{"id":"https://openalex.org/W4387636048","doi":"https://doi.org/10.48550/arxiv.2310.08576","title":"Learning to Act from Actionless Videos through Dense Correspondences","display_name":"Learning to Act from Actionless Videos through Dense Correspondences","publication_year":2023,"publication_date":"2023-10-12","ids":{"openalex":"https://openalex.org/W4387636048","doi":"https://doi.org/10.48550/arxiv.2310.08576"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.08576","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08576","pdf_url":"https://arxiv.org/pdf/2310.08576","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.08576","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114090777","display_name":"Po-Chen Ko","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ko, Po-Chen","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102358408","display_name":"Jiayuan Mao","orcid":"https://orcid.org/0000-0003-4798-3748","observed_orcids":["https://orcid.org/0000-0003-4798-3748"]},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mao, Jiayuan","raw_affiliation_strings":["MIT CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041777043","display_name":"Yilun Du","orcid":"https://orcid.org/0000-0001-6792-5946","observed_orcids":["https://orcid.org/0000-0001-6792-5946"]},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Du, Yilun","raw_affiliation_strings":["MIT CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sun, Shao-Hua","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sun, Shao-Hua","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071093940","display_name":"Joshua B. Tenenbaum","orcid":"https://orcid.org/0000-0002-1925-2035","observed_orcids":["https://orcid.org/0000-0002-1925-2035","https://orcid.org/0000-0002-0138-163X"]},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tenenbaum, Joshua B.","raw_affiliation_strings":["MIT BCS , CBMM , CSAIL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT BCS , CBMM , CSAIL","institution_ids":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":119,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6015999913215637,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6015999913215637,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.388700008392334,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.004000000189989805,"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/dense-correspondence","display_name":"dense correspondence","score":0.8270000219345093},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.9649999737739563},{"id":"https://openalex.org/keywords/video-modeling","display_name":"video modeling","score":0.6570000052452087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8263883590698242},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.6860700249671936},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6680447459220886},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6193642616271973},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5905929207801819},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5851548910140991},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5549138188362122},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5533487796783447},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5503300428390503},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5146349668502808},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4517953395843506},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.08576","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08576","pdf_url":"https://arxiv.org/pdf/2310.08576","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.08576","doi":"https://doi.org/10.48550/arxiv.2310.08576","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.08576","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:2310.08576","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.08576","pdf_url":"https://arxiv.org/pdf/2310.08576","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387636048.pdf","grobid_xml":"https://content.openalex.org/works/W4387636048.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2776202271","https://openalex.org/W4322716943","https://openalex.org/W4324128075","https://openalex.org/W4390874575","https://openalex.org/W7133189841","https://openalex.org/W7133231380"],"related_works":["https://openalex.org/W4416552080","https://openalex.org/W4417011628","https://openalex.org/W4415083219","https://openalex.org/W4392120743","https://openalex.org/W4383109144","https://openalex.org/W4416189451","https://openalex.org/W7162685497","https://openalex.org/W4417086207","https://openalex.org/W7111212896","https://openalex.org/W4415311614"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,133],"present":[4],"an":[5,84,135],"approach":[6,75,122],"to":[7,81,83,99,112],"construct":[8],"a":[9,38,51,153],"video-based":[10],"robot":[11,56,63],"policy":[12,102,147],"capable":[13],"of":[14,89,120,145],"reliably":[15],"executing":[16,64],"diverse":[17],"tasks":[18],"across":[19],"different":[20],"robots":[21],"and":[22,45,48,66,108,129],"environments":[23],"from":[24],"few":[25],"video":[26,140],"demonstrations":[27],"without":[28,86],"using":[29],"any":[30,90],"action":[31,46,80,92],"annotations.":[32],"Our":[33],"method":[34],"leverages":[35],"images":[36],"as":[37,50],"task-agnostic":[39],"representation,":[40],"encoding":[41],"both":[42],"the":[43,78,87,101,118,143],"state":[44],"information,":[47],"text":[49],"general":[52],"representation":[53],"for":[54,138],"specifying":[55],"goals.":[57],"By":[58],"synthesizing":[59],"videos":[60,107],"that":[61],"``hallucinate''":[62],"actions":[65],"in":[67,123],"combination":[68],"with":[69,149],"dense":[70],"correspondences":[71],"between":[72],"frames,":[73],"our":[74,121],"can":[76],"infer":[77],"closed-formed":[79],"execute":[82],"environment":[85],"need":[88],"explicit":[91],"labels.":[93],"This":[94],"unique":[95],"capability":[96],"allows":[97],"us":[98],"train":[100],"solely":[103],"based":[104],"on":[105,126],"RGB":[106],"deploy":[109],"learned":[110],"policies":[111,125],"various":[113],"robotic":[114],"tasks.":[115,131],"We":[116],"demonstrate":[117],"efficacy":[119],"learning":[124],"table-top":[127],"manipulation":[128],"navigation":[130],"Additionally,":[132],"contribute":[134],"open-source":[136],"framework":[137],"efficient":[139],"modeling,":[141],"enabling":[142],"training":[144],"high-fidelity":[146],"models":[148],"four":[150],"GPUs":[151],"within":[152],"single":[154],"day.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":47},{"year":2025,"cited_by_count":51},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-10-14T00:00:00"}