{"id":"https://openalex.org/W4413145140","doi":"https://doi.org/10.1109/cvpr52734.2025.00510","title":"Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models","display_name":"Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145140","doi":"https://doi.org/10.1109/cvpr52734.2025.00510"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069806433","display_name":"Zhejun Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zhejun Zhang","raw_affiliation_strings":["NVIDIA Research"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069739104","display_name":"P\u00e9ter Karkus","orcid":"https://orcid.org/0000-0002-1474-9771"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Karkus","raw_affiliation_strings":["NVIDIA Research"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024136382","display_name":"Maximilian Igl","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maximilian Igl","raw_affiliation_strings":["NVIDIA Research"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103072831","display_name":"Wenhao Ding","orcid":"https://orcid.org/0000-0003-3811-8728"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenhao Ding","raw_affiliation_strings":["NVIDIA Research"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366786","display_name":"Yuxiao Chen","orcid":"https://orcid.org/0000-0001-5276-7156"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuxiao Chen","raw_affiliation_strings":["NVIDIA Research"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091869385","display_name":"Boris Ivanovic","orcid":"https://orcid.org/0000-0002-8698-202X"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Boris Ivanovic","raw_affiliation_strings":["NVIDIA Research"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050003000","display_name":"Marco Pavone","orcid":"https://orcid.org/0000-0002-0206-4337"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marco Pavone","raw_affiliation_strings":["NVIDIA Research"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research","institution_ids":["https://openalex.org/I1304085615"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5069806433"],"corresponding_institution_ids":["https://openalex.org/I1304085615"],"apc_list":null,"apc_paid":null,"fwci":4.4044,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94792855,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5422","last_page":"5432"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.9302999973297119,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.9302999973297119,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12810","display_name":"Real-time simulation and control systems","score":0.9139999747276306,"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/T10524","display_name":"Traffic control and management","score":0.90420001745224,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5891571640968323},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.44781872630119324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3228100538253784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11449933052062988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5891571640968323},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.44781872630119324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3228100538253784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11449933052062988},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W24774503","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Traffic":[0],"simulation":[1,108],"aims":[2],"to":[3,81,110],"learn":[4],"a":[5,74,103,112],"policy":[6,109],"for":[7],"traffic":[8,41,107],"agents":[9],"that,":[10],"when":[11,58],"unrolled":[12],"in":[13,23,40,60],"closed-loop,":[14],"faithfully":[15],"recovers":[16],"the":[17,24,38,116,121,125,132],"joint":[18],"distribution":[19],"of":[20,134],"trajectories":[21],"observed":[22],"real":[25],"world.":[26],"Inspired":[27],"by":[28],"large":[29],"language":[30],"models,":[31],"tokenized":[32,106],"multi-agent":[33],"policies":[34],"have":[35],"recently":[36],"become":[37],"state-of-the-art":[39],"simulation.":[42,63],"However,":[43],"they":[44],"are":[45],"typically":[46],"trained":[47],"through":[48],"open-loop":[49],"behavior":[50],"cloning,":[51],"and":[52],"thus":[53],"suffer":[54],"from":[55,115],"covariate":[56,83],"shift":[57],"executed":[59],"closed-loop":[61,78],"during":[62],"In":[64],"this":[65],"work,":[66],"we":[67],"present":[68],"Closest":[69],"Among":[70],"Top-K":[71],"(CAT-K)":[72],"rollouts,":[73],"simple":[75],"yet":[76],"effective":[77],"fine-tuning":[79,86,101],"strategy":[80],"mitigate":[82],"shift.":[84],"CAT-K":[85,100],"only":[87],"requires":[88],"existing":[89],"trajectory":[90],"data,":[91],"without":[92],"reinforcement":[93],"learning":[94],"or":[95],"generative":[96],"adversarial":[97],"imitation.":[98],"Concretely,":[99],"enables":[102],"small":[104],"7M-parameter":[105],"outperform":[111],"102M-parameter":[113],"model":[114,118],"same":[117],"family,":[119],"achieving":[120],"top":[122],"spot":[123],"on":[124],"Waymo":[126],"Sim":[127],"Agent":[128],"Challenge":[129],"leaderboard":[130],"at":[131,140],"time":[133],"submission.":[135],"The":[136],"code":[137],"is":[138],"available":[139],"https://github.com/NVlabs/catk.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}