{"id":"https://openalex.org/W7164013738","doi":"https://doi.org/10.48550/arxiv.2606.07974","title":"PRISM: PRior-guided Imagination Sampling in world Models","display_name":"PRISM: PRior-guided Imagination Sampling in world Models","publication_year":2026,"publication_date":"2026-06-06","ids":{"openalex":"https://openalex.org/W7164013738","doi":"https://doi.org/10.48550/arxiv.2606.07974"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.07974","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.07974","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.07974","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138232771","display_name":"Yuhai Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yuhai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138257042","display_name":"Jiawei Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Jiawei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111039154","display_name":"Rongxuan Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Rongxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138248641","display_name":"Xiao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138256823","display_name":"Yongliang Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yongliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138210168","display_name":"Jing Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138217408","display_name":"Yang Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Yang","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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.24609999358654022,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.24609999358654022,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.12600000202655792,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1216999962925911,"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/inference","display_name":"Inference","score":0.6035000085830688},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5641000270843506},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.5411999821662903},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.51419997215271},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3847000002861023},{"id":"https://openalex.org/keywords/prism","display_name":"Prism","score":0.38029998540878296},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.3711000084877014},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.36739999055862427},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.3587000072002411}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6323000192642212},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6035000085830688},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5641000270843506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.550599992275238},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.5411999821662903},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.51419997215271},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4927000105381012},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C67666897","wikidata":"https://www.wikidata.org/wiki/Q165896","display_name":"Prism","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3711000084877014},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.36739999055862427},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.3587000072002411},{"id":"https://openalex.org/C53051483","wikidata":"https://www.wikidata.org/wiki/Q861555","display_name":"Cube (algebra)","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32269999384880066},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.30809998512268066},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.274399995803833},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.07974","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.07974","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.07974","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.07974","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":"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"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.43208709359169006}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"A":[0],"learned":[1,114],"world":[2,118,152],"model":[3,38,119],"provides":[4],"a":[5,37,67,80,131,138,148,156,166,183],"powerful":[6],"physical":[7],"intuition":[8],"for":[9,28],"evaluating":[10,50],"future":[11],"states.":[12],"But":[13],"its":[14,161],"effectiveness":[15],"in":[16,51],"continuous":[17],"control":[18,204],"also":[19],"depends":[20],"critically":[21],"on":[22,89,147,221,227],"how":[23,35],"candidate":[24,46],"actions":[25,47],"are":[26,48],"generated":[27],"model-based":[29],"planning.":[30],"Rather":[31],"than":[32],"solely":[33],"asking":[34],"accurately":[36],"can":[39],"simulate":[40],"the":[41,52,71,107,113,117,124,178,192,196],"future,":[42],"we":[43],"ask:":[44],"which":[45],"worth":[49],"first":[53],"place?":[54],"Existing":[55],"planners":[56],"typically":[57],"search":[58,78],"arbitrarily":[59],"or":[60,93],"use":[61],"expert":[62],"demonstrations":[63],"only":[64],"to":[65,96,160,164],"initialize":[66],"sampling":[68,180,193],"mean,":[69],"discarding":[70],"expert's":[72],"state-conditioned":[73,167],"confidence.":[74],"Properly":[75],"guiding":[76],"this":[77,102,175],"requires":[79],"robust":[81],"action":[82,126],"prior,":[83],"yet":[84],"current":[85],"approaches":[86],"often":[87],"rely":[88],"independent":[90],"visual":[91],"encoders":[92],"large-scale":[94],"VLMs":[95],"obtain":[97],"one.":[98],"We":[99,128],"argue":[100],"that":[101,134],"architectural":[103,144],"bloat":[104],"is":[105,201,207],"unnecessary:":[106],"exact":[108],"same":[109],"data":[110],"-":[111,121],"and":[112,202,223],"representations":[115],"of":[116],"itself":[120],"inherently":[122],"encode":[123],"agent's":[125],"intuition.":[127],"introduce":[129],"PRISM,":[130],"task-agnostic":[132],"framework":[133],"extracts":[135],"both":[136],"from":[137],"single":[139],"dataset":[140],"while":[141],"maintaining":[142],"strict":[143],"simplicity.":[145],"Building":[146],"standard":[149],"JEPA-style":[150],"latent":[151],"model,":[153],"PRISM":[154,173,209],"attaches":[155],"lightweight":[157],"MLP":[158],"directly":[159],"frozen":[162],"encoder":[163],"predict":[165],"Gaussian":[168],"prior.":[169],"At":[170],"plan":[171],"time,":[172],"fuses":[174],"prior":[176,197],"into":[177],"planner's":[179],"distribution":[181],"via":[182],"precision-weighted":[184],"Product-of-Gaussians":[185],"update.":[186],"This":[187],"parameter-free,":[188],"closed-form":[189],"integration":[190],"steers":[191],"process,":[194],"making":[195],"confident":[198],"where":[199,205],"it":[200,206],"ceding":[203],"not.":[208],"improves":[210],"success":[211],"rates":[212],"by":[213],"35":[214],"percentage":[215,225],"points":[216,226],"over":[217],"vanilla":[218],"world-model-based":[219],"MPC":[220],"Cube":[222],"32":[224],"PushT,":[228],"without":[229],"introducing":[230],"significant":[231],"inference":[232],"overhead.":[233]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}