{"id":"https://openalex.org/W7204197618","doi":"https://doi.org/10.48550/arxiv.2608.22764","title":"LpWM: A Case for Sparse Representations in World Models","display_name":"LpWM: A Case for Sparse Representations in World Models","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204197618","doi":"https://doi.org/10.48550/arxiv.2608.22764"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22764","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22764","pdf_url":"https://arxiv.org/pdf/2608.22764","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22764","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048399742","display_name":"Yilun Kuang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kuang, Yilun","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121834862","display_name":"Yash Dagade","orcid":"https://orcid.org/0000-0001-5447-6942","observed_orcids":["https://orcid.org/0000-0001-5447-6942"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dagade, Yash","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044439834","display_name":"Quentin Le Lidec","orcid":"https://orcid.org/0000-0001-7973-1030","observed_orcids":["https://orcid.org/0000-0001-7973-1030"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lidec, Quentin Le","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078025694","display_name":"Lucas Maes","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maes, Lucas","raw_affiliation_strings":["Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047293370","display_name":"Randall Balestriero","orcid":"https://orcid.org/0000-0002-5692-4187","observed_orcids":["https://orcid.org/0000-0002-5692-4187"]},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Balestriero, Randall","raw_affiliation_strings":["Brown University , AMI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University , AMI Labs","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001226970","display_name":"Yann LeCun","orcid":"https://orcid.org/0000-0002-1992-2684","observed_orcids":["https://orcid.org/0000-0002-1992-2684"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"LeCun, Yann","raw_affiliation_strings":["NYU , AMI Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU , AMI Labs","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"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":0.9922000169754028,"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":0.9922000169754028,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0026000000070780516,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.000699999975040555,"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":0.7979999780654907},{"id":"https://openalex.org/keywords/sparse-representation","display_name":"sparse representation","score":0.921999990940094},{"id":"https://openalex.org/keywords/jepa","display_name":"JEPA","score":0.8930000066757202},{"id":"https://openalex.org/keywords/latent-dynamics","display_name":"latent dynamics","score":0.7979999780654907},{"id":"https://openalex.org/keywords/planning","display_name":"planning","score":0.47699999809265137},{"id":"https://openalex.org/keywords/representation-collapse","display_name":"representation collapse","score":0.6200000047683716},{"id":"https://openalex.org/keywords/vicreg","display_name":"VICReg","score":0.49300000071525574}],"concepts":[{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.5979999899864197},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5813999772071838},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4514000117778778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44830000400543213},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4481000006198883},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4268999993801117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4250999987125397},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C37616216","wikidata":"https://www.wikidata.org/wiki/Q3218363","display_name":"Lasso (programming language)","level":2,"score":0.3644999861717224},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.33230000734329224},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30630001425743103},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C156872377","wikidata":"https://www.wikidata.org/wiki/Q6786281","display_name":"Matching pursuit","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.2935999929904938},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C2776157432","wikidata":"https://www.wikidata.org/wiki/Q1375683","display_name":"Normality","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22764","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22764","pdf_url":"https://arxiv.org/pdf/2608.22764","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22764","doi":"https://doi.org/10.48550/arxiv.2608.22764","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22764","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":"pmh:oai:arXiv.org:2608.22764","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22764","pdf_url":"https://arxiv.org/pdf/2608.22764","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5693414920","display_name":"NRT-HDR: FUTURE Foundations, Translation, and Responsibility for Data Science Impact","funder_award_id":"1922658","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204197618.pdf","grobid_xml":"https://content.openalex.org/works/W7204197618.