{"id":"https://openalex.org/W7138256579","doi":"https://doi.org/10.1609/aaai.v40i10.37805","title":"Sharp Eyes and Memory for VideoLLMs: Information-Aware Visual Token Pruning for Efficient and Reliable VideoLLM Reasoning","display_name":"Sharp Eyes and Memory for VideoLLMs: Information-Aware Visual Token Pruning for Efficient and Reliable VideoLLM Reasoning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138256579","doi":"https://doi.org/10.1609/aaai.v40i10.37805"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i10.37805","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37805","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i10.37805","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jialong Qin","orcid":null},"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"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jialong Qin","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou)\nThe Hong Kong University of Science and Technology\nBeijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou)\nThe Hong Kong University of Science and Technology\nBeijing Institute of Technology","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129696008","display_name":"Xin Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Zou","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou)\nThe Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou)\nThe Hong Kong University of Science and Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129653915","display_name":"Di Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Lu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129722198","display_name":"Yibo Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yibo Yan","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou)\nThe Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou)\nThe Hong Kong University of Science and Technology","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129663223","display_name":"Xuming Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuming Hu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou)\nThe Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou)\nThe Hong Kong University of Science and Technology","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"40","issue":"10","first_page":"8538","last_page":"8546"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9017000198364258,"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":0.9017000198364258,"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":0.021199999377131462,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.013100000098347664,"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":0.6783000230789185},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.43220001459121704},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4203999936580658},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.33090001344680786},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.3149999976158142},{"id":"https://openalex.org/keywords/visual-memory","display_name":"Visual memory","score":0.3091000020503998},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3068000078201294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456000089645386},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6783000230789185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5072000026702881},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3366999924182892},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C178278151","wikidata":"https://www.wikidata.org/wiki/Q7936607","display_name":"Visual memory","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.28049999475479126},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2572000026702881},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i10.37805","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37805","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37805","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37805","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"Video":[1],"Large":[2],"Language":[3],"Models":[4],"(VideoLLMs)":[5],"suffer":[6],"from":[7,47,116],"quadratic":[8],"computational":[9],"complexity":[10],"and":[11,34,43],"key-value":[12],"cache":[13,82,114],"scaling,":[14],"due":[15],"to":[16,104,141,160],"their":[17],"reliance":[18],"on":[19,58,86,131],"processing":[20],"excessive":[21],"redundant":[22],"visual":[23,41,89,95,106],"tokens.":[24],"To":[25],"address":[26],"this":[27,62,109],"problem,":[28],"we":[29],"propose":[30],"SharpV,":[31],"a":[32,73,98,123],"minimalist":[33],"efficient":[35],"method":[36],"for":[37,76],"adaptive":[38,63,77],"pruning":[39,55,83,115,153],"of":[40,88,119,138,144],"tokens":[42],"KV":[44,81],"cache.":[45],"Different":[46],"most":[48],"uniform":[49],"compression":[50],"approaches,":[51],"SharpV":[52,92,111,147],"dynamically":[53],"adjusts":[54],"ratios":[56],"based":[57,85],"spatial-temporal":[59],"information.":[60],"Remarkably,":[61],"mechanism":[64],"occasionally":[65],"achieves":[66,112],"performance":[67],"gains":[68],"over":[69],"dense":[70],"models,":[71],"offering":[72,122],"novel":[74],"paradigm":[75],"pruning.":[78],"During":[79],"the":[80,117,136,142,150],"stage,":[84],"observations":[87],"information":[90,120,128],"degradation,":[91],"prunes":[93],"degraded":[94],"features":[96],"via":[97],"self-calibration":[99],"manner,":[100],"guided":[101],"by":[102],"similarity":[103],"original":[105],"features.":[107],"In":[108],"way,":[110],"hierarchical":[113],"perspective":[118],"bottleneck,":[121],"new":[124],"insight":[125],"into":[126],"VideoLLMs'":[127],"flow.":[129],"Experiments":[130],"multiple":[132],"public":[133],"benchmarks":[134],"demonstrate":[135],"superiority":[137],"SharpV.":[139],"Moreover,":[140],"best":[143],"our":[145],"knowledge,":[146],"is":[148],"notably":[149],"first":[151],"two-stage":[152],"framework":[154],"that":[155],"operates":[156],"without":[157],"requiring":[158],"access":[159],"exposed":[161],"attention":[162],"scores,":[163],"ensuring":[164],"full":[165],"compatibility":[166],"with":[167],"hardware":[168],"acceleration":[169],"techniques":[170],"like":[171],"Flash":[172],"Attention.":[173]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}