{"id":"https://openalex.org/W4403796089","doi":"https://doi.org/10.48550/arxiv.2409.17692","title":"MIO: A Foundation Model on Multimodal Tokens","display_name":"MIO: A Foundation Model on Multimodal Tokens","publication_year":2024,"publication_date":"2024-09-26","ids":{"openalex":"https://openalex.org/W4403796089","doi":"https://doi.org/10.48550/arxiv.2409.17692"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.17692","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.17692","pdf_url":"https://arxiv.org/pdf/2409.17692","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.17692","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100776737","display_name":"Zekun Wang","orcid":"https://orcid.org/0000-0001-5175-4118"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Zekun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhu, King","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, King","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113258487","display_name":"Chunpu Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Chunpu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074508950","display_name":"Wangchunshu Zhou","orcid":"https://orcid.org/0000-0003-4668-3348"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Wangchunshu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101622327","display_name":"Jiaheng Liu","orcid":"https://orcid.org/0000-0001-7861-9995"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiaheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011471451","display_name":"Yibo Zhang","orcid":"https://orcid.org/0009-0006-4169-3837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yibo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047840452","display_name":"Jiashuo Wang","orcid":"https://orcid.org/0009-0006-9116-3287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiashuo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057319842","display_name":"Ning Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Ning","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436442","display_name":"Siyu Li","orcid":"https://orcid.org/0009-0007-2961-8655"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Siyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023694591","display_name":"Yizhi Li","orcid":"https://orcid.org/0000-0002-4864-2593"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yizhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092998429","display_name":"Haoran Que","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Que, Haoran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101589393","display_name":"Zhaoxiang Zhang","orcid":"https://orcid.org/0000-0002-1469-1469"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhaoxiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020022791","display_name":"Yuanxing Zhang","orcid":"https://orcid.org/0000-0003-1460-8124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yuanxing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326077","display_name":"Ge Zhang","orcid":"https://orcid.org/0000-0003-0704-0657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ge","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100665809","display_name":"Ke Xu","orcid":"https://orcid.org/0000-0001-8669-3909"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Ke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075420800","display_name":"Jie Fu","orcid":"https://orcid.org/0000-0002-5489-2732"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Jie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083410012","display_name":"Wenhao Huang","orcid":"https://orcid.org/0000-0002-0036-6278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Wenhao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":17,"corresponding_author_ids":["https://openalex.org/A5100776737"],"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/T12031","display_name":"Speech and dialogue systems","score":0.9757999777793884,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9757999777793884,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9480999708175659,"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"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9124000072479248,"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/foundation","display_name":"Foundation (evidence)","score":0.7934339046478271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4888884127140045},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.18521538376808167},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.06577074527740479}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7934339046478271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4888884127140045},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.18521538376808167},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.06577074527740479}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.17692","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.17692","pdf_url":"https://arxiv.org/pdf/2409.17692","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.17692","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.17692","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:2409.17692","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.17692","pdf_url":"https://arxiv.org/pdf/2409.17692","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2358060160","https://openalex.org/W2035483685"],"abstract_inverted_index":{"In":[0],"this":[1,104],"paper,":[2],"we":[3,106],"introduce":[4],"MIO,":[5,108],"a":[6,113,127],"novel":[7],"foundation":[8],"model":[9,172],"built":[10],"on":[11,112,145],"multimodal":[12,38,99,123],"tokens,":[13],"capable":[14],"of":[15,32,64,71,98,115],"understanding":[16,58],"and":[17,22,37,59,81,86,92,140,149,160,174],"generating":[18],"speech,":[19,85],"text,":[20],"images,":[21,84],"videos":[23],"in":[24,45,161],"an":[25],"end-to-end,":[26],"autoregressive":[27],"manner.":[28],"While":[29],"the":[30,62,68,96],"emergence":[31],"large":[33,39],"language":[34,40],"models":[35,41],"(LLMs)":[36],"(MM-LLMs)":[42],"propels":[43],"advancements":[44],"artificial":[46],"general":[47],"intelligence":[48],"through":[49],"their":[50],"versatile":[51],"capabilities,":[52],"they":[53],"still":[54],"lack":[55],"true":[56],"any-to-any":[57,72,171,186],"generation.":[60],"Recently,":[61],"release":[63],"GPT-4o":[65],"has":[66],"showcased":[67],"remarkable":[69],"potential":[70],"LLMs":[73],"for":[74],"complex":[75],"real-world":[76],"tasks,":[77],"enabling":[78],"omnidirectional":[79],"input":[80],"output":[82],"across":[83,118],"text.":[87],"However,":[88],"it":[89],"is":[90,110],"closed-source":[91],"does":[93],"not":[94],"support":[95],"generation":[97],"interleaved":[100,135,190],"sequences.":[101],"To":[102],"address":[103],"gap,":[105],"present":[107],"which":[109],"trained":[111],"mixture":[114],"discrete":[116],"tokens":[117],"four":[119],"modalities":[120],"using":[121],"causal":[122],"modeling.":[124],"MIO":[125,157,179],"undergoes":[126],"four-stage":[128],"training":[129],"process:":[130],"(1)":[131],"alignment":[132],"pre-training,":[133,136,139],"(2)":[134],"(3)":[137],"speech-enhanced":[138],"(4)":[141],"comprehensive":[142],"supervised":[143],"fine-tuning":[144],"diverse":[146],"textual,":[147],"visual,":[148],"speech":[150],"tasks.":[151],"Our":[152],"experimental":[153],"results":[154],"indicate":[155],"that":[156],"exhibits":[158],"competitive,":[159],"some":[162],"cases":[163],"superior,":[164],"performance":[165],"compared":[166],"to":[167,184],"previous":[168],"dual-modal":[169],"baselines,":[170,173],"even":[175],"modality-specific":[176],"baselines.":[177],"Moreover,":[178],"demonstrates":[180],"advanced":[181],"capabilities":[182],"inherent":[183],"its":[185],"feature,":[187],"such":[188],"as":[189],"video-text":[191],"generation,":[192,197],"chain-of-visual-thought":[193],"reasoning,":[194],"visual":[195],"guideline":[196],"instructional":[198],"image":[199],"editing,":[200],"etc.":[201]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}
