{"id":"https://openalex.org/W7214926701","doi":"https://doi.org/10.48550/arxiv.2609.36934","title":"VLALight: A Vision-Language-Action Model for Traffic Signal Control","display_name":"VLALight: A Vision-Language-Action Model for Traffic Signal Control","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214926701","doi":"https://doi.org/10.48550/arxiv.2609.36934"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.36934","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36934","pdf_url":"https://arxiv.org/pdf/2609.36934","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.36934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153607908","display_name":"Pan Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Pan","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153572582","display_name":"Siqi Lai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lai, Siqi","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021898331","display_name":"\u8463\u53ef\u6728","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong, Kemu","raw_affiliation_strings":["Dalian University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458897","display_name":"Hao Liu","orcid":"https://orcid.org/0000-0003-4271-1567","observed_orcids":["https://orcid.org/0000-0003-4271-1567","https://orcid.org/0000-0002-2568-5339"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Hao","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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/T10524","display_name":"Traffic control and management","score":0.986299991607666,"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/T10524","display_name":"Traffic control and management","score":0.986299991607666,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.008200000040233135,"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/T10370","display_name":"Traffic and Road Safety","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/traffic-signal-control","display_name":"traffic signal control","score":0.9990000128746033},{"id":"https://openalex.org/keywords/vision-language-action-models","display_name":"vision-language-action models","score":0.9300000071525574},{"id":"https://openalex.org/keywords/cooperative-perception","display_name":"cooperative perception","score":0.46700000762939453},{"id":"https://openalex.org/keywords/agentic-reinforcement-learning","display_name":"agentic reinforcement learning","score":0.7229999899864197},{"id":"https://openalex.org/keywords/adaptive-reasoning","display_name":"adaptive reasoning","score":0.7080000042915344},{"id":"https://openalex.org/keywords/signalized-intersections","display_name":"signalized intersections","score":0.6800000071525574},{"id":"https://openalex.org/keywords/traffic-congestion","display_name":"traffic congestion","score":0.5820000171661377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7199000120162964},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5008000135421753},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4918999969959259},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4869999885559082},{"id":"https://openalex.org/C2987419075","wikidata":"https://www.wikidata.org/wiki/Q8004","display_name":"Traffic signal","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4074999988079071},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.38530001044273376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3693999946117401},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.3269999921321869},{"id":"https://openalex.org/C2775905063","wikidata":"https://www.wikidata.org/wiki/Q6132995","display_name":"Road traffic control","level":3,"score":0.3199999928474426},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3190000057220459},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C2778391309","wikidata":"https://www.wikidata.org/wiki/Q7832527","display_name":"Traffic simulation","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2776006172","wikidata":"https://www.wikidata.org/wiki/Q7512741","display_name":"Signal timing","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.36934","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36934","pdf_url":"https://arxiv.org/pdf/2609.36934","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.2609.36934","doi":"https://doi.org/10.48550/arxiv.2609.36934","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.36934","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:2609.36934","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36934","pdf_url":"https://arxiv.org/pdf/2609.36934","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":[{"score":0.8787999749183655,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"},{"score":0.651199996471405,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214926701.pdf","grobid_xml":"https://content.openalex.org/works/W7214926701.