{"id":"https://openalex.org/W7215782878","doi":"https://doi.org/10.48550/arxiv.2610.00575","title":"Token-World: World Modeling in Vision-Language Model Token Space for Robot Manipulation","display_name":"Token-World: World Modeling in Vision-Language Model Token Space for Robot Manipulation","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7215782878","doi":"https://doi.org/10.48550/arxiv.2610.00575"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.00575","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00575","pdf_url":"https://arxiv.org/pdf/2610.00575","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/2610.00575","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134269825","display_name":"Chuyao Fu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Chuyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5156093822","display_name":"Xiaowei Chi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chi, Xiaowei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019431040","display_name":"Yuhan Rui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui, Yuhan","raw_affiliation_strings":["MUKA Robotics","Southern University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MUKA Robotics","institution_ids":[]},{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155835428","display_name":"Yu-kai Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yu-kai","raw_affiliation_strings":["MUKA Robotics","State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MUKA Robotics","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129091190","display_name":"Zezhong Qian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian, Zezhong","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5156253297","display_name":"Xiaojie Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhang, Xiaojie","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128886746","display_name":"Yunfan Lou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lou, Yunfan","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5154680792","display_name":"Kevin Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Kevin","raw_affiliation_strings":["MUKA Robotics","State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MUKA Robotics","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115638338","display_name":"Kuangzhi Ge","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ge, Kuangzhi","raw_affiliation_strings":["MUKA Robotics","State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MUKA Robotics","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155750785","display_name":"Chak Wing Mak","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mak, Chak Wing","raw_affiliation_strings":["MUKA Robotics","State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MUKA Robotics","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5154487920","display_name":"Zhiyang Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Zhiyang","raw_affiliation_strings":["MUKA Robotics","State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MUKA Robotics","institution_ids":[]},{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139181609","display_name":"Athena Zhuoming Zhong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong, Athena Zhuoming","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155378206","display_name":"Hongyang Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hongyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155766114","display_name":"Haoran Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Haoran","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045081171","display_name":"Yike Guo","orcid":"https://orcid.org/0000-0002-3075-2161","observed_orcids":["https://orcid.org/0000-0002-3075-2161","https://orcid.org/0009-0005-8401-282X","https://orcid.org/0000-0002-4026-2983"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Guo, Yike","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021255269","display_name":"Sirui Han","orcid":"https://orcid.org/0000-0001-7303-0671","observed_orcids":["https://orcid.org/0000-0001-7303-0671"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Han, Sirui","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5154388339","display_name":"Shanghang Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Shanghang","raw_affiliation_strings":["State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimedia Information Processing , School of Computer Science , Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.5321999788284302,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5321999788284302,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4507000148296356,"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":0.007799999788403511,"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/world-modeling","display_name":"world modeling","score":0.8769999742507935},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8730000257492065},{"id":"https://openalex.org/keywords/visual-tokens","display_name":"visual tokens","score":0.7200000286102295},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.9359999895095825},{"id":"https://openalex.org/keywords/state-compression","display_name":"state compression","score":0.49900001287460327},{"id":"https://openalex.org/keywords/future-state-prediction","display_name":"future state prediction","score":0.6449999809265137},{"id":"https://openalex.org/keywords/closed-loop-evaluation","display_name":"closed-loop