{"id":"https://openalex.org/W7220986366","doi":"https://doi.org/10.48550/arxiv.2610.08150","title":"ViDAL: A Visual Dynamics-Grounded Action Latent Space for Vision-Language-Action Models","display_name":"ViDAL: A Visual Dynamics-Grounded Action Latent Space for Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-10-06","ids":{"openalex":"https://openalex.org/W7220986366","doi":"https://doi.org/10.48550/arxiv.2610.08150"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.08150","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.08150","pdf_url":"https://arxiv.org/pdf/2610.08150","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/2610.08150","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157950351","display_name":"Yuan Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Yuan","raw_affiliation_strings":["Alibaba Group FiveAges"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group FiveAges","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157987437","display_name":"Yixiang Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Yixiang","raw_affiliation_strings":["Alibaba Group FiveAges"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group FiveAges","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157948586","display_name":"Qisen Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Qisen","raw_affiliation_strings":["Alibaba Group FiveAges"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group FiveAges","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157973065","display_name":"Jiabing Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Jiabing","raw_affiliation_strings":["Alibaba Group FiveAges"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group FiveAges","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157904079","display_name":"Peiyan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Peiyan","raw_affiliation_strings":["Alibaba Group FiveAges"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group FiveAges","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157948448","display_name":"Kai Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Kai","raw_affiliation_strings":["Alibaba Group FiveAges"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group FiveAges","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157953532","display_name":"Jianhua Yang","orcid":"https://orcid.org/0000-0002-5455-1874","observed_orcids":["https://orcid.org/0000-0002-5455-1874"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Jianhua","raw_affiliation_strings":["Alibaba Group FiveAges"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group FiveAges","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079767760","display_name":"Jianlou Si","orcid":"https://orcid.org/0000-0002-2029-6588","observed_orcids":["https://orcid.org/0000-0002-2029-6588","https://orcid.org/0000-0002-4220-5667"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Si, Jianlou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157943919","display_name":"Jun Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Jun","raw_affiliation_strings":["Alibaba Group FiveAges"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group FiveAges","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157888391","display_name":"Jing Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Jing","raw_affiliation_strings":["Alibaba Group FiveAges"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group FiveAges","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074100803","display_name":"Nianfeng Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Nianfeng","raw_affiliation_strings":["Alibaba Group FiveAges"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group FiveAges","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157981672","display_name":"Yan Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Yan","raw_affiliation_strings":["Alibaba Group FiveAges"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group FiveAges","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157951963","display_name":"Liang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Liang","raw_affiliation_strings":["Alibaba Group FiveAges"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group FiveAges","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.9214000105857849,"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":0.9214000105857849,"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":0.07180000096559525,"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":0.00419999985024333,"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":0.9879999756813049},{"id":"https://openalex.org/keywords/visual-dynamics","display_name":"visual dynamics","score":0.8600000143051147},{"id":"https://openalex.org/keywords/robot-policy-learning","display_name":"robot policy learning","score":0.9259999990463257},{"id":"https://openalex.org/keywords/dual-arm-robot","display_name":"dual-arm robot","score":0.5789999961853027},{"id":"https://openalex.org/keywords/franka-emika-robot","display_name":"Franka