{"id":"https://openalex.org/W7204456208","doi":"https://doi.org/10.48550/arxiv.2608.26103","title":"Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization","display_name":"Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization","publication_year":2026,"publication_date":"2026-08-26","ids":{"openalex":"https://openalex.org/W7204456208","doi":"https://doi.org/10.48550/arxiv.2608.26103"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.26103","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26103","pdf_url":"https://arxiv.org/pdf/2608.26103","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.26103","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138317672","display_name":"Jiaming Zhou","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/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhou, Jiaming","raw_affiliation_strings":["HKUST (GZ) ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST (GZ) ,","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124429737","display_name":"Qihang Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136033581","display_name":"Gangwei Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Gangwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136012834","display_name":"Cunxin Fan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Cunxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121202332","display_name":"Yujie Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yujie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138805136","display_name":"Ruilin Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ruilin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109781406","display_name":"Yiming Luo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121204761","display_name":"Shuai Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123332289","display_name":"Xing Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140315609","display_name":"Yujun Shen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Yujun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059207044","display_name":"Junwei Liang","orcid":"https://orcid.org/0000-0003-2219-5569","observed_orcids":["https://orcid.org/0000-0003-2219-5569"]},"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/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Liang, Junwei","raw_affiliation_strings":["HKUST (GZ) ,","HKUST * Project Lead ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST (GZ) ,","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I4405261251"]},{"raw_affiliation_string":"HKUST * Project Lead ,","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140399417","display_name":"Yinghao Xu","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"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xu, Yinghao","raw_affiliation_strings":["HKUST * Project Lead ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HKUST * Project Lead ,","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.9574999809265137,"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":0.9574999809265137,"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":0.03889999911189079,"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":0.0020000000949949026,"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/in-context-learning","display_name":"in-context learning","score":0.8759999871253967},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.8349999785423279},{"id":"https://openalex.org/keywords/human-robot-interaction","display_name":"human-robot interaction","score":0.7170000076293945},{"id":"https://openalex.org/keywords/task-specification","display_name":"task specification","score":0.4350000023841858},{"id":"https://openalex.org/keywords/multi-object-manipulation","display_name":"multi-object manipulation","score":0.6549999713897705},{"id":"https://openalex.org/keywords/long-horizon-manipulation","display_name":"long-horizon manipulation","score":0.890999972820282}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7936999797821045},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7849000096321106},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720000147819519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6654999852180481},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6243000030517578},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.600600004196167},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.5055999755859375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44940000772476196},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4318000078201294},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.3714999854564667},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.35010001063346863},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2987000048160553},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.26103","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26103","pdf_url":"https://arxiv.org/pdf/2608.26103","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.26103","doi":"https://doi.org/10.48550/arxiv.2608.26103","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.26103","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.26103","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26103","pdf_url":"https://arxiv.org/pdf/2608.26103","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","license_id":"https://openalex.org/licenses/cc-by","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/W7204456208.pdf","grobid_xml":"https://content.openalex.org/works/W7204456208.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4403788204","https://openalex.org/W4319451949","https://openalex.org/W4401417162","https://openalex.org/W7220967560","https://openalex.org/W6910493287","https://openalex.org/W7165646993","https://openalex.org/W7214939170","https://openalex.org/W4414580806","https://openalex.org/W4383109144","https://openalex.org/W7130552073"],"abstract_inverted_index":{"Zero-shot":[0],"cross-task":[1,58],"generalization,":[2,59],"where":[3],"a":[4,15,25,51,77,95,135,187],"policy":[5,168],"must":[6],"execute":[7],"manipulation":[8,75],"tasks":[9,102,164,180],"never":[10],"seen":[11,163],"during":[12],"training,":[13,147],"remains":[14],"central":[16],"challenge":[17],"in":[18,35,181],"robot":[19,126],"learning.":[20],"In":[21,204],"large":[22],"language":[23],"models,":[24],"novel":[26],"task":[27,54,72,90,171,216],"can":[28],"be":[29],"performed":[30],"simply":[31],"by":[32,103],"specifying":[33],"it":[34,82,207],"the":[36,70,88,111,167,174,200],"context,":[37],"without":[38],"any":[39],"parameter":[40],"update.":[41],"This":[42],"form":[43],"of":[44,53,113,137,195],"in-context":[45,105,152],"learning":[46],"(ICL)":[47],"turns":[48],"generalization":[49],"into":[50,128],"problem":[52],"specification.":[55],"To":[56,109],"achieve":[57],"we":[60,118,148],"bring":[61],"this":[62],"paradigm":[63],"to":[64,169,212,214],"robotic":[65],"manipulation,":[66,222],"and":[67,165,223],"argue":[68],"that":[69,99,123,158],"natural":[71],"specification":[73],"for":[74],"is":[76],"human":[78,106,131,209],"video:":[79],"unlike":[80],"language,":[81],"provides":[83],"rich":[84],"visual":[85],"cues":[86],"about":[87],"intended":[89],"evolution.":[91],"We":[92],"present":[93],"Zero-WAM,":[94],"causal":[96],"video-action":[97,202],"model":[98,146],"executes":[100],"unseen":[101,179,215],"following":[104],"video":[107,175,210],"guidance.":[108],"address":[110],"scarcity":[112],"task-rich":[114],"paired":[115],"human-robot":[116,139],"data,":[117],"propose":[119],"an":[120,151,192],"automatic":[121],"pipeline":[122],"converts":[124],"task-sampled":[125],"trajectories":[127],"semantically":[129],"matched":[130],"videos,":[132],"yielding":[133],"HumanGen,":[134],"dataset":[136],"74.2K":[138],"ICL":[140],"pairs":[141],"across":[142],"8.6K":[143],"tasks.":[144],"For":[145],"further":[149],"introduce":[150],"future":[153],"chunk":[154],"prediction":[155],"(IFP)":[156],"objective":[157],"suppresses":[159],"shortcuts":[160],"learned":[161],"from":[162,173],"forces":[166],"draw":[170],"information":[172],"prompt.":[176],"On":[177],"seven":[178],"RoboTwin":[182],"2.0":[183],"simulation,":[184],"Zero-WAM":[185],"achieves":[186],"47.0%":[188],"average":[189],"success":[190],"rate,":[191],"absolute":[193],"improvement":[194],"29.5":[196],"percentage":[197],"points":[198],"over":[199],"strongest":[201],"baseline.":[203],"real-world":[205],"evaluations,":[206],"follows":[208],"guidance":[211],"generalize":[213],"configurations":[217],"involving":[218],"multi-object":[219],"scenes,":[220],"long-horizon":[221],"fine-grained":[224],"insertion.":[225]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-28T00:00:00"}
