{"id":"https://openalex.org/W7162751059","doi":"https://doi.org/10.48550/arxiv.2605.28865","title":"Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision","display_name":"Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision","publication_year":2026,"publication_date":"2026-05-22","ids":{"openalex":"https://openalex.org/W7162751059","doi":"https://doi.org/10.48550/arxiv.2605.28865"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.28865","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28865","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.28865","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137388988","display_name":"Jiayi Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fang, Jiayi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5137388988"],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.19550000131130219,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.19550000131130219,"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/T11431","display_name":"Action Observation and Synchronization","score":0.13770000636577606,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1103999987244606,"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/embodied-cognition","display_name":"Embodied cognition","score":0.7792999744415283},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5256999731063843},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49219998717308044},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.47450000047683716},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4323999881744385},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3346000015735626},{"id":"https://openalex.org/keywords/geometric-modeling","display_name":"Geometric modeling","score":0.30869999527931213}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.7792999744415283},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5289000272750854},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5256999731063843},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49219998717308044},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.47450000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46810001134872437},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4323999881744385},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37950000166893005},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2849000096321106},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2538999915122986},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.28865","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28865","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.28865","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.28865","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":"article"},"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":{"What":[0],"does":[1],"a":[2,20,31,60,108],"world":[3,33,159,166],"model":[4,34,167],"learn":[5],"from":[6,119],"physical":[7,28,51,158],"exploration,":[8,38],"without":[9],"any":[10],"linguistic":[11],"supervision?":[12],"We":[13,104],"argue":[14],"the":[15,23,27,101,116,139,162,173],"answer":[16],"is":[17],"organized":[18],"by":[19,133],"single":[21],"principle:":[22],"geometric":[24,120,148],"structure":[25,48],"of":[26,165,175],"world.":[29],"Training":[30],"VAE-based":[32],"on":[35],"random":[36,71],"embodied":[37,178],"we":[39],"find":[40],"that":[41,49,76],"its":[42],"latent":[43],"space":[44],"develops":[45],"spatial":[46],"semantic":[47,93,127],"mirrors":[50],"geometry":[52,160],"--":[53,136],"direction":[54],"accuracy":[55],"0.677+-0.029":[56],"versus":[57,68],"0.547":[58],"for":[59,70,172],"randomly":[61],"initialized":[62],"encoder,":[63],"and":[64,92,122,126,150],"position":[65],"RSA":[66],"0.192+-0.047":[67],"0.029":[69],"encoders":[72],"(6.6x":[73],"improvement),":[74],"showing":[75],"training":[77],"induces":[78],"genuine":[79],"structural":[80],"organization":[81],"beyond":[82],"CNN":[83],"inductive":[84],"bias.":[85],"Across":[86],"20":[87],"temporal":[88],"checkpoints,":[89],"prediction":[90,124],"performance":[91,125],"alignment":[94,128],"co-improve":[95],"(Spearman":[96],"r=-0.61,":[97],"p=0.004),":[98],"consistent":[99],"with":[100,169],"shared-driver":[102,140],"account.":[103],"confirm":[105],"this":[106],"through":[107],"double":[109],"knockout:":[110],"standard":[111],"KL":[112],"regularization":[113],"(beta=0.1)":[114],"forces":[115],"encoder":[117],"away":[118],"structure,":[121],"both":[123,152],"collapse":[129],"simultaneously":[130],"to":[131,145],"near-chance":[132],"step":[134],"50,000":[135],"exactly":[137],"as":[138,161],"account":[141],"predicts.":[142],"Reducing":[143],"beta":[144],"0.001":[146],"restores":[147],"access":[149],"recovers":[151],"capabilities":[153],"together.":[154],"These":[155],"findings":[156],"establish":[157],"organizing":[163],"principle":[164],"representations,":[168],"direct":[170],"implications":[171],"design":[174],"semantically":[176],"grounded":[177],"agents.":[179]},"counts_by_year":[],"updated_date":"2026-05-30T06:22:53.267495","created_date":"2026-05-30T00:00:00"}