{"id":"https://openalex.org/W4404648850","doi":"https://doi.org/10.1109/iccv51701.2025.00582","title":"Hints of Prompt: Enhancing Visual Representation for Multimodal LLMs in Autonomous Driving","display_name":"Hints of Prompt: Enhancing Visual Representation for Multimodal LLMs in Autonomous Driving","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404648850","doi":"https://doi.org/10.1109/iccv51701.2025.00582"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.13076","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002929656","display_name":"Hao Zhou","orcid":"https://orcid.org/0000-0002-8411-1589"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhou","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068652728","display_name":"Zhanning Gao","orcid":"https://orcid.org/0000-0003-2031-2805"},"institutions":[{"id":"https://openalex.org/I4210089559","display_name":"Shenzhen Metro (China)","ror":"https://ror.org/008hpge95","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210089559"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanning Gao","raw_affiliation_strings":["DeepRoute.AI,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepRoute.AI,Shenzhen,China","institution_ids":["https://openalex.org/I4210089559"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081842988","display_name":"Zhili Chen","orcid":"https://orcid.org/0000-0002-8272-156X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhili Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050109730","display_name":"Maosheng Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089559","display_name":"Shenzhen Metro (China)","ror":"https://ror.org/008hpge95","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210089559"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maosheng Ye","raw_affiliation_strings":["DeepRoute.AI,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepRoute.AI,Shenzhen,China","institution_ids":["https://openalex.org/I4210089559"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100719529","display_name":"Qifeng Chen","orcid":"https://orcid.org/0000-0003-2199-3948"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qifeng Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058424592","display_name":"Tongyi Cao","orcid":"https://orcid.org/0000-0003-2157-1526"},"institutions":[{"id":"https://openalex.org/I4210089559","display_name":"Shenzhen Metro (China)","ror":"https://ror.org/008hpge95","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210089559"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongyi Cao","raw_affiliation_strings":["DeepRoute.AI,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepRoute.AI,Shenzhen,China","institution_ids":["https://openalex.org/I4210089559"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047226078","display_name":"Honggang Qi","orcid":"https://orcid.org/0000-0002-7947-1491"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honggang Qi","raw_affiliation_strings":["University of Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6165","last_page":"6175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9502999782562256,"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/T12031","display_name":"Speech and dialogue systems","score":0.9502999782562256,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9300000071525574,"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/representation","display_name":"Representation (politics)","score":0.6932160258293152},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4139247536659241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3595288395881653},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.33589354157447815},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3217829465866089},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.2404034435749054},{"id":"https://openalex.org/keywords/politics","display_name":"Politics","score":0.051091164350509644}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6932160258293152},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4139247536659241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3595288395881653},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33589354157447815},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3217829465866089},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.2404034435749054},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.051091164350509644},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iccv51701.2025.00582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.13076","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.13076","pdf_url":"https://arxiv.org/pdf/2411.13076","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-171529","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-171529","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"doi:10.48550/arxiv.2411.13076","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.13076","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.13076","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.13076","pdf_url":"https://arxiv.org/pdf/2411.13076","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3346419271","display_name":null,"funder_award_id":"2023YFF0716500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3446077531","display_name":null,"funder_award_id":"62271466","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404648850.pdf"},"referenced_works_count":0,"referenced_works":[],"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":{"In":[0],"light":[1],"of":[2,6,41,125],"the":[3,39,87,123,126],"dynamic":[4],"nature":[5],"autonomous":[7],"driving":[8,118],"environments":[9],"and":[10,31,76,79],"stringent":[11],"safety":[12],"requirements,":[13],"general":[14],"MLLMs":[15],"combined":[16],"with":[17,86,110],"CLIP":[18],"alone":[19],"often":[20],"struggle":[21],"to":[22,52,62,67,82,117],"accurately":[23],"represent":[24],"driving-specific":[25,68],"scenarios,":[26],"particularly":[27],"in":[28,137],"complex":[29,72],"interactions":[30,73],"long-tail":[32],"cases.":[33],"To":[34],"address":[35],"this,":[36],"we":[37],"propose":[38],"Hints":[40],"Prompt":[42],"(HoP)":[43],"framework,":[44,128],"which":[45],"introduces":[46],"three":[47],"key":[48,139],"enhancements:":[49],"Affinity":[50],"hint":[51,61,81],"emphasize":[53],"instance-level":[54],"structure":[55],"by":[56,106],"strengthening":[57],"token-wise":[58],"connections,":[59],"Semantic":[60],"incorporate":[63],"high-level":[64],"information":[65],"relevant":[66],"cases,":[69],"such":[70],"as":[71],"among":[74],"vehicles":[75],"traffic":[77],"signs,":[78],"Question":[80],"align":[83],"visual":[84,104],"features":[85],"query":[88],"context,":[89],"focusing":[90],"on":[91],"question-relevant":[92],"regions.":[93],"These":[94],"hints":[95],"are":[96],"fused":[97],"through":[98],"a":[99],"Hint":[100],"Fusion":[101],"module,":[102],"enriching":[103],"representations":[105,109],"capturing":[107],"driving-related":[108],"limited":[111],"domain":[112],"data,":[113],"ensuring":[114],"faster":[115],"adaptation":[116],"scenarios.":[119],"Extensive":[120],"experiments":[121],"confirm":[122],"effectiveness":[124],"HoP":[127],"showing":[129],"that":[130],"it":[131],"significantly":[132],"outperforms":[133],"previous":[134],"state-of-the-art":[135],"methods":[136],"all":[138],"metrics.":[140]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}