{"id":"https://openalex.org/W7160289547","doi":"https://doi.org/10.1109/wacv61042.2026.00799","title":"Conversational Image Generation: Towards Multi-Round Personalized Generation with Multi-Modal Language Models","display_name":"Conversational Image Generation: Towards Multi-Round Personalized Generation with Multi-Modal Language Models","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160289547","doi":"https://doi.org/10.1109/wacv61042.2026.00799"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5100708288","display_name":"Haochen Zhang","orcid":"https://orcid.org/0009-0006-6950-5244"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haochen Zhang","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135343347","display_name":"Animesh Sinha","orcid":null},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Animesh Sinha","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135348578","display_name":"Felix Juefei-Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Juefei-Xu","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135371358","display_name":"Haoyu Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoyu Ma","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135355617","display_name":"Kunpeng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunpeng Li","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135370159","display_name":"Zhipeng Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhipeng Fan","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135305188","display_name":"Xiaoliang Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoliang Dai","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109007952","display_name":"Tingbo Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tingbo Hou","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057613852","display_name":"Peizhao Zhang","orcid":"https://orcid.org/0000-0001-7128-191X"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peizhao Zhang","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135317428","display_name":"Zecheng He","orcid":null},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zecheng He","raw_affiliation_strings":["UC San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Diego","institution_ids":["https://openalex.org/I2800935791"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2800935791"],"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":"8282","last_page":"8291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.46239998936653137,"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":0.46239998936653137,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2362000048160553,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0284000001847744,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4693000018596649},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42809998989105225},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3456999957561493},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.32910001277923584},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.2989000082015991},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.29649999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984999775886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4986000061035156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49300000071525574},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34459999203681946},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.32910001277923584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30469998717308044},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6789015531539917,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2969985801","https://openalex.org/W3087871082","https://openalex.org/W3216352822","https://openalex.org/W4239455594","https://openalex.org/W4312933868","https://openalex.org/W4372334257","https://openalex.org/W4386072096","https://openalex.org/W4386076215","https://openalex.org/W4390871856","https://openalex.org/W4390872297","https://openalex.org/W4390873054","https://openalex.org/W4390874265","https://openalex.org/W4390874393","https://openalex.org/W4390874575","https://openalex.org/W4393148714","https://openalex.org/W4402703076","https://openalex.org/W4402727536","https://openalex.org/W7133193597","https://openalex.org/W7133239970"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,35,69,163],"diffusion":[3,27],"models":[4,55],"have":[5],"significantly":[6],"enhanced":[7],"personalized":[8,164],"image":[9,165],"generation,":[10,113],"enabling":[11],"high-fidelity":[12],"synthesis":[13],"of":[14,26,72,146],"human-subject-specific":[15],"images.":[16],"However,":[17],"existing":[18],"approaches":[19],"are":[20],"constrained":[21],"by":[22],"the":[23,70,86,122,144,151],"inherent":[24],"limitations":[25],"models,":[28],"which":[29,75],"lack":[30],"conversational":[31,59,156],"capabilities,":[32],"and":[33,106,120],"operate":[34],"a":[36,47,66,89,97,116],"single-round":[37],"setting,":[38],"restricting":[39],"user":[40],"interaction.":[41],"In":[42],"this":[43,149],"work,":[44],"we":[45,64,84,114],"propose":[46],"novel":[48],"framework":[49],"that":[50,133],"integrates":[51],"multi-modal":[52],"large":[53],"language":[54],"(MLLMs)":[56],"for":[57,161],"multi-round":[58,112,124],"personalization.":[60],"To":[61,110,143],"achieve":[62],"this,":[63],"identified":[65],"performance":[67,138],"bottleneck":[68],"detokenizer":[71,87],"current":[73],"MLLMs,":[74],"struggles":[76],"to":[77,102,154],"reconstruct":[78],"fine-grained":[79],"facial":[80],"identity":[81],"details.":[82],"Thus,":[83],"enhance":[85],"with":[88],"personalization-enhaced":[90],"Diffusion":[91],"Transformer":[92],"(DiT).":[93],"We":[94],"also":[95],"introduce":[96],"multi-stage":[98],"instruction":[99],"fine-tuning":[100],"strategy":[101],"balance":[103],"face":[104],"preservation":[105],"prompt":[107],"alignment":[108],"effectively.":[109],"support":[111],"implement":[115],"chat-history":[117],"caching":[118],"mechanism":[119],"construct":[121],"first":[123,152],"personalization":[125,141],"dataset":[126],"from":[127],"video":[128],"clips.":[129],"Experimental":[130],"results":[131],"demonstrate":[132],"our":[134,147],"approach":[135],"achieves":[136],"state-of-the-art":[137],"among":[139],"MLLM-based":[140],"methods.":[142],"best":[145],"knowledge,":[148],"is":[150],"work":[153],"enable":[155],"personalization,":[157],"unlocking":[158],"new":[159],"capabilities":[160],"MLLMs":[162],"generation.":[166]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}
