{"id":"https://openalex.org/W7138125927","doi":"https://doi.org/10.1609/aaai.v40i4.37290","title":"VILTA: A VLM-in-the-Loop Adversary for Enhancing Driving Policy Robustness","display_name":"VILTA: A VLM-in-the-Loop Adversary for Enhancing Driving Policy Robustness","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138125927","doi":"https://doi.org/10.1609/aaai.v40i4.37290"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i4.37290","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37290","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37290/41252","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37290/41252","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114085650","display_name":"Qimao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qimao Chen","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129648420","display_name":"Fang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Fang Li","raw_affiliation_strings":["University of Macau\nXiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau\nXiaomi EV","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129666642","display_name":"Shaoqing Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Shaoqing Xu","raw_affiliation_strings":["University of Macau\nXiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau\nXiaomi EV","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112939058","display_name":"Zhiyi Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyi Lai","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111162805","display_name":"Zixun Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixun Xie","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129665396","display_name":"Yuechen Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuechen Luo","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129705655","display_name":"Shengyin Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyin Jiang","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123465206","display_name":"Hanbing Li","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanbing Li","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129713475","display_name":"Long Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129695108","display_name":"Bing Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Wang","raw_affiliation_strings":["Xiaomi EV"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi EV","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129751847","display_name":"Yi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011123518","display_name":"Zhi-Xin Yang","orcid":"https://orcid.org/0000-0001-9151-7758"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Zhi-Xin Yang","raw_affiliation_strings":["University of Macau"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Macau","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":2,"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":"40","issue":"4","first_page":"2984","last_page":"2992"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.85589998960495,"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"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.85589998960495,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.05700000002980232,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.018200000748038292,"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/robustness","display_name":"Robustness (evolution)","score":0.6355000138282776},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5315999984741211},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.5245000123977661},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.49140000343322754},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.44179999828338623},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4090999960899353},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.35260000824928284},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.3481000065803528}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7024999856948853},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6355000138282776},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.5245000123977661},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.44179999828338623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42820000648498535},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.33469998836517334},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32580000162124634},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.3010999858379364},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i4.37290","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37290","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37290/41252","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37290","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i4.37290","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37290","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37290/41252","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1806835934","display_name":null,"funder_award_id":"2023YFE0205800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4074719757","display_name":null,"funder_award_id":"62461160260","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G522244876","display_name":null,"funder_award_id":"62473224","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138125927.pdf","grobid_xml":"https://content.openalex.org/works/W7138125927.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"safe":[1],"deployment":[2],"of":[3,90,95,106,131,159,179,189,203],"autonomous":[4],"driving":[5,19,148],"(AD)":[6],"systems":[7],"is":[8,99],"fundamentally":[9],"hindered":[10],"by":[11,102,144],"the":[12,87,93,96,103,107,128,141,146,169,187,199,204],"long-tail":[13,215],"problem,":[14],"where":[15],"rare":[16],"yet":[17,181],"critical":[18,214],"scenarios":[20,154,183],"are":[21],"severely":[22],"underrepresented":[23],"in":[24,77,140,209],"real-world":[25],"data.":[26],"Existing":[27],"solutions":[28],"including":[29],"safety-critical":[30],"scenario":[31],"generation":[32],"and":[33,43,56,150,201],"closed-loop":[34,129],"learning":[35],"often":[36],"rely":[37],"on":[38],"rule-based":[39],"heuristics,":[40],"resampling":[41],"methods":[42],"generative":[44,88],"models":[45],"learned":[46],"from":[47],"offline":[48],"datasets,":[49],"limiting":[50],"their":[51],"ability":[52,211],"to":[53,67,174,212],"produce":[54,68],"diverse":[55,177],"novel":[57,121],"challenges.":[58],"While":[59],"recent":[60],"works":[61],"leverage":[62],"Vision":[63],"Language":[64],"Models":[65],"(VLMs)":[66],"scene":[69],"descriptions":[70],"that":[71,123,184,194],"guide":[72],"a":[73,120,125,176],"separate,":[74],"downstream":[75,108],"model":[76],"generating":[78,152],"hazardous":[79],"trajectories":[80,98],"for":[81],"agents,":[82],"such":[83],"two-stage":[84],"framework":[85,122],"constrains":[86],"potential":[89],"VLMs,":[91],"as":[92],"diversity":[94],"final":[97],"ultimately":[100],"limited":[101],"generalization":[104,172],"ceiling":[105],"algorithm.":[109],"To":[110],"overcome":[111],"these":[112],"limitations,":[113],"we":[114],"introduce":[115],"VILTA":[116,137],"(VLM-In-the-Loop":[117],"Trajectory":[118],"Adversary),":[119],"integrates":[124],"VLM":[126],"into":[127],"training":[130,142],"AD":[132,206],"agents.":[133],"Unlike":[134],"prior":[135],"works,":[136],"actively":[138],"participates":[139],"loop":[143],"comprehending":[145],"dynamic":[147],"environment":[149],"strategically":[151],"challenging":[153,182],"through":[155],"direct,":[156],"fine-grained":[157],"editing":[158],"surrounding":[160],"agents'":[161],"future":[162],"trajectories.":[163],"This":[164],"direct-editing":[165],"approach":[166,196],"fully":[167],"leverages":[168],"VLM's":[170],"powerful":[171],"capabilities":[173],"create":[175],"curriculum":[178],"plausible":[180],"extend":[185],"beyond":[186],"scope":[188],"traditional":[190],"methods.":[191],"We":[192],"demonstrate":[193],"our":[195],"substantially":[197],"enhances":[198],"safety":[200],"robustness":[202],"resulting":[205],"policy,":[207],"particularly":[208],"its":[210],"navigate":[213],"events.":[216]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}