{"id":"https://openalex.org/W7212293299","doi":"https://doi.org/10.20944/preprints202609.0894.v1","title":"World Models for Embodied Intelligence: From Plausible to Controllable to Actionable","display_name":"World Models for Embodied Intelligence: From Plausible to Controllable to Actionable","publication_year":2026,"publication_date":"2026-09-11","ids":{"openalex":"https://openalex.org/W7212293299","doi":"https://doi.org/10.20944/preprints202609.0894.v1"},"language":"en","primary_location":{"id":"doi:10.20944/preprints202609.0894.v1","doi":"https://doi.org/10.20944/preprints202609.0894.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202609.0894.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.20944/preprints202609.0894.v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102674783","display_name":"Nanjie Yao","orcid":"https://orcid.org/0009-0007-4930-7758","observed_orcids":["https://orcid.org/0009-0007-4930-7758"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nanjie Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446112","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-3086-3128","observed_orcids":["https://orcid.org/0000-0002-3086-3128","https://orcid.org/0000-0003-1662-2480"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112127590","display_name":"Chong Cheng","orcid":"https://orcid.org/0009-0009-0466-0632","observed_orcids":["https://orcid.org/0009-0009-0466-0632"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123649693","display_name":"Zhikang Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhikang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136877588","display_name":"Wenzhe Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenzhe Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151331547","display_name":"Jiafei Lyu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiafei Lyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137061605","display_name":"Li Shen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015991234","display_name":"Peilin Zhao","orcid":"https://orcid.org/0000-0001-8543-3953","observed_orcids":["https://orcid.org/0000-0001-8543-3953"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peilin Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151341050","display_name":"Zongqing Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zongqing Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5151406574","display_name":"Gao Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074834854","display_name":"Steven C. H. Hoi","orcid":"https://orcid.org/0000-0002-4584-3453","observed_orcids":["https://orcid.org/0000-0002-4584-3453"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven Hoi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074103823","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0001-7225-5449","observed_orcids":["https://orcid.org/0000-0001-7225-5449","https://orcid.org/0000-0002-5979-578X","https://orcid.org/0000-0002-9209-036X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073681676","display_name":"Deheng Ye","orcid":"https://orcid.org/0000-0002-1754-1837","observed_orcids":["https://orcid.org/0000-0002-1754-1837"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Deheng Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5073681676","https://openalex.org/A5100446112"],"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":0.9340999722480774,"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":0.9340999722480774,"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/T11883","display_name":"Embodied and Extended Cognition","score":0.03420000150799751,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.007699999958276749,"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-models","display_name":"world models","score":0.9950000047683716},{"id":"https://openalex.org/keywords/embodied-ai","display_name":"embodied AI","score":0.9490000009536743},{"id":"https://openalex.org/keywords/physical-grounding","display_name":"physical grounding","score":0.42899999022483826},{"id":"https://openalex.org/keywords/causal-intervention","display_name":"causal intervention","score":0.5419999957084656},{"id":"https://openalex.org/keywords/uncertainty-calibration","display_name":"uncertainty calibration","score":0.9959999918937683},{"id":"https://openalex.org/keywords/cross-embodiment-transfer","display_name":"cross-embodiment transfer","score":0.7839999794960022},{"id":"https://openalex.org/keywords/manipulation","display_name":"manipulation","score":0.6010000109672546},{"id":"https://openalex.org/keywords/navigation","display_name":"navigation","score":0.878000020980835},{"id":"https://openalex.org/keywords/locomotion","display_name":"locomotion","score":0.9229999780654907},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.9990000128746033},{"id":"https://openalex.org/keywords/embodied-learning","display_name":"embodied learning","score":0.824999988079071},{"id":"https://openalex.org/keywords/evaluation-protocol","display_name":"evaluation protocol","score":0.4359999895095825},{"id":"https://openalex.org/keywords/closed-loop-behavior","display_name":"closed-loop behavior","score":0.5210000276565552}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.7998999953269958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492000222206116},{"id":"https://openalex.org/C176777502","wikidata":"https://www.wikidata.org/wiki/Q4774623","display_name":"Anticipation (artificial intelligence)","level":2,"score":0.6152999997138977},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5910000205039978},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5903000235557556},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5625},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.519599974155426},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4918999969959259},{"id":"https://openalex.org/C106306483","wikidata":"https://www.wikidata.org/wiki/Q183984","display_name":"Futures