{"id":"https://openalex.org/W4413917449","doi":"https://doi.org/10.1109/icra55743.2025.11128326","title":"Towards Robust Autonomous Driving: Conditional Multimodal Large Language Models for Fine-Grained Perception","display_name":"Towards Robust Autonomous Driving: Conditional Multimodal Large Language Models for Fine-Grained Perception","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917449","doi":"https://doi.org/10.1109/icra55743.2025.11128326"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5109731559","display_name":"Fengzhao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengzhao Sun","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090623425","display_name":"Yunxiang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunxiang Zhang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaming Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Hou","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042511273","display_name":"Xilong Lu","orcid":"https://orcid.org/0000-0001-6815-9024"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xilong Lu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102870049","display_name":"Heng Song","orcid":"https://orcid.org/0000-0002-0049-5053"},"institutions":[{"id":"https://openalex.org/I4210133882","display_name":"China Railway Construction Corporation (China)","ror":"https://ror.org/03gyssm79","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210133882"]},{"id":"https://openalex.org/I4210135994","display_name":"China Railway Group (China)","ror":"https://ror.org/03za3eq42","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210135994"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Song","raw_affiliation_strings":["China Railway No.4 Engineering Group Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Railway No.4 Engineering Group Co., Ltd","institution_ids":["https://openalex.org/I4210133882","https://openalex.org/I4210135994"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037394596","display_name":"Fang Gao","orcid":"https://orcid.org/0000-0003-1226-3011"},"institutions":[{"id":"https://openalex.org/I150807315","display_name":"Guangxi University","ror":"https://ror.org/02c9qn167","country_code":"CN","type":"education","lineage":["https://openalex.org/I150807315"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Gao","raw_affiliation_strings":["Guangxi University,Nanning,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi University,Nanning,China","institution_ids":["https://openalex.org/I150807315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":"8234","last_page":"8241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9951000213623047,"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":0.9951000213623047,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9765999913215637,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9761999845504761,"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/computer-science","display_name":"Computer science","score":0.692293643951416},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5787069797515869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4214448630809784},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41269680857658386},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10792246460914612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.692293643951416},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5787069797515869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4214448630809784},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41269680857658386},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10792246460914612},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2560730294","https://openalex.org/W2948672349","https://openalex.org/W2963109634","https://openalex.org/W2963150697","https://openalex.org/W2963518342","https://openalex.org/W2970603850","https://openalex.org/W2979382951","https://openalex.org/W2983943451","https://openalex.org/W3035574168","https://openalex.org/W4225650823","https://openalex.org/W4285294723","https://openalex.org/W4389519972","https://openalex.org/W4393148430","https://openalex.org/W4393178509","https://openalex.org/W4394862623","https://openalex.org/W4401386967","https://openalex.org/W4401414574","https://openalex.org/W4401416408","https://openalex.org/W4402671847","https://openalex.org/W4402716381","https://openalex.org/W4402727764","https://openalex.org/W4403081466","https://openalex.org/W4404575065","https://openalex.org/W4404820176","https://openalex.org/W4405595839","https://openalex.org/W4409366257"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3],"(MLLMs)":[4],"have":[5],"shown":[6],"remarkable":[7],"performance":[8],"across":[9],"various":[10],"visual":[11,31],"understanding":[12],"tasks.":[13,52,128],"However,":[14],"most":[15],"existing":[16,112],"MLLMs":[17,113],"still":[18],"lack":[19],"image":[20],"detail":[21],"perception,":[22],"limiting":[23],"their":[24],"effectiveness":[25,130],"in":[26,49,102,120],"tasks":[27],"that":[28,73],"require":[29],"detailed":[30],"information.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36],"introduce":[37],"Percept-DriveLM,":[38],"a":[39,69,103],"novel":[40],"MLLM":[41],"designed":[42],"to":[43,86],"tackle":[44],"the":[45,54,60,96],"fine-grained":[46,98],"perception":[47,99,124],"challenges":[48],"autonomous":[50,122],"driving":[51,123],"At":[53],"core":[55],"of":[56,131],"our":[57,106,132],"model":[58,107],"is":[59,134],"Visual":[61],"Fusion":[62],"Module,":[63],"which":[64],"integrates":[65],"several":[66],"innovative":[67],"components:":[68],"dynamic":[70],"resolution":[71,79],"mechanism":[72,85],"combines":[74],"both":[75,121],"high":[76],"and":[77,81,118,125],"low":[78],"features,":[80],"an":[82],"RoI":[83],"conditional":[84],"incorporate":[87],"object/region-level":[88],"features":[89],"identified":[90],"by":[91],"offline":[92],"detectors,":[93],"further":[94],"refining":[95],"model's":[97],"abilities.":[100],"Trained":[101],"two-stage":[104],"process,":[105],"demonstrates":[108],"exceptional":[109],"performance,":[110],"outperforming":[111],"with":[114],"comparable":[115],"parameter":[116],"sizes":[117],"excelling":[119],"general":[126],"vision-language":[127],"The":[129],"approach":[133],"validated":[135],"through":[136],"extensive":[137],"empirical":[138],"studies.":[139],"Code":[140],"will":[141],"be":[142],"available":[143],"at":[144],"https://github.com/DebuggerSunfz/PerceptDriveLM.":[145]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}