{"id":"https://openalex.org/W7215048873","doi":"https://doi.org/10.48550/arxiv.2609.40341","title":"Ego4WAM: What Matters When Scaling Egocentric Human Data for Robot Learning?","display_name":"Ego4WAM: What Matters When Scaling Egocentric Human Data for Robot Learning?","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7215048873","doi":"https://doi.org/10.48550/arxiv.2609.40341"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.40341","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.40341","pdf_url":"https://arxiv.org/pdf/2609.40341","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/2609.40341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153927358","display_name":"Zhihao Sun","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Zhihao","raw_affiliation_strings":["Institute of Trustworthy Embodied AI , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5154111168","display_name":"Liu Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Liu","raw_affiliation_strings":["Horizon Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Horizon Robotics","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153787638","display_name":"Xinjiang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Xinjiang","raw_affiliation_strings":["Horizon Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Horizon Robotics","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126779163","display_name":"Haoyi Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Haoyi","raw_affiliation_strings":["Huazhong University of Science & Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science & Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153897614","display_name":"Wei Feng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng, Wei","raw_affiliation_strings":["Horizon Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Horizon Robotics","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153762037","display_name":"Huiqiang Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Huiqiang","raw_affiliation_strings":["Zhejiang University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University of Technology","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153909877","display_name":"Xiaosong Jia","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia, Xiaosong","raw_affiliation_strings":["Institute of Trustworthy Embodied AI , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153934714","display_name":"Zhizhong Su","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Su, Zhizhong","raw_affiliation_strings":["Horizon Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Horizon Robotics","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5154108815","display_name":"Zuxuan Wu","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Zuxuan","raw_affiliation_strings":["Institute of Trustworthy Embodied AI , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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":0.8633000254631042,"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":0.8633000254631042,"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":0.12759999930858612,"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":0.003100000089034438,"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/robot-learning","display_name":"robot learning","score":0.8539999723434448},{"id":"https://openalex.org/keywords/world-action-models","display_name":"world action models","score":0.75},{"id":"https://openalex.org/keywords/data-scaling","display_name":"data scaling","score":0.5820000171661377},{"id":"https://openalex.org/keywords/task-variety","display_name":"task variety","score":0.8610000014305115},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.9929999709129333},{"id":"https://openalex.org/keywords/human-demonstrations","display_name":"human demonstrations","score":0.5580000281333923}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6811000108718872},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6646000146865845},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6586999893188477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6585999727249146},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.613099992275238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5724999904632568},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4876999855041504},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4357999861240387},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.42969998717308044},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3885999917984009},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C91682802","wikidata":"https://www.wikidata.org/wiki/Q620538","display_name":"Multidimensional scaling","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30730000138282776},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2734000086784363},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2700999975204468}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.40341","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.40341","pdf_url":"https://arxiv.org/pdf/2609.40341","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.2609.40341","doi":"https://doi.org/10.48550/arxiv.2609.40341","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.40341","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:2609.40341","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.40341","pdf_url":"https://arxiv.org/pdf/2609.40341","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/W7215048873.pdf","grobid_xml":"https://content.openalex.org/works/W7215048873.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W4414674749","https://openalex.org/W4417327307","https://openalex.org/W4417492598","https://openalex.org/W7117736774","https://openalex.org/W7130590664","https://openalex.org/W7138923929","https://openalex.org/W7151757339","https://openalex.org/W7153003613","https://openalex.org/W7156704535","https://openalex.org/W7160159555","https://openalex.org/W7161247360","https://openalex.org/W7164992005","https://openalex.org/W7167635130","https://openalex.org/W7169616986","https://openalex.org/W7172433693","https://openalex.org/W7204958538","https://openalex.org/W7212073125"],"related_works":["https://openalex.org/W7164047625","https://openalex.org/W7153003613","https://openalex.org/W7172433693","https://openalex.org/W7165356889","https://openalex.org/W7213945734","https://openalex.org/W7167920296","https://openalex.org/W7221032799","https://openalex.org/W7162413329","https://openalex.org/W6910769791","https://openalex.org/W7130590664"],"abstract_inverted_index":{"Egocentric":[0],"human":[1,30,60,100,178],"data":[2,37,48,61,85,93,110,112,154,179],"provides":[3],"a":[4,55,68,130],"scalable":[5],"source":[6],"of":[7,58,82,176],"experience":[8],"for":[9,133,180],"robot":[10,41,109,181],"learning,":[11],"but":[12,32],"varies":[13],"substantially":[14,102],"in":[15],"human-robot":[16,83],"alignment,":[17,84,164],"behavioral":[18],"coverage,":[19],"and":[20,43,65,87,92,106,114,121,149,169],"available":[21,167],"supervision.":[22],"Existing":[23],"work":[24],"shows":[25,162],"favorable":[26],"scaling":[27,159],"with":[28,62],"increasing":[29],"data,":[31],"it":[33],"remains":[34,124],"unclear":[35],"which":[36],"properties":[38],"drive":[39],"downstream":[40,118],"gains":[42],"how":[44,163],"to":[45],"use":[46],"such":[47],"throughout":[49],"the":[50,74,80,157,174],"training":[51],"pipeline.":[52],"We":[53,96,137],"present":[54],"systematic":[56],"study":[57],"egocentric":[59,177],"different":[63],"alignment":[64],"supervision":[66,123],"under":[67],"unified":[69],"world-action":[70],"model":[71,75],"framework.":[72],"With":[73],"backbone":[76],"fixed,":[77],"we":[78],"disentangle":[79],"effects":[81],"duration":[86,113,155],"task":[88,115,165],"diversity,":[89,166],"action":[90,127],"supervision,":[91,168],"usage":[94,170],"strategies.":[95],"find":[97],"that":[98],"aligned":[99],"demonstrations":[101],"improve":[103],"out-of-distribution":[104],"generalization":[105],"reduce":[107],"target-task":[108],"requirements;":[111],"diversity":[116],"affect":[117],"capabilities":[119],"differently;":[120],"video-only":[122],"effective":[125],"without":[126],"labels,":[128],"providing":[129],"strong":[131],"foundation":[132],"subsequent":[134],"video-action":[135],"training.":[136],"validate":[138],"these":[139],"findings":[140],"through":[141],"closed-loop":[142],"policy":[143],"evaluation":[144],"on":[145],"both":[146],"real":[147],"robots":[148],"RoboDojo.":[150],"Rather":[151],"than":[152],"treating":[153],"as":[156],"sole":[158],"axis,":[160],"Ego4WAM":[161],"strategy":[171],"jointly":[172],"shape":[173],"value":[175],"learning.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-10-02T00:00:00"}