{"id":"https://openalex.org/W7155486524","doi":"https://doi.org/10.48550/arxiv.2604.21479","title":"Frozen LLMs as Map-Aware Spatio-Temporal Reasoners for Vehicle Trajectory Prediction","display_name":"Frozen LLMs as Map-Aware Spatio-Temporal Reasoners for Vehicle Trajectory Prediction","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7155486524","doi":"https://doi.org/10.48550/arxiv.2604.21479"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.21479","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21479","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.21479","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134553613","display_name":"Yanjiao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yanjiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134501335","display_name":"Jiawei Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jiawei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134475160","display_name":"Xun Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Xun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019941514","display_name":"Zifei Nie","orcid":"https://orcid.org/0000-0001-5404-527X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Zifei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.772599995136261,"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":0.772599995136261,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.053700000047683716,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T13282","display_name":"Automated Road and Building Extraction","score":0.03280000016093254,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/trajectory","display_name":"Trajectory","score":0.6322000026702881},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5311999917030334},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4936999976634979},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.45730000734329224},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.43320000171661377},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4244999885559082},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.41999998688697815}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6322000026702881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6092000007629395},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5311999917030334},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4560000002384186},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41999998688697815},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.21479","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21479","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.21479","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21479","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6146278381347656}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"recently":[5],"demonstrated":[6],"strong":[7,186],"reasoning":[8,83,116],"capabilities":[9],"and":[10,30,43,70,174,192],"attracted":[11],"increasing":[12],"research":[13],"attention":[14],"in":[15,62],"the":[16,39,44,58,64,71,82,107,114,120,136,140,159,165],"field":[17],"of":[18,25,37,60,66,73,97,118,158,161,167,178],"autonomous":[19],"driving":[20],"(AD).":[21],"However,":[22],"safe":[23],"application":[24],"LLMs":[26,61,80,180],"on":[27,170],"AD":[28],"perception":[29],"prediction":[31,137,172],"still":[32],"requires":[33],"a":[34,54,86,100,131,142,155,194],"thorough":[35],"understanding":[36,63],"both":[38],"dynamic":[40,67],"traffic":[41,68,87],"agents":[42,69],"static":[45],"road":[46,74],"infrastructure.":[47],"To":[48,112],"this":[49,51],"end,":[50],"study":[52],"introduces":[53],"framework":[55,77,153],"to":[56,89,148],"evaluate":[57],"capability":[59],"behaviors":[65],"topology":[72],"networks.":[75],"The":[76,152],"leverages":[78],"frozen":[79,179],"as":[81],"engine,":[84],"employing":[85],"encoder":[88],"extract":[90],"spatial-level":[91],"scene":[92,122],"features":[93,123],"from":[94],"observed":[95],"trajectories":[96],"agents,":[98],"while":[99],"lightweight":[101],"Convolutional":[102],"Neural":[103],"Network":[104],"(CNN)":[105],"encodes":[106],"local":[108],"high-definition":[109],"(HD)":[110],"maps.":[111],"assess":[113],"intrinsic":[115],"ability":[117],"LLMs,":[119,141],"extracted":[121],"are":[124],"then":[125],"transformed":[126],"into":[127],"LLM-compatible":[128],"tokens":[129],"via":[130],"reprogramming":[132],"adapter.":[133],"By":[134],"residing":[135],"burden":[138],"with":[139,181],"simpler":[143],"linear":[144],"decoder":[145],"is":[146],"applied":[147],"output":[149],"future":[150],"trajectories.":[151],"enables":[154],"quantitative":[156],"analysis":[157],"influence":[160],"multi-modal":[162],"information,":[163],"especially":[164],"impact":[166],"map":[168],"semantics":[169],"trajectory":[171],"accuracy,":[173],"allows":[175],"seamless":[176],"integration":[177],"minimal":[182],"adaptation,":[183],"thereby":[184],"demonstrating":[185],"generalizability":[187],"across":[188],"diverse":[189],"LLM":[190],"architectures":[191],"providing":[193],"unified":[195],"platform":[196],"for":[197],"model":[198],"evaluation.":[199]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-25T00:00:00"}