Emika robot","score":0.609000027179718},{"id":"https://openalex.org/keywords/libero-benchmark","display_name":"LIBERO benchmark","score":0.7720000147819519}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7833999991416931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6717000007629395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664000153541565},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6650999784469604},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5620999932289124},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3544999957084656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2962000072002411},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.08150","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.08150","pdf_url":"https://arxiv.org/pdf/2610.08150","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.2610.08150","doi":"https://doi.org/10.48550/arxiv.2610.08150","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.08150","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:2610.08150","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.08150","pdf_url":"https://arxiv.org/pdf/2610.08150","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":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220986366.pdf","grobid_xml":"https://content.openalex.org/works/W7220986366.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W4297808394","https://openalex.org/W4385430674","https://openalex.org/W4385430679","https://openalex.org/W4389115686","https://openalex.org/W4399695759","https://openalex.org/W4402354047","https://openalex.org/W4402387301","https://openalex.org/W4403364995","https://openalex.org/W4409092337","https://openalex.org/W4414051084","https://openalex.org/W4414079054","https://openalex.org/W4414674749","https://openalex.org/W4414901575","https://openalex.org/W4414921730","https://openalex.org/W4415183980","https://openalex.org/W4415346794","https://openalex.org/W4417011628","https://openalex.org/W4417086207","https://openalex.org/W4417087106","https://openalex.org/W4417252820","https://openalex.org/W4417261359","https://openalex.org/W6948104436","https://openalex.org/W7128621118","https://openalex.org/W7130552073","https://openalex.org/W7131686095","https://openalex.org/W7135069019","https://openalex.org/W7135085452","https://openalex.org/W7214960512"],"related_works":["https://openalex.org/W7147055570","https://openalex.org/W7163867220","https://openalex.org/W7164919993","https://openalex.org/W7215088143","https://openalex.org/W7106709520","https://openalex.org/W7160159555","https://openalex.org/W7161110949","https://openalex.org/W7204783650","https://openalex.org/W4414921730","https://openalex.org/W7214761167"],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2],"have":[3],"become":[4],"a":[5,50,107,137],"central":[6],"paradigm":[7],"for":[8],"robot":[9,99,176],"policy":[10,140],"learning,":[11],"which":[12],"predict":[13],"actions":[14],"in":[15,61],"three":[16],"forms:":[17],"raw":[18],"action":[19,22,26,30,34,59,72,85,109],"chunks,":[20],"discrete":[21],"tokens,":[23],"or":[24],"continuous":[25,58],"latents.":[27],"However,":[28],"existing":[29],"representations":[31],"primarily":[32],"model":[33],"trajectories,":[35],"with":[36,91,112,132],"limited":[37],"consideration":[38],"of":[39,66],"the":[40,62,67,101],"visual":[41,64],"dynamics":[42,65],"induced":[43],"by":[44,75],"these":[45],"actions.":[46],"We":[47],"introduce":[48],"ViDAL,":[49],"Visual":[51],"Dynamics-grounded":[52],"Action":[53,78,103],"Latent":[54],"Space":[55],"that":[56],"anchors":[57],"latents":[60],"future":[63,92],"scene.":[68],"Specifically,":[69],"ViDAL":[70,126],"learns":[71],"latent":[73,90],"space":[74],"training":[76],"an":[77,122],"Variational":[79],"Autoencoder":[80],"(Action":[81],"VAE)":[82],"to":[83,146,152],"reconstruct":[84],"chunks":[86],"while":[87],"aligning":[88],"its":[89],"scene":[93],"dynamics.":[94],"When":[95],"integrated":[96],"into":[97],"downstream":[98],"policies,":[100],"proposed":[102],"VAE":[104],"serves":[105],"as":[106,121],"plug-in":[108],"interface":[110],"compatible":[111],"multiple":[113],"VLA":[114],"architectures":[115],"and":[116,149,161,164,173],"enables":[117],"optional":[118],"future-video":[119],"prediction":[120],"additional":[123],"capability.":[124],"Empirically,":[125],"outperforms":[127],"competitive":[128],"baselines":[129],"on":[130,141,169],"LIBERO":[131],"98.1%":[133],"average":[134],"success,":[135],"improves":[136],"multi-task":[138],"$\u03c0_{0.5}$":[139],"RoboTwin":[142],"2.0":[143],"from":[144,150],"54.3%":[145],"65.5%":[147],"(Clean)":[148],"33.2%":[151],"43.1%":[153],"(Random)":[154],"success":[155],"rates":[156],"over":[157],"50":[158],"dual-arm":[159,174],"tasks,":[160],"yields":[162],"20.0%":[163],"23.4%":[165],"absolute":[166],"success-rate":[167],"gains":[168],"real-world":[170],"single-arm":[171],"Franka":[172],"ARX":[175],"platforms.":[177]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-09T00:00:00"}
