{"id":"https://openalex.org/W4415062805","doi":"https://doi.org/10.1109/iccv51701.2025.00880","title":"Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving","display_name":"Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415062805","doi":"https://doi.org/10.1109/iccv51701.2025.00880"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00880","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/2503.21505","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046749835","display_name":"Yu Li","orcid":"https://orcid.org/0000-0003-3691-0199"},"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":"Yue Li","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037703740","display_name":"Meng Tian","orcid":"https://orcid.org/0000-0002-2767-406X"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Meng Tian","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040619778","display_name":"Zhenyu Lin","orcid":"https://orcid.org/0000-0003-4020-4422"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zhenyu Lin","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041796299","display_name":"Jiangtong Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jiangtong Zhu","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021950588","display_name":"Dechang Zhu","orcid":"https://orcid.org/0000-0002-4375-5644"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Dechang Zhu","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101559417","display_name":"Haiqiang Liu","orcid":"https://orcid.org/0000-0002-3314-169X"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Haiqiang Liu","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696147","display_name":"Zining Wang","orcid":"https://orcid.org/0000-0001-6866-0230"},"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":"Yueyi Zhang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008612863","display_name":"Zhiwei Xiong","orcid":"https://orcid.org/0000-0002-9787-7460"},"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":"Zhiwei Xiong","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"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/A5008612863","display_name":"Zhiwei Xiong","orcid":"https://orcid.org/0000-0002-9787-7460"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xinhai Zhao","raw_affiliation_strings":["Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"9431","last_page":"9442"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9751999974250793,"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":0.9751999974250793,"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/interpretability","display_name":"Interpretability","score":0.8870999813079834},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7409999966621399},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6089000105857849},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4986000061035156},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44589999318122864},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.43790000677108765}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8870999813079834},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7409999966621399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692799985408783},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6089000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5400999784469604},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4796999990940094},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00880","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00880","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:2503.21505","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21505","pdf_url":"https://arxiv.org/pdf/2503.21505","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.21505","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.21505","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:2503.21505","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21505","pdf_url":"https://arxiv.org/pdf/2503.21505","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Existing":[0],"benchmarks":[1],"for":[2,57,99,137,187],"Vision-Language":[3],"Model":[4],"(VLM)":[5],"on":[6,112,151],"autonomous":[7],"driving":[8,30],"(AD)":[9],"primarily":[10],"assess":[11,26],"interpretability":[12],"through":[13],"open-form":[14],"visual":[15],"question":[16],"answering":[17],"(QA)":[18],"within":[19],"coarse-grained":[20],"tasks,":[21],"which":[22],"remain":[23],"insufficient":[24],"to":[25,54],"capabilities":[27],"in":[28,122,182],"complex":[29],"scenarios.":[31],"To":[32,125],"this":[33,113],"end,":[34],"we":[35,140],"introduce":[36],"$\\textbf{VLADBench}$,":[37],"a":[38,100,143,172,176],"challenging":[39],"and":[40,52,80,83,95,108,119,130,146,194],"fine-grained":[41],"dataset":[42],"featuring":[43],"close-form":[44],"QAs":[45,159],"that":[46,167],"progress":[47],"from":[48,142,156],"static":[49],"foundational":[50],"knowledge":[51],"elements":[53],"advanced":[55],"reasoning":[56,131],"dynamic":[58],"on-road":[59],"situations.":[60],"The":[61,163],"elaborate":[62],"$\\textbf{VLADBench}$":[63],"spans":[64],"5":[65,135],"key":[66],"domains:":[67],"Traffic":[68,74],"Knowledge":[69],"Understanding,":[70],"General":[71],"Element":[72],"Recognition,":[73],"Graph":[75],"Generation,":[76],"Target":[77],"Attribute":[78],"Comprehension,":[79],"Ego":[81],"Decision-Making":[82],"Planning.":[84],"These":[85],"domains":[86,136],"are":[87],"further":[88,126],"broken":[89],"down":[90],"into":[91],"11":[92],"secondary":[93],"aspects":[94],"29":[96],"tertiary":[97],"tasks":[98],"granular":[101],"evaluation.":[102],"A":[103],"thorough":[104],"assessment":[105,179],"of":[106,180,190],"general":[107],"domain-specific":[109],"(DS)":[110],"VLMs":[111,181],"benchmark":[114,170],"reveals":[115],"both":[116],"their":[117],"strengths":[118],"critical":[120],"limitations":[121],"AD":[123,138,196],"contexts.":[124],"exploit":[127],"the":[128,134,148,168,185,188],"cognitive":[129],"interactions":[132],"among":[133],"understanding,":[139],"start":[141],"small-scale":[144],"VLM":[145],"train":[147],"DS":[149,158],"models":[150],"individual":[152],"domain":[153],"datasets":[154],"(collected":[155],"1.4M":[157],"across":[160],"public":[161],"sources).":[162],"experimental":[164],"results":[165],"demonstrate":[166],"proposed":[169],"provides":[171],"crucial":[173],"step":[174],"toward":[175],"more":[177,191],"comprehensive":[178],"AD,":[183],"paving":[184],"way":[186],"development":[189],"cognitively":[192],"sophisticated":[193],"reasoning-capable":[195],"systems.":[197]},"counts_by_year":[],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-11T00:00:00"}