{"id":"https://openalex.org/W7162106874","doi":"https://doi.org/10.48550/arxiv.2605.21611","title":"UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation","display_name":"UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7162106874","doi":"https://doi.org/10.48550/arxiv.2605.21611"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.21611","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21611","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.21611","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136790616","display_name":"Jiayun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiayun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136771377","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0003-0975-8937"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136797162","display_name":"Weijie Gan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gan, Weijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136756029","display_name":"Zhenting Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhenting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136737833","display_name":"Wei Wei","orcid":"https://orcid.org/0009-0009-2633-0335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Wei","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":0.6344000101089478,"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":0.6344000101089478,"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":0.25220000743865967,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.007899999618530273,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6377999782562256},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5629000067710876},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5566999912261963},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.538100004196167},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5299999713897705},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4828000068664551},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4779999852180481},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.39910000562667847}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519999742507935},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6377999782562256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.590399980545044},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5629000067710876},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5566999912261963},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.538100004196167},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4544000029563904},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38850000500679016},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3792000114917755},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.35989999771118164},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.2808000147342682},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.21611","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21611","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.21611","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21611","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.5124276876449585,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"introduce":[1],"spatially":[2,254],"grounded":[3,255],"contextual":[4,81],"image":[5,9,22,82,201,256],"generation,":[6],"a":[7,20,24,50,70,103,122,136,154,174,186,259],"controllable":[8],"generation":[10,83,257],"task":[11],"that":[12,126,192],"reframes":[13],"the":[14,56,62,67,107,116,147,163,222,243,246,250],"conditioning":[15,261],"paradigm.":[16,262],"Instead":[17],"of":[18,188,245],"supplying":[19],"reference":[21],"and":[23,35,120,129,151,197,212,233],"global":[25],"text":[26,72,165,177,223],"prompt":[27],"through":[28],"two":[29],"separate":[30],"encoders,":[31],"one":[32,36],"for":[33,37,69,195,252],"vision":[34],"language,":[38],"UniVL":[39,108,123,145,160,199],"is":[40,59],"trained":[41],"to":[42,45,210,217,231,237],"bind":[43],"semantics":[44],"spatial":[46,63,133],"locations":[47,134],"directly":[48],"from":[49,111,208,215],"single":[51,137],"unified":[52,117,260],"visual":[53,128],"input,":[54],"where":[55],"textual":[57],"instruction":[58],"rendered":[60],"onto":[61],"mask.":[64],"This":[65],"removes":[66],"need":[68],"standalone":[71,164],"encoder":[73,224],"at":[74],"inference":[75,227],"time.":[76],"The":[77],"resulting":[78],"model":[79],"supports":[80],"by":[84,229,235],"following":[85],"user-specified":[86],"instructions":[87],"about":[88],"what":[89],"should":[90],"appear":[91],"where,":[92],"while":[93],"substantially":[94],"reducing":[95,206,226],"computation.":[96],"To":[97],"address":[98],"this":[99,171],"task,":[100],"we":[101,193],"propose":[102],"framework":[104],"in":[105,135],"which":[106],"encoder,":[109,166],"adapted":[110],"an":[112],"optical-character-recognition-pretrained":[113],"backbone,":[114],"reads":[115],"condition":[118],"optically":[119],"produces":[121],"embedding,":[124],"fVIL,":[125],"fuses":[127],"semantic":[130],"intent":[131],"with":[132,146,258],"token":[138],"sequence.":[139],"A":[140],"two-stage":[141],"pipeline":[142],"first":[143],"aligns":[144],"VAE":[148],"embedding":[149],"space":[150],"then":[152],"conditions":[153],"pretrained":[155],"diffusion":[156],"backbone":[157],"entirely":[158],"on":[159],"embeddings,":[161],"eliminating":[162],"such":[167],"as":[168],"T5.":[169],"Although":[170],"reframing":[172],"uses":[173],"deliberately":[175],"minimal":[176],"interface,":[178],"it":[179],"yields":[180],"strong":[181],"empirical":[182],"gains.":[183],"On":[184],"UniVL-ImgGen,":[185],"benchmark":[187],"477K":[189],"mask-annotated":[190],"images":[191],"construct":[194],"training":[196],"evaluation,":[198],"improves":[200],"quality":[202],"over":[203],"text-prompted":[204],"baselines,":[205],"FID":[207],"14":[209],"11":[211],"increasing":[213],"PSNR":[214],"16":[216],"20.":[218],"It":[219],"also":[220],"eliminates":[221],"entirely,":[225],"TFLOPs":[228],"up":[230,236],"52%":[232],"runtime":[234],"44%.":[238],"Additional":[239],"ablation":[240],"studies":[241],"validate":[242],"contributions":[244],"proposed":[247],"components,":[248],"paving":[249],"way":[251],"efficient,":[253]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-23T00:00:00"}