{"id":"https://openalex.org/W7138138930","doi":"https://doi.org/10.1609/aaai.v40i22.38903","title":"Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling","display_name":"Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138138930","doi":"https://doi.org/10.1609/aaai.v40i22.38903"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i22.38903","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38903","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i22.38903","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129730639","display_name":"Hao Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Li","raw_affiliation_strings":["University of Science and Technology of China\nShanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China\nShanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129718435","display_name":"Shuai Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I4210164862","display_name":"Artificial Intelligence in Medicine (Canada)","ror":"https://ror.org/05p590m36","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210164862"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Shuai Yang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory\nZhejiang University"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory\nZhejiang University","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I4210164862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129712693","display_name":"Yilun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilun Chen","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129736479","display_name":"Xinyi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Chen","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040461965","display_name":"Xiaoda Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoda Yang","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129700953","display_name":"Yang Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Tian","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129643584","display_name":"Hanqing Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanqing Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129685773","display_name":"Tai Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tai Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129650621","display_name":"Dahua Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dahua Lin","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129730650","display_name":"Feng Zhao","orcid":null},"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":"Feng Zhao","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129693096","display_name":"Jiangmiao Pang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangmiao Pang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5129730639"],"corresponding_institution_ids":["https://openalex.org/I4210100255"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"22","first_page":"18388","last_page":"18396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8188999891281128,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8188999891281128,"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":0.03880000114440918,"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":0.025499999523162842,"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/robustness","display_name":"Robustness (evolution)","score":0.8069999814033508},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7602999806404114},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6004999876022339},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5508999824523926},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4162999987602234},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.39820000529289246},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.3610000014305115},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.3411000072956085}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8069999814033508},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7602999806404114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322999835014343},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6004999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.573199987411499},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5508999824523926},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5196999907493591},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.39820000529289246},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.3610000014305115},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3061999976634979},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i22.38903","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38903","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i22.38903","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38903","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"vision-language-action":[1],"(VLA)":[2],"models":[3,8,19,64],"built":[4],"on":[5,77,177,184,191],"pretrained":[6],"vision-language":[7,91,102],"(VLMs)":[9],"have":[10],"demonstrated":[11],"strong":[12],"performance":[13,168],"in":[14,158],"robotic":[15],"manipulation.":[16],"However,":[17],"these":[18],"remain":[20],"constrained":[21],"by":[22,36],"the":[23,32,66,98,101,120,131,187,194],"single-frame":[24,62],"image":[25],"paradigm":[26],"and":[27,51,110,135,150,160,169,186],"fail":[28],"to":[29,65,107],"fully":[30],"leverage":[31],"temporal":[33,134],"information":[34,113],"offered":[35],"multi-frame":[37,67,124,198],"histories,":[38],"as":[39],"directly":[40],"feeding":[41],"multiple":[42],"frames":[43],"into":[44],"VLM":[45],"backbones":[46],"incurs":[47],"substantial":[48],"computational":[49],"overhead":[50],"inference":[52],"latency.":[53],"We":[54],"propose":[55],"CronusVLA,":[56],"a":[57,71,141,173,179],"unified":[58],"framework":[59],"that":[60,164],"extends":[61],"VLA":[63,202],"paradigm.":[68],"CronusVLA":[69,117,165],"follows":[70],"two-stage":[72],"process:":[73],"(1)":[74],"Single-frame":[75],"pretraining":[76],"large-scale":[78],"embodied":[79,90],"datasets":[80],"with":[81,172],"autoregressive":[82],"prediction":[83,99],"of":[84,100,123,147,196],"action":[85],"tokens,":[86],"establishing":[87],"an":[88],"effective":[89],"foundation;":[92],"(2)":[93],"Multi-frame":[94],"post-training,":[95],"which":[96],"adapts":[97],"backbone":[103],"from":[104],"discrete":[105],"tokens":[106],"learnable":[108],"features,":[109],"aggregates":[111],"historical":[112],"via":[114],"feature":[115],"chunking.":[116],"effectively":[118],"addresses":[119],"existing":[121],"challenges":[122],"modeling":[125],"while":[126],"enhancing":[127],"performance.":[128],"To":[129],"evaluate":[130],"robustness":[132,189],"under":[133],"spatial":[136],"disturbances,":[137],"we":[138],"introduce":[139],"SimplerEnv-OR,":[140,192],"novel":[142],"benchmark":[143],"featuring":[144],"24":[145],"types":[146],"observational":[148],"disturbances":[149],"120":[151],"severity":[152],"levels.":[153],"Experiments":[154],"across":[155],"three":[156],"embodiments":[157],"simulated":[159],"real-world":[161,201],"environments":[162],"demonstrate":[163],"achieves":[166],"leading":[167],"superior":[170],"robustness,":[171],"70.9%":[174],"success":[175],"rate":[176],"SimplerEnv,":[178],"26.8%":[180],"improvement":[181],"over":[182],"OpenVLA":[183],"LIBERO,":[185],"highest":[188],"score":[190],"showing":[193],"promise":[195],"efficient":[197],"adaptation":[199],"for":[200],"deployment.":[203]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}