{"id":"https://openalex.org/W7134905625","doi":"https://doi.org/10.48550/arxiv.2603.09877","title":"InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing","display_name":"InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134905625","doi":"https://doi.org/10.48550/arxiv.2603.09877"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.09877","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09877","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.09877","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128731252","display_name":"Changyao Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tian, Changyao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128758010","display_name":"Danni Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Danni","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128710798","display_name":"Guanzhou Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Guanzhou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128785884","display_name":"Erfei Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Erfei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128779035","display_name":"Zhaokai Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhaokai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128705322","display_name":"Yuchen Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Yuchen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123384595","display_name":"Penghao Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Penghao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027847451","display_name":"Sitao Chen","orcid":"https://orcid.org/0009-0000-8913-6059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Sitao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028230401","display_name":"Ganlin Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Ganlin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128758172","display_name":"Mingxin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Mingxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128767892","display_name":"Zirun Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Zirun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128735292","display_name":"Ziqian Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Ziqian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128795790","display_name":"Leyao Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Leyao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128707879","display_name":"Haomin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haomin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128764985","display_name":"Qi Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102216495","display_name":"Jinhui Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Jinhui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128744020","display_name":"Xue Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128740358","display_name":"Zhihang Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Zhihang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128755278","display_name":"Qi Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128693597","display_name":"Yi Xin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin, Yi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128787969","display_name":"Bin Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Bin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128796189","display_name":"Yihao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yihao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101324826","display_name":"Jiaye Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge, Jiaye","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128764441","display_name":"Qipeng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Qipeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128769771","display_name":"Gen Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Gen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128691981","display_name":"Hongsheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hongsheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128706202","display_name":"Yu Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128784222","display_name":"Kai rong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Kai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128718502","display_name":"Hongjie Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hongjie","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":29,"corresponding_author_ids":["https://openalex.org/A5128731252"],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9399999976158142,"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":0.9399999976158142,"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":0.01899999938905239,"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":0.004399999976158142,"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/modular-design","display_name":"Modular design","score":0.6883000135421753},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6420000195503235},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.47870001196861267},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4350000023841858},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.40149998664855957},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.3686000108718872},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.34610000252723694},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.33880001306533813}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032000064849854},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6883000135421753},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6420000195503235},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.48539999127388},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4415000081062317},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.31029999256134033},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C145644426","wikidata":"https://www.wikidata.org/wiki/Q169411","display_name":"Unified Modeling Language","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.09877","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09877","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.09877","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.09877","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":"article"},"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":{"Unified":[0],"multimodal":[1,162],"models":[2,143],"(UMMs)":[3],"that":[4,34,106,124],"integrate":[5],"understanding,":[6],"reasoning,":[7,101],"generation,":[8],"and":[9,19,50,82,99,156,164],"editing":[10,157],"face":[11],"inherent":[12],"trade-offs":[13],"between":[14,79],"maintaining":[15],"strong":[16,161],"semantic":[17],"comprehension":[18],"acquiring":[20],"powerful":[21],"generation":[22,72,81,119,155],"capabilities.":[23,166],"In":[24],"this":[25],"report,":[26],"we":[27,85],"present":[28],"InternVL-U,":[29],"a":[30,39,60,68,87,103,127],"lightweight":[31],"4B-parameter":[32],"UMM":[33],"democratizes":[35],"these":[36],"capabilities":[37],"within":[38],"unified":[40,47,141],"framework.":[41],"Guided":[42],"by":[43],"the":[44,77],"principles":[45],"of":[46],"contextual":[48],"modeling":[49],"modality-specific":[51],"modular":[52],"design":[53],"with":[54,67,116,144],"decoupled":[55],"visual":[56,71,118],"representations,":[57],"InternVL-U":[58,125],"integrates":[59],"state-of-the-art":[61],"Multimodal":[62],"Large":[63],"Language":[64],"Model":[65],"(MLLM)":[66],"specialized":[69],"MMDiT-based":[70],"head.":[73],"To":[74],"further":[75],"bridge":[76],"gap":[78],"aesthetic":[80],"high-level":[83],"intelligence,":[84],"construct":[86],"comprehensive":[88],"data":[89],"synthesis":[90],"pipeline":[91],"targeting":[92],"high-semantic-density":[93],"tasks,":[94,158],"such":[95,149],"as":[96,150],"text":[97],"rendering":[98],"scientific":[100],"under":[102],"reasoning-centric":[104],"paradigm":[105],"leverages":[107],"Chain-of-Thought":[108],"(CoT)":[109],"to":[110],"better":[111],"align":[112],"abstract":[113],"user":[114],"intent":[115],"fine-grained":[117],"details.":[120],"Extensive":[121],"experiments":[122],"demonstrate":[123],"achieves":[126],"superior":[128],"performance":[129],"-":[130],"efficiency":[131],"balance.":[132],"Despite":[133],"using":[134],"only":[135],"4B":[136],"parameters,":[137],"it":[138],"consistently":[139],"outperforms":[140],"baseline":[142],"over":[145],"3x":[146],"larger":[147],"scales":[148],"BAGEL":[151],"(14B)":[152],"on":[153],"various":[154],"while":[159],"retaining":[160],"understanding":[163],"reasoning":[165]},"counts_by_year":[],"updated_date":"2026-03-12T06:18:43.230356","created_date":"2026-03-12T00:00:00"}