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2787666871","https://openalex.org/W3041919418","https://openalex.org/W3091507139","https://openalex.org/W3094502228","https://openalex.org/W3134652006","https://openalex.org/W3168867926","https://openalex.org/W3205065023","https://openalex.org/W4221164116","https://openalex.org/W4286695273","https://openalex.org/W4386076428","https://openalex.org/W4388090547","https://openalex.org/W4390872297","https://openalex.org/W4393027293","https://openalex.org/W4394861491","https://openalex.org/W4404313764","https://openalex.org/W4404360744","https://openalex.org/W4404987034","https://openalex.org/W4416338927","https://openalex.org/W4417261359","https://openalex.org/W6960139023","https://openalex.org/W7127358364","https://openalex.org/W7129589260","https://openalex.org/W7129706894","https://openalex.org/W7133204408","https://openalex.org/W7140141371","https://openalex.org/W7150938507","https://openalex.org/W7162129256","https://openalex.org/W7166853236","https://openalex.org/W7196931009","https://openalex.org/W7203687260"],"related_works":["https://openalex.org/W7214783055","https://openalex.org/W7214719230","https://openalex.org/W7201875857","https://openalex.org/W7171663849","https://openalex.org/W7214965162","https://openalex.org/W7221541595","https://openalex.org/W7212430217","https://openalex.org/W7172432896","https://openalex.org/W7203687260","https://openalex.org/W7211897660"],"abstract_inverted_index":{"Joint-embedding":[0],"predictive":[1],"architectures":[2],"(JEPAs)":[3],"learn":[4],"latent":[5,55,89],"dynamics":[6,56,74,83],"for":[7,38,146,221],"planning":[8,161],"and":[9,60,201],"avoid":[10],"representation":[11],"collapse":[12],"by":[13,80,156],"matching":[14],"features":[15,128],"to":[16,58,125,129,158],"maximum-entropy":[17],"distributions":[18],"such":[19,66],"as":[20,95,104],"isotropic":[21],"Gaussians,":[22],"yielding":[23,135],"dense":[24,31,154,178],"representations.":[25,67],"However,":[26],"it":[27],"is":[28],"unclear":[29],"whether":[30,46],"representations":[32,103,180,192,214],"are":[33,193],"the":[34,96,142,189,217],"most":[35],"favorable":[36],"geometry":[37],"modeling":[39],"dynamics.":[40],"In":[41],"this":[42],"work,":[43],"we":[44],"ask":[45],"a":[47,85,105,115,130],"different":[48],"geometry,":[49],"sparse":[50,102,137,151,191,213],"representations,":[51],"can":[52,75,215],"make":[53],"action-conditioned":[54,81],"easier":[57],"model,":[59],"what":[61],"dynamical":[62,199],"structure":[63],"emerges":[64],"from":[65],"We":[68,111,185],"first":[69],"show":[70],"that":[71,188,212],"nonlinear":[72],"Lipschitz":[73],"be":[76],"approximated":[77],"arbitrarily":[78],"well":[79],"linear":[82],"in":[84,160],"sufficiently":[86],"high-dimensional":[87],"one-hot":[88,109],"space,":[90],"with":[91,119,175,195],"rollout":[92],"error":[93],"vanishing":[94],"dimension":[97],"grows.":[98],"This":[99,167],"motivates":[100],"distributed":[101],"practical":[106],"relaxation":[107],"of":[108],"sparsity.":[110],"introduce":[112],"LpWorldModel":[113],"(LpWM),":[114],"JEPA":[116],"model":[117],"regularized":[118],"Rectified":[120,131],"Distribution":[121],"Matching":[122],"Regularization":[123],"(RDMReg)":[124],"match":[126],"encoder":[127],"Generalized":[132],"Gaussian":[133,172],"distribution,":[134],"non-negative":[136],"codes.":[138],"Empirically,":[139],"sparsity":[140],"lowers":[141],"predictor":[143,165,183,218],"complexity":[144,219],"required":[145,220],"successful":[147],"planning:":[148],"on":[149],"PushT,":[150],"LpWM":[152,176],"outperforms":[153],"LeWM":[155],"up":[157],"57%":[159],"success":[162],"at":[163],"intermediate":[164],"capacities.":[166],"advantage":[168],"also":[169],"extends":[170],"beyond":[171],"distribution":[173],"matching,":[174],"outperforming":[177],"VICReg":[179],"across":[181],"multiple":[182],"families.":[184],"further":[186],"find":[187],"learned":[190],"mode-factored,":[194],"support":[196],"encoding":[197],"discrete":[198],"regimes":[200],"feature":[202],"magnitudes":[203],"capturing":[204],"continuous":[205],"within-regime":[206],"state.":[207],"Together,":[208],"these":[209],"results":[210],"suggest":[211],"reduce":[216],"control":[222],"while":[223],"revealing":[224],"interpretable":[225],"structure.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":8}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}