{"id":"https://openalex.org/W4377164418","doi":"https://doi.org/10.48550/arxiv.2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","display_name":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","publication_year":2023,"publication_date":"2023-05-18","ids":{"openalex":"https://openalex.org/W4377164418","doi":"https://doi.org/10.48550/arxiv.2305.11172"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.11172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.11172","pdf_url":"https://arxiv.org/pdf/2305.11172","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.11172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100396039","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0002-5397-9115"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Peng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374850","display_name":"Shijie Wang","orcid":"https://orcid.org/0000-0002-7990-4883"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shijie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100612233","display_name":"Junyang Lin","orcid":"https://orcid.org/0000-0001-9931-383X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Junyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101014470","display_name":"Shuai Bai","orcid":"https://orcid.org/0000-0002-6896-8590"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Shuai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102545093","display_name":"Xiaohuan Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Xiaohuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057864403","display_name":"Jingren Zhou","orcid":"https://orcid.org/0000-0002-4220-2634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jingren","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037191476","display_name":"Xinggang Wang","orcid":"https://orcid.org/0000-0001-6732-7823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xinggang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102025315","display_name":"Chang Zhou","orcid":"https://orcid.org/0000-0001-9241-702X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Chang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100396039"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":42,"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":0.9900000095367432,"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":0.9900000095367432,"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/T11309","display_name":"Music and Audio Processing","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9581999778747559,"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/modalities","display_name":"Modalities","score":0.8674888610839844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8132925629615784},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.7265661954879761},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5667378306388855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5011458396911621},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49410250782966614},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.48241791129112244},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46615704894065857},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43440577387809753},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.42961376905441284},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41979196667671204},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35982492566108704},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09461528062820435}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.8674888610839844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132925629615784},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.7265661954879761},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5667378306388855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5011458396911621},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49410250782966614},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.48241791129112244},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46615704894065857},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43440577387809753},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.42961376905441284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41979196667671204},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35982492566108704},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09461528062820435},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.11172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.11172","pdf_url":"https://arxiv.org/pdf/2305.11172","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2305.11172","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.11172","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.11172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.11172","pdf_url":"https://arxiv.org/pdf/2305.11172","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,79],"explore":[4],"a":[5,10,20,138],"scalable":[6],"way":[7],"for":[8,56,131],"building":[9],"general":[11],"representation":[12],"model":[13,23,130],"toward":[14],"unlimited":[15,121],"modalities.":[16,39,122],"We":[17],"release":[18],"ONE-PEACE,":[19,78],"highly":[21],"extensible":[22],"with":[24],"4B":[25],"parameters":[26],"that":[27],"can":[28],"seamlessly":[29],"align":[30,93],"and":[31,37,50,66,88,100,111,143,170],"integrate":[32],"representations":[33],"across":[34],"vision,":[35],"audio,":[36],"language":[38,128],"The":[40],"architecture":[41,110],"of":[42,60,97,141],"ONE-PEACE":[43,114,133],"comprises":[44],"modality":[45,51],"adapters,":[46],"shared":[47],"self-attention":[48,74],"layers,":[49],"FFNs.":[52],"This":[53],"design":[54],"allows":[55],"the":[57,94,108,116],"easy":[58],"extension":[59],"new":[61],"modalities":[62,99,105],"by":[63],"adding":[64],"adapters":[65],"FFNs,":[67],"while":[68],"also":[69],"enabling":[70],"multi-modal":[71,144],"fusion":[72],"through":[73],"layers.":[75],"To":[76],"pretrain":[77],"develop":[80],"two":[81],"modality-agnostic":[82],"pretraining":[83,112],"tasks,":[84,113,145],"cross-modal":[85],"aligning":[86],"contrast":[87],"intra-modal":[89],"denoising":[90],"contrast,":[91],"which":[92],"semantic":[95,150],"space":[96],"different":[98],"capture":[101],"fine-grained":[102],"details":[103],"within":[104],"concurrently.":[106],"With":[107],"scaling-friendly":[109],"has":[115],"potential":[117],"to":[118,120],"expand":[119],"Without":[123],"using":[124],"any":[125],"vision":[126],"or":[127],"pretrained":[129],"initialization,":[132],"achieves":[134],"leading":[135],"results":[136],"on":[137],"wide":[139],"range":[140],"uni-modal":[142],"including":[146],"image":[147],"classification":[148,158],"(ImageNet),":[149],"segmentation":[151],"(ADE20K),":[152],"audio-text":[153],"retrieval":[154,167],"(AudioCaps,":[155],"Clotho),":[156],"audio":[157,162],"(ESC-50,":[159],"FSD50K,":[160],"VGGSound),":[161],"question":[163],"answering":[164],"(AVQA),":[165],"image-text":[166],"(MSCOCO,":[168],"Flickr30K),":[169],"visual":[171],"grounding":[172],"(RefCOCO/+/g).":[173],"Code":[174],"is":[175],"available":[176],"at":[177],"https://github.com/OFA-Sys/ONE-PEACE.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