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2007894170","https://openalex.org/W2809148419","https://openalex.org/W2903709398","https://openalex.org/W2939228328","https://openalex.org/W2944397927","https://openalex.org/W2964749398","https://openalex.org/W2983178256","https://openalex.org/W2993539758","https://openalex.org/W2998187693","https://openalex.org/W3011507876","https://openalex.org/W3034604283","https://openalex.org/W3092592791","https://openalex.org/W3131323599","https://openalex.org/W3200607907","https://openalex.org/W4225884200","https://openalex.org/W4283813407","https://openalex.org/W4306317029","https://openalex.org/W4385473486","https://openalex.org/W4385568146","https://openalex.org/W4385768151","https://openalex.org/W4392822484","https://openalex.org/W4393405223","https://openalex.org/W4396982312","https://openalex.org/W4399695759","https://openalex.org/W4400612090","https://openalex.org/W4401863490","https://openalex.org/W4407874080","https://openalex.org/W4409158145","https://openalex.org/W4414051084","https://openalex.org/W4415109354","https://openalex.org/W4415797921","https://openalex.org/W4415879030","https://openalex.org/W4416017022","https://openalex.org/W4417102697","https://openalex.org/W4417348363","https://openalex.org/W7120177137","https://openalex.org/W7137004122","https://openalex.org/W7197013050"],"related_works":["https://openalex.org/W7214661365","https://openalex.org/W7197013050","https://openalex.org/W4409158145","https://openalex.org/W4410616288","https://openalex.org/W7220377036","https://openalex.org/W7157557216","https://openalex.org/W7162787509","https://openalex.org/W7124165514","https://openalex.org/W7151933715","https://openalex.org/W3156140343"],"abstract_inverted_index":{"Traffic":[0],"signal":[1,64,77,107],"control":[2,51,65,119,146],"(TSC)":[3],"is":[4,215],"essential":[5],"for":[6,61,102,208],"improving":[7],"urban":[8,175],"mobility":[9],"and":[10,22,50,84,106,120,129,152,163,184,197],"reducing":[11],"congestion.":[12],"Although":[13],"roadside":[14,68],"cameras":[15],"are":[16],"widely":[17],"deployed":[18],"at":[19,217],"signalized":[20],"intersections":[21],"provide":[23],"rich":[24],"visual":[25,73,103],"observations":[26,49,74],"of":[27,192,205],"evolving":[28],"traffic,":[29],"existing":[30],"TSC":[31],"methods":[32],"typically":[33],"rely":[34],"on":[35,168],"manually":[36],"engineered":[37],"traffic":[38,63,82,104,122,211],"states":[39],"or":[40],"separate":[41],"perception":[42,87],"modules,":[43],"creating":[44],"a":[45,96],"gap":[46],"between":[47],"physical":[48,210],"decisions.":[52],"We":[53],"present":[54],"VLALight,":[55],"the":[56,134,190,203],"first":[57],"vision-language-action":[58],"(VLA)":[59],"model":[60],"end-to-end":[62],"from":[66],"multi-view":[67],"videos.":[69],"VLALight":[70,125,156,179],"directly":[71],"maps":[72],"to":[75,136,158],"coordinated":[76],"actions":[78],"through":[79],"multi-target":[80],"spatiotemporal":[81],"reasoning":[83,131,139],"topology-aware":[85],"cooperative":[86,111,193],"across":[88,173],"intersections.":[89],"To":[90],"establish":[91],"this":[92],"capability,":[93],"we":[94],"develop":[95],"two-stage":[97],"supervised":[98],"cold-start":[99],"training":[100],"strategy":[101],"understanding":[105],"decision-making,":[108],"followed":[109],"by":[110],"agentic":[112],"reinforcement":[113],"learning":[114],"that":[115,178],"jointly":[116],"optimizes":[117],"local":[118],"network-wide":[121],"efficiency.":[123],"Furthermore,":[124],"introduces":[126],"adaptive":[127,198],"fast":[128],"slow":[130],"modes,":[132],"enabling":[133],"policy":[135],"allocate":[137],"deeper":[138],"only":[140],"when":[141],"additional":[142],"deliberation":[143],"provides":[144],"sufficient":[145],"benefits.":[147],"Through":[148],"balanced":[149],"mode-aware":[150],"rollouts":[151],"relative":[153],"advantage":[154],"optimization,":[155,196],"learns":[157],"trade":[159],"off":[160],"decision":[161],"quality":[162],"inference":[164],"cost.":[165],"Extensive":[166],"experiments":[167],"seven":[169],"real-world":[170,209],"traffic-flow":[171],"datasets":[172],"three":[174],"networks":[176],"demonstrate":[177,202],"consistently":[180],"outperforms":[181],"transportation-based,":[182],"RL-based,":[183],"LLM/VLM-based":[185],"baselines.":[186],"Ablation":[187],"studies":[188],"validate":[189],"effectiveness":[191],"perception,":[194],"network-level":[195],"reasoning.":[199],"These":[200],"results":[201],"potential":[204],"VLA":[206],"models":[207],"control.":[212],"Our":[213],"project":[214],"available":[216],"https://github.com/usail-hkust/VLALight.git.":[218]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}