{"id":"https://openalex.org/W4416251412","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228924","title":"EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts","display_name":"EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251412","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228924"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5100738290","display_name":"Yucheng Han","orcid":"https://orcid.org/0009-0003-5853-3117"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yucheng Han","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431313","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0002-7974-9510"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Tencent,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078454858","display_name":"Chi Zhang","orcid":"https://orcid.org/0000-0001-6607-6196"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["Tencent,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063090569","display_name":"Juntao Hu","orcid":"https://orcid.org/0000-0001-7652-7050"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juntao Hu","raw_affiliation_strings":["Tencent,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326687","display_name":"Pei Chen","orcid":"https://orcid.org/0000-0003-0696-9018"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pei Chen","raw_affiliation_strings":["Fudan University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109799482","display_name":"Bin Fu","orcid":"https://orcid.org/0009-0003-3131-9903"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Fu","raw_affiliation_strings":["Tencent,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"8"},"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":0.8578000068664551,"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":0.8578000068664551,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.04170000180602074,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/modular-design","display_name":"Modular design","score":0.6967999935150146},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.607699990272522},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5644999742507935},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5386999845504761},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5194000005722046},{"id":"https://openalex.org/keywords/natural-language-generation","display_name":"Natural language generation","score":0.4302000105381012},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.42570000886917114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7001000046730042},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6967999935150146},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.607699990272522},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5644999742507935},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5386999845504761},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49810001254081726},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.4302000105381012},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3605000078678131},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3495999872684479},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W4312933868","https://openalex.org/W4386072096","https://openalex.org/W4390872297","https://openalex.org/W4390874393","https://openalex.org/W4400573550","https://openalex.org/W4402703076","https://openalex.org/W4402704604","https://openalex.org/W4402782221","https://openalex.org/W4410096683","https://openalex.org/W4410773830"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,149,155],"image":[3,45,169],"generation":[4,46,66,170],"have":[5],"enabled":[6],"the":[7,65,96,109,113,145],"creation":[8],"of":[9,67,98,147],"high-quality":[10],"images":[11,103],"from":[12],"diverse":[13],"conditions,":[14],"such":[15],"as":[16,59,161],"text":[17,51],"and":[18,52,81,133,139,153],"images.":[19,68,141],"However,":[20],"existing":[21,99,127],"methods":[22],"struggle":[23],"to":[24,58,63,101,125],"balance":[25],"multiple":[26,106],"conditions":[27],"effectively,":[28],"typically":[29],"favoring":[30],"certain":[31],"modalities":[32,107],"over":[33],"others.":[34],"To":[35],"address":[36],"this":[37],"challenge,":[38],"we":[39,56,91],"introduce":[40],"EMMA,":[41],"a":[42,86,93,131,162],"novel":[43],"multi-modal":[44,167],"model":[47],"that":[48],"integrates":[49,79],"both":[50],"additional":[53,116],"modalities,":[54],"which":[55,77],"refer":[57],"\"text":[60],"+":[61],"X\",":[62],"guide":[64],"EMMA":[69,130,148],"incorporates":[70],"an":[71],"innovative":[72],"Multi-modal":[73],"Feature":[74],"Connector":[75],"design,":[76],"effectively":[78],"textual":[80],"supplementary":[82],"modal":[83],"information":[84],"through":[85],"special":[87],"attention":[88],"mechanism.":[89],"Additionally,":[90],"propose":[92],"method":[94],"for":[95,115,136,165],"assembly":[97],"modules":[100],"produce":[102],"conditioned":[104],"on":[105],"at":[108],"same":[110],"time,":[111],"eliminating":[112],"need":[114],"training.":[117],"This":[118],"modular":[119],"nature":[120],"also":[121],"facilitates":[122],"easy":[123],"adaptation":[124],"different":[126],"frameworks,":[128],"making":[129],"flexible":[132],"effective":[134],"tool":[135],"producing":[137],"personalized":[138],"context-aware":[140],"Extensive":[142],"experiments":[143],"demonstrate":[144],"effectiveness":[146],"maintaining":[150],"high":[151],"fidelity":[152],"detail":[154],"generated":[156],"images,":[157],"showcasing":[158],"its":[159],"potential":[160],"robust":[163],"solution":[164],"advanced":[166],"conditional":[168],"tasks.":[171]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}