{"id":"https://openalex.org/W7204175267","doi":"https://doi.org/10.48550/arxiv.2608.22364","title":"WAM-OPD: Joint Video-Action Supervision for World Action Model Post-Training with On-Policy Distillation","display_name":"WAM-OPD: Joint Video-Action Supervision for World Action Model Post-Training with On-Policy Distillation","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204175267","doi":"https://doi.org/10.48550/arxiv.2608.22364"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22364","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22364","pdf_url":"https://arxiv.org/pdf/2608.22364","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22364","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107915496","display_name":"Liuhaichen Yang","orcid":"https://orcid.org/0009-0008-4353-3612","observed_orcids":["https://orcid.org/0009-0008-4353-3612"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang, Liuhaichen","raw_affiliation_strings":["Department of Computer Science , University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157592352","display_name":"Zhengyang Zhong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Zhengyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153648284","display_name":"Hanshang Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Hanshang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157374338","display_name":"Ningwei Bai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Ningwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113146534","display_name":"Qichen Yin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Qichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157537503","display_name":"Zhi Han","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Zhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060200431","display_name":"Jiarui Qin","orcid":"https://orcid.org/0000-0002-9064-885X","observed_orcids":["https://orcid.org/0000-0002-9064-885X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Jiarui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032451060","display_name":"Zhuang Jiang","orcid":"https://orcid.org/0000-0001-5692-8308","observed_orcids":["https://orcid.org/0000-0001-5692-8308"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiang, Zhuang","raw_affiliation_strings":["Department of Computer Science , University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140011621","display_name":"Chenchao Sheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sheng, Chenchao","raw_affiliation_strings":["Department of Mechanical Engineering , University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering , University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153565833","display_name":"Hanbo Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Hanbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157519033","display_name":"Junkai Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Junkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064434669","display_name":"Junkai Sun","orcid":"https://orcid.org/0000-0002-7006-0960","observed_orcids":["https://orcid.org/0000-0002-7006-0960"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Junkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157576379","display_name":"Dongcheng Lyu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Dongcheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157631137","display_name":"Bo Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100650289","display_name":"Yi Dong","orcid":"https://orcid.org/0000-0003-3047-7777","observed_orcids":["https://orcid.org/0000-0003-3047-7777"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075862536","display_name":"Zezhi Tang","orcid":"https://orcid.org/0000-0002-0182-6010","observed_orcids":["https://orcid.org/0000-0002-0182-6010"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tang, Zezhi","raw_affiliation_strings":["Department of Computer Science , University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University College London","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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":0.9535999894142151,"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":0.9535999894142151,"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":0.039799999445676804,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0019000000320374966,"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/world-action-models","display_name":"world action models","score":0.8610000014305115},{"id":"https://openalex.org/keywords/on-policy-distillation","display_name":"on-policy distillation","score":0.7870000004768372},{"id":"https://openalex.org/keywords/video-generation","display_name":"video generation","score":0.6990000009536743},{"id":"https://openalex.org/keywords/robotwin","display_name":"RoboTwin","score":0.6039999723434448},{"id":"https://openalex.org/keywords/teacher-student-learning","display_name":"teacher-student learning","score":0.5889999866485596}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7674999833106995},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6726999878883362},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6571999788284302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6352999806404114},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5583000183105469},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49810001254081726},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4740999937057495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46320000290870667},{"id":"https://openalex.org/C2778671685","wikidata":"https://www.wikidata.org/wiki/Q219239","display_name":"Recipe","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C76100544","wikidata":"https://www.wikidata.org/wiki/Q4118095","display_name":"Batch distillation","level":4,"score":0.31119999289512634},{"id":"https://openalex.org/C111852164","wikidata":"https://www.wikidata.org/wiki/Q1414679","display_name":"Handover","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.26969999074935913}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22364","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22364","pdf_url":"https://arxiv.org/pdf/2608.22364","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.2608.22364","doi":"https://doi.org/10.48550/arxiv.2608.22364","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22364","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:2608.22364","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22364","pdf_url":"https://arxiv.org/pdf/2608.22364","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/W7204175267.pdf","grobid_xml":"https://content.openalex.org/works/W7204175267.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W4394656839","https://openalex.org/W4394972242","https://openalex.org/W6929480010","https://openalex.org/W7081569152","https://openalex.org/W7126180855","https://openalex.org/W7143342743","https://openalex.org/W7160838488","https://openalex.org/W7161243847","https://openalex.org/W7163686620","https://openalex.org/W7165020664"],"related_works":["https://openalex.org/W7202204377","https://openalex.org/W7221770770","https://openalex.org/W7214939170","https://openalex.org/W7221029694","https://openalex.org/W7220743213","https://openalex.org/W7220902832","https://openalex.org/W7221154520","https://openalex.org/W7223125825","https://openalex.org/W7214229511","https://openalex.org/W7215951493"],"abstract_inverted_index":{"World":[0],"Action":[1],"Models":[2],"(WAMs)":[3],"generate":[4],"both":[5,57],"future":[6],"video":[7,49,63],"and":[8,43,50,64],"robot":[9],"actions,":[10],"offering":[11],"two":[12,132],"connected":[13],"outputs":[14],"for":[15,47,144],"post-training":[16],"supervision.":[17],"How":[18],"can":[19],"a":[20,25,45],"pretrained":[21],"WAM":[22,146],"learn":[23],"from":[24,56,78,90],"stronger":[26],"Teacher":[27,46],"on":[28,109],"the":[29,95,105,131,138],"histories":[30,42,98,126],"it":[31,86],"encounters":[32],"during":[33],"execution?":[34],"We":[35],"present":[36],"WAM-OPD,":[37],"which":[38],"collects":[39],"Student":[40,54,97],"rollout":[41],"queries":[44],"paired":[48,141],"action":[51,65],"targets.":[52],"The":[53],"learns":[55],"targets":[58],"while":[59,114],"retaining":[60],"its":[61],"one-step":[62],"generation":[66],"at":[67],"deployment.":[68],"Across":[69],"12":[70],"RoboTwin":[71],"2.0":[72],"tasks,":[73,85,113],"WAM-OPD":[74],"improves":[75,87,119],"average":[76,88],"success":[77,89,108],"33.8%":[79],"to":[80,92],"65.7%;":[81],"across":[82],"four":[83],"real-robot":[84],"51.4%":[91],"64.6%.":[93],"With":[94],"collected":[96],"held":[99],"fixed,":[100],"joint":[101],"video-action":[102,142],"supervision":[103,143],"achieves":[104],"highest":[106],"observed":[107],"all":[110],"three":[111],"ablation":[112],"either":[115],"modality":[116],"alone":[117],"also":[118],"performance.":[120],"A":[121],"separate":[122],"comparison":[123],"with":[124],"Teacher-generated":[125],"finds":[127],"task-dependent":[128],"differences":[129],"between":[130],"history":[133],"sources.":[134],"These":[135],"results":[136],"demonstrate":[137],"value":[139],"of":[140],"improving":[145],"policies":[147],"without":[148],"increasing":[149],"their":[150],"deployed":[151],"sampling":[152],"budget.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-26T00:00:00"}