{"id":"https://openalex.org/W7166674457","doi":"https://doi.org/10.48550/arxiv.2606.30332","title":"UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception","display_name":"UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception","publication_year":2026,"publication_date":"2026-06-29","ids":{"openalex":"https://openalex.org/W7166674457","doi":"https://doi.org/10.48550/arxiv.2606.30332"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.30332","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30332","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.30332","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139647953","display_name":"Qin Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Qin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139682778","display_name":"Hao Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114231560","display_name":"Dongxu Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue, Dongxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067398239","display_name":"Weixuan Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Weixuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139670988","display_name":"Xiao Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029787563","display_name":"Fang Wang","orcid":"https://orcid.org/0000-0002-3327-4177"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019421104","display_name":"D Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Dan","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":0.677299976348877,"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":0.677299976348877,"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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.1054999977350235,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.06260000169277191,"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/unified-model","display_name":"Unified Model","score":0.6582000255584717},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5425000190734863},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5242000222206116},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5163999795913696},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.47119998931884766},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.45649999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7336999773979187},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.6582000255584717},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5285999774932861},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5242000222206116},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.47119998931884766},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45649999380111694},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.375},{"id":"https://openalex.org/C46451288","wikidata":"https://www.wikidata.org/wiki/Q1080745","display_name":"Unified field theory","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3203999996185303},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C3018907156","wikidata":"https://www.wikidata.org/wiki/Q7785058","display_name":"Third generation","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.30332","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30332","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.30332","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.30332","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,9,201],"diffusion":[3],"models":[4],"have":[5],"shown":[6],"impressive":[7],"performance":[8],"controllable":[10,23,54,80,102],"image":[11,134],"generation":[12,24,55,81,158],"and":[13,25,56,82,106,116,159,173],"dense":[14,26,57,104,140],"prediction":[15,27,58,83],"tasks.":[16,161],"However,":[17],"existing":[18],"approaches":[19,172],"typically":[20],"treat":[21],"diffusion-based":[22],"as":[28],"separate":[29],"tasks,":[30],"overlooking":[31],"the":[32,38,64,74,91,110,125,145],"potential":[33],"benefits":[34],"of":[35,94,100,114,127,136],"jointly":[36,156],"modeling":[37],"heterogeneous":[39,148],"distributions.":[40],"In":[41],"this":[42],"work,":[43],"we":[44,181],"introduce":[45],"UniGP,":[46],"a":[47,117,132,151],"framework":[48,154],"built":[49],"upon":[50],"MMDiT,":[51],"which":[52],"unifies":[53],"through":[59],"simple":[60],"joint":[61,92,107,185],"training,":[62],"without":[63],"need":[65],"for":[66],"complex":[67],"task-specific":[68],"designs":[69],"or":[70],"losses,":[71],"while":[72,144,195],"preserving":[73],"backbone's":[75],"versatile":[76,101],"priors.":[77],"By":[78],"learning":[79,197],"under":[84],"different":[85],"conditions,":[86],"our":[87,166],"model":[88,139,157,168],"effectively":[89],"captures":[90],"distribution":[93],"image-geometry":[95],"pairs.":[96],"UniGP":[97,112],"is":[98],"capable":[99],"generation,":[103],"prediction,":[105],"generation.":[108,202],"Specifically,":[109],"proposed":[111],"consists":[113],"DUGP":[115],"unified":[118,152,167,171],"dataset":[119],"training":[120,153,186],"strategy.":[121],"The":[122],"former,":[123],"following":[124],"principle":[126],"Occam's":[128],"razor,":[129],"uses":[130],"only":[131],"copied":[133],"branch":[135],"MMDiT":[137],"to":[138,155],"distributions":[141],"beyond":[142],"RGB,":[143],"latter":[146],"integrates":[147],"datasets":[149],"into":[150],"perception":[160],"Extensive":[162],"experiments":[163],"demonstrate":[164,182],"that":[165,183],"surpasses":[169],"prior":[170],"performs":[174],"on":[175],"par":[176],"with":[177],"specialized":[178],"methods.":[179],"Furthermore,":[180],"multi-task":[184],"provides":[187],"complementary":[188],"benefits:":[189],"generative":[190],"priors":[191],"enrich":[192],"perceptual":[193,196],"details,":[194],"improves":[198],"structural":[199],"alignment":[200]},"counts_by_year":[],"updated_date":"2026-07-01T06:29:00.853634","created_date":"2026-07-01T00:00:00"}