{"id":"https://openalex.org/W4413017831","doi":"https://doi.org/10.1109/iv64158.2025.11097438","title":"Video Token Sparsification for Efficient Multimodal LLMs in Driving Visual Question Answering","display_name":"Video Token Sparsification for Efficient Multimodal LLMs in Driving Visual Question Answering","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4413017831","doi":"https://doi.org/10.1109/iv64158.2025.11097438"},"language":"en","primary_location":{"id":"doi:10.1109/iv64158.2025.11097438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv64158.2025.11097438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Intelligent Vehicles Symposium (IV)","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/A5103050279","display_name":"Yunsheng Ma","orcid":"https://orcid.org/0000-0003-3933-2574"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunsheng Ma","raw_affiliation_strings":["Toyota InfoTech Labs,Mountain View,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota InfoTech Labs,Mountain View,CA,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070231367","display_name":"Amr Abdelraouf","orcid":"https://orcid.org/0000-0001-9068-6664"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amr Abdelraouf","raw_affiliation_strings":["Toyota InfoTech Labs,Mountain View,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota InfoTech Labs,Mountain View,CA,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100653804","display_name":"Rohit Gupta","orcid":"https://orcid.org/0000-0002-8398-680X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohit Gupta","raw_affiliation_strings":["Toyota InfoTech Labs,Mountain View,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota InfoTech Labs,Mountain View,CA,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041101884","display_name":"Ahmadreza Moradipari","orcid":"https://orcid.org/0000-0002-0197-8639"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmadreza Moradipari","raw_affiliation_strings":["Toyota InfoTech Labs,Mountain View,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota InfoTech Labs,Mountain View,CA,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038550389","display_name":"Ziran Wang","orcid":"https://orcid.org/0000-0003-2702-7150"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziran Wang","raw_affiliation_strings":["Purdue University,West Lafayette,IN,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,West Lafayette,IN,USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009775690","display_name":"Kyungtae Han","orcid":"https://orcid.org/0000-0001-8291-5025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyungtae Han","raw_affiliation_strings":["Toyota InfoTech Labs,Mountain View,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota InfoTech Labs,Mountain View,CA,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2235","last_page":"2242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9986000061035156,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9973000288009644,"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/security-token","display_name":"Security token","score":0.7439948320388794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6673568487167358},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5321128964424133},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40503498911857605},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37859639525413513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3689870536327362},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.19306418299674988}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7439948320388794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6673568487167358},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5321128964424133},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40503498911857605},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37859639525413513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3689870536327362},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.19306418299674988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iv64158.2025.11097438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv64158.2025.11097438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2506483933","https://openalex.org/W4319300501","https://openalex.org/W4385801014","https://openalex.org/W4386076083","https://openalex.org/W4394595621","https://openalex.org/W4394862623","https://openalex.org/W4401109681","https://openalex.org/W4401386967","https://openalex.org/W4401414574","https://openalex.org/W4402716132","https://openalex.org/W4402727014","https://openalex.org/W4402727451","https://openalex.org/W4402727495","https://openalex.org/W4402727550","https://openalex.org/W4402753604","https://openalex.org/W4402754149","https://openalex.org/W4402754221","https://openalex.org/W4403908286","https://openalex.org/W4404782025","https://openalex.org/W4404820176","https://openalex.org/W4408697174","https://openalex.org/W4409917695","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6784333009","https://openalex.org/W6796581206","https://openalex.org/W6809646742","https://openalex.org/W6846577953","https://openalex.org/W6851592950","https://openalex.org/W6857112689","https://openalex.org/W6858692988","https://openalex.org/W6859532197","https://openalex.org/W6859902353","https://openalex.org/W6861455346","https://openalex.org/W6870738919","https://openalex.org/W6876016101","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Multimodal":[0],"large":[1,67],"language":[2],"models":[3,41],"(MLLMs)":[4],"have":[5],"shown":[6],"significant":[7,44],"potential":[8],"in":[9,33,80,101,154,161],"enhancing":[10],"driving":[11,27,36],"scene":[12],"understanding":[13],"and":[14,30,52,83,123,130,142,157],"visual":[15,70,77,107],"question":[16],"answering":[17],"(VQA)":[18],"through":[19],"advanced":[20],"logical":[21],"reasoning":[22],"capabilities.":[23],"These":[24],"tasks":[25],"support":[26],"action":[28],"generation":[29],"explanation,":[31],"especially":[32],"end-to-end":[34],"autonomous":[35],"applications.":[37],"However,":[38],"deploying":[39],"these":[40],"poses":[42],"a":[43,95,115,151,158],"challenge":[45],"due":[46],"to":[47,73,105,119,150,165],"their":[48],"substantial":[49],"parameter":[50],"sizes":[51],"computational":[53,59],"demands,":[54],"which":[55],"often":[56],"exceed":[57],"onboard":[58],"limits.":[60],"A":[61],"key":[62,121],"limitation":[63],"stems":[64],"from":[65],"the":[66,140],"number":[68],"of":[69],"tokens":[71,108],"needed":[72],"capture":[74],"detailed,":[75],"long-context":[76],"information,":[78],"resulting":[79],"increased":[81],"latency":[82],"memory":[84,162],"use.":[85],"To":[86],"address":[87],"this,":[88],"we":[89],"propose":[90],"Video":[91],"Token":[92],"Sparsification":[93],"(VTS),":[94],"novel":[96],"approach":[97],"that":[98,146],"leverages":[99],"redundancy":[100],"consecutive":[102],"video":[103],"frames":[104,122],"reduce":[106],"while":[109],"preserving":[110],"critical":[111],"information.":[112],"VTS":[113,147],"employs":[114],"lightweight":[116],"CNN-based":[117],"model":[118],"identify":[120],"prune":[124],"less":[125],"informative":[126],"tokens,":[127],"mitigating":[128],"hallucinations":[129],"boosting":[131],"inference":[132,155],"throughput":[133,156],"without":[134],"performance":[135],"loss.":[136],"Comprehensive":[137],"experiments":[138],"on":[139],"LingoQA":[141],"DRAMA":[143],"benchmarks":[144],"show":[145],"achieves":[148],"up":[149],"33%":[152],"improvement":[153],"28%":[159],"reduction":[160],"usage":[163],"compared":[164],"baselines,":[166],"maintaining":[167],"comparable":[168],"performance.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}