{"id":"https://openalex.org/W7166841656","doi":"https://doi.org/10.18653/v1/2026.findings-acl.344","title":"MoPrune: Scene-Guided Motion-Aware Token Pruning for Efficient Video Large Language Models","display_name":"MoPrune: Scene-Guided Motion-Aware Token Pruning for Efficient Video Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166841656","doi":"https://doi.org/10.18653/v1/2026.findings-acl.344"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.344","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.344","pdf_url":"https://aclanthology.org/2026.findings-acl.344.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.344.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139743707","display_name":"Wenhao Hong","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":"Wenhao Hong","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139732319","display_name":"Ziyang Wang","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":"Ziyang Wang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139751242","display_name":"Yixin 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":"Yixin Zhang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139850125","display_name":"Zilei Wang","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":"Zilei Wang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8708117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6929","last_page":"6941"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9452999830245972,"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":0.9452999830245972,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.023800000548362732,"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/T11448","display_name":"Face recognition and analysis","score":0.004900000058114529,"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/pruning","display_name":"Pruning","score":0.39320001006126404},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3140000104904175},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.27950000762939453},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.2786000072956085},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27570000290870667},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.26989999413490295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013000249862671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5699999928474426},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33239999413490295},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.344","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.344","pdf_url":"https://aclanthology.org/2026.findings-acl.344.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.344","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.344","pdf_url":"https://aclanthology.org/2026.findings-acl.344.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8289875194","display_name":null,"funder_award_id":"62376256","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166841656.pdf","grobid_xml":"https://content.openalex.org/works/W7166841656.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"Large":[1],"Language":[2],"Models":[3],"(VideoLLMs)":[4],"struggle":[5],"with":[6,151],"the":[7,23,43,90,135,145],"heavy":[8],"computational":[9],"cost":[10],"of":[11,26,128,144],"long":[12],"or":[13,35,132],"high-resolution":[14],"videos":[15,67],"due":[16],"to":[17,72],"massive":[18],"visual":[19,129],"token":[20,33,59,91],"counts":[21],"and":[22,42,57,75,98,110,117,138],"quadratic":[24],"complexity":[25],"attention.Prior":[27],"pruning":[28,60],"approaches":[29],"mainly":[30],"rely":[31],"on":[32],"importance":[34],"similarity,":[36],"while":[37],"largely":[38],"overlooking":[39],"video":[40],"dynamics":[41],"fact":[44],"that":[45],"different":[46,49],"scenes":[47,71],"exhibit":[48],"redundancy":[50],"patterns.We":[51],"introduce":[52],"MoPrune,":[53],"a":[54,102],"training-free,":[55],"scene-guided":[56],"motion-centric":[58],"framework":[61],"for":[62],"accelerating":[63],"Vide-oLLMs.MoPrune":[64],"first":[65],"segments":[66],"into":[68],"semantically":[69],"coherent":[70],"preserve":[73],"temporal":[74],"motion":[76],"consistency.Within":[77],"each":[78],"scene,":[79],"it":[80],"determines":[81],"frame":[82,87],"retention":[83],"rates":[84],"from":[85],"intrascene":[86],"uniqueness.Finally,":[88],"at":[89],"level,":[92],"MoPrune":[93],"retains":[94],"visually":[95],"distinctive":[96],"tokens":[97,100,130,141],"motion-salient":[99],"via":[101],"unified":[103],"score,":[104],"preserving":[105],"both":[106],"informative":[107],"static":[108],"details":[109],"dynamic":[111],"regions.Extensive":[112],"experiments":[113],"across":[114],"multiple":[115],"VideoLLMs":[116],"public":[118],"benchmarks":[119],"demonstrate":[120],"MoPrune's":[121],"superior":[122],"efficiency-performance":[123],"trade-offs.On":[124],"LLaVA-OneVision,":[125],"retaining":[126,139],"25%":[127],"matches":[131],"slightly":[133],"improves":[134],"dense":[136],"baseline,":[137],"15%":[140],"preserves":[142],"99%":[143],"original":[146],"performance.MoPrune":[147],"is":[148],"fully":[149],"compatible":[150],"hardware-efficient":[152],"techniques":[153],"such":[154],"as":[155],"Flash":[156],"Attention.":[157]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}