{"id":"https://openalex.org/W4416612959","doi":"https://doi.org/10.48550/arxiv.2505.23661","title":"OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation","display_name":"OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation","publication_year":2025,"publication_date":"2025-05-29","ids":{"openalex":"https://openalex.org/W4416612959","doi":"https://doi.org/10.48550/arxiv.2505.23661"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.23661","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23661","pdf_url":"https://arxiv.org/pdf/2505.23661","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-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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/2505.23661","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101236497","display_name":"Size Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wu, Size","raw_affiliation_strings":["S-Lab , Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab , Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091312510","display_name":"Zhonghua Wu","orcid":"https://orcid.org/0000-0002-8036-022X","observed_orcids":["https://orcid.org/0000-0002-8036-022X"]},"institutions":[{"id":"https://openalex.org/I4401727009","display_name":"Sensetime (China)","ror":"https://ror.org/049wsmj07","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401727009"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Zhonghua","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":["https://openalex.org/I4401727009"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049740224","display_name":"Zhaopeng Gong","orcid":"https://orcid.org/0000-0002-7313-3918","observed_orcids":["https://orcid.org/0000-0002-7313-3918"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Gong, Zerui","raw_affiliation_strings":["S-Lab , Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab , Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tao, Qingyi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401727009","display_name":"Sensetime (China)","ror":"https://ror.org/049wsmj07","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401727009"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao, Qingyi","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":["https://openalex.org/I4401727009"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jin, Sheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401727009","display_name":"Sensetime (China)","ror":"https://ror.org/049wsmj07","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401727009"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin, Sheng","raw_affiliation_strings":["SenseTime Research and Tetras.AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research and Tetras.AI","institution_ids":["https://openalex.org/I4401727009"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Qinyue","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401727009","display_name":"Sensetime (China)","ror":"https://ror.org/049wsmj07","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401727009"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Qinyue","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":["https://openalex.org/I4401727009"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041704012","display_name":"Wei Li","orcid":"https://orcid.org/0000-0001-8524-217X","observed_orcids":["https://orcid.org/0000-0001-8524-217X"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Li, Wei","raw_affiliation_strings":["S-Lab , Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab , Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005626854","display_name":"Chen Change Loy","orcid":"https://orcid.org/0000-0001-5345-1591","observed_orcids":["https://orcid.org/0000-0001-5345-1591"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Loy, Chen Change","raw_affiliation_strings":["S-Lab , Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"S-Lab , Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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":0.9951000213623047,"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":0.9951000213623047,"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":0.004600000102072954,"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":0.0,"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/unified-multimodal-models","display_name":"unified multimodal models","score":0.8159999847412109},{"id":"https://openalex.org/keywords/learnable-queries","display_name":"learnable queries","score":0.7620000243186951},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.6010000109672546},{"id":"https://openalex.org/keywords/image-generation","display_name":"image generation","score":0.6019999980926514},{"id":"https://openalex.org/keywords/instruction-alignment","display_name":"instruction alignment","score":0.6100000143051147},{"id":"https://openalex.org/keywords/efficient-training","display_name":"efficient training","score":0.6259999871253967},{"id":"https://openalex.org/keywords/open-source-models","display_name":"open-source models","score":0.656000018119812},{"id":"https://openalex.org/keywords/image-text-pairs","display_name":"image-text pairs","score":0.6930000185966492}],"concepts":[{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7961000204086304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7692000269889832},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7432000041007996},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5324000120162964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5234000086784363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4726000130176544},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26739999651908875},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2667999863624573}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.23661","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23661","pdf_url":"https://arxiv.org/pdf/2505.23661","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-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.23661","doi":"https://doi.org/10.48550/arxiv.2505.23661","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.23661","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:2505.23661","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.23661","pdf_url":"https://arxiv.org/pdf/2505.23661","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-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416612959.pdf","grobid_xml":"https://content.openalex.org/works/W4416612959.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7196956674","https://openalex.org/W4416611615","https://openalex.org/W7166108033","https://openalex.org/W4407384793","https://openalex.org/W7214890402","https://openalex.org/W7171645928","https://openalex.org/W4414742964","https://openalex.org/W7155358372","https://openalex.org/W4415314506","https://openalex.org/W6948254895"],"abstract_inverted_index":{"In":[0],"this":[1],"report,":[2],"we":[3,27,69,109],"present":[4],"OpenUni,":[5],"a":[6,53,59,64],"simple,":[7],"lightweight,":[8],"and":[9,17,38,49,58,77,80,93,98,106,116],"fully":[10],"open-source":[11],"baseline":[12],"for":[13],"unifying":[14],"multimodal":[15,44],"understanding":[16],"generation.":[18],"Inspired":[19],"by":[20,40],"prevailing":[21],"practices":[22],"in":[23],"unified":[24],"model":[25,112],"learning,":[26],"adopt":[28],"an":[29],"efficient":[30],"training":[31,36,114,119],"strategy":[32],"that":[33,71],"minimizes":[34],"the":[35,42],"complexity":[37],"overhead":[39],"bridging":[41],"off-the-shelf":[43],"large":[45],"language":[46],"models":[47,51],"(LLMs)":[48],"diffusion":[50],"through":[52],"set":[54],"of":[55,67],"learnable":[56],"queries":[57],"light-weight":[60],"transformer-based":[61],"connector.":[62],"With":[63],"minimalist":[65],"choice":[66],"architecture,":[68],"demonstrate":[70],"OpenUni":[72],"can:":[73],"1)":[74],"generate":[75],"high-quality":[76],"instruction-aligned":[78],"images,":[79],"2)":[81],"achieve":[82],"exceptional":[83],"performance":[84],"on":[85],"standard":[86],"benchmarks":[87],"such":[88],"as":[89],"GenEval,":[90],"DPG-":[91],"Bench,":[92],"WISE,":[94],"with":[95],"only":[96],"1.1B":[97],"3.1B":[99],"activated":[100],"parameters.":[101],"To":[102],"support":[103],"open":[104],"research":[105],"community":[107],"advancement,":[108],"release":[110],"all":[111],"weights,":[113],"code,":[115],"our":[117],"curated":[118],"datasets":[120],"(including":[121],"23M":[122],"image-text":[123],"pairs)":[124],"at":[125],"https://github.com/wusize/OpenUni.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-10T00:00:00"}