{"id":"https://openalex.org/W7204264807","doi":"https://doi.org/10.48550/arxiv.2608.24563","title":"X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis","display_name":"X-MULTI: VLM-based Imaging Factor Disentanglement for Factor-Aware Image Synthesis","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204264807","doi":"https://doi.org/10.48550/arxiv.2608.24563"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.24563","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24563","pdf_url":"https://arxiv.org/pdf/2608.24563","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.24563","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136036213","display_name":"Sonali Godavarthy","orcid":"https://orcid.org/0009-0001-5379-1139","observed_orcids":["https://orcid.org/0009-0001-5379-1139"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Godavarthy, Sonali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144137035","display_name":"Matthias Neuwirth-Trapp","orcid":"https://orcid.org/0009-0006-5320-6354","observed_orcids":["https://orcid.org/0009-0006-5320-6354"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neuwirth-Trapp, Matthias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137779132","display_name":"Tim-Felix Faasch","orcid":"https://orcid.org/0009-0004-7410-5232","observed_orcids":["https://orcid.org/0009-0004-7410-5232"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Faasch, Tim-Felix","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022867597","display_name":"Maarten Bieshaar","orcid":"https://orcid.org/0000-0002-6471-6062","observed_orcids":["https://orcid.org/0000-0002-6471-6062"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bieshaar, Maarten","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135910833","display_name":"Michael Moeller","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moeller, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119379474","display_name":"Kristof Van Laerhoven","orcid":"https://orcid.org/0000-0001-5296-5347","observed_orcids":["https://orcid.org/0000-0001-5296-5347"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Van Laerhoven, Kristof","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050696776","display_name":"Danda Pani Paudel","orcid":"https://orcid.org/0000-0002-1739-1867","observed_orcids":["https://orcid.org/0000-0002-1739-1867"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paudel, Danda Pani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"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":0.9990000128746033,"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":0.9990000128746033,"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":0.0006000000284984708,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/text-to-image-generation","display_name":"text-to-image generation","score":0.9599999785423279},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9330000281333923},{"id":"https://openalex.org/keywords/viewpoint-control","display_name":"viewpoint control","score":0.6159999966621399},{"id":"https://openalex.org/keywords/event-cameras","display_name":"event cameras","score":0.40799999237060547},{"id":"https://openalex.org/keywords/fisheye-lens","display_name":"fisheye lens","score":0.8149999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6256999969482422},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6230999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5702999830245972},{"id":"https://openalex.org/C14103023","wikidata":"https://www.wikidata.org/wiki/Q11681459","display_name":"Pairing","level":3,"score":0.5430999994277954},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48159998655319214},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.4797999858856201},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4147999882698059},{"id":"https://openalex.org/C76935873","wikidata":"https://www.wikidata.org/wiki/Q209121","display_name":"Image sensor","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35089999437332153},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C163018871","wikidata":"https://www.wikidata.org/wiki/Q1302587","display_name":"Cross-correlation","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2678000032901764},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26019999384880066}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.24563","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24563","pdf_url":"https://arxiv.org/pdf/2608.24563","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2608.24563","doi":"https://doi.org/10.48550/arxiv.2608.24563","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24563","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.24563","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24563","pdf_url":"https://arxiv.org/pdf/2608.24563","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7161020137","https://openalex.org/W4361188957","https://openalex.org/W7171945573","https://openalex.org/W4417050549","https://openalex.org/W7102403317","https://openalex.org/W3014290105","https://openalex.org/W4401346565","https://openalex.org/W3035149916","https://openalex.org/W4312531268","https://openalex.org/W4390571101"],"abstract_inverted_index":{"Imaging":[0],"factor":[1,35,99,123,168,189,204],"disentanglement":[2,78,141,190],"in":[3,38,54,182],"text-to-image":[4],"generation":[5],"aims":[6],"to":[7,24,64,76,120,153,174],"independently":[8],"control":[9],"image":[10],"acquisition":[11],"properties":[12],"such":[13,42],"as":[14,43],"types":[15],"of":[16,187,203],"camera":[17],"lenses,":[18],"sensor":[19,51],"types,":[20],"viewpoints,":[21],"and":[22,82,157,191,196],"domains":[23],"enable":[25],"combinatorial":[26],"generalization.":[27],"This":[28],"should":[29],"let":[30],"the":[31,39,70,93,131,185],"model":[32,94,118],"synthesize":[33],"novel":[34,107,122,171],"combinations":[36,124,172],"unobserved":[37],"training":[40,55,104],"data,":[41],"pairing":[44],"a":[45,115,199],"fisheye":[46],"lens":[47],"with":[48,69],"an":[49],"event":[50],"never":[52],"observed":[53,97],"data.":[56],"Recent":[57],"work,":[58],"MULTI,":[59],"introduced":[60],"learnable,":[61],"factor-specific":[62,150],"embeddings":[63],"disentangle":[65],"imaging":[66,98],"factors,":[67],"along":[68],"Factor":[71],"Alignment":[72],"Accuracy":[73],"(FAA)":[74],"metric":[75,133],"evaluate":[77],"quality.":[79,142],"We":[80,109,143],"identify":[81],"address":[83],"two":[84],"independent":[85],"limitations.":[86],"First,":[87],"MULTI's":[88],"pixel-level":[89],"reconstruction":[90],"objective":[91],"supervises":[92],"only":[95],"on":[96,170],"combinations,":[100],"providing":[101],"no":[102],"direct":[103],"signal":[105],"for":[106],"combinations.":[108],"therefore":[110,144,197],"propose":[111,145],"X-MULTI,":[112],"which":[113,148],"uses":[114],"pretrained":[116],"vision-language":[117],"(VLM)":[119],"supervise":[121],"synthesized":[125],"during":[126],"training.":[127],"Second,":[128],"we":[129,177],"show":[130,178],"FAA":[132,183],"exhibits":[134],"severe":[135],"cross-factor":[136],"correlation":[137,180],"leakage,":[138],"misrepresenting":[139],"true":[140,188],"Improved-FAA":[146],"(I-FAA),":[147],"employs":[149],"augmentation":[151],"strategies":[152],"break":[154],"these":[155],"correlations":[156],"enables":[158],"more":[159,200],"rigorous":[160],"evaluation.":[161],"Experiments":[162],"demonstrate":[163],"that":[164,179],"X-MULTI":[165],"achieves":[166],"improved":[167],"alignment":[169],"compared":[173],"MULTI.":[175],"Moreover,":[176],"leakage":[181,195],"distorts":[184],"evaluation":[186],"I-FAA":[192],"reduces":[193],"this":[194],"provides":[198],"robust":[201],"assessment":[202],"alignment.":[205]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-27T00:00:00"}