{"id":"https://openalex.org/W7161595133","doi":"https://doi.org/10.48550/arxiv.2605.15705","title":"Feedback World Model Enables Precise Guidance of Diffusion Policy","display_name":"Feedback World Model Enables Precise Guidance of Diffusion Policy","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161595133","doi":"https://doi.org/10.48550/arxiv.2605.15705"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.15705","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15705","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.15705","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136430041","display_name":"Tuo An","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"An, Tuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004534196","display_name":"Jindou Jia","orcid":"https://orcid.org/0000-0002-1866-6180"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Jindou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136403458","display_name":"Gen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Gen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125534605","display_name":"Jingliang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jingliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136387842","display_name":"Chuhao Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Chuhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136403795","display_name":"Pengfei Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Pengfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101307843","display_name":"Bofan Lyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Bofan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111174933","display_name":"Jiaqi Bai","orcid":"https://orcid.org/0009-0003-9792-3556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Jiaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136356954","display_name":"Xinying Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Xinying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136362478","display_name":"Geng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Geng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136394075","display_name":"Jianfei Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jianfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.5356000065803528,"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":0.5356000065803528,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.2004999965429306,"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":0.060600001364946365,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5885999798774719},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.550000011920929},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5424000024795532},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5353000164031982},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43619999289512634},{"id":"https://openalex.org/keywords/feedback-loop","display_name":"Feedback loop","score":0.3862999975681305},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.37439998984336853},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.36410000920295715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6647999882698059},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5885999798774719},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.550000011920929},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4523000121116638},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40720000863075256},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.26649999618530273},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.15705","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15705","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.15705","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15705","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8011893630027771,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"World":[0],"models":[1],"aim":[2],"to":[3,111,154,202,228],"improve":[4],"robotic":[5],"decision":[6],"making":[7],"by":[8,161,200,210],"predicting":[9],"the":[10,23,28,50,54,59,80,92],"consequences":[11],"of":[12,90],"actions.":[13],"However,":[14],"in":[15],"practice,":[16],"their":[17,32],"predictions":[18,158],"often":[19],"become":[20],"unreliable":[21],"once":[22],"robot":[24,51],"encounters":[25],"states":[26],"outside":[27],"training":[29,125],"distribution,":[30],"limiting":[31],"effectiveness":[33],"at":[34,86,219],"deployment.":[35],"We":[36,130,149],"observe":[37],"that":[38,78,107,132,178,215],"execution":[39],"itself":[40],"provides":[41,222],"a":[42,75,96,103,139,223],"natural":[43],"but":[44],"underutilized":[45],"signal:":[46],"after":[47],"each":[48],"action,":[49],"directly":[52],"observes":[53],"true":[55],"next":[56],"state,":[57],"revealing":[58],"mismatch":[60],"between":[61,82],"predicted":[62],"and":[63,84,142,173,186,204],"actual":[64],"outcomes.":[65],"Building":[66],"on":[67,170],"this":[68,133],"insight,":[69],"we":[70],"propose":[71],"feedback":[72,105,218],"world":[73,93,196,230],"model,":[74],"new":[76],"paradigm":[77],"closes":[79],"loop":[81],"prediction":[83,184,198],"observation":[85],"inference":[87,220],"time.":[88],"Instead":[89],"treating":[91],"model":[94,118,197],"as":[95,138],"static":[97,229],"open-loop":[98],"predictor,":[99],"our":[100,179],"method":[101,180],"maintains":[102],"lightweight":[104],"state":[106],"is":[108],"updated":[109],"online":[110],"iteratively":[112],"correct":[113],"future":[114],"predictions,":[115],"compensating":[116],"for":[117],"errors":[119],"using":[120],"real-time":[121,217],"observations":[122],"without":[123],"additional":[124],"data":[126],"or":[127],"parameter":[128],"updates.":[129],"show":[131,214],"process":[134],"can":[135],"be":[136],"interpreted":[137],"latent-space":[140],"observer":[141],"admits":[143],"convergence":[144],"guarantees":[145],"under":[146,189],"mild":[147],"conditions.":[148],"further":[150],"introduce":[151],"action-aware":[152],"guidance":[153],"better":[155],"translate":[156],"corrected":[157],"into":[159],"control":[160],"emphasizing":[162],"action-controllable":[163],"components":[164],"while":[165],"suppressing":[166],"irrelevant":[167],"variations.":[168],"Experiments":[169],"LIBERO-Plus,":[171],"Robomimic,":[172],"real-world":[174],"manipulation":[175],"tasks":[176],"demonstrate":[177],"substantially":[181],"improves":[182,205],"both":[183],"accuracy":[185],"policy":[187],"performance":[188],"distribution":[190],"shift.":[191],"In":[192],"particular,":[193],"it":[194],"reduces":[195],"error":[199],"up":[201],"76.4%":[203],"out-of-distribution":[206],"(OOD)":[207],"success":[208],"rate":[209],"30%.":[211],"These":[212],"results":[213],"incorporating":[216],"time":[221],"simple":[224],"yet":[225],"powerful":[226],"alternative":[227],"modeling.":[231]},"counts_by_year":[],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2026-05-19T00:00:00"}