{"id":"https://openalex.org/W4408353952","doi":"https://doi.org/10.1109/icassp49660.2025.10889541","title":"Boosting Text-To-Image Generation via Multilingual Prompting in Large Multimodal Models","display_name":"Boosting Text-To-Image Generation via Multilingual Prompting in Large Multimodal Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353952","doi":"https://doi.org/10.1109/icassp49660.2025.10889541"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889541","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/A5024348709","display_name":"Yongyu Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yongyu Mu","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021861548","display_name":"Hengyu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengyu Li","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057240571","display_name":"Wang Jun-xin","orcid":"https://orcid.org/0009-0009-6542-4561"},"institutions":[{"id":"https://openalex.org/I7350606","display_name":"Dalian Jiaotong University","ror":"https://ror.org/05gp45n31","country_code":"CN","type":"education","lineage":["https://openalex.org/I7350606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junxin Wang","raw_affiliation_strings":["Dalian Jiaotong University,School of Economics and Management,Dalian,China"],"affiliations":[{"raw_affiliation_string":"Dalian Jiaotong University,School of Economics and Management,Dalian,China","institution_ids":["https://openalex.org/I7350606"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102522363","display_name":"Xiaoxuan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxuan Zhou","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367825","display_name":"Chenglong Wang","orcid":"https://orcid.org/0000-0003-2391-0923"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Wang","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057019417","display_name":"Yingfeng Luo","orcid":"https://orcid.org/0000-0003-1950-9045"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingfeng Luo","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005184712","display_name":"Qiaozhi He","orcid":"https://orcid.org/0000-0002-9475-8319"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiaozhi He","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600701","display_name":"Tong Xiao","orcid":"https://orcid.org/0000-0002-5842-6501"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Xiao","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001145192","display_name":"Guocheng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guocheng Chen","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100370145","display_name":"Jingbo Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingbo Zhu","raw_affiliation_strings":["Northeastern University,School of Computer Science and Engineering,Shenyang,China"],"affiliations":[{"raw_affiliation_string":"Northeastern University,School of Computer Science and Engineering,Shenyang,China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5024348709"],"corresponding_institution_ids":["https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":1.3104,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77881749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9296000003814697,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9296000003814697,"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/boosting","display_name":"Boosting (machine learning)","score":0.8584843873977661},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7198193073272705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5850279927253723},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4734218716621399},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37475496530532837}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8584843873977661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7198193073272705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5850279927253723},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4734218716621399},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37475496530532837}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889541","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/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W3153469116","https://openalex.org/W3180355996","https://openalex.org/W3199400376","https://openalex.org/W4389520538","https://openalex.org/W4389523853","https://openalex.org/W4389911544","https://openalex.org/W4392822465","https://openalex.org/W4402670262","https://openalex.org/W4402672046","https://openalex.org/W4402727443","https://openalex.org/W6779823529","https://openalex.org/W6810940779","https://openalex.org/W6811013733","https://openalex.org/W6838639034","https://openalex.org/W6846007759","https://openalex.org/W6846948161","https://openalex.org/W6852162230","https://openalex.org/W6853182488","https://openalex.org/W6853927091","https://openalex.org/W6859768500","https://openalex.org/W6861170066","https://openalex.org/W6862123847","https://openalex.org/W6870018273"],"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":{"Previous":[0],"work":[1],"on":[2,14,110],"augmenting":[3],"large":[4],"multimodal":[5],"models":[6,100],"(LMMs)":[7],"for":[8,42],"text-to-image":[9],"(T2I)":[10],"generation":[11],"has":[12],"focused":[13],"enriching":[15],"the":[16,56,82,91,99,103,107],"input":[17,53,92],"space":[18],"of":[19,52,72,85,139],"in-context":[20],"learning":[21],"(ICL).":[22],"This":[23],"includes":[24],"providing":[25],"a":[26,60],"few":[27],"demonstrations":[28],"and":[29,37,45,97,106,127,156],"optimizing":[30],"image":[31,47],"descriptions":[32,48],"to":[33],"be":[34,161],"more":[35,43,141],"detailed":[36],"logical.":[38],"However,":[39],"as":[40],"demand":[41],"complex":[44],"flexible":[46],"grows,":[49],"enhancing":[50],"comprehension":[51],"text":[54,93,105],"within":[55],"ICL":[57],"paradigm":[58],"remains":[59],"critical":[61],"yet":[62],"underexplored":[63],"area.":[64],"In":[65],"this":[66,70],"work,":[67],"we":[68,89],"extend":[69],"line":[71],"research":[73],"by":[74],"constructing":[75],"parallel":[76,157],"multilingual":[77,83,158],"prompts":[78,148],"aimed":[79],"at":[80,163],"harnessing":[81],"capabilities":[84],"LMMs.":[86],"More":[87],"specifically,":[88],"translate":[90],"into":[94],"several":[95],"languages":[96],"provide":[98],"with":[101,136,151],"both":[102],"original":[104],"translations.":[108],"Experiments":[109],"two":[111],"LMMs":[112],"across":[113],"3":[114],"benchmarks":[115],"show":[116],"that":[117],"our":[118],"method,":[119],"PMT2I,":[120],"achieves":[121],"superior":[122],"performance":[123],"in":[124,131],"general,":[125],"compositional,":[126],"fine-grained":[128],"assessments,":[129],"especially":[130],"human":[132],"preference":[133],"alignment":[134],"Additionally,":[135],"its":[137],"advantage":[138],"generating":[140],"diverse":[142],"images,":[143],"PMT2I":[144],"significantly":[145],"outperforms":[146],"baseline":[147],"when":[149],"incorporated":[150],"reranking":[152],"methods.":[153],"Our":[154],"code":[155],"data":[159],"can":[160],"found":[162],"https://github.com/takagi97/PMT2I.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}