{"id":"https://openalex.org/W7223242516","doi":"https://doi.org/10.48550/arxiv.2610.28801","title":"JUICE: Unified Multimodal Modeling in Pretrained Representation Spaces","display_name":"JUICE: Unified Multimodal Modeling in Pretrained Representation Spaces","publication_year":2026,"publication_date":"2026-10-20","ids":{"openalex":"https://openalex.org/W7223242516","doi":"https://doi.org/10.48550/arxiv.2610.28801"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.28801","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.28801","pdf_url":"https://arxiv.org/pdf/2610.28801","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/2610.28801","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159271379","display_name":"Jiahan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Jiahan","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102616647","display_name":"Huangyuan Su","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Su, Huangyuan","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055545928","display_name":"Shengbang Tong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong, Shengbang","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159293119","display_name":"Shusheng Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Shusheng","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100595351","display_name":"Ruihan Guo","orcid":"https://orcid.org/0000-0001-5018-6606","observed_orcids":["https://orcid.org/0000-0001-5018-6606","https://orcid.org/0009-0004-6451-8914"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guo, Ruihan","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123477518","display_name":"Suozhi Huang","orcid":"https://orcid.org/0009-0001-7922-0051","observed_orcids":["https://orcid.org/0009-0001-7922-0051"]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Suozhi","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030301481","display_name":"Hexu Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao, Hexu","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053819690","display_name":"Pratyusha Sharma","orcid":"https://orcid.org/0000-0001-9053-4943","observed_orcids":["https://orcid.org/0000-0001-9053-4943"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharma, Pratyusha","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159268597","display_name":"Sherry Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Sherry","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159282480","display_name":"Jiatao Gu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gu, Jiatao","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089960673","display_name":"Rob Fergus","orcid":"https://orcid.org/0009-0005-3077-2495","observed_orcids":["https://orcid.org/0009-0005-3077-2495"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fergus, Rob","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159278767","display_name":"Kyunghyun Cho","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cho, Kyunghyun","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9907000064849854,"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":0.9907000064849854,"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":0.009100000374019146,"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/T10028","display_name":"Topic Modeling","score":0.0,"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/flow-matching","display_name":"flow matching","score":0.859000027179718},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.9890000224113464},{"id":"https://openalex.org/keywords/image-generation","display_name":"image generation","score":0.6610000133514404},{"id":"https://openalex.org/keywords/maze-solving","display_name":"maze solving","score":0.5879999995231628},{"id":"https://openalex.org/keywords/text-to-image-generation","display_name":"text-to-image generation","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7566999793052673},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6100000143051147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.599399983882904},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5519999861717224},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5160999894142151},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49799999594688416},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4562999904155731},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43619999289512634},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.43369999527931213},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.34299999475479126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.31220000982284546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.28801","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.28801","pdf_url":"https://arxiv.org/pdf/2610.28801","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.28801","doi":"https://doi.org/10.48550/arxiv.2610.28801","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.28801","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.28801","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.28801","pdf_url":"https://arxiv.org/pdf/2610.28801","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223242516.pdf","grobid_xml":"https://content.openalex.org/works/W7223242516.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7170145606","https://openalex.org/W7215108157","https://openalex.org/W4407384793","https://openalex.org/W7136210873","https://openalex.org/W4415061330","https://openalex.org/W7164961950","https://openalex.org/W4405031468","https://openalex.org/W4416612959","https://openalex.org/W7025209376","https://openalex.org/W6967290142"],"abstract_inverted_index":{"Most":[0],"unified":[1],"multimodal":[2,105],"models":[3],"treat":[4],"images":[5],"and":[6,21,71,77,88,119,135,192,199,206,219,229,274],"text":[7,120,163],"asymmetrically:":[8],"a":[9,29,111,176,247,250],"pretrained":[10],"language":[11,216],"model":[12,92,177,217],"generates":[13,19],"text,":[14],"an":[15],"attached":[16],"diffusion":[17],"head":[18],"images,":[20],"outputs":[22],"that":[23,53],"contain":[24],"both":[25,44,65,235],"are":[26,133,137],"produced":[27],"in":[28,67,97,122],"fixed":[30],"order,":[31],"so":[32],"the":[33,39,93,141,238,255],"first":[34],"output":[35],"cannot":[36],"adapt":[37],"to":[38,225,272,278],"second.":[40],"We":[41,90,100],"ask":[42],"whether":[43],"modalities":[45,66,132,236],"can":[46,244],"instead":[47],"be":[48],"generated":[49,138],"by":[50],"one":[51,68],"process":[52],"is":[54],"trained":[55,178],"on":[56,190,227,231,249],"them":[57,81],"jointly":[58],"from":[59,237,267],"scratch.":[60],"Pretrained":[61],"encoder":[62,201],"spaces":[63,202],"hold":[64],"continuous":[69,165],"form":[70],"carry":[72],"knowledge":[73],"learned":[74],"at":[75,220,290],"scale,":[76],"recent":[78],"work":[79],"finds":[80],"effective":[82],"as":[83,164,209],"generative":[84],"targets":[85],"for":[86,175,180],"vision":[87],"language.":[89],"therefore":[91],"joint":[94,150,191,239,264],"distribution":[95,240],"directly":[96],"these":[98],"spaces.":[99],"introduce":[101],"JUICE":[102,222,285],"(Joint":[103],"Unified":[104],"modeling":[106],"In":[107],"Continuous":[108],"Encoder":[109],"spaces),":[110],"single":[112],"flow":[113],"matching":[114,256],"Transformer":[115],"over":[116],"frozen":[117],"image":[118,143,168],"representations,":[121],"which":[123,136],"each":[124,156],"modality":[125,276],"has":[126,277],"its":[127,291],"own":[128],"noise":[129],"level.":[130],"Which":[131],"clean":[134],"then":[139],"decides":[140],"task:":[142],"generation,":[144],"captioning,":[145],"visual":[146,282],"question":[147],"answering,":[148],"or":[149],"generation.":[151],"Controlled":[152],"pretraining":[153],"runs":[154],"test":[155],"design":[157],"choice.":[158],"At":[159,211],"equal":[160],"guidance,":[161],"generating":[162],"states":[166],"leaves":[167],"generation":[169],"intact":[170],"(48.41":[171],"GenEval,":[172],"against":[173],"47.86":[174],"only":[179],"text-to-image":[181],"generation),":[182],"while":[183,252],"captions":[184],"lose":[185],"some":[186],"exact":[187],"wording.":[188],"Training":[189],"conditional":[193],"denoising":[194],"together":[195],"beats":[196],"either":[197],"alone,":[198],"semantic":[200],"beat":[203],"VAE":[204],"latents":[205],"raw":[207],"pixels":[208],"targets.":[210],"2.1B":[212],"parameters,":[213],"with":[214,260,269],"no":[215,275],"initialization":[218],"224x224,":[221],"reaches":[223],"up":[224],"0.88":[226],"GenEval":[228],"73.1":[230],"VQAv2.":[232],"By":[233],"sampling":[234,271],"(coupled":[241],"sampling),":[242],"it":[243],"also":[245],"draw":[246],"route":[248],"map":[251],"writing":[253],"out":[254],"moves.":[257],"On":[258,281],"mazes":[259],"several":[261],"valid":[262],"solutions,":[263],"success":[265],"rises":[266],"54.6%":[268],"independent":[270],"93.7%,":[273],"go":[279],"first.":[280],"spatial":[283],"planning,":[284],"solves":[286],"99.8%":[287],"of":[288],"maps":[289],"training":[292],"sizes.":[293]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-23T00:00:00"}