{"id":"https://openalex.org/W4403799526","doi":"https://doi.org/10.48550/arxiv.2409.18869","title":"Emu3: Next-Token Prediction is All You Need","display_name":"Emu3: Next-Token Prediction is All You Need","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4403799526","doi":"https://doi.org/10.48550/arxiv.2409.18869"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.18869","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.18869","pdf_url":"https://arxiv.org/pdf/2409.18869","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":"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/2409.18869","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100653846","display_name":"Xinlong Wang","orcid":"https://orcid.org/0000-0002-8137-1692"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Xinlong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780271","display_name":"Xiaosong Zhang","orcid":"https://orcid.org/0000-0002-9430-3525"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaosong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029541865","display_name":"Zhengxiong Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Zhengxiong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101648820","display_name":"Quan Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Quan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052226444","display_name":"Yufeng Cui","orcid":"https://orcid.org/0000-0002-0031-7871"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Yufeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101465710","display_name":"Jinsheng Wang","orcid":"https://orcid.org/0000-0003-2830-8755"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jinsheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403414","display_name":"Fan Zhang","orcid":"https://orcid.org/0000-0001-9017-5864"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Fan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038675825","display_name":"Yueze Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yueze","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332586","display_name":"Zhen Li","orcid":"https://orcid.org/0000-0002-2233-9465"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067981474","display_name":"Qiying Yu","orcid":"https://orcid.org/0009-0008-8245-3914"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Qiying","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101036525","display_name":"Yingli Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yingli","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001005409","display_name":"Yulong Ao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ao, Yulong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065478732","display_name":"Xuhong Min","orcid":"https://orcid.org/0000-0001-5312-0274"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min, Xuebin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455282","display_name":"Tao Li","orcid":"https://orcid.org/0000-0002-1448-3619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Tao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101234400","display_name":"Boya Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Boya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024012132","display_name":"Bo Zhao","orcid":"https://orcid.org/0000-0002-6406-3911"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Bo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385142","display_name":"Bowen Zhang","orcid":"https://orcid.org/0000-0002-4971-4878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Bowen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017706182","display_name":"Liangdong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Liangdong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625155","display_name":"Liu Guang","orcid":"https://orcid.org/0000-0002-9958-6077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Guang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003073852","display_name":"Zhini He","orcid":"https://orcid.org/0000-0002-9185-5500"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Zheqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103133745","display_name":"Xi Yang","orcid":"https://orcid.org/0000-0003-2981-3972"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442542","display_name":"Jingjing Liu","orcid":"https://orcid.org/0009-0002-6277-5816"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jingjing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103510896","display_name":"Yonghua Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Yonghua","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058066577","display_name":"Tiejun Huang","orcid":"https://orcid.org/0000-0002-4234-6099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Tiejun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110942112","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0009-0005-7313-0855"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhongyuan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":25,"corresponding_author_ids":["https://openalex.org/A5100653846"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T13759","display_name":"Medical Imaging and Pathology Studies","score":0.5516999959945679,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T13759","display_name":"Medical Imaging and Pathology Studies","score":0.5516999959945679,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7984929084777832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.553783118724823},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.30654793977737427}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7984929084777832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.553783118724823},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.30654793977737427}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.18869","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.18869","pdf_url":"https://arxiv.org/pdf/2409.18869","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.18869","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.18869","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":"pmh:oai:arXiv.org:2409.18869","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.18869","pdf_url":"https://arxiv.org/pdf/2409.18869","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","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/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700"],"abstract_inverted_index":{"While":[0],"next-token":[1,54,152],"prediction":[2,153],"is":[3,109,154],"considered":[4],"a":[5,44,63,68,74,122,134,155],"promising":[6,156],"path":[7,157],"towards":[8,158],"artificial":[9],"general":[10,160],"intelligence,":[11],"it":[12],"has":[13],"struggled":[14],"to":[15,171],"excel":[16],"in":[17,85,121,175],"multimodal":[18,49,77,128,161],"tasks,":[19,90],"which":[20],"are":[21],"still":[22],"dominated":[23],"by":[24,131],"diffusion":[25,104],"models":[26,50,84,93,170],"(e.g.,":[27,33],"Stable":[28],"Diffusion)":[29],"and":[30,60,88,97,146,169],"compositional":[31,106],"approaches":[32],"CLIP":[34],"combined":[35],"with":[36,53],"LLMs).":[37],"In":[38],"this":[39,176],"paper,":[40],"we":[41,66],"introduce":[42],"Emu3,":[43],"new":[45],"suite":[46],"of":[47,76,112],"state-of-the-art":[48],"trained":[51],"solely":[52],"prediction.":[55],"By":[56],"tokenizing":[57],"images,":[58],"text,":[59],"videos":[61],"into":[62],"discrete":[64],"space,":[65],"train":[67],"single":[69],"transformer":[70],"from":[71],"scratch":[72],"on":[73,133],"mixture":[75],"sequences.":[78],"Emu3":[79,108],"outperforms":[80],"several":[81],"well-established":[82],"task-specific":[83],"both":[86,143],"generation":[87],"perception":[89],"surpassing":[91],"flagship":[92],"such":[94],"as":[95],"SDXL":[96],"LLaVA-1.6,":[98],"while":[99],"eliminating":[100],"the":[101,118],"need":[102],"for":[103,141],"or":[105],"architectures.":[107],"also":[110],"capable":[111],"generating":[113],"high-fidelity":[114],"video":[115,123],"via":[116],"predicting":[117],"next":[119],"token":[120],"sequence.":[124],"We":[125,165],"simplify":[126],"complex":[127],"model":[129],"designs":[130],"converging":[132],"singular":[135],"focus:":[136],"tokens,":[137],"unlocking":[138],"great":[139],"potential":[140],"scaling":[142],"during":[144],"training":[145],"inference.":[147],"Our":[148],"results":[149],"demonstrate":[150],"that":[151],"building":[159],"intelligence":[162],"beyond":[163],"language.":[164],"open-source":[166],"key":[167],"techniques":[168],"support":[172],"further":[173],"research":[174],"direction.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}
