{"id":"https://openalex.org/W4406273434","doi":"https://doi.org/10.1109/iccv51701.2025.01776","title":"An Empirical Study of Autoregressive Pre-Training from Videos","display_name":"An Empirical Study of Autoregressive Pre-Training from Videos","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4406273434","doi":"https://doi.org/10.1109/iccv51701.2025.01776"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.05453","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053765366","display_name":"Jathushan Rajasegaran","orcid":"https://orcid.org/0000-0003-1081-4254"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jathushan Rajasegaran","raw_affiliation_strings":["Meta FAIR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta FAIR","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080355298","display_name":"Ilija Radosavovic","orcid":"https://orcid.org/0009-0004-9200-5980"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ilija Radosavovic","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108488166","display_name":"Rahul Ravishankar","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rahul Ravishankar","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051101769","display_name":"Yossi Gandelsman","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yossi Gandelsman","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036069974","display_name":"Christoph Feichtenhofer","orcid":"https://orcid.org/0000-0001-9756-7238"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christoph Feichtenhofer","raw_affiliation_strings":["Meta FAIR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta FAIR","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594573","display_name":"Jitendra Malik","orcid":"https://orcid.org/0000-0003-3695-1580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jitendra Malik","raw_affiliation_strings":["Meta FAIR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta FAIR","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"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":"19108","last_page":"19118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.33009999990463257,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.33009999990463257,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.842681884765625},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6221726536750793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46790939569473267},{"id":"https://openalex.org/keywords/star-model","display_name":"STAR model","score":0.4481205940246582},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.42526885867118835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4076230525970459},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3311172127723694},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.21913689374923706},{"id":"https://openalex.org/keywords/autoregressive-integrated-moving-average","display_name":"Autoregressive integrated moving average","score":0.21228817105293274},{"id":"https://openalex.org/keywords/time-series","display_name":"Time series","score":0.1614229381084442},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.12922745943069458},{"id":"https://openalex.org/keywords/meteorology","display_name":"Meteorology","score":0.051026105880737305}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.842681884765625},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6221726536750793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46790939569473267},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.4481205940246582},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.42526885867118835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4076230525970459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3311172127723694},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.21913689374923706},{"id":"https://openalex.org/C24338571","wikidata":"https://www.wikidata.org/wiki/Q2566298","display_name":"Autoregressive integrated moving average","level":3,"score":0.21228817105293274},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.1614229381084442},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12922745943069458},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.051026105880737305}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.05453","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.05453","pdf_url":"https://arxiv.org/pdf/2501.05453","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.05453","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.05453","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.05453","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.05453","pdf_url":"https://arxiv.org/pdf/2501.05453","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/W2439807930","https://openalex.org/W2009692134","https://openalex.org/W1972271943","https://openalex.org/W2019155478","https://openalex.org/W2024529895","https://openalex.org/W2168175994","https://openalex.org/W1902630399","https://openalex.org/W2120434453","https://openalex.org/W3120578569","https://openalex.org/W1487412319"],"abstract_inverted_index":{"We":[0,21,56,65],"empirically":[1],"study":[2],"autoregressive":[3,16,94],"pre-training":[4,95],"from":[5],"videos.":[6],"To":[7],"perform":[8],"our":[9,108],"study,":[10],"we":[11,104],"construct":[12],"a":[13,43,72,124],"series":[14],"of":[15,26,46,74],"video":[17,80,109],"models,":[18,121],"called":[19],"Toto.":[20],"treat":[22],"videos":[23,47],"as":[24],"sequences":[25],"visual":[27,54,69],"tokens":[28],"and":[29,48,61,84],"train":[30],"transformer":[31],"models":[32,39,110],"to":[33,97,116],"autoregressively":[34],"predict":[35],"future":[36],"tokens.":[37,55],"Our":[38,86],"are":[40],"pre-trained":[41],"on":[42,71],"diverse":[44],"dataset":[45],"images":[49],"comprising":[50],"over":[51],"1":[52],"trillion":[53],"explore":[57],"different":[58,125],"architectural,":[59],"training,":[60],"inference":[62],"design":[63],"choices.":[64],"evaluate":[66],"the":[67],"learned":[68],"representations":[70],"range":[73],"downstream":[75],"tasks":[76],"including":[77],"image":[78],"recognition,":[79],"classification,":[81],"object":[82],"tracking,":[83],"robotics.":[85],"results":[87,111],"demonstrate":[88],"that,":[89],"despite":[90],"minimal":[91],"inductive":[92],"biases,":[93],"leads":[96],"competitive":[98],"performance":[99],"across":[100],"all":[101],"benchmarks.":[102],"Finally,":[103],"find":[105],"that":[106],"scaling":[107,114],"in":[112,119],"similar":[113],"curves":[115],"those":[117],"seen":[118],"language":[120],"albeit":[122],"with":[123],"rate.":[126],"More":[127],"details":[128],"at":[129],"https://brjathu.github.io/toto/":[130]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}