{"id":"https://openalex.org/W7129045487","doi":"https://doi.org/10.36227/techrxiv.177126525.54038135/v1","title":"From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data","display_name":"From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129045487","doi":"https://doi.org/10.36227/techrxiv.177126525.54038135/v1"},"language":"en","primary_location":{"id":"doi:10.36227/techrxiv.177126525.54038135/v1","doi":"https://doi.org/10.36227/techrxiv.177126525.54038135/v1","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.177126525.54038135/v1","pdf_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.177126525.54038135","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.177126525.54038135","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125516826","display_name":"Zhiyuan Feng","orcid":"https://orcid.org/0009-0002-4610-422X","observed_orcids":["https://orcid.org/0009-0002-4610-422X"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Feng","raw_affiliation_strings":["Microsoft Research Asia","Tsinghua University"],"raw_orcid":"https://orcid.org/0009-0002-4610-422X","affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107503613","display_name":"Qixiu Li","orcid":"https://orcid.org/0009-0002-4866-6920","observed_orcids":["https://orcid.org/0009-0002-4866-6920"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qixiu Li","raw_affiliation_strings":["Microsoft Research Asia","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075528828","display_name":"Huizhi Liang","orcid":"https://orcid.org/0000-0003-4408-4528","observed_orcids":["https://orcid.org/0000-0003-4408-4528"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huizhi Liang","raw_affiliation_strings":["Microsoft Research Asia","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113231897","display_name":"Rushuai Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Rushuai Yang","raw_affiliation_strings":["HKUST","Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010359709","display_name":"Yichao Shen","orcid":"https://orcid.org/0000-0002-5257-6808","observed_orcids":["https://orcid.org/0000-0002-5257-6808"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichao Shen","raw_affiliation_strings":["Microsoft Research Asia","Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126171162","display_name":"Zhiying Du","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiying Du","raw_affiliation_strings":["Fudan University","Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683814","display_name":"Zhaowei Zhang","orcid":"https://orcid.org/0000-0002-3639-8466","observed_orcids":["https://orcid.org/0000-0002-3639-8466"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaowei Zhang","raw_affiliation_strings":["Microsoft Research Asia","Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045624501","display_name":"Yu Deng","orcid":"https://orcid.org/0000-0001-7241-8519","observed_orcids":["https://orcid.org/0000-0001-7241-8519"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Deng","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101858782","display_name":"Li Zhao","orcid":"https://orcid.org/0000-0001-6918-0204","observed_orcids":["https://orcid.org/0000-0001-6918-0204"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhao","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143911445","display_name":"Hao Zhao","orcid":"https://orcid.org/0000-0001-7903-581X","observed_orcids":["https://orcid.org/0000-0001-7903-581X"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103979188","display_name":"Zongqing Lu","orcid":"https://orcid.org/0000-0002-1191-9069","observed_orcids":["https://orcid.org/0000-0002-1191-9069","https://orcid.org/0000-0003-3967-2704"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongqing Lu","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054505204","display_name":"Oier Mees","orcid":"https://orcid.org/0000-0001-6020-9744","observed_orcids":["https://orcid.org/0000-0001-6020-9744"]},"institutions":[{"id":"https://openalex.org/I4210139986","display_name":"Microsoft (Switzerland)","ror":"https://ror.org/03zryq964","country_code":"CH","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210139986"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Oier Mees","raw_affiliation_strings":["Microsoft Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Zurich","institution_ids":["https://openalex.org/I4210139986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021908609","display_name":"Marc Pollefeys","orcid":"https://orcid.org/0000-0003-2448-2318","observed_orcids":["https://orcid.org/0000-0003-2448-2318"]},"institutions":[{"id":"https://openalex.org/I4210139986","display_name":"Microsoft (Switzerland)","ror":"https://ror.org/03zryq964","country_code":"CH","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210139986"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marc Pollefeys","raw_affiliation_strings":["Microsoft Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Zurich","institution_ids":["https://openalex.org/I4210139986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076804411","display_name":"Jiaolong Yang","orcid":"https://orcid.org/0000-0002-7314-6567","observed_orcids":["https://orcid.org/0000-0002-7314-6567"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaolong Yang","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032079003","display_name":"B. Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baining Guo","raw_affiliation_strings":["Microsoft Research Asia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5045624501","https://openalex.org/A5076804411"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"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":0.9897000193595886,"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":0.9897000193595886,"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":0.0071000000461936,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/vision-language-action-models","display_name":"vision-language-action models","score":0.9200000166893005},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.9760000109672546},{"id":"https://openalex.org/keywords/embodied-control","display_name":"embodied control","score":0.9359999895095825},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.8240000009536743},{"id":"https://openalex.org/keywords/evaluation-protocol","display_name":"evaluation protocol","score":0.5059999823570251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777899980545044},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.597000002861023},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5942999720573425},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5893999934196472},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.588699996471405},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5695000290870667},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5692999958992004},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5250999927520752},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4936999976634979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4779999852180481},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3788999915122986},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.257099986076355}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.36227/techrxiv.177126525.54038135/v1","doi":"https://doi.org/10.36227/techrxiv.177126525.54038135/v1","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.177126525.54038135/v1","pdf_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.177126525.54038135","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:arXiv.org:2606.00054","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.00054","pdf_url":"https://arxiv.org/pdf/2606.00054","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.2606.00054","doi":"https://doi.org/10.48550/arxiv.2606.00054","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00054","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:10.36227/techrxiv.177126525.54038135/v1","doi":"https://doi.org/10.36227/techrxiv.177126525.54038135/v1","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.177126525.54038135/v1","pdf_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.177126525.54038135","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7129045487.pdf","grobid_xml":"https://content.openalex.org/works/W7129045487.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W4226167593","https://openalex.org/W4306884028","https://openalex.org/W4366208220","https://openalex.org/W4389115686","https://openalex.org/W4392872989","https://openalex.org/W4401415042","https://openalex.org/W4403344670","https://openalex.org/W4403345601","https://openalex.org/W4403884728","https://openalex.org/W4404350203","https://openalex.org/W4406191642","https://openalex.org/W4409015946","https://openalex.org/W4414079054","https://openalex.org/W4414901575","https://openalex.org/W4414921730","https://openalex.org/W4416189451","https://openalex.org/W4417029006","https://openalex.org/W4417299960","https://openalex.org/W4417327307","https://openalex.org/W4417453644","https://openalex.org/W4417492598","https://openalex.org/W6929480010","https://openalex.org/W6947593395","https://openalex.org/W7083673192","https://openalex.org/W7106217043","https://openalex.org/W7116084174","https://openalex.org/W7117736774","https://openalex.org/W7138414178"],"related_works":["https://openalex.org/W6947593395","https://openalex.org/W4416222632","https://openalex.org/W7127377703","https://openalex.org/W7166882999","https://openalex.org/W4417327307","https://openalex.org/W7163027319","https://openalex.org/W7083709417","https://openalex.org/W4403575186","https://openalex.org/W7165133119","https://openalex.org/W4417492598"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,71,150],"generalizable":[3],"embodied":[4],"control":[5],"has":[6],"been":[7],"driven":[8],"by":[9,40],"large-scale":[10],"pretraining":[11],"of":[12,24,64,81,191],"Vision\u2013Language\u2013Action":[13],"(VLA)":[14],"models.":[15,92],"However,":[16],"most":[17],"existing":[18,95],"approaches":[19,96],"rely":[20],"on":[21,101],"large":[22],"collections":[23],"robot":[25],"demonstrations,":[26],"which":[27],"are":[28,42,85],"costly":[29],"to":[30,35],"obtain":[31],"and":[32,44,51,60,131,167,170,180,193],"tightly":[33],"coupled":[34],"specific":[36],"embodiments.":[37],"Human":[38],"videos,":[39],"contrast,":[41],"abundant":[43],"capture":[45],"rich":[46],"interactions,":[47],"providing":[48],"diverse":[49],"semantic":[50],"physical":[52],"cues":[53],"for":[54,90],"real-world":[55,177],"manipulation.":[56],"Yet,":[57],"embodiment":[58,166],"differences":[59],"the":[61,102],"frequent":[62],"absence":[63],"task-aligned":[65],"annotations":[66],"make":[67],"their":[68],"direct":[69],"use":[70],"VLA":[72,91],"models":[73,118],"challenging.":[74],"This":[75],"survey":[76],"provides":[77],"a":[78],"unified":[79],"view":[80],"how":[82],"human":[83],"videos":[84,155],"transformed":[86],"into":[87,97,156,162],"effective":[88],"knowledge":[89],"We":[93],"categorize":[94],"four":[98],"classes":[99],"based":[100],"action-related":[103],"information":[104],"they":[105],"derive:":[106],"(i)":[107],"latent":[108],"action":[109],"representations":[110],"that":[111,119,127,136,174],"encode":[112],"inter-frame":[113],"changes;":[114],"(ii)":[115],"predictive":[116],"world":[117],"forecast":[120],"future":[121,185],"frames;":[122],"(iii)":[123],"explicit":[124,133],"2D":[125],"supervision":[126,161],"extracts":[128],"image-plane":[129],"cues;":[130],"(iv)":[132],"3D":[134],"reconstruction":[135],"recovers":[137],"geometry":[138],"or":[139],"motion.":[140],"Beyond":[141],"this":[142,151],"taxonomy,":[143],"we":[144],"highlight":[145],"three":[146],"key":[147],"open":[148],"challenges":[149],"area:":[152],"structuring":[153],"unstructured":[154],"training-ready":[157],"episodes,":[158],"grounding":[159],"video-derived":[160],"robot-executable":[163],"actions":[164],"under":[165],"viewpoint":[168],"heterogeneity,":[169],"designing":[171],"evaluation":[172],"protocols":[173],"better":[175],"predict":[176],"deployment":[178],"performance":[179],"transfer":[181],"efficiency,":[182],"thereby":[183],"informing":[184],"research":[186],"directions.":[187],"A":[188],"curated":[189],"list":[190],"papers":[192],"resources":[194],"is":[195],"available":[196],"at":[197],"https://github.com/AaronFengZY/HumanCentricToVLA-Survey":[198],".":[199]},"counts_by_year":[{"year":2026,"cited_by_count":7}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-17T00:00:00"}
