{"id":"https://openalex.org/W7223250865","doi":"https://doi.org/10.48550/arxiv.2610.30120","title":"ALPS: Visual State Encoders for World Models","display_name":"ALPS: Visual State Encoders for World Models","publication_year":2026,"publication_date":"2026-10-21","ids":{"openalex":"https://openalex.org/W7223250865","doi":"https://doi.org/10.48550/arxiv.2610.30120"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.30120","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.30120","pdf_url":"https://arxiv.org/pdf/2610.30120","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"},"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/2610.30120","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159292704","display_name":"Yanqing Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Yanqing","raw_affiliation_strings":["University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159281723","display_name":"Letian Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Letian","raw_affiliation_strings":["University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159268029","display_name":"Chengzhi Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Chengzhi","raw_affiliation_strings":["University of California , Santa Barbara"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159258470","display_name":"Zijun Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Zijun","raw_affiliation_strings":["University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077206511","display_name":"Jieru Mei","orcid":"https://orcid.org/0000-0002-4710-9463","observed_orcids":["https://orcid.org/0000-0002-4710-9463"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mei, Jieru","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068755696","display_name":"Hongliang Fei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei, Hongliang","raw_affiliation_strings":["Google"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159282556","display_name":"Yuyin Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Yuyin","raw_affiliation_strings":["University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159269101","display_name":"Cihang Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xie, Cihang","raw_affiliation_strings":["University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]}],"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":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":0.7900000214576721,"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":0.7900000214576721,"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":0.10499999672174454,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.04340000078082085,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/world-models","display_name":"world models","score":0.9940000176429749},{"id":"https://openalex.org/keywords/language-alignment","display_name":"language alignment","score":0.7170000076293945},{"id":"https://openalex.org/keywords/pixel-reconstruction","display_name":"pixel reconstruction","score":0.9710000157356262},{"id":"https://openalex.org/keywords/libero-benchmark","display_name":"LIBERO benchmark","score":0.6150000095367432},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.45899999141693115},{"id":"https://openalex.org/keywords/visual-inspection","display_name":"visual inspection","score":0.38499999046325684},{"id":"https://openalex.org/keywords/patch-tokens","display_name":"patch tokens","score":0.3659999966621399}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7914000153541565},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7324000000953674},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.6470000147819519},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.597000002861023},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5932999849319458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.579200029373169},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4611999988555908},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3352000117301941},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C178278151","wikidata":"https://www.wikidata.org/wiki/Q7936607","display_name":"Visual memory","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.30120","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.30120","pdf_url":"https://arxiv.org/pdf/2610.30120","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.2610.30120","doi":"https://doi.org/10.48550/arxiv.2610.30120","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.30120","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.30120","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.30120","pdf_url":"https://arxiv.org/pdf/2610.30120","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223250865.pdf","grobid_xml":"https://content.openalex.org/works/W7223250865.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W3094502228","https://openalex.org/W3213836217","https://openalex.org/W4221159977","https://openalex.org/W4294435908","https://openalex.org/W4366208220","https://openalex.org/W4385431288","https://openalex.org/W4390091477","https://openalex.org/W4394868314","https://openalex.org/W4396786754","https://openalex.org/W4399657827","https://openalex.org/W4401202545","https://openalex.org/W4404360744","https://openalex.org/W4404988257","https://openalex.org/W4405095407","https://openalex.org/W4406191642","https://openalex.org/W4407310663","https://openalex.org/W4407815020","https://openalex.org/W4417261359","https://openalex.org/W4417271208","https://openalex.org/W6910554155","https://openalex.org/W6947949040","https://openalex.org/W6948101618","https://openalex.org/W6979267127","https://openalex.org/W7083083501","https://openalex.org/W7118009763","https://openalex.org/W7125507447","https://openalex.org/W7140141371","https://openalex.org/W7140205376","https://openalex.org/W7154379977","https://openalex.org/W7154477368","https://openalex.org/W7163996718","https://openalex.org/W7164506104","https://openalex.org/W7204197618"],"related_works":["https://openalex.org/W4415058764","https://openalex.org/W4414809328","https://openalex.org/W7223071726","https://openalex.org/W7215782878","https://openalex.org/W7213998990","https://openalex.org/W7202162548","https://openalex.org/W7171621232","https://openalex.org/W7215060812","https://openalex.org/W7214932816","https://openalex.org/W7222215483"],"abstract_inverted_index":{"World":[0],"models":[1,113],"turn":[2],"visual":[3,13,55,174,182],"representations":[4],"into":[5,171],"predictions":[6],"and":[7,22,34,73,84,88,125,160,162,191],"actions.":[8],"We":[9,176],"argue":[10],"that":[11,26,58],"their":[12],"foundation":[14,187],"should":[15],"combine":[16],"physical-state":[17],"information,":[18],"native":[19,146],"language":[20,123],"alignment,":[21],"pixel":[23,127],"reconstruction,":[24,83],"so":[25],"a":[27,53,63,77,96,185],"single":[28,64],"representation":[29],"can":[30],"support":[31],"prediction,":[32,190],"instruction,":[33],"inspection.":[35,175],"However,":[36],"existing":[37],"encoders":[38,153],"typically":[39],"specialize":[40],"in":[41,62,193],"only":[42,70],"one":[43],"or":[44,150],"two":[45],"of":[46,66],"these":[47],"capabilities;":[48],"we":[49,75],"therefore":[50],"introduce":[51],"ALPS,":[52],"pretrained":[54],"state":[56],"encoder":[57],"unifies":[59],"all":[60],"three":[61],"set":[65],"patch":[67],"tokens.":[68],"Using":[69],"still":[71],"images":[72],"text,":[74],"pretrain":[76],"ViT-B/16":[78],"from":[79],"scratch":[80],"with":[81,144],"language,":[82],"spatial":[85],"correspondence":[86],"objectives,":[87],"then":[89],"refine":[90],"it":[91],"via":[92],"cross-view":[93],"self-distillation.":[94],"In":[95],"unified":[97],"evaluation":[98],"across":[99,157],"fifteen":[100],"public":[101],"encoders,":[102],"ALPS":[103,131],"achieves":[104],"the":[105,115,134],"lowest":[106],"aggregate":[107],"LIBERO":[108,140],"state-probe":[109],"error":[110],"among":[111],"ViT-B":[112],"(matching":[114],"3.5x":[116],"larger":[117],"V-JEPA":[118],"2-L)":[119],"while":[120],"maintaining":[121],"strong":[122],"alignment":[124],"accurate":[126],"reconstruction.":[128],"Downstream,":[129],"frozen":[130],"tokens":[132,166],"reach":[133],"highest":[135],"mean":[136],"policy":[137],"success":[138],"on":[139,154],"(85.5%)":[141],"when":[142],"paired":[143],"our":[145],"text":[147],"tower,":[148],"match":[149],"exceed":[151],"leading":[152],"world-model":[155],"planning":[156],"PushT,":[158],"Wall,":[159],"Granular,":[161],"allow":[163],"predicted":[164],"future":[165],"to":[167],"be":[168],"decoded":[169],"directly":[170],"pixels":[172],"for":[173,188],"hope":[177],"this":[178],"work":[179],"helps":[180],"establish":[181],"pretraining":[183],"as":[184],"shared":[186],"understanding,":[189],"action":[192],"world":[194],"models.":[195]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-23T00:00:00"}