evaluation","score":0.45399999618530273},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196999788284302},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5358999967575073},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5328999757766724},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5228000283241272},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44609999656677246},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4359999895095825},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3440999984741211},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3116999864578247},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29440000653266907},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2705000042915344},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.00575","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00575","pdf_url":"https://arxiv.org/pdf/2610.00575","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.2610.00575","doi":"https://doi.org/10.48550/arxiv.2610.00575","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.00575","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:2610.00575","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00575","pdf_url":"https://arxiv.org/pdf/2610.00575","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215782878.pdf","grobid_xml":"https://content.openalex.org/works/W7215782878.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2795843265","https://openalex.org/W2992977009","https://openalex.org/W2998108143","https://openalex.org/W4394861491","https://openalex.org/W4398192846","https://openalex.org/W4399695759","https://openalex.org/W4403578364","https://openalex.org/W4404360744","https://openalex.org/W4405470261","https://openalex.org/W4414079054","https://openalex.org/W4414581984","https://openalex.org/W4414674749","https://openalex.org/W4415273528","https://openalex.org/W4415332750","https://openalex.org/W4415336982","https://openalex.org/W4416236772","https://openalex.org/W4416254450","https://openalex.org/W4416780398","https://openalex.org/W4417261359","https://openalex.org/W6910795718","https://openalex.org/W6929480010","https://openalex.org/W6947949040","https://openalex.org/W7083695050","https://openalex.org/W7106013284","https://openalex.org/W7116915969","https://openalex.org/W7119723348","https://openalex.org/W7129725900","https://openalex.org/W7147055570","https://openalex.org/W7151595925","https://openalex.org/W7151757339","https://openalex.org/W7155227085","https://openalex.org/W7160875620","https://openalex.org/W7163328665","https://openalex.org/W7164919993"],"related_works":["https://openalex.org/W7202162548","https://openalex.org/W7213998990","https://openalex.org/W7222215483","https://openalex.org/W7204184769","https://openalex.org/W7214176126","https://openalex.org/W7160875620","https://openalex.org/W4416716729","https://openalex.org/W7135076397","https://openalex.org/W7164506104","https://openalex.org/W7204081175"],"abstract_inverted_index":{"A":[0,52],"common":[1],"approach":[2],"to":[3,11,102],"world-model":[4,123],"simulation":[5,28,154],"for":[6,107],"vision-language-action":[7],"(VLA)":[8],"systems":[9],"is":[10,55],"predict":[12],"future":[13,91],"RGB":[14],"observations":[15],"and":[16,29,65,97,118,162],"then":[17],"re-encode":[18],"them":[19],"into":[20,85],"policy":[21,31,137,144],"inputs,":[22],"introducing":[23],"an":[24,77],"indirect":[25],"interface":[26],"between":[27],"downstream":[30,108],"execution.":[32],"We":[33],"instead":[34],"investigate":[35],"whether":[36],"world":[37,79],"dynamics":[38,68,92],"can":[39],"be":[40,170],"modeled":[41],"in":[42,93],"a":[43,86],"compact,":[44],"policy-oriented":[45],"state":[46],"derived":[47],"from":[48],"VLM":[49,58,83],"visual":[50,59],"tokens.":[51],"key":[53],"challenge":[54],"that":[56,81,159],"raw":[57],"tokens":[60],"are":[61],"high-dimensional,":[62],"making":[63],"efficient":[64],"accurate":[66],"autoregressive":[67],"modeling":[69],"challenging.":[70],"To":[71],"address":[72],"this,":[73],"we":[74],"introduce":[75],"Token-World,":[76],"action-conditioned":[78],"model":[80],"compresses":[82],"features":[84],"compact":[87],"token":[88],"state,":[89],"learns":[90],"this":[94],"reduced":[95],"space,":[96],"maps":[98],"predicted":[99],"states":[100],"back":[101],"the":[103],"original":[104],"policy-facing":[105],"representation":[106],"use.":[109],"Across":[110],"manipulation":[111],"benchmarks,":[112],"Token-World":[113],"improves":[114],"open-loop":[115],"feature":[116],"fidelity":[117],"policy-action":[119],"consistency":[120],"over":[121,128],"recent":[122],"simulators,":[124],"with":[125,142],"slower":[126],"degradation":[127],"long":[129],"rollout":[130],"horizons.":[131],"In":[132],"closed-loop":[133],"evaluation,":[134],"its":[135],"simulated":[136],"performance":[138,145],"correlates":[139],"more":[140],"strongly":[141],"reference":[143],"than":[146],"Ctrl-World":[147],"($r=0.794$":[148],"vs.\\":[149],"$0.583$),":[150],"while":[151],"requiring":[152],"lower":[153],"latency.":[155],"Ablations":[156],"further":[157],"show":[158],"compact-representation":[160],"design":[161],"dimensionality":[163],"substantially":[164],"affect":[165],"future-state":[166],"prediction.":[167],"Code":[168],"will":[169],"available":[171],"at":[172],"https://chuyaofu.github.io/Token-World/.":[173]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-03T00:00:00"}
