{"id":"https://openalex.org/W4414360091","doi":"https://doi.org/10.24963/ijcai.2025/81","title":"IterMeme: Expert-Guided Multimodal LLM for Interactive Meme Creation with Layout-Aware Generation","display_name":"IterMeme: Expert-Guided Multimodal LLM for Interactive Meme Creation with Layout-Aware Generation","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360091","doi":"https://doi.org/10.24963/ijcai.2025/81"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/81","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/81","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5102877899","display_name":"Yang Cai","orcid":"https://orcid.org/0000-0002-5426-1324"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaqi Cai","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001989503","display_name":"Shouen Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shancheng Fang","raw_affiliation_strings":["YuanShi Technology"],"affiliations":[{"raw_affiliation_string":"YuanShi Technology","institution_ids":["https://openalex.org/I99908691"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071238622","display_name":"Yadong Qu","orcid":"https://orcid.org/0000-0003-0265-5011"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Qu","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658021","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0002-3968-891X"},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["YuanShi Technology"],"affiliations":[{"raw_affiliation_string":"YuanShi Technology","institution_ids":["https://openalex.org/I99908691"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100756208","display_name":"Meng Shao","orcid":"https://orcid.org/0000-0002-3978-4784"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Shao","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078162380","display_name":"Hongtao Xie","orcid":"https://orcid.org/0000-0002-6249-5315"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtao Xie","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102877899"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35007093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"720","last_page":"728"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11197","display_name":"Digital Games and Media","score":0.9822999835014343,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11197","display_name":"Digital Games and Media","score":0.9822999835014343,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9416999816894531,"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/T10803","display_name":"Innovative Human-Technology Interaction","score":0.9394999742507935,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/personalization","display_name":"Personalization","score":0.6230999827384949},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.585099995136261},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5773000121116638},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5598999857902527},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.536300003528595},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5042999982833862},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.39660000801086426},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.3797999918460846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276000022888184},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.6230999827384949},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.585099995136261},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5773000121116638},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.536300003528595},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5239999890327454},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5042999982833862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4277999997138977},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/81","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/81","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Meme":[0],"creation":[1,44,169],"is":[2],"a":[3,48,67,73,80,103,108],"creative":[4],"process":[5],"that":[6,46,112,161],"blends":[7],"images":[8,119],"and":[9,23,78,93,120,135,155,178],"text.":[10,121],"However,":[11],"existing":[12],"methods":[13],"lack":[14,101],"critical":[15],"components,":[16],"failing":[17],"to":[18,29,55,90,183],"support":[19],"intent-driven":[20],"caption-layout":[21,68,95],"generation":[22,69,96],"personalized":[24],"generation,":[25],"making":[26],"it":[27],"difficult":[28],"generate":[30],"high-quality":[31,173],"memes.":[32],"To":[33,62,98],"address":[34,99],"this":[35],"limitation,":[36],"we":[37,71,106,123,148],"propose":[38],"IterMeme,":[39],"an":[40],"end-to-end":[41],"interactive":[42],"meme":[43,168],"framework":[45],"utilizes":[47],"unified":[49],"Multimodal":[50],"Large":[51],"Language":[52],"Model":[53],"(MLLM)":[54],"facilitate":[56],"seamless":[57],"collaboration":[58],"among":[59],"multiple":[60],"components.":[61],"overcome":[63],"the":[64,87,100,114,125,146,165,184],"absence":[65],"of":[66,102,117,145,152,167],"component,":[70,105],"develop":[72],"robust":[74],"layout":[75],"representation":[76],"method":[77],"construct":[79],"large-scale":[81],"image-caption-layout":[82],"dataset,":[83],"MemeCap,":[84],"which":[85],"enhances":[86],"model\u2019s":[88],"ability":[89],"comprehend":[91],"emotions":[92],"coordinate":[94],"effectively.":[97],"personalization":[104],"introduce":[107],"parameter-shared":[109],"dual-LLM":[110],"architecture":[111],"decouples":[113],"intricate":[115],"representations":[116],"reference":[118],"Furthermore,":[122],"incorporate":[124],"expert-guided":[126],"M\u00b3OE":[127],"for":[128],"fine-grained":[129],"identity":[130],"properties":[131],"(IP)":[132],"feature":[133],"extraction":[134],"cross-modal":[136],"fusion.":[137],"By":[138],"dynamically":[139],"injecting":[140],"features":[141],"into":[142],"every":[143],"layer":[144],"model,":[147,177],"enable":[149],"adaptive":[150],"refinement":[151],"both":[153],"visual":[154],"semantic":[156],"information.":[157],"Experimental":[158],"results":[159],"demonstrate":[160],"IterMeme":[162],"significantly":[163],"advances":[164],"field":[166],"by":[170],"delivering":[171],"consistently":[172],"outcomes.":[174],"The":[175],"code,":[176],"dataset":[179],"will":[180],"be":[181],"open-sourced":[182],"community.":[185]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
