{"id":"https://openalex.org/W7204202043","doi":"https://doi.org/10.48550/arxiv.2608.22750","title":"MOSH-WM: Mask-Grounded Soft-Hamiltonian Dynamics for Object-Centric World Models","display_name":"MOSH-WM: Mask-Grounded Soft-Hamiltonian Dynamics for Object-Centric World Models","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204202043","doi":"https://doi.org/10.48550/arxiv.2608.22750"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22750","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22750","pdf_url":"https://arxiv.org/pdf/2608.22750","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22750","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124339914","display_name":"Zhekai Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zhekai","raw_affiliation_strings":["Beijing Institute of Technology","Equal contribution"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Equal contribution","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113987202","display_name":"Haoxiang Huang","orcid":"https://orcid.org/0009-0007-3354-4425","observed_orcids":["https://orcid.org/0009-0007-3354-4425"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Haoxiang","raw_affiliation_strings":["Equal contribution","University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal contribution","institution_ids":[]},{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125953254","display_name":"Xiang Liu","orcid":"https://orcid.org/0000-0001-6720-0371","observed_orcids":["https://orcid.org/0000-0001-6720-0371","https://orcid.org/0000-0001-9815-2579"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Xiang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123649693","display_name":"Zhikang Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Zhikang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137569646","display_name":"Yueqing Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yueqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125572529","display_name":"Qi Gu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127984385","display_name":"Shiji Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Shiji","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133320044","display_name":"Miao Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Miao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5151595590","display_name":"Sen Cui","orcid":"https://orcid.org/0000-0002-9517-1923","observed_orcids":["https://orcid.org/0000-0002-9517-1923"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cui, Sen","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8925999999046326,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8925999999046326,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.04340000078082085,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.010200000368058681,"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/error-accumulation","display_name":"error accumulation","score":0.382999986410141}],"concepts":[{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.7019000053405762},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6243000030517578},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5821999907493591},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5257999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48809999227523804},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4575999975204468},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4514000117778778},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40630000829696655},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38199999928474426},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C129537906","wikidata":"https://www.wikidata.org/wiki/Q7603913","display_name":"State variable","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C204707403","wikidata":"https://www.wikidata.org/wiki/Q1152398","display_name":"Canonical form","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22750","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22750","pdf_url":"https://arxiv.org/pdf/2608.22750","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.2608.22750","doi":"https://doi.org/10.48550/arxiv.2608.22750","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22750","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:2608.22750","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22750","pdf_url":"https://arxiv.org/pdf/2608.22750","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":[],"sustainable_development_goals_aurora":[{"display_name":"Affordable and clean energy","score":0.7204740047454834,"id":"https://metadata.un.org/sdg/7"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204202043.pdf","grobid_xml":"https://content.openalex.org/works/W7204202043.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7147297612","https://openalex.org/W7134050592","https://openalex.org/W7202342342","https://openalex.org/W4306176903","https://openalex.org/W7160376398","https://openalex.org/W7220902636","https://openalex.org/W7163181597","https://openalex.org/W7214573510","https://openalex.org/W7221835266","https://openalex.org/W4391631338"],"abstract_inverted_index":{"Object-centric":[0],"world":[1,30],"models":[2],"forecast":[3],"future":[4],"videos":[5],"by":[6,126,131],"evolving":[7],"a":[8,27,57,66,70,75,87],"set":[9],"of":[10,53],"entity":[11],"slots,":[12],"but":[13],"the":[14,102,119,135,148,152,166,174],"variables":[15],"receiving":[16],"dynamics":[17],"supervision":[18],"are":[19,83,155],"often":[20],"unconstrained":[21],"visual":[22,89,160],"features.":[23],"We":[24],"introduce":[25],"\\method{},":[26],"mask-grounded":[28],"soft-Hamiltonian":[29],"model":[31,168],"that":[32,165],"makes":[33],"its":[34],"position-like":[35],"state":[36,59,105],"explicitly":[37],"depend":[38],"on":[39],"slot-owned":[40],"image":[41],"support.":[42],"A":[43,91],"frozen":[44],"video-slot":[45],"encoder":[46],"produces":[47],"slots":[48],"and":[49,65,81,94,116,128,145,157,161],"masks;":[50],"spatial":[51,129],"moments":[52],"mask-owned":[54],"support":[55],"form":[56,63],"canonical":[58],"$Q$,":[60],"temporal":[61],"differences":[62],"$P$,":[64],"learned":[67,77],"energy":[68],"supplies":[69],"soft":[71],"directional":[72],"bias":[73],"to":[74,106,134],"bounded":[76,95],"increment.":[78],"Decoder-relevant":[79],"appearance":[80],"identity":[82],"stored":[84],"separately":[85],"in":[86],"causal":[88],"context.":[90],"gated":[92],"composer":[93],"residual":[96],"then":[97],"combine":[98],"this":[99],"context":[100],"with":[101],"propagated":[103],"phase":[104],"reconstruct":[107],"decoder-compatible":[108],"slots.":[109],"On":[110,139],"OBJ3D,":[111],"given":[112,141],"six":[113,142],"observed":[114,143],"frames":[115,144],"evaluated":[117,146],"over":[118,147],"following":[120,149],"30":[121],"frames,":[122,151],"\\method{}":[123],"reduces":[124],"LPIPS":[125],"25.0\\%":[127],"MSE":[130],"33.7\\%":[132],"relative":[133],"strongest":[136],"object-centric":[137],"baseline.":[138],"CLEVRER,":[140],"ten":[150],"corresponding":[153],"reductions":[154],"14.5\\%":[156],"18.7\\%.":[158],"Horizon-resolved":[159],"object-state":[162],"measurements":[163],"show":[164],"complete":[167],"accumulates":[169],"error":[170],"more":[171],"slowly":[172],"throughout":[173],"30-frame":[175],"closed-loop":[176],"rollout.":[177],"Project":[178],"page:https://github.com/moshwm-anon/-moshwm-anon.github.io.":[179]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}
