{"id":"https://openalex.org/W4415539101","doi":"https://doi.org/10.1145/3746027.3755111","title":"DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment","display_name":"DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompting and Motion Alignment","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539101","doi":"https://doi.org/10.1145/3746027.3755111"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755111","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755111","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755111","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111306667","display_name":"Xiaofan Li","orcid":"https://orcid.org/0009-0001-7931-4285"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofan Li","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-7931-4285","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103089859","display_name":"Chenming Wu","orcid":"https://orcid.org/0000-0001-8012-1547"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenming Wu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8012-1547","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhao Yang","orcid":"https://orcid.org/0009-0000-5169-3669"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Yang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-5169-3669","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhihao Xu","orcid":"https://orcid.org/0009-0004-2814-6543"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Xu","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-2814-6543","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071673122","display_name":"Yumeng Zhang","orcid":"https://orcid.org/0000-0002-0174-4824"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yumeng Zhang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0174-4824","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012178361","display_name":"Dingkang Liang","orcid":"https://orcid.org/0000-0003-3035-1373"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingkang Liang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3035-1373","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103120004","display_name":"Ji Wan","orcid":"https://orcid.org/0000-0002-1761-352X"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji Wan","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1761-352X","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-6619-1669"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6619-1669","affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98301712"],"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":"9753","last_page":"9762"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9972000122070312,"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":0.9972000122070312,"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/T12290","display_name":"Human Motion and Animation","score":0.9962999820709229,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9563000202178955,"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/trajectory","display_name":"Trajectory","score":0.7150999903678894},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5507000088691711},{"id":"https://openalex.org/keywords/heading","display_name":"Heading (navigation)","score":0.5346999764442444},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.44620001316070557},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.40709999203681946},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.38929998874664307},{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.3878999948501587},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838000059127808},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7150999903678894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6043000221252441},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5803999900817871},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5507000088691711},{"id":"https://openalex.org/C2776937971","wikidata":"https://www.wikidata.org/wiki/Q4384217","display_name":"Heading (navigation)","level":2,"score":0.5346999764442444},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.40709999203681946},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.3878999948501587},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3264999985694885},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C2985909886","wikidata":"https://www.wikidata.org/wiki/Q193147","display_name":"Spatial coherence","level":3,"score":0.2667999863624573},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755111","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755111","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755111","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755111","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1612997784","https://openalex.org/W3035172746","https://openalex.org/W3204588463","https://openalex.org/W4312933868","https://openalex.org/W4386075767","https://openalex.org/W4390872297","https://openalex.org/W4396754486","https://openalex.org/W4402716059","https://openalex.org/W4402716256","https://openalex.org/W4402778069","https://openalex.org/W4403780703","https://openalex.org/W4403791574","https://openalex.org/W4404722496"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"DriVerse,":[3],"a":[4,13,17,108,143],"generative":[5,54],"model":[6],"for":[7,86,112,189],"simulating":[8],"navigation-driven":[9],"driving":[10,22,90,133],"scenes":[11],"from":[12],"single":[14],"image":[15],"and":[16,46,116,186,205],"future":[18,197],"trajectory.":[19],"Previous":[20],"autonomous":[21,89],"world":[23],"models":[24,195],"either":[25],"directly":[26],"feed":[27],"the":[28,35,43,47,51,75,132,151,159,203],"trajectory":[29,95],"or":[30,68],"discrete":[31,69],"control":[32,44,71,127],"signals":[33],"into":[34,104,120],"generation":[36,199],"pipeline,":[37],"leading":[38],"to":[39,77,125,174],"poor":[40],"alignment":[41,146],"between":[42],"inputs":[45],"implicit":[48],"features":[49],"of":[50,154,162],"2D":[52,121],"base":[53],"model,":[55],"which":[56,73,148],"results":[57],"in":[58,97],"low-fidelity":[59],"video":[60,81,198],"outputs.":[61],"Some":[62],"methods":[63],"use":[64],"coarse":[65],"textual":[66,105],"commands":[67],"vehicle":[70,180],"signals,":[72],"lack":[74],"precision":[76],"guide":[78],"fine-grained,":[79],"trajectory-specific":[80],"generation,":[82],"making":[83],"them":[84],"unsuitable":[85],"evaluating":[87],"actual":[88],"algorithms.":[91],"DriVerse":[92,192],"introduces":[93],"explicit":[94],"guidance":[96],"two":[98],"complementary":[99],"forms:":[100],"it":[101],"tokenizes":[102],"trajectories":[103,119],"prompts":[106],"using":[107],"predefined":[109],"trend":[110],"vocabulary":[111],"seamless":[113],"language":[114],"integration,":[115],"converts":[117],"3D":[118],"spatial":[122],"motion":[123,145],"priors":[124],"enhance":[126],"over":[128,165],"static":[129],"content":[130],"within":[131],"scene.":[134],"To":[135],"better":[136],"handle":[137],"dynamic":[138,155],"objects,":[139],"we":[140],"further":[141],"introduce":[142],"lightweight":[144],"module,":[147],"focuses":[149],"on":[150,196],"inter-frame":[152],"consistency":[153],"pixels,":[156],"significantly":[157],"enhancing":[158],"temporal":[160],"coherence":[161],"moving":[163],"elements":[164],"long":[166],"sequences.":[167],"We":[168],"also":[169],"propose":[170],"an":[171],"inference-time":[172],"strategy":[173],"address":[175],"issues":[176],"caused":[177],"by":[178],"rapid":[179],"heading":[181],"changes.":[182],"With":[183],"minimal":[184],"training":[185],"no":[187],"need":[188],"additional":[190],"data,":[191],"outperforms":[193],"specialized":[194],"tasks":[200],"across":[201],"both":[202],"nuScenes":[204],"Waymo":[206],"datasets.":[207],"Code":[208],"is":[209],"available":[210],"at":[211],"https://github.com/shalfun/DriVerse":[212]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}