{"id":"https://openalex.org/W4406193278","doi":"https://doi.org/10.1109/iccv51701.2025.00621","title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives","display_name":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4406193278","doi":"https://doi.org/10.1109/iccv51701.2025.00621"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.04003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012852633","display_name":"Shaoyuan Xie","orcid":"https://orcid.org/0009-0008-1358-3010"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaoyuan Xie","raw_affiliation_strings":["University of California,Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Irvine","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086548564","display_name":"Lingdong Kong","orcid":"https://orcid.org/0000-0003-3884-2185"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"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":"Lingdong Kong","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101532931","display_name":"Yu Dong","orcid":"https://orcid.org/0000-0002-0231-6274"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"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":"Yuhao Dong","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011614317","display_name":"Chonghao Sima","orcid":"https://orcid.org/0000-0001-6350-4116"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"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":"Chonghao Sima","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100619686","display_name":"Wenwei Zhang","orcid":"https://orcid.org/0000-0002-2745-9773"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"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":"Wenwei Zhang","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063270515","display_name":"Qi Alfred Chen","orcid":"https://orcid.org/0000-0003-0316-9285"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Alfred Chen","raw_affiliation_strings":["University of California,Irvine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Irvine","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406050","display_name":"Ziwei Liu","orcid":"https://orcid.org/0000-0002-4220-5958"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziwei Liu","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101601534","display_name":"Liang Pan","orcid":"https://orcid.org/0000-0001-7437-0125"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"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":"Liang Pan","raw_affiliation_strings":["Shanghai AI Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory","institution_ids":["https://openalex.org/I4210122302","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":"6285","last_page":"6297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10698","display_name":"Transportation Planning and Optimization","score":0.8154000043869019,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10698","display_name":"Transportation Planning and Optimization","score":0.8154000043869019,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.7710999846458435,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12095","display_name":"Vehicle emissions and performance","score":0.7681000232696533,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6834619641304016},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6375177502632141},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.5631700754165649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4994680881500244},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.4712646007537842},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3685246706008911},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.24353212118148804},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2188568115234375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18866389989852905},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.14653939008712769},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08529293537139893}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6834619641304016},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6375177502632141},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.5631700754165649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4994680881500244},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.4712646007537842},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3685246706008911},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24353212118148804},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2188568115234375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18866389989852905},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.14653939008712769},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08529293537139893},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.04003","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.04003","pdf_url":"https://arxiv.org/pdf/2501.04003","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.04003","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.04003","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.04003","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.04003","pdf_url":"https://arxiv.org/pdf/2501.04003","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406193278.pdf","grobid_xml":"https://content.openalex.org/works/W4406193278.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2033512842","https://openalex.org/W4233600955","https://openalex.org/W4322734194","https://openalex.org/W3116237489","https://openalex.org/W4404996554","https://openalex.org/W2913665393","https://openalex.org/W2369695847","https://openalex.org/W3005535424","https://openalex.org/W2994319598","https://openalex.org/W2047067935"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,9,16,126,151,196],"Vision-Language":[3],"Models":[4],"(VLMs)":[5],"have":[6],"sparked":[7],"interest":[8],"their":[10,183],"use":[11],"for":[12,37,188],"autonomous":[13,130,198],"driving,":[14],"particularly":[15],"generating":[17],"interpretable":[18,35,193],"driving":[19,38,76,199],"decisions":[20],"through":[21],"natural":[22],"language.":[23],"However,":[24],"the":[25,173],"assumption":[26],"that":[27,88,135,162],"VLMs":[28,89,136],"inherently":[29],"provide":[30],"visually":[31],"grounded,":[32],"reliable,":[33],"and":[34,62,78,119,141,167,192],"explanations":[36],"remains":[39],"largely":[40],"unexamined.":[41],"To":[42,153],"address":[43,154],"this":[44],"gap,":[45],"we":[46,157,171],"introduce":[47],"DriveBench,":[48],"a":[49,79,186],"benchmark":[50,202],"dataset":[51,117],"designed":[52],"to":[53,145,149,181],"evaluate":[54],"VLM":[55],"reliability":[56],"across":[57],"17":[58],"settings":[59],"(clean,":[60],"corrupted,":[61],"text-only":[63],"inputs),":[64],"encompassing":[65],"19,200":[66],"frames,":[67],"20,498":[68],"question-answer":[69],"pairs,":[70],"three":[71],"question":[72],"types,":[73],"four":[74],"mainstream":[75],"tasks,":[77],"total":[80],"of":[81,175,179],"12":[82],"popular":[83],"VLMs.":[84],"Our":[85],"findings":[86],"reveal":[87],"often":[90],"generate":[91],"plausible":[92],"responses":[93],"derived":[94],"from":[95],"general":[96],"knowledge":[97],"or":[98,109],"textual":[99],"cues":[100],"rather":[101],"than":[102],"true":[103],"visual":[104,111,165],"grounding,":[105],"especially":[106],"under":[107],"degraded":[108],"missing":[110],"inputs.":[112],"This":[113],"behavior,":[114],"concealed":[115],"by":[116],"imbalances":[118],"insufficient":[120],"evaluation":[121,160],"metrics,":[122],"poses":[123],"significant":[124],"risks":[125],"safety-critical":[127],"scenarios":[128],"like":[129],"driving.":[131],"We":[132],"further":[133],"observe":[134],"struggle":[137],"with":[138],"multi-modal":[139,168],"reasoning":[140],"display":[142],"heightened":[143],"sensitivity":[144],"input":[146],"corruptions,":[147],"leading":[148],"inconsistencies":[150],"performance.":[152],"these":[155],"challenges,":[156],"propose":[158],"refined":[159],"metrics":[161],"prioritize":[163],"robust":[164],"grounding":[166],"understanding.":[169],"Additionally,":[170],"highlight":[172],"potential":[174],"leveraging":[176],"VLMs'":[177],"awareness":[178],"corruptions":[180],"enhance":[182],"reliability,":[184],"offering":[185],"roadmap":[187],"developing":[189],"more":[190],"trustworthy":[191],"decision-making":[194],"systems":[195],"real-world":[197],"contexts.":[200],"The":[201],"toolkit":[203],"is":[204],"publicly":[205],"accessible.":[206]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}