contract","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42879998683929443},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3903999924659729},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.3160000145435333},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3027999997138977},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.3021000027656555},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C27415008","wikidata":"https://www.wikidata.org/wiki/Q7256382","display_name":"Psychological intervention","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.20944/preprints202609.0894.v1","doi":"https://doi.org/10.20944/preprints202609.0894.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202609.0894.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},{"id":"pmh:oai:arXiv.org:2609.16697","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.16697","pdf_url":"https://arxiv.org/pdf/2609.16697","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.2609.16697","doi":"https://doi.org/10.48550/arxiv.2609.16697","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.16697","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":"doi:10.20944/preprints202609.0894.v1","doi":"https://doi.org/10.20944/preprints202609.0894.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202609.0894.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7221311832","https://openalex.org/W4415958550","https://openalex.org/W7214285830","https://openalex.org/W7164931460","https://openalex.org/W7163066776","https://openalex.org/W7223039910","https://openalex.org/W7163155583","https://openalex.org/W7212087202","https://openalex.org/W7160406480","https://openalex.org/W7156571201"],"abstract_inverted_index":{"World":[0],"models":[1],"are":[2],"emerging":[3],"as":[4,230],"a":[5,51,70,72,111,156,192,270,276,280],"key":[6,104],"interface":[7],"between":[8],"perception":[9],"and":[10,26,64,77,84,95,166,200,207,223,240,244,262,264,294],"decision":[11,65],"making":[12],"in":[13,176,252,272],"embodied":[14,45,225,301],"intelligence,":[15],"enabling":[16],"agents":[17],"to":[18,55,172,283,292],"preserve":[19],"hidden":[20],"state,":[21,289],"anticipate":[22],"consequences,":[23],"compare":[24],"interventions,":[25],"adapt":[27],"when":[28],"execution":[29],"departs":[30],"from":[31,274],"expectation.":[32],"Much":[33],"of":[34,50,110,299],"this":[35,120,131,188,212],"progress":[36],"has":[37],"been":[38],"measured":[39],"by":[40,58,122],"visual":[41],"fidelity.":[42],"For":[43],"an":[44,167,300],"agent,":[46],"however,":[47],"the":[48,82,85,101,234,287,296],"purpose":[49],"world":[52,137,147],"model":[53,138,148,158,169,277],"is":[54,93,106],"improve":[56,115],"behavior":[57,298],"predicting":[59],"futures":[60],"that":[61,164,196],"inform":[62],"intervention":[63,258],"making.":[66],"Before":[67],"reaching":[68],"for":[69],"cup,":[71],"person":[73],"anticipates":[74],"its":[75],"weight":[76],"how":[78,161],"it":[79,99,114,285],"will":[80],"resist":[81],"grasp,":[83],"hand":[86],"shapes":[87],"itself":[88],"before":[89],"contact.":[90],"That":[91],"anticipation":[92],"coarse":[94],"rarely":[96],"pictorial,":[97],"yet":[98],"guides":[100],"movement.":[102],"The":[103],"question":[105,132],"therefore":[107],"which":[108,129],"properties":[109],"prediction":[112,171],"let":[113],"behavior.":[116],"Existing":[117],"surveys":[118],"organize":[119,228],"literature":[121],"architecture,":[123],"output":[124],"modality,":[125],"or":[126,153,183],"application":[127],"domain,":[128],"leaves":[130],"implicit.":[133],"We":[134,186,227],"accordingly":[135],"characterize":[136],"capability":[139,189,235],"through":[140],"three":[141],"progressively":[142],"stronger":[143],"levels:":[144],"A":[145],"Plausible":[146],"preserves":[149],"task-relevant":[150],"temporal,":[151],"geometric,":[152],"physical":[154],"structure;":[155,165],"Controllable":[157],"additionally":[159],"predicts":[160],"interventions":[162],"change":[163],"Actionable":[168],"uses":[170],"produce":[173],"measurable":[174],"improvements":[175],"planning,":[177],"action,":[178,293],"learning,":[179],"evaluation,":[180],"verification,":[181],"recovery,":[182,263],"data":[184],"selection.":[185],"complement":[187],"ladder":[190],"with":[191,203],"3x4":[193],"analysis":[194],"matrix":[195],"crosses":[197],"geometry,":[198],"physics,":[199],"action":[201],"grounding":[202],"data,":[204],"reward,":[205],"policy,":[206],"model-self":[208],"improvement":[209],"loops.":[210],"Using":[211],"framework,":[213],"we":[214,248],"survey":[215],"research":[216],"across":[217],"manipulation,":[218],"navigation,":[219],"locomotion,":[220],"autonomous":[221],"driving,":[222],"general":[224],"learning.":[226],"methods":[229],"technical":[231],"progressions,":[232],"clarify":[233],"required":[236],"at":[237],"each":[238],"level,":[239],"examine":[241],"datasets,":[242],"benchmarks,":[243],"evaluation":[245,273],"protocols.":[246],"Finally,":[247],"identify":[249],"open":[250],"challenges":[251],"long-horizon":[253],"consistency,":[254],"uncertainty":[255],"calibration,":[256],"causal":[257],"testing,":[259],"latency,":[260],"verification":[261],"cross-embodiment":[265],"transfer.":[266],"This":[267],"perspective":[268],"motivates":[269],"shift":[271],"whether":[275,284],"can":[278],"generate":[279],"convincing":[281],"future":[282],"represents":[286],"right":[288],"responds":[290],"correctly":[291],"improves":[295],"closed-loop":[297],"agent.":[302]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-12T00:00:00"}