{"id":"https://openalex.org/W7155227085","doi":"https://doi.org/10.48550/arxiv.2604.19683","title":"Mask World Model: Predicting What Matters for Robust Robot Policy Learning","display_name":"Mask World Model: Predicting What Matters for Robust Robot Policy Learning","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155227085","doi":"https://doi.org/10.48550/arxiv.2604.19683"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.19683","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19683","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.2604.19683","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128886746","display_name":"Yunfan Lou","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lou, Yunfan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134246971","display_name":"Xiaowei Chi","orcid":null},"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/A5100718556","display_name":"Xiaojie Zhang","orcid":"https://orcid.org/0009-0005-6576-1876"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaojie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129091190","display_name":"Zezhong Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Zezhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134342036","display_name":"Chengxuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chengxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134235846","display_name":"Rongyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Rongyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121602472","display_name":"Yaoxu Lyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Yaoxu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134288709","display_name":"Guoyu Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Guoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134269825","display_name":"Chuyao Fu","orcid":null},"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/A5134354902","display_name":"Haoxuan Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Haoxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134330945","display_name":"Pengwei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Pengwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134344819","display_name":"Shanghang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shanghang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5128886746"],"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4551999866962433,"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":0.4551999866962433,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1826999932527542,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0723000019788742,"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/robustness","display_name":"Robustness (evolution)","score":0.6672000288963318},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4632999897003174},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.4474000036716461},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4020000100135803},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3828999996185303},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.3709000051021576},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.328000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218999862670898},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6672000288963318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6208000183105469},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.4474000036716461},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4090999960899353},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40799999237060547},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.30559998750686646},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3021000027656555},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2874999940395355},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.19683","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19683","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.2604.19683","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19683","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":{"World":[0,67],"models":[1],"derived":[2],"from":[3],"large-scale":[4],"video":[5,27,72],"generative":[6],"pre-training":[7],"have":[8],"emerged":[9],"as":[10,38],"a":[11,88,116],"promising":[12],"paradigm":[13],"for":[14],"generalist":[15],"robot":[16],"policy":[17,118],"learning.":[18],"However,":[19],"standard":[20],"approaches":[21],"often":[22],"focus":[23],"on":[24,132],"high-fidelity":[25],"RGB":[26],"prediction,":[28],"this":[29,111],"can":[30],"result":[31],"in":[32],"overfitting":[33],"to":[34,50,54,75,95,120,166],"irrelevant":[35],"factors,":[36],"such":[37],"dynamic":[39],"backgrounds":[40],"and":[41,56,100,135,149,163],"illumination":[42],"changes.":[43],"These":[44],"distractions":[45],"reduce":[46],"the":[47,65,77,93,128,133,141],"model's":[48],"ability":[49],"generalize,":[51],"ultimately":[52],"leading":[53],"unreliable":[55],"fragile":[57],"control":[58],"policies.":[59],"To":[60],"address":[61],"this,":[62],"we":[63],"introduce":[64],"Mask":[66],"Model":[68],"(MWM),":[69],"which":[70],"leverages":[71],"diffusion":[73],"architectures":[74],"predict":[76],"evolution":[78],"of":[79,83,130],"semantic":[80],"masks":[81],"instead":[82],"pixels.":[84],"This":[85],"shift":[86],"imposes":[87],"geometric":[89],"information":[90,168],"bottleneck,":[91],"forcing":[92],"model":[94],"capture":[96],"essential":[97],"physical":[98],"dynamics":[99,113],"contact":[101],"relations":[102],"while":[103],"filtering":[104],"out":[105],"visual":[106],"noise.":[107],"We":[108],"seamlessly":[109],"integrate":[110],"mask":[112],"backbone":[114],"with":[115],"diffusion-based":[117],"head":[119],"enable":[121],"robust":[122,164],"end-to-end":[123],"control.":[124],"Extensive":[125],"evaluations":[126],"demonstrate":[127],"superiority":[129],"MWM":[131,158],"LIBERO":[134],"RLBench":[136],"simulation":[137],"benchmarks,":[138],"significantly":[139],"outperforming":[140],"state-of-the-art":[142],"RGB-based":[143],"world":[144],"models.":[145],"Furthermore,":[146],"real-world":[147],"experiments":[148],"robustness":[150],"evaluation":[151],"(via":[152],"random":[153],"token":[154],"pruning)":[155],"reveal":[156],"that":[157],"exhibits":[159],"superior":[160],"generalization":[161],"capabilities":[162],"resilience":[165],"texture":[167],"loss.":[169]},"counts_by_year":[],"updated_date":"2026-04-23T06:20:18.424754","created_date":"2026-04-23T00:00:00"}