{"id":"https://openalex.org/W7204279518","doi":"https://doi.org/10.48550/arxiv.2608.24885","title":"Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning","display_name":"Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204279518","doi":"https://doi.org/10.48550/arxiv.2608.24885"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.24885","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24885","pdf_url":"https://arxiv.org/pdf/2608.24885","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.24885","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000301628","display_name":"Sixiang Chen","orcid":"https://orcid.org/0009-0003-6837-886X","observed_orcids":["https://orcid.org/0009-0003-6837-886X","https://orcid.org/0000-0002-0910-8945"]},"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":"Chen, Sixiang","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147076066","display_name":"Jiaming Liu","orcid":null,"observed_orcids":[]},"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":"Liu, Jiaming","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139169120","display_name":"Jixian Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wu, Jixian","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics","New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics","institution_ids":[]},{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135303335","display_name":"Yichen Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Guo, Yichen","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136718043","display_name":"Tinghao Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Tinghao","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics","University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics","institution_ids":[]},{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051096521","display_name":"Qr Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, QR","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028696491","display_name":"Siyuan Qian","orcid":"https://orcid.org/0000-0002-7562-3689","observed_orcids":["https://orcid.org/0000-0002-7562-3689"]},"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":"Qian, Siyuan","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128772041","display_name":"Jiajun Cao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Co, Peterson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159692940","display_name":"Hao Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen, Hao","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159574884","display_name":"Jiajun Cao","orcid":null,"observed_orcids":[]},"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":"Cao, Jiajun","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics","State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159604924","display_name":"Zhoujian Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhoujian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149467088","display_name":"Lingfei Zhai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhai, Lingfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159664412","display_name":"Jian Tang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jian","raw_affiliation_strings":["Beijing Innovation Center of Humanoid Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Innovation Center of Humanoid Robotics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159584156","display_name":"Shanghang Zhang","orcid":null,"observed_orcids":[]},"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":"Zhang, Shanghang","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0015999999595806003,"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":9.999999747378752e-05,"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-policy-learning","display_name":"robot policy learning","score":0.49399998784065247},{"id":"https://openalex.org/keywords/visual-integrity","display_name":"visual integrity","score":0.6840000152587891},{"id":"https://openalex.org/keywords/robotwin","display_name":"RoboTwin","score":0.6629999876022339}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7669000029563904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6725000143051147},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5738000273704529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5313000082969666},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C106306483","wikidata":"https://www.wikidata.org/wiki/Q183984","display_name":"Futures contract","level":2,"score":0.49709999561309814},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4325999915599823},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33980000019073486},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.31769999861717224},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3133000135421753},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C183759332","wikidata":"https://www.wikidata.org/wiki/Q343680","display_name":"Action learning","level":4,"score":0.27900001406669617},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.25270000100135803},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.24885","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24885","pdf_url":"https://arxiv.org/pdf/2608.24885","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.2608.24885","doi":"https://doi.org/10.48550/arxiv.2608.24885","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24885","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:2608.24885","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24885","pdf_url":"https://arxiv.org/pdf/2608.24885","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/W7204279518.pdf","grobid_xml":"https://content.openalex.org/works/W7204279518.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7212044376","https://openalex.org/W7162777228","https://openalex.org/W7172341836","https://openalex.org/W7134848822","https://openalex.org/W7212644850","https://openalex.org/W7163532949","https://openalex.org/W7214949430","https://openalex.org/W7167068969","https://openalex.org/W4415273528","https://openalex.org/W6910795718"],"abstract_inverted_index":{"Action-conditioned":[0],"world":[1],"models":[2,70],"increasingly":[3],"serve":[4],"as":[5],"learned":[6],"simulators":[7],"for":[8,136],"robotic":[9],"policy":[10,138],"improvement,":[11,139],"yet":[12],"their":[13],"reliability":[14],"rests":[15],"on":[16,73,131,147],"an":[17,112],"unverified":[18],"assumption:":[19],"generated":[20],"futures":[21],"faithfully":[22],"reflect":[23],"the":[24,85],"consequences":[25],"of":[26],"arbitrary":[27],"valid":[28],"actions.":[29],"Systematic":[30],"evaluation":[31],"against":[32],"action-specific":[33],"ground":[34],"truth":[35],"remains":[36],"limited":[37],"beyond":[38],"expert":[39],"demonstrations.":[40],"To":[41,92],"address":[42],"this":[43],"gap,":[44],"we":[45,96],"introduce":[46],"WorldEcho,":[47],"which":[48,99],"evaluates":[49],"action":[50,55,101,122],"following":[51],"over":[52],"a":[53],"broader":[54],"distribution":[56],"through":[57,111],"visual":[58],"integrity":[59],"and":[60,115,118,146],"SE(3)":[61],"end-effector":[62],"trajectory":[63],"alignment.":[64],"Our":[65],"diagnosis":[66],"shows":[67],"that":[68,126],"expert-trained":[69],"perform":[71],"better":[72],"demonstrated":[74],"actions":[75,87],"but":[76],"struggle":[77],"with":[78,84],"off-expert":[79],"trajectories,":[80],"producing":[81],"motion":[82],"inconsistent":[83],"commanded":[86],"or":[88],"visually":[89],"invalid":[90],"rollouts.":[91],"mitigate":[93],"these":[94],"failures,":[95],"propose":[97],"WorldSync,":[98],"broadens":[100],"coverage,":[102],"grounds":[103],"intermediate":[104],"video":[105],"representations":[106],"in":[107,144],"action-induced":[108],"robot":[109],"dynamics":[110],"Action-Forcing":[113],"Expert,":[114],"aligns":[116],"predicted":[117],"ground-truth":[119],"changes":[120],"under":[121],"interventions.":[123],"Experiments":[124],"show":[125],"WorldSync":[127],"reduces":[128],"integrity-gated":[129],"error":[130],"RoboTwin":[132],"and,":[133],"when":[134],"used":[135],"iterative":[137],"yields":[140],"higher":[141],"success":[142],"rates":[143],"simulation":[145],"real":[148],"robots.":[149]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-27T00:00:00"}