{"id":"https://openalex.org/W7224116265","doi":"https://doi.org/10.48550/arxiv.2610.37381","title":"PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations","display_name":"PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224116265","doi":"https://doi.org/10.48550/arxiv.2610.37381"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.37381","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37381","pdf_url":"https://arxiv.org/pdf/2610.37381","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","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/2610.37381","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160060205","display_name":"Hanqing Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hanqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160005529","display_name":"Zhaotian Cai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Zhaotian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102639331","display_name":"Ruichuan An","orcid":"https://orcid.org/0009-0000-3758-4335","observed_orcids":["https://orcid.org/0009-0000-3758-4335","https://orcid.org/0009-0002-0376-1844"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"An, Ruichuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125526142","display_name":"Bohan Zeng","orcid":"https://orcid.org/0009-0009-0999-6231","observed_orcids":["https://orcid.org/0009-0009-0999-6231"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Bohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160044417","display_name":"Tao Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160037310","display_name":"Yilin Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yilin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160026516","display_name":"Xu Jiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033564217","display_name":"Kaiquan Chen","orcid":"https://orcid.org/0000-0003-2484-6644","observed_orcids":["https://orcid.org/0000-0003-2484-6644"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Kaiquan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160059566","display_name":"Chongyang Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Chongyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160044126","display_name":"Haoran Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160059619","display_name":"Fan Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160002275","display_name":"Mingan Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Mingan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160019192","display_name":"Wentao Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wentao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160028965","display_name":"Zenan Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zenan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032476044","display_name":"WU Youzheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Youzheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160827586","display_name":"Xiaodong He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Xiaodong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.9355000257492065,"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":0.9355000257492065,"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":0.029200000688433647,"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":0.02850000001490116,"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/vision-language-action-models","display_name":"vision-language-action models","score":0.9789999723434448},{"id":"https://openalex.org/keywords/video-world-models","display_name":"video world models","score":0.8849999904632568},{"id":"https://openalex.org/keywords/optical-flow-prediction","display_name":"optical flow prediction","score":0.6779999732971191},{"id":"https://openalex.org/keywords/simulation-benchmarking","display_name":"simulation benchmarking","score":0.48100000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753000259399414},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6593999862670898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5735999941825867},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5382999777793884},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4916999936103821},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41290000081062317},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34130001068115234},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3330000042915344},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.26750001311302185}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.37381","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37381","pdf_url":"https://arxiv.org/pdf/2610.37381","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.37381","doi":"https://doi.org/10.48550/arxiv.2610.37381","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.37381","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:2610.37381","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37381","pdf_url":"https://arxiv.org/pdf/2610.37381","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224116265.pdf","grobid_xml":"https://content.openalex.org/works/W7224116265.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7220986366","https://openalex.org/W7222573474","https://openalex.org/W4416716729","https://openalex.org/W7118852108","https://openalex.org/W7164812032","https://openalex.org/W4414975320","https://openalex.org/W7133354094","https://openalex.org/W7221543377","https://openalex.org/W7215088143","https://openalex.org/W7223154590"],"abstract_inverted_index":{"Vision--Language--Action":[0],"(VLA)":[1],"models":[2,22],"generate":[3],"robot":[4],"actions":[5],"from":[6,49],"visual":[7],"observations":[8],"and":[9,70,96,119,131,139],"language":[10],"instructions,":[11],"but":[12],"their":[13],"understanding":[14],"of":[15,66,109],"physical":[16,47],"dynamics":[17],"remains":[18],"limited.":[19],"Video":[20],"world":[21,81],"can":[23],"capture":[24],"scene":[25],"dynamics,":[26],"yet":[27],"generating":[28],"future":[29,67,126,136],"videos":[30],"introduces":[31],"high":[32],"latency":[33],"into":[34],"the":[35],"control":[36],"loop.":[37],"We":[38],"introduce":[39],"PDRVLA,":[40],"whose":[41],"lightweight":[42],"Physical":[43],"Dynamics":[44],"Module":[45],"extracts":[46],"tokens":[48],"vision--language":[50],"features":[51],"to":[52],"condition":[53],"action":[54,143],"generation":[55],"without":[56],"online":[57],"video":[58,80],"generation.":[59],"The":[60],"module":[61],"learns":[62],"through":[63,76,91],"direct":[64],"prediction":[65,127],"RGB,":[68],"depth,":[69],"optical-flow":[71],"features,":[72],"with":[73,128],"auxiliary":[74],"supervision":[75,130],"a":[77],"frozen":[78],"pretrained":[79],"model.":[82],"Training":[83],"relies":[84],"entirely":[85],"on":[86,111,114,117,121],"publicly":[87],"available":[88],"data,":[89],"expanded":[90],"human-to-robot":[92],"synthesis,":[93],"subtask":[94,134],"annotation,":[95],"embodied":[97],"chain-of-thought":[98],"(ECoT)":[99],"annotation.":[100],"Across":[101],"four":[102],"simulation":[103],"benchmarks,":[104],"PDRVLA":[105],"achieves":[106],"success":[107],"rates":[108],"99.3%":[110],"LIBERO,":[112],"89.9%":[113],"LIBERO-Plus,":[115],"93.6%":[116],"RoboTwin~2.0,":[118],"81.5%":[120],"SimplerEnv.":[122],"Ablations":[123],"show":[124],"improved":[125],"world-model":[129],"evaluate":[132],"how":[133],"conditioning,":[135],"object-pose":[137],"supervision,":[138],"ECoT":[140],"training":[141],"affect":[142],"success.":[144]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-29T00:00:00"}