{"id":"https://openalex.org/W4407760071","doi":"https://doi.org/10.48550/arxiv.2502.13142","title":"Pre-training Auto-regressive Robotic Models with 4D Representations","display_name":"Pre-training Auto-regressive Robotic Models with 4D Representations","publication_year":2025,"publication_date":"2025-02-18","ids":{"openalex":"https://openalex.org/W4407760071","doi":"https://doi.org/10.48550/arxiv.2502.13142"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.13142","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.13142","pdf_url":"https://arxiv.org/pdf/2502.13142","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/2502.13142","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021184639","display_name":"Dantong Niu","orcid":"https://orcid.org/0009-0006-7421-5858","observed_orcids":["https://orcid.org/0009-0006-7421-5858"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niu, Dantong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108944952","display_name":"Yuvan Sharma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharma, Yuvan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102522540","display_name":"Haoru Xue","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Haoru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008384649","display_name":"Giscard Biamby","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biamby, Giscard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010262713","display_name":"Junyi Zhang","orcid":"https://orcid.org/0000-0002-2392-1967","observed_orcids":["https://orcid.org/0000-0002-2392-1967"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Junyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ji, Ziteng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Ziteng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533","observed_orcids":["https://orcid.org/0000-0001-5453-8533"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Darrell, Trevor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066997569","display_name":"Roei Herzig","orcid":"https://orcid.org/0000-0002-5451-6059","observed_orcids":["https://orcid.org/0000-0002-5451-6059"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herzig, Roei","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":null,"has_fulltext":true,"cited_by_count":24,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.638700008392334,"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":0.638700008392334,"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":0.3425000011920929,"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":0.008100000210106373,"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-models","display_name":"foundation models","score":0.5839999914169312},{"id":"https://openalex.org/keywords/3d-point-tracking","display_name":"3D point tracking","score":0.9010000228881836},{"id":"https://openalex.org/keywords/monocular-depth-estimation","display_name":"monocular depth estimation","score":0.9819999933242798},{"id":"https://openalex.org/keywords/robot-control","display_name":"robot control","score":0.722000002861023},{"id":"https://openalex.org/keywords/autoregressive-models","display_name":"autoregressive models","score":0.4749999940395355}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6610752940177917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5107934474945068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49997758865356445},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4473094046115875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36923182010650635},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.23168227076530457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18861904740333557},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.14219722151756287},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.05786624550819397}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.13142","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.13142","pdf_url":"https://arxiv.org/pdf/2502.13142","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.2502.13142","doi":"https://doi.org/10.48550/arxiv.2502.13142","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.13142","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:2502.13142","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.13142","pdf_url":"https://arxiv.org/pdf/2502.13142","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407760071.pdf","grobid_xml":"https://content.openalex.org/works/W4407760071.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W3168867926","https://openalex.org/W3198002980","https://openalex.org/W3209532394","https://openalex.org/W4226167593","https://openalex.org/W4296406182","https://openalex.org/W4312891162","https://openalex.org/W4320002570","https://openalex.org/W4385430679","https://openalex.org/W4385473486","https://openalex.org/W4388512477","https://openalex.org/W4392886475","https://openalex.org/W4398192846","https://openalex.org/W4399695759","https://openalex.org/W4399795511","https://openalex.org/W4400222258","https://openalex.org/W4403575186","https://openalex.org/W4403888324","https://openalex.org/W4403928958","https://openalex.org/W4405434146","https://openalex.org/W4413145609"],"related_works":["https://openalex.org/W7077911548","https://openalex.org/W4221159977","https://openalex.org/W4404342133","https://openalex.org/W6948352277","https://openalex.org/W7163335773","https://openalex.org/W7160173286","https://openalex.org/W4327673655","https://openalex.org/W4381253614","https://openalex.org/W4402354028","https://openalex.org/W7127099986"],"abstract_inverted_index":{"Foundation":[0],"models":[1],"pre-trained":[2,78],"on":[3,84,156],"massive":[4],"unlabeled":[5],"datasets":[6],"have":[7,28],"revolutionized":[8],"natural":[9],"language":[10],"and":[11,117,152,162],"computer":[12],"vision,":[13],"exhibiting":[14],"remarkable":[15],"generalization":[16],"capabilities,":[17],"thus":[18],"highlighting":[19],"the":[20,37,44,51,115],"importance":[21],"of":[22,46],"pre-training.":[23],"Yet,":[24],"efforts":[25],"in":[26],"robotics":[27,151],"struggled":[29],"to":[30,74,122,134,150],"achieve":[31],"similar":[32],"success,":[33],"limited":[34],"by":[35,93],"either":[36],"need":[38],"for":[39],"costly":[40],"robotic":[41,79,136],"annotations":[42],"or":[43],"lack":[45],"representations":[47,89,96,108,120],"that":[48,64,141],"effectively":[49],"model":[50],"physical":[52],"world.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,82],"introduce":[58],"ARM4R,":[59],"an":[60],"Auto-regressive":[61],"Robotic":[62],"Model":[63],"leverages":[65],"low-level":[66,135],"4D":[67,107],"Representations":[68],"learned":[69],"from":[70,90,130,146],"human":[71,131,147],"video":[72,132,148],"data":[73,133,149],"yield":[75],"a":[76,110,123],"better":[77],"model.":[80],"Specifically,":[81],"focus":[83],"utilizing":[85],"3D":[86,98],"point":[87],"tracking":[88],"videos":[91],"derived":[92],"lifting":[94],"2D":[95],"into":[97],"space":[99],"via":[100],"monocular":[101],"depth":[102],"estimation":[103],"across":[104,158],"time.":[105],"These":[106],"maintain":[109],"shared":[111],"geometric":[112],"structure":[113],"between":[114],"points":[116],"robot":[118,160],"state":[119],"up":[121],"linear":[124],"transformation,":[125],"enabling":[126],"efficient":[127],"transfer":[128,144],"learning":[129],"control.":[137],"Our":[138],"experiments":[139],"show":[140],"ARM4R":[142],"can":[143],"efficiently":[145],"consistently":[153],"improves":[154],"performance":[155],"tasks":[157],"various":[159],"environments":[161],"configurations.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":10}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-02-20T00:00:00"}