{"id":"https://openalex.org/W7214801407","doi":"https://doi.org/10.48550/arxiv.2609.33464","title":"VIDEAS: Distilling Explicit Action Semantics from Demonstration Videos for World Models via Prior-Guided Simulation","display_name":"VIDEAS: Distilling Explicit Action Semantics from Demonstration Videos for World Models via Prior-Guided Simulation","publication_year":2026,"publication_date":"2026-09-27","ids":{"openalex":"https://openalex.org/W7214801407","doi":"https://doi.org/10.48550/arxiv.2609.33464"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.33464","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33464","pdf_url":"https://arxiv.org/pdf/2609.33464","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/2609.33464","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153516400","display_name":"Jianan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Jianan","raw_affiliation_strings":["College of Computer Science and Technology , National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology , National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153451797","display_name":"Haoquan Zhai","orcid":"https://orcid.org/0009-0008-6991-9097","observed_orcids":["https://orcid.org/0009-0008-6991-9097"]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhai, Haoquan","raw_affiliation_strings":["School of Electronic, Electrical and Communication Engineering , University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic, Electrical and Communication Engineering , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153035232","display_name":"Siyang Zhang","orcid":"https://orcid.org/0000-0002-3349-5375","observed_orcids":["https://orcid.org/0000-0002-3349-5375"]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Siyang","raw_affiliation_strings":["College of Computer Science and Technology , National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology , National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153546421","display_name":"Bin Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bin","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153477683","display_name":"Juan Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Juan","raw_affiliation_strings":["College of Computer Science and Technology , National University of Defense Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology , National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123473315","display_name":"Jingtao Qi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi, Jingtao","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153447905","display_name":"Zhuo Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhuo","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100761561","display_name":"Enze Wang","orcid":"https://orcid.org/0000-0003-2521-063X","observed_orcids":["https://orcid.org/0000-0003-2521-063X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Enze","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153492431","display_name":"Haoxiang Jin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Haoxiang","raw_affiliation_strings":["Intelligent Game and Decision Lab (IGDL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Game and Decision Lab (IGDL)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5146462436","display_name":"Chen Qian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian, Chen","raw_affiliation_strings":["School of Artificial Intelligence , Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"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/T10653","display_name":"Robot Manipulation and Learning","score":0.3100999891757965,"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":0.3100999891757965,"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":0.2451999932527542,"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":0.219200000166893,"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-models","display_name":"world models","score":0.9869999885559082},{"id":"https://openalex.org/keywords/action-semantics","display_name":"action semantics","score":0.7179999947547913},{"id":"https://openalex.org/keywords/demonstration-videos","display_name":"demonstration videos","score":0.7910000085830688},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7739999890327454},{"id":"https://openalex.org/keywords/dataset-distillation","display_name":"dataset distillation","score":0.6650000214576721},{"id":"https://openalex.org/keywords/physical-dynamics","display_name":"physical dynamics","score":0.4650000035762787},{"id":"https://openalex.org/keywords/embodied-reasoning","display_name":"embodied reasoning","score":0.5419999957084656},{"id":"https://openalex.org/keywords/cognitive-bias-mitigation","display_name":"cognitive bias mitigation","score":0.5220000147819519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648000121116638},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5909000039100647},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5562999844551086},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4514999985694885},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.36419999599456787},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C150607116","wikidata":"https://www.wikidata.org/wiki/Q4677421","display_name":"Action