{"id":"https://openalex.org/W7216480476","doi":"https://doi.org/10.48550/arxiv.2610.01531","title":"Towards Reliable Vision-Language Models for Autonomous Driving","display_name":"Towards Reliable Vision-Language Models for Autonomous Driving","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7216480476","doi":"https://doi.org/10.48550/arxiv.2610.01531"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.01531","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01531","pdf_url":"https://arxiv.org/pdf/2610.01531","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/2610.01531","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112290785","display_name":"Manasa Mariam Mammen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1332474105","display_name":"Mercedes-Benz (Germany)","ror":"https://ror.org/055rn2a38","country_code":"DE","type":"company","lineage":["https://openalex.org/I1332474105"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mammen, Manasa Mariam","raw_affiliation_strings":["Mercedes Benz AG , Sindelfingen , Germany","Technical University of Munich , Heilbronn , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mercedes Benz AG , Sindelfingen , Germany","institution_ids":["https://openalex.org/I1332474105"]},{"raw_affiliation_string":"Technical University of Munich , Heilbronn , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060394319","display_name":"Priyanka Mary Mammen","orcid":"https://orcid.org/0000-0001-7627-4479","observed_orcids":["https://orcid.org/0000-0001-7627-4479"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mammen, Priyanka Mary","raw_affiliation_strings":["University of Massachusetts , Amherst , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts , Amherst , USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074456431","display_name":"Zafer Kayatas","orcid":"https://orcid.org/0000-0003-0880-0304","observed_orcids":["https://orcid.org/0000-0003-0880-0304"]},"institutions":[{"id":"https://openalex.org/I1332474105","display_name":"Mercedes-Benz (Germany)","ror":"https://ror.org/055rn2a38","country_code":"DE","type":"company","lineage":["https://openalex.org/I1332474105"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kayatas, Zafer","raw_affiliation_strings":["Mercedes Benz AG , Sindelfingen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mercedes Benz AG , Sindelfingen , Germany","institution_ids":["https://openalex.org/I1332474105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5155609134","display_name":"Stefan Wagner","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wagner, Stefan","raw_affiliation_strings":["Technical University of Munich , Heilbronn , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich , Heilbronn , Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9003999829292297,"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":0.9003999829292297,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.07810000330209732,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.006099999882280827,"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-models","display_name":"vision-language models","score":0.9980000257492065},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.9980000257492065},{"id":"https://openalex.org/keywords/model-reliability","display_name":"model reliability","score":0.7630000114440918},{"id":"https://openalex.org/keywords/confidence-calibration","display_name":"confidence calibration","score":0.6150000095367432},{"id":"https://openalex.org/keywords/sensor-degradation","display_name":"sensor degradation","score":0.5979999899864197},{"id":"https://openalex.org/keywords/safety-critical-decision-making","display_name":"safety-critical decision-making","score":0.6650000214576721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6929000020027161},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6915000081062317},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6661999821662903},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.506600022315979},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3801000118255615},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.314300000667572},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2687999904155731},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.2671999931335449}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.01531","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01531","pdf_url":"https://arxiv.org/pdf/2610.01531","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.2610.01531","doi":"https://doi.org/10.48550/arxiv.2610.01531","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.01531","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.01531","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.01531","pdf_url":"https://arxiv.org/pdf/2610.01531","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/W7216480476.pdf","grobid_xml":"https://content.openalex.org/works/W7216480476.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4406193278","https://openalex.org/W4405655797","https://openalex.org/W4416959523","https://openalex.org/W7164349783","https://openalex.org/W4417466207","https://openalex.org/W6929339462","https://openalex.org/W7164378593","https://openalex.org/W7124173247","https://openalex.org/W7162763550","https://openalex.org/W4402674250"],"abstract_inverted_index":{"Vision-Language":[0],"models":[1,71,176],"(VLMs)":[2],"are":[3,182],"increasingly":[4,34],"being":[5],"explored":[6],"in":[7,64,133],"autonomous":[8,65],"driving":[9,16],"for":[10,174],"tasks":[11],"such":[12],"as":[13],"scene":[14],"understanding,":[15],"reasoning,":[17],"decision-making,":[18],"and":[19,31,47,55,76,95,112,128,135,138,177],"end-to-end":[20],"driving.":[21],"As":[22],"their":[23,29,56,79],"role":[24],"becomes":[25],"more":[26],"prominent,":[27],"ensuring":[28],"robustness":[30],"reliability":[32,137,162],"is":[33,61],"important.":[35],"In":[36,84],"real-world":[37],"conditions,":[38,49],"visual":[39,105,122,165],"inputs":[40],"may":[41,81],"be":[42,82],"degraded":[43,164],"by":[44],"sensor":[45],"imperfections":[46],"environmental":[48],"potentially":[50],"affecting":[51],"both":[52],"model":[53,161],"predictions":[54,75,80],"associated":[57],"confidence.":[58],"Such":[59],"degradation":[60],"especially":[62],"concerning":[63],"driving,":[66],"where":[67],"safety-critical":[68],"decisions":[69],"require":[70],"to":[72,155],"make":[73],"accurate":[74],"recognize":[77],"when":[78],"unreliable.":[83],"this":[85],"work,":[86],"we":[87],"evaluate":[88],"five":[89],"VLMs":[90],"(Qwen3.5-9B,":[91],"Gemma4-E4B,":[92],"LLaVA-OneVision-7B,":[93],"DriveFusion/DriveFusionQA-4B,":[94],"NVIDIA":[96],"Alpamayo-1.5-10B)":[97],"across":[98,125,141,185],"four":[99],"driving-related":[100],"QA":[101],"datasets":[102],"with":[103,131],"different":[104],"input":[106,129],"settings,":[107,130],"including":[108],"single-frame,":[109],"multi-view,":[110],"multi-frame,":[111],"monocular":[113],"inputs.":[114],"Our":[115],"results":[116],"show":[117],"that":[118,169],"the":[119,180],"effects":[120],"of":[121],"corruption":[123],"vary":[124],"models,":[126],"datasets,":[127,178],"changes":[132],"accuracy":[134],"confidence":[136],"also":[139],"differing":[140],"conditions.":[142,166],"We":[143,167],"then":[144],"apply":[145],"Visual":[146],"Evidence":[147],"Augmentation":[148],"($\\mathrm{V}{\\scriptstyle":[149],"\\mathrm{EA}}$),":[150],"a":[151],"recent":[152],"inference-time":[153],"method":[154],"examine":[156],"whether":[157],"it":[158],"can":[159],"improve":[160],"under":[163],"find":[168],"$\\mathrm{V}{\\scriptstyle":[170],"\\mathrm{EA}}$":[171],"improves":[172],"performance":[173],"some":[175],"although":[179],"gains":[181],"not":[183],"consistent":[184],"all":[186],"settings.":[187]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-03T00:00:00"}