{"id":"https://openalex.org/W7203743383","doi":"https://doi.org/10.48550/arxiv.2608.17600","title":"LIBERO-VIFO: Benchmarking the Capability and Safety of Visual Cue Following in Vision-Language-Action Models","display_name":"LIBERO-VIFO: Benchmarking the Capability and Safety of Visual Cue Following in Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-08-18","ids":{"openalex":"https://openalex.org/W7203743383","doi":"https://doi.org/10.48550/arxiv.2608.17600"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.17600","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17600","pdf_url":"https://arxiv.org/pdf/2608.17600","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.17600","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011550241","display_name":"\u94b1\u4e89\u8273","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Zhengyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134687802","display_name":"Rui Yan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125532882","display_name":"Alex Jinpeng Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Alex Jinpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126307307","display_name":"Jinhui Tang","orcid":"https://orcid.org/0000-0001-9008-222X","observed_orcids":["https://orcid.org/0000-0001-9008-222X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jinhui","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":false,"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":0.9330999851226807,"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":0.9330999851226807,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.048500001430511475,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.007000000216066837,"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/vision-language-action-models","display_name":"vision-language-action models","score":0.9660000205039978},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.6549999713897705},{"id":"https://openalex.org/keywords/robot-safety","display_name":"robot safety","score":0.6290000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6629999876022339},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6003000140190125},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.5892999768257141},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.531499981880188},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4609000086784363},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42590001225471497},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.36230000853538513},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.32910001277923584},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32839998602867126},{"id":"https://openalex.org/C105842133","wikidata":"https://www.wikidata.org/wiki/Q1899679","display_name":"Visual communication","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.17600","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17600","pdf_url":"https://arxiv.org/pdf/2608.17600","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.2608.17600","doi":"https://doi.org/10.48550/arxiv.2608.17600","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.17600","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:2608.17600","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.17600","pdf_url":"https://arxiv.org/pdf/2608.17600","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":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7165682249","https://openalex.org/W4415276858","https://openalex.org/W7130730707","https://openalex.org/W4414880224","https://openalex.org/W7166132482","https://openalex.org/W7139945117","https://openalex.org/W7134245333","https://openalex.org/W7164336854","https://openalex.org/W7128388565","https://openalex.org/W7213252271"],"abstract_inverted_index":{"Visual":[0],"cues":[1,18,52],"are":[2,103,146],"increasingly":[3],"adopted":[4],"to":[5,72,148],"guide":[6],"robot":[7],"learning,":[8],"but":[9],"whether":[10],"Vision-Language-Action":[11],"(VLA)":[12],"models":[13,131],"can":[14],"reliably":[15,140],"follow":[16],"authorized":[17,54,111],"while":[19,113],"disregarding":[20],"unauthorized":[21,60,117,160],"ones":[22],"remains":[23],"unclear.":[24],"Existing":[25],"work":[26],"covers":[27],"only":[28,42],"a":[29,43,70,195],"narrow":[30],"range":[31],"of":[32,46,59,79,97,159,184],"cue":[33,81,90,108,119,136,162,186],"forms":[34],"and":[35,77,110,124,171,182],"focuses":[36],"on":[37,166],"final":[38],"task":[39],"success,":[40],"providing":[41],"coarse":[44],"assessment":[45],"cue-following":[47],"capability.":[48],"Treating":[49],"all":[50],"visual":[51,80,89,118,135,161,185],"as":[53,194],"also":[55],"leaves":[56],"safety":[57,78,183,193],"risks":[58],"following":[61,82,120,187],"unexplored.":[62],"To":[63],"address":[64],"these":[65,175],"gaps,":[66],"we":[67],"introduce":[68],"LIBERO-VIFO,":[69],"benchmark":[71],"evaluate":[73],"both":[74,179],"the":[75,180,199],"capability":[76,181],"in":[83,100],"VLA":[84,130,200],"models.":[85],"LIBERO-VIFO":[86,177],"defines":[87],"eight":[88],"families":[91],"spanning":[92],"diverse":[93],"forms.":[94],"A":[95],"total":[96],"four":[98],"protocols":[99],"two":[101],"parts":[102],"defined:":[104],"Part":[105,114],"I":[106],"tests":[107],"understanding":[109,137],"following,":[112],"II":[115],"evaluates":[116],"under":[121],"language-cue":[122],"conflict":[123],"empty":[125],"language":[126,153],"conditions.":[127],"Evaluating":[128],"seven":[129],"reveals":[132],"that":[133],"although":[134],"does":[138],"not":[139],"translate":[141],"into":[142,188],"execution,":[143],"current":[144],"VLAs":[145],"able":[147],"execute":[149],"cue-indicated":[150],"tasks":[151],"without":[152],"instruction,":[154],"exposing":[155],"an":[156],"emerging":[157],"risk":[158],"following.":[163],"Extended":[164],"experiments":[165],"scene-instantiated":[167],"cues,":[168],"safety-critical":[169],"settings,":[170],"real-robot":[172],"deployment":[173],"corroborate":[174],"findings.":[176],"brings":[178],"systematic":[189],"evaluation,":[190],"establishing":[191],"visual-centric":[192],"new":[196],"perspective":[197],"for":[198],"community.":[201]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-20T00:00:00"}