semantics","level":5,"score":0.3244999945163727},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30880001187324524},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C156325763","wikidata":"https://www.wikidata.org/wiki/Q1930895","display_name":"Operational semantics","level":3,"score":0.26019999384880066},{"id":"https://openalex.org/C39920170","wikidata":"https://www.wikidata.org/wiki/Q693083","display_name":"Soundness","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.33464","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33464","pdf_url":"https://arxiv.org/pdf/2609.33464","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.33464","doi":"https://doi.org/10.48550/arxiv.2609.33464","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.33464","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:2609.33464","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.33464","pdf_url":"https://arxiv.org/pdf/2609.33464","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/W7214801407.pdf","grobid_xml":"https://content.openalex.org/works/W7214801407.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W2795843265","https://openalex.org/W2923016229","https://openalex.org/W2964094654","https://openalex.org/W3040046528","https://openalex.org/W3207758636","https://openalex.org/W4386076428","https://openalex.org/W4389520747","https://openalex.org/W4392427358","https://openalex.org/W4401306886","https://openalex.org/W4402671260","https://openalex.org/W4402716105","https://openalex.org/W4402727736","https://openalex.org/W4403788204","https://openalex.org/W4407794264","https://openalex.org/W4409147637","https://openalex.org/W4413144616","https://openalex.org/W4414581307","https://openalex.org/W4414939355","https://openalex.org/W4415058764","https://openalex.org/W4415162380","https://openalex.org/W4416036799","https://openalex.org/W4416131829","https://openalex.org/W4416748371","https://openalex.org/W4416750979","https://openalex.org/W4417261359","https://openalex.org/W6948279226","https://openalex.org/W7104030085","https://openalex.org/W7125169144","https://openalex.org/W7133861738","https://openalex.org/W7166838576","https://openalex.org/W7196933803"],"related_works":["https://openalex.org/W7124421528","https://openalex.org/W7214058556","https://openalex.org/W7160406480","https://openalex.org/W7161006933","https://openalex.org/W7164027667","https://openalex.org/W7222993935","https://openalex.org/W7204573472","https://openalex.org/W7166648824","https://openalex.org/W7168142037","https://openalex.org/W7163680241"],"abstract_inverted_index":{"World":[0],"models":[1,24,84,144],"learn":[2],"internal":[3],"representations":[4],"of":[5,141],"environment":[6,110],"dynamics":[7,60],"to":[8,14,32,86,111,122,130],"predict":[9],"future":[10],"states,":[11],"enabling":[12],"agents":[13],"optimize":[15],"action":[16,36,66,78,91,165],"plans":[17],"without":[18],"physical":[19,30,59,97,170],"interactions.":[20],"However,":[21],"developing":[22],"world":[23,143],"that":[25,56,157],"genuinely":[26],"internalize":[27],"underlying":[28],"causal":[29],"laws":[31],"explicitly":[33],"reason":[34],"about":[35],"preconditions":[37,92],"and":[38,80,93,126,172],"subsequent":[39],"state":[40],"transitions":[41],"remains":[42],"an":[43,138],"open":[44],"challenge.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,99,118,135],"propose":[50],"VIDEAS,":[51],"a":[52,101,108],"data":[53,128],"distillation":[54],"framework":[55],"transforms":[57],"continuous":[58],"from":[61,151],"operational":[62],"videos":[63],"into":[64,76],"explicit":[65],"semantics":[67],"for":[68],"foundation":[69],"models.":[70],"Specifically,":[71],"it":[72],"deconstructs":[73],"visual":[74],"demonstrations":[75],"discrete":[77],"trajectories":[79,121],"utilizes":[81],"advanced":[82],"vision-language":[83],"(VLMs)":[85],"extract":[87],"structured":[88],"knowledge":[89,124],"encapsulating":[90],"effects.":[94],"To":[95],"ensure":[96],"consistency,":[98],"introduce":[100],"prior-guided":[102],"trajectory":[103],"simulation":[104],"mechanism":[105],"grounded":[106],"within":[107],"text-based":[109],"rigorously":[112],"validate":[113],"the":[114],"extracted":[115],"knowledge.":[116],"Notably,":[117],"incorporate":[119],"negative":[120],"enrich":[123],"completeness":[125],"enhance":[127],"diversity":[129],"mitigate":[131],"cognitive":[132],"bias.":[133],"Furthermore,":[134],"present":[136],"VIDEAS-WM,":[137],"8B/9B-parameter":[139],"suite":[140],"language-based":[142],"trained":[145],"on":[146],"34K":[147],"high-quality":[148],"samples":[149],"derived":[150],"AgiBot-World":[152],"dataset.":[153],"Extensive":[154],"experiments":[155],"demonstrate":[156],"VIDEAS-WM":[158],"establishes":[159],"state-of-the-art":[160],"performance":[161],"in":[162],"high-level":[163],"embodied":[164],"semantic":[166],"reasoning,":[167],"exhibiting":[168],"profound":[169],"understanding":[171],"robust":[173],"generalization":[174],"across":[175],"unseen":[176],"scenarios.":[177]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}