{"id":"https://openalex.org/W4417029055","doi":"https://doi.org/10.48550/arxiv.2512.03454","title":"Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles","display_name":"Think Before You Drive: World Model-Inspired Multimodal Grounding for Autonomous Vehicles","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4417029055","doi":"https://doi.org/10.48550/arxiv.2512.03454"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2512.03454","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.03454","pdf_url":"https://arxiv.org/pdf/2512.03454","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.03454","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008555154","display_name":"Haicheng Liao","orcid":"https://orcid.org/0000-0002-9966-8451"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liao, Haicheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109715075","display_name":"Huanming Shen","orcid":"https://orcid.org/0009-0003-9867-0802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Huanming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037763576","display_name":"Bonan Wang","orcid":"https://orcid.org/0000-0003-0413-886X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Bonan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404262","display_name":"Yingchun Li","orcid":"https://orcid.org/0000-0002-5371-3587"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yongkang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021157","display_name":"Yihong Tang","orcid":"https://orcid.org/0000-0002-3684-3072"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Yihong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084288560","display_name":"Chengyue Wang","orcid":"https://orcid.org/0009-0000-6957-5468"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chengyue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120688487","display_name":"Dingyi Zhuang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Dingyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Kehua","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Kehua","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064695149","display_name":"Hai Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Hai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012773300","display_name":"Chengzhong Xu","orcid":"https://orcid.org/0000-0001-9480-0356"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Chengzhong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078491548","display_name":"Zhenning Li","orcid":"https://orcid.org/0000-0002-6323-1506"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhenning","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5008555154"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9595000147819519,"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":0.9595000147819519,"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"}},{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.007499999832361937,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.007000000216066837,"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":0.6459000110626221},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.44339999556541443},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.37389999628067017},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3686999976634979},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3564000129699707},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3391999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6504999995231628},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6459000110626221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6126000285148621},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.37389999628067017},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3345000147819519},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26100000739097595}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.03454","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.03454","pdf_url":"https://arxiv.org/pdf/2512.03454","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.03454","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.03454","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.03454","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.03454","pdf_url":"https://arxiv.org/pdf/2512.03454","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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":{"Interpreting":[0],"natural-language":[1],"commands":[2],"to":[3,73],"localize":[4],"target":[5],"objects":[6],"is":[7,65],"critical":[8],"for":[9,18,98,118],"autonomous":[10,19],"driving":[11],"(AD).":[12],"Existing":[13],"visual":[14],"grounding":[15,60],"(VG)":[16],"methods":[17],"vehicles":[20],"(AVs)":[21],"typically":[22],"struggle":[23],"with":[24,110],"ambiguous,":[25],"context-dependent":[26],"instructions,":[27],"as":[28],"they":[29],"lack":[30],"reasoning":[31],"over":[32],"3D":[33],"spatial":[34,56,116],"relations":[35],"and":[36,86,141,158,165,173,181],"anticipated":[37],"scene":[38,80],"evolution.":[39],"Grounded":[40],"in":[41,130,175],"the":[42,78,111,155,191],"principles":[43],"of":[44,91,190],"world":[45],"models,":[46],"we":[47,123],"propose":[48],"ThinkDeeper,":[49],"a":[50,66,82,89,102,126,137],"framework":[51],"that":[52,71],"reasons":[53],"about":[54],"future":[55,92],"states":[57,109],"before":[58],"making":[59],"decisions.":[61],"At":[62],"its":[63],"core":[64],"Spatial-Aware":[67],"World":[68],"Model":[69],"(SA-WM)":[70],"learns":[72],"reason":[74],"ahead":[75],"by":[76,136],"distilling":[77],"current":[79],"into":[81],"command-aware":[83],"latent":[84,93],"state":[85],"rolling":[87],"out":[88],"sequence":[90],"states,":[94],"providing":[95],"forward-looking":[96],"cues":[97],"disambiguation.":[99],"Complementing":[100],"this,":[101],"hypergraph-guided":[103],"decoder":[104],"then":[105],"hierarchically":[106],"fuses":[107],"these":[108],"multimodal":[112],"input,":[113],"capturing":[114],"higher-order":[115],"dependencies":[117],"robust":[119],"localization.":[120],"In":[121],"addition,":[122],"present":[124],"DrivePilot,":[125,163],"multi-source":[127],"VG":[128],"dataset":[129],"AD,":[131],"featuring":[132],"semantic":[133],"annotations":[134],"generated":[135],"Retrieval-Augmented":[138],"Generation":[139],"(RAG)":[140],"Chain-of-Thought":[142],"(CoT)-prompted":[143],"LLM":[144],"pipeline.":[145],"Extensive":[146],"evaluations":[147],"on":[148,154,162,188],"six":[149],"benchmarks,":[150],"ThinkDeeper":[151],"ranks":[152],"#1":[153],"Talk2Car":[156],"leaderboard":[157],"surpasses":[159],"state-of-the-art":[160],"baselines":[161],"MoCAD,":[164],"RefCOCO/+/g":[166],"benchmarks.":[167],"Notably,":[168],"it":[169],"shows":[170],"strong":[171],"robustness":[172],"efficiency":[174],"challenging":[176],"scenes":[177],"(long-text,":[178],"multi-agent,":[179],"ambiguity)":[180],"retains":[182],"superior":[183],"performance":[184],"even":[185],"when":[186],"trained":[187],"50%":[189],"data.":[192]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-12-05T00:00:00"}