","score":0.9912999868392944,"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":0.9840999841690063,"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":0.7541193962097168},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5839686393737793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5154812932014465},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49300262331962585},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.48768794536590576},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4695601761341095},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.4611930847167969},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4355594217777252},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36862874031066895},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27410879731178284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541193962097168},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5839686393737793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5154812932014465},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49300262331962585},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.48768794536590576},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4695601761341095},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.4611930847167969},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4355594217777252},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36862874031066895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27410879731178284},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3681652","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.12700","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.12700","pdf_url":"https://arxiv.org/pdf/2410.12700","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.12700","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.12700","pdf_url":"https://arxiv.org/pdf/2410.12700","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6394240923","display_name":null,"funder_award_id":"2024QY1400","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2763110165","https://openalex.org/W2914584698","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2964243274","https://openalex.org/W2966792645","https://openalex.org/W2981852735","https://openalex.org/W3026874504","https://openalex.org/W4281661987","https://openalex.org/W4288083803","https://openalex.org/W4288089799","https://openalex.org/W4306820534","https://openalex.org/W4312879041","https://openalex.org/W4312933868","https://openalex.org/W4322718246","https://openalex.org/W4366330503","https://openalex.org/W4382202677","https://openalex.org/W4384464487","https://openalex.org/W4386066536","https://openalex.org/W4386072096","https://openalex.org/W4386242353","https://openalex.org/W4386246859","https://openalex.org/W4389519380","https://openalex.org/W4390871724","https://openalex.org/W4390874260","https://openalex.org/W4393160410","https://openalex.org/W4394593019","https://openalex.org/W4402753790","https://openalex.org/W6851592950"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3009369890","https://openalex.org/W4312490297","https://openalex.org/W2312145515"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,115],"diffusion":[3,103],"models":[4,67],"trained":[5],"on":[6,36],"large-scale":[7],"data":[8],"have":[9],"enabled":[10],"the":[11,41,85,89,111,132,168],"generation":[12],"of":[13,43,91,147],"indistinguishable":[14],"human-level":[15],"images,":[16],"yet":[17],"they":[18],"often":[19],"produce":[20],"harmful":[21,174],"content":[22],"misaligned":[23],"with":[24,68,84],"human":[25,69],"values,":[26],"e.g.,":[27],"social":[28],"bias,":[29],"and":[30,97,127,162,176,184,199,205],"offensive":[31],"content.":[32],"Despite":[33],"extensive":[34],"research":[35],"Large":[37],"Language":[38],"Models":[39],"(LLMs),":[40],"challenge":[42],"Text-to-Image":[44],"(T2I)":[45],"model":[46,113,160],"alignment":[47,117],"remains":[48],"largely":[49],"unexplored.":[50],"Addressing":[51],"this":[52],"problem,":[53],"we":[54,100,135],"propose":[55],"LiVO":[56,71,171],"(Lightweight":[57],"Value":[58],"Optimization),":[59],"a":[60,74,80,102,120,138,143],"novel":[61],"lightweight":[62],"method":[63],"for":[64],"aligning":[65],"T2I":[66,192],"values.":[70,98],"only":[72],"optimizes":[73],"plug-and-play":[75],"value":[76,82,128,133,154,165],"encoder":[77],"to":[78,140],"integrate":[79],"specified":[81],"principle":[83],"input":[86,169],"prompt,":[87,170],"allowing":[88],"control":[90],"generated":[92],"images":[93,200],"over":[94],"both":[95],"semantics":[96],"Specifically,":[99],"design":[101],"model-tailored":[104],"preference":[105,145],"optimization":[106],"loss,":[107],"which":[108],"theoretically":[109],"approximates":[110],"Bradley-Terry":[112],"used":[114],"LLM":[116],"but":[118],"provides":[119],"more":[121],"flexible":[122],"trade-off":[123],"between":[124],"image":[125],"quality":[126],"conformity.":[129],"To":[130],"optimize":[131],"encoder,":[134],"also":[136],"develop":[137],"framework":[139],"automatically":[141],"construct":[142],"text-image":[144],"dataset":[146],"86k":[148],"(prompt,":[149],"aligned":[150,191],"image,":[151,153],"violating":[152],"principle)":[155],"samples.":[156],"Without":[157],"updating":[158],"most":[159],"parameters":[161],"through":[163],"adaptive":[164],"selection":[166],"from":[167],"significantly":[172],"reduces":[173],"outputs":[175],"achieves":[177],"faster":[178],"convergence,":[179],"surpassing":[180],"several":[181],"strong":[182],"baselines":[183],"taking":[185],"an":[186],"initial":[187],"step":[188],"towards":[189],"ethically":[190],"models.":[193],"Warning:":[194],"This":[195],"paper":[196],"involves":[197],"descriptions":[198],"depicting":[201],"discriminatory,":[202],"pornographic,":[203],"bloody,":[204],"horrific":[206],"scenes.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2024-10-21T00:00:00"}