{"id":"https://openalex.org/W4402354080","doi":"https://doi.org/10.15607/rss.2024.xx.052","title":"Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers","display_name":"Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402354080","doi":"https://doi.org/10.15607/rss.2024.xx.052"},"language":"en","primary_location":{"id":"doi:10.15607/rss.2024.xx.052","doi":"https://doi.org/10.15607/rss.2024.xx.052","is_oa":true,"landing_page_url":"https://doi.org/10.15607/rss.2024.xx.052","pdf_url":"https://doi.org/10.15607/rss.2024.xx.052","source":{"id":"https://openalex.org/S4306420803","display_name":"Robotics: Science and Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics: Science and Systems XX","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.15607/rss.2024.xx.052","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029884559","display_name":"Vidhi Jain","orcid":"https://orcid.org/0009-0000-7960-8542","observed_orcids":["https://orcid.org/0009-0000-7960-8542"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vidhi Jain","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043566305","display_name":"Maria Attarian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria Attarian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Nikhil Joshi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikhil Joshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051147070","display_name":"Ayzaan Wahid","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ayzaan Wahid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080239685","display_name":"Danny Driess","orcid":"https://orcid.org/0000-0002-8258-1659","observed_orcids":["https://orcid.org/0000-0002-8258-1659"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danny Driess","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101445461","display_name":"Quan Vuong","orcid":"https://orcid.org/0009-0009-1829-9614","observed_orcids":["https://orcid.org/0009-0009-1829-9614"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan Vuong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064611781","display_name":"Pannag Sanketi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pannag Sanketi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066544075","display_name":"Pierre Sermanet","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierre Sermanet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090341246","display_name":"Stefan Welker","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Welker","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Christine Chan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christine Chan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078356081","display_name":"Igor Gilitschenski","orcid":"https://orcid.org/0000-0001-6426-365X","observed_orcids":["https://orcid.org/0000-0001-6426-365X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Igor Gilitschenski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041302228","display_name":"Yonatan Bisk","orcid":"https://orcid.org/0000-0002-2111-9081","observed_orcids":["https://orcid.org/0000-0002-2111-9081"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yonatan Bisk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047363556","display_name":"Debidatta Dwibedi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Debidatta Dwibedi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":39.594,"has_fulltext":true,"cited_by_count":75,"citation_normalized_percentile":{"value":0.99881113,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9276999831199646,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9276999831199646,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.07090000063180923,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0006000000284984708,"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/robotic-manipulation","display_name":"robotic manipulation","score":0.6700000166893005},{"id":"https://openalex.org/keywords/cross-attention-transformer","display_name":"cross-attention transformer","score":0.8709999918937683},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.6610000133514404}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7886908054351807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5906832814216614},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5718364119529724},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2619420289993286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.190675288438797},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19009730219841003},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.15607/rss.2024.xx.052","doi":"https://doi.org/10.15607/rss.2024.xx.052","is_oa":true,"landing_page_url":"https://doi.org/10.15607/rss.2024.xx.052","pdf_url":"https://doi.org/10.15607/rss.2024.xx.052","source":{"id":"https://openalex.org/S4306420803","display_name":"Robotics: Science and Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics: Science and Systems XX","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.12943","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.12943","pdf_url":"https://arxiv.org/pdf/2403.12943","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.12943","doi":"https://doi.org/10.48550/arxiv.2403.12943","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.12943","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":"doi:10.15607/rss.2024.xx.052","doi":"https://doi.org/10.15607/rss.2024.xx.052","is_oa":true,"landing_page_url":"https://doi.org/10.15607/rss.2024.xx.052","pdf_url":"https://doi.org/10.15607/rss.2024.xx.052","source":{"id":"https://openalex.org/S4306420803","display_name":"Robotics: Science and Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics: Science and Systems XX","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402354080.pdf","grobid_xml":"https://content.openalex.org/works/W4402354080.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W3089768235","https://openalex.org/W3098810814","https://openalex.org/W4226167593","https://openalex.org/W4322616306","https://openalex.org/W4366999289","https://openalex.org/W4385430679","https://openalex.org/W4385473486","https://openalex.org/W4387764390","https://openalex.org/W4390873312"],"related_works":["https://openalex.org/W4383109144","https://openalex.org/W7111212896","https://openalex.org/W4403788204","https://openalex.org/W7222675174","https://openalex.org/W4417529444","https://openalex.org/W4417011628","https://openalex.org/W4415083219","https://openalex.org/W4415036289","https://openalex.org/W7071907604","https://openalex.org/W3038245394"],"abstract_inverted_index":{"Large-scale":[0],"multi-task":[1],"robotic":[2],"manipulation":[3,60],"systems":[4],"often":[5],"rely":[6],"on":[7,138,170],"text":[8],"to":[9,81,105,124,165,177],"specify":[10],"the":[11,29,38,44,101,107,111,117,126,174,181],"task.":[12],"In":[13],"this":[14],"work,":[15],"we":[16,154],"explore":[17],"whether":[18],"a":[19,33,73,167],"robot":[20,30,66,88,103,129],"can":[21],"learn":[22,82],"by":[23],"observing":[24],"humans.":[25],"To":[26],"do":[27],"so,":[28],"must":[31],"understand":[32],"person's":[34],"intent":[35],"and":[36,46,64,87,100,109,128,141],"perform":[37,110],"inferred":[39],"task":[40,113],"despite":[41],"differences":[42],"in":[43,116,173,180],"embodiments":[45],"environments.":[47],"We":[48,119,135],"introduce":[49],"Vid2Robot,":[50],"an":[51],"end-to-end":[52],"video-conditioned":[53,163],"policy":[54],"that":[55,161],"takes":[56],"human":[57,86,150],"videos":[58],"demonstrating":[59],"tasks":[61],"as":[62,114],"input":[63],"produces":[65],"actions.":[67],"Our":[68],"model":[69],"is":[70],"trained":[71],"with":[72],"large":[74],"dataset":[75],"of":[76,85],"prompt":[77,127,151,175],"video-robot":[78],"trajectory":[79],"pairs":[80],"unified":[83],"representations":[84,131],"actions":[89,108],"from":[90],"videos.":[91,152],"Vid2Robot":[92,137],"uses":[93],"cross-attention":[94],"transformer":[95],"layers":[96],"between":[97],"video":[98,130,176],"features":[99],"current":[102],"state":[104],"produce":[106],"same":[112],"shown":[115],"video.":[118],"use":[120],"auxiliary":[121],"contrastive":[122],"losses":[123],"align":[125],"for":[132],"better":[133],"policies.":[134],"evaluate":[136],"real-world":[139],"robots":[140],"observe":[142],"over":[143,146],"20%":[144],"improvement":[145],"BC-Z":[147],"when":[148],"using":[149],"Further,":[153],"also":[155],"show":[156],"cross-object":[157],"motion":[158,168],"transfer":[159,166],"ability":[160],"enables":[162],"policies":[164],"observed":[169],"one":[171],"object":[172,179],"another":[178],"robot's":[182],"own":[183],"environment.":[184],"Videos":[185],"available":[186],"at":[187],"https://vid2robot.github.io":[188]},"counts_by_year":[{"year":2026,"cited_by_count":35},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":6}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2024-09-10T00:00:00"}
