{"id":"https://openalex.org/W4411449683","doi":"https://doi.org/10.1145/3729343","title":"VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation","display_name":"VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411449683","doi":"https://doi.org/10.1145/3729343"},"language":"en","primary_location":{"id":"doi:10.1145/3729343","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729343","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3729343","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100419338","display_name":"Zhijie Wang","orcid":"https://orcid.org/0000-0003-4559-5426"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Zhijie Wang","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":"https://orcid.org/0000-0003-4559-5426","affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026971084","display_name":"Zhehua Zhou","orcid":"https://orcid.org/0000-0001-9542-4858"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhehua Zhou","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":"https://orcid.org/0000-0001-9542-4858","affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104291087","display_name":"Jiayang Song","orcid":"https://orcid.org/0009-0008-7093-9781"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jiayang Song","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":"https://orcid.org/0009-0008-7093-9781","affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101684275","display_name":"Yuheng Huang","orcid":"https://orcid.org/0000-0003-3666-4020"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuheng Huang","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3666-4020","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101561346","display_name":"Zhan Shu","orcid":"https://orcid.org/0000-0002-5933-254X"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhan Shu","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5933-254X","affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101468661","display_name":"Lei Ma","orcid":"https://orcid.org/0000-0002-8621-2420"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["CA","JP"],"is_corresponding":false,"raw_author_name":"Lei Ma","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan","University of Alberta, Edmonton, Canada"],"raw_orcid":"https://orcid.org/0000-0002-8621-2420","affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100419338"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":5.6385,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96025037,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"2","issue":"FSE","first_page":"1615","last_page":"1638"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.7734466791152954},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6587655544281006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6125643253326416},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5521951913833618},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4931740164756775},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.43418294191360474},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.409909188747406},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.17931696772575378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734466791152954},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6587655544281006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6125643253326416},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5521951913833618},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4931740164756775},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43418294191360474},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.409909188747406},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.17931696772575378},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3729343","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729343","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3729343","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729343","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W40327287","https://openalex.org/W128638292","https://openalex.org/W1564897360","https://openalex.org/W2397222277","https://openalex.org/W2911270308","https://openalex.org/W2911282308","https://openalex.org/W2990964856","https://openalex.org/W3007766188","https://openalex.org/W3046168276","https://openalex.org/W3049666257","https://openalex.org/W3089635645","https://openalex.org/W3109716606","https://openalex.org/W3121222079","https://openalex.org/W3134399564","https://openalex.org/W3152331843","https://openalex.org/W3206349396","https://openalex.org/W4200514762","https://openalex.org/W4210811559","https://openalex.org/W4221143046","https://openalex.org/W4223929614","https://openalex.org/W4224947967","https://openalex.org/W4238124605","https://openalex.org/W4243385754","https://openalex.org/W4250935087","https://openalex.org/W4256088380","https://openalex.org/W4285417467","https://openalex.org/W4285490400","https://openalex.org/W4288391571","https://openalex.org/W4300989059","https://openalex.org/W4313459318","https://openalex.org/W4313641686","https://openalex.org/W4319348618","https://openalex.org/W4321230297","https://openalex.org/W4323644408","https://openalex.org/W4323921917","https://openalex.org/W4362519817","https://openalex.org/W4362663195","https://openalex.org/W4362672763","https://openalex.org/W4366204357","https://openalex.org/W4366208220","https://openalex.org/W4377130677","https://openalex.org/W4377864654","https://openalex.org/W4378189609","https://openalex.org/W4379409284","https://openalex.org/W4384155563","https://openalex.org/W4384347367","https://openalex.org/W4388596098","https://openalex.org/W4389162688","https://openalex.org/W4390603751","https://openalex.org/W4391558518","https://openalex.org/W4391614764","https://openalex.org/W4399114781","https://openalex.org/W4400890564","https://openalex.org/W4402443087","https://openalex.org/W4405968021","https://openalex.org/W4410992944","https://openalex.org/W6849590751"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372","https://openalex.org/W3022067003"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,51,97,122,128,151],"generative":[4],"AI":[5],"and":[6,37,58,137,164],"multi-modal":[7],"foundation":[8],"models":[9,43,109],"has":[10],"shown":[11],"significant":[12],"potential":[13],"in":[14,21,60],"advancing":[15],"robotic":[16,78],"manipulation.":[17],"Vision-language-action":[18],"(VLA)":[19],"models,":[20,154],"particular,":[22],"have":[23],"emerged":[24],"as":[25],"a":[26,48,72],"promising":[27],"approach":[28],"for":[29,81,114,158],"visuomotor":[30],"control":[31],"by":[32],"leveraging":[33],"large-scale":[34],"vision-language":[35],"data":[36],"robot":[38],"demonstrations.":[39],"However,":[40],"current":[41,107],"VLA":[42,83,100,108,143,153,166],"are":[44],"typically":[45],"evaluated":[46],"using":[47],"limited":[49],"set":[50],"hand-crafted":[52],"scenes,":[53],"leaving":[54],"their":[55],"general":[56],"performance":[57,96],"robustness":[59,112],"diverse":[61],"scenarios":[62],"largely":[63],"unexplored.":[64],"To":[65],"address":[66],"this":[67],"gap,":[68],"we":[69,88,118],"present":[70],"VLATest,":[71,87],"fuzzing":[73],"framework":[74],"designed":[75],"to":[76,93,161],"generate":[77],"manipulation":[79],"scenes":[80],"testing":[82],"models.":[84,101],"Based":[85],"on":[86,141],"conducted":[89],"an":[90],"empirical":[91],"study":[92,103],"assess":[94],"the":[95,111,120,126,142,149,156],"seven":[98],"representative":[99],"Our":[102,146],"results":[104],"revealed":[105],"that":[106],"lack":[110],"necessary":[113],"practical":[115],"deployment.":[116],"Additionally,":[117],"investigated":[119],"impact":[121],"various":[123],"factors,":[124],"including":[125],"number":[127],"confounding":[129],"objects,":[130,136],"lighting":[131],"conditions,":[132],"camera":[133],"poses,":[134],"unseen":[135],"task":[138],"instruction":[139],"mutations,":[140],"model's":[144],"performance.":[145],"findings":[147],"highlight":[148],"limitations":[150],"existing":[152],"emphasizing":[155],"need":[157],"further":[159],"research":[160],"develop":[162],"reliable":[163],"trustworthy":[165],"applications.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}