{"id":"https://openalex.org/W4414110562","doi":"https://doi.org/10.1109/lra.2025.3608656","title":"Probing Multimodal LLMs as World Models for Driving","display_name":"Probing Multimodal LLMs as World Models for Driving","publication_year":2025,"publication_date":"2025-09-10","ids":{"openalex":"https://openalex.org/W4414110562","doi":"https://doi.org/10.1109/lra.2025.3608656"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3608656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3608656","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5057045831","display_name":"Shiva Sreeram","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiva Sreeram","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0009-0003-3105-7624","affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017563787","display_name":"Tsun-Hsuan Wang","orcid":"https://orcid.org/0000-0002-7259-5686"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tsun-Hsuan Wang","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-7259-5686","affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060064468","display_name":"Alaa Maalouf","orcid":"https://orcid.org/0000-0002-3800-9460"},"institutions":[{"id":"https://openalex.org/I91203450","display_name":"University of Haifa","ror":"https://ror.org/02f009v59","country_code":"IL","type":"education","lineage":["https://openalex.org/I91203450"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Alaa Maalouf","raw_affiliation_strings":["Department of Computer Science, University of Haifa, Haifa, Israel"],"raw_orcid":"https://orcid.org/0000-0002-3800-9460","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Haifa, Haifa, Israel","institution_ids":["https://openalex.org/I91203450"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000400312","display_name":"Guy Rosman","orcid":null},"institutions":[{"id":"https://openalex.org/I4391768151","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4391768151"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guy Rosman","raw_affiliation_strings":["Toyota Research Institute, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-9334-1706","affiliations":[{"raw_affiliation_string":"Toyota Research Institute, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4391768151"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081073767","display_name":"Serta\u00e7 Karaman","orcid":"https://orcid.org/0000-0002-2225-7275"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sertac Karaman","raw_affiliation_strings":["Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2225-7275","affiliations":[{"raw_affiliation_string":"Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066830185","display_name":"Daniela Rus","orcid":"https://orcid.org/0000-0001-5473-3566"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniela Rus","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5473-3566","affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.584,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.9577672,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"10","issue":"11","first_page":"11403","last_page":"11410"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9463000297546387,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9463000297546387,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.499099999666214},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.46950000524520874},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3237000107765198},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.27880001068115234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5613999962806702},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.46950000524520874},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43160000443458557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4311999976634979},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3271999955177307},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26660001277923584},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3608656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3608656","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1965455100","https://openalex.org/W2140246545","https://openalex.org/W2982419388","https://openalex.org/W3003205975","https://openalex.org/W3003954087","https://openalex.org/W3035574168","https://openalex.org/W3083074253","https://openalex.org/W3100307207","https://openalex.org/W3175727500","https://openalex.org/W3181350748","https://openalex.org/W3210065386","https://openalex.org/W3215048956","https://openalex.org/W4385430679","https://openalex.org/W4385431115","https://openalex.org/W4386065742","https://openalex.org/W4386066076","https://openalex.org/W4386075660","https://openalex.org/W4386076483","https://openalex.org/W4391827404","https://openalex.org/W4392240262","https://openalex.org/W4394595621","https://openalex.org/W4394862611","https://openalex.org/W4394862623","https://openalex.org/W4394862732","https://openalex.org/W4394862768","https://openalex.org/W4401345073","https://openalex.org/W4401414574","https://openalex.org/W4401415107","https://openalex.org/W4403906447","https://openalex.org/W4404612908","https://openalex.org/W4413925095","https://openalex.org/W4414334072"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2887502709","https://openalex.org/W2805501957","https://openalex.org/W4293160375","https://openalex.org/W2085494547","https://openalex.org/W2526509441","https://openalex.org/W3124221720","https://openalex.org/W4212864094"],"abstract_inverted_index":{"We":[0,99],"provide":[1],"a":[2],"sober":[3],"look":[4],"at":[5,63],"the":[6,101,122],"application":[7],"of":[8],"Multimodal":[9],"Large":[10],"Language":[11],"Models":[12],"(MLLMs)":[13],"in":[14,30,36,79,117,127],"autonomous":[15],"driving,":[16],"challenging":[17],"common":[18],"assumptions":[19],"about":[20],"their":[21,34],"ability":[22],"to":[23,69,76,111],"interpret":[24],"dynamic":[25,128],"driving":[26,38],"scenarios.":[27],"Despite":[28],"advances":[29],"models":[31,51,61,126],"like":[32],"GPT-4o,":[33],"performance":[35],"complex":[37],"environments":[39],"remains":[40],"largely":[41],"unexplored.":[42],"Our":[43],"experimental":[44],"study":[45],"assesses":[46],"various":[47],"MLLMs":[48],"as":[49],"world":[50],"using":[52],"in-car":[53],"camera":[54],"perspectives":[55],"and":[56,94,106,121],"reveals":[57],"that":[58],"while":[59],"these":[60],"excel":[62],"interpreting":[64],"individual":[65],"images,":[66],"they":[67],"struggle":[68],"synthesize":[70],"coherent":[71],"narratives":[72],"across":[73],"frames,":[74],"leading":[75],"considerable":[77],"inaccuracies":[78],"understanding":[80],"(i)":[81],"ego":[82],"vehicle":[83],"dynamics,":[84],"(ii)":[85],"interactions":[86],"with":[87],"other":[88],"road":[89],"actors,":[90],"(iii)":[91],"trajectory":[92],"planning,":[93],"(iv)":[95],"open-set":[96],"scene":[97],"reasoning.":[98],"introduce":[100],"<sc":[102,107],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[103,108],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">EVAL-LLM-DRIVE</small>":[104],"dataset":[105],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">DRIVESIM</small>":[109],"simulator":[110],"enhance":[112],"our":[113],"evaluation,":[114],"highlighting":[115],"gaps":[116],"current":[118],"MLLM":[119],"capabilities":[120],"need":[123],"for":[124],"improved":[125],"real-world":[129],"environments.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-13T07:31:44.756512","created_date":"2025-10-10T00:00:00"}