{"id":"https://openalex.org/W7135191656","doi":"https://doi.org/10.1109/lra.2026.3673995","title":"Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling","display_name":"Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling","publication_year":2026,"publication_date":"2026-03-13","ids":{"openalex":"https://openalex.org/W7135191656","doi":"https://doi.org/10.1109/lra.2026.3673995"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3673995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3673995","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066468525","display_name":"Hao Qi","orcid":"https://orcid.org/0000-0002-2849-6226"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Han Qi","raw_affiliation_strings":["School of Engineering, Applied Sciences, Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129033898","display_name":"Haocheng Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haocheng Yin","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076920767","display_name":"Aris Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aris Zhu","raw_affiliation_strings":["School of Engineering, Applied Sciences, Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129019330","display_name":"Yilun Du","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yilun Du","raw_affiliation_strings":["School of Engineering, Applied Sciences, Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100378741","display_name":"H. J. Yang","orcid":"https://orcid.org/0009-0004-8274-9863"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Yang","raw_affiliation_strings":["School of Engineering, Applied Sciences, Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066468525"],"corresponding_institution_ids":["https://openalex.org/I2801851002"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.7893035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"5","first_page":"5534","last_page":"5541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.28060001134872437,"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":0.28060001134872437,"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/T12290","display_name":"Human Motion and Animation","score":0.09740000218153,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.07249999791383743,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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","display_name":"Robot","score":0.3921000063419342},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3546000123023987},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.29670000076293945},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.29159998893737793},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.28040000796318054},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.2743000090122223}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5806999802589417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5712000131607056},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2705000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.265500009059906},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26019999384880066},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2026.3673995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3673995","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"<italic":[2,11,37],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[3,12,38],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">generative":[4],"predictive":[5,89],"control</i>":[6],"(GPC),":[7],"a":[8,26,36,85],"framework":[9],"for":[10],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">inference-time</i>":[13],"enhancement":[14],"of":[15,60,84],"pretrained":[16],"behavior-cloning":[17],"policies.":[18],"Rather":[19],"than":[20],"retraining":[21],"or":[22],"fine-tuning,":[23],"GPC":[24],"augments":[25],"frozen":[27],"diffusion":[28,66],"policy":[29],"at":[30],"deployment":[31],"by":[32,64],"coupling":[33],"it":[34],"with":[35,88],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">predictive":[39],"world":[40,47],"model</i>.":[41],"Concretely,":[42],"we":[43],"train":[44],"an":[45],"action-conditioned":[46],"model":[48],"on":[49,104],"expert":[50],"demonstrations":[51],"and":[52,75,99,103,112],"random":[53],"exploration":[54],"rollouts":[55],"to":[56,115],"forecast":[57],"the":[58,65],"consequences":[59],"action":[61],"proposals":[62,78],"produced":[63],"policy,":[67],"then":[68],"perform":[69],"lightweight":[70],"online":[71],"planning":[72],"that":[73],"ranks":[74],"refines":[76],"these":[77],"via":[79],"model-based":[80],"look-ahead.":[81],"This":[82],"combination":[83],"generative":[86],"prior":[87],"foresight":[90],"enables":[91],"test-time":[92],"adaptation.":[93],"Across":[94],"diverse":[95],"robotic":[96],"manipulation":[97],"tasks\u2014state-":[98],"vision-based,":[100],"in":[101],"simulation":[102],"real":[105],"hardware\u2014GPC":[106],"consistently":[107],"outperforms":[108],"standard":[109],"behavior":[110],"cloning":[111],"compares":[113],"favorably":[114],"other":[116],"inference-time":[117],"adaptation":[118],"baselines.":[119]},"counts_by_year":[],"updated_date":"2026-03-24T05:59:24.953642","created_date":"2026-03-14T00:00:00"}