{"id":"https://openalex.org/W7169806139","doi":"https://doi.org/10.48550/arxiv.2607.15689","title":"Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors","display_name":"Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors","publication_year":2026,"publication_date":"2026-07-17","ids":{"openalex":"https://openalex.org/W7169806139","doi":"https://doi.org/10.48550/arxiv.2607.15689"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.15689","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15689","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.15689","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5141211378","display_name":"Yilin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yilin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141201326","display_name":"Xiangxi Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Xiangxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081885517","display_name":"Dongxing Mao","orcid":"https://orcid.org/0000-0003-2829-7830"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Dongxing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141196698","display_name":"Linjie Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Linjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141188248","display_name":"Zhengyuan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhengyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141202625","display_name":"Ping Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Ping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042798453","display_name":"Yan Ru","orcid":"https://orcid.org/0000-0002-2686-7185"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141202744","display_name":"Yuan Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087779128","display_name":"A F Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Alex Jinpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.43630000948905945,"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":0.43630000948905945,"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/T11439","display_name":"Video Analysis and Summarization","score":0.19210000336170197,"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":0.08860000222921371,"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/frame","display_name":"Frame (networking)","score":0.7069000005722046},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.677299976348877},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5852000117301941},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5770999789237976},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.573199987411499},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5393999814987183},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5291000008583069},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.526199996471405},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4839000105857849}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404999732971191},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.7069000005722046},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.677299976348877},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5852000117301941},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5770999789237976},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.573199987411499},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5393999814987183},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5291000008583069},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.526199996471405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5250999927520752},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4839000105857849},{"id":"https://openalex.org/C204641915","wikidata":"https://www.wikidata.org/wiki/Q7315509","display_name":"Residual frame","level":4,"score":0.44130000472068787},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.42489999532699585},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38179999589920044},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3434999883174896},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.30000001192092896},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28360000252723694},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.26179999113082886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.15689","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15689","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.2607.15689","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15689","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.4181801378726959,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"long":[1],"videos":[2],"with":[3,36,78],"multimodal":[4],"large":[5],"language":[6],"models":[7],"(MLLMs)":[8],"requires":[9,26],"selecting":[10],"a":[11,37,69,124,133],"compact":[12],"set":[13],"of":[14,18,115],"frames":[15,24],"from":[16],"thousands":[17],"candidates,":[19],"yet":[20],"identifying":[21],"the":[22,28,105,112],"right":[23],"seemingly":[25],"understanding":[27],"video":[29],"first.":[30],"We":[31,57],"resolve":[32],"this":[33,59],"circular":[34],"dependency":[35],"simple":[38],"observation:":[39],"cross-modal":[40],"attention":[41,89],"at":[42],"validation-selected":[43],"extraction":[44],"layers":[45],"in":[46],"MLLMs":[47],"already":[48],"provides":[49],"query-relevant":[50],"frame":[51,71,156],"evidence":[52,85],"without":[53,100,168],"requiring":[54],"autoregressive":[55,101],"generation.":[56],"exploit":[58],"property":[60],"to":[61,144],"build":[62],"DAFS":[63],"(Dynamic":[64],"Attention-based":[65],"Budget-aware":[66],"Frame":[67],"Selection),":[68],"training-free":[70],"selector.":[72],"A":[73],"lightweight":[74],"MLLM":[75],"selector,":[76],"even":[77],"only":[79],"2B":[80],"parameters,":[81],"can":[82],"extract":[83],"frame-level":[84],"by":[86,129,142],"converting":[87],"selected-layer":[88],"into":[90],"relevance":[91],"scores":[92],"through":[93],"query-conditioned":[94],"aggregation.":[95],"This":[96],"enables":[97],"cross-frame":[98],"comparison":[99],"decoding.":[102],"To":[103],"handle":[104],"selector's":[106],"own":[107],"context":[108],"constraint,":[109],"we":[110],"formulate":[111],"joint":[113],"allocation":[114],"candidate":[116],"pool":[117],"size":[118],"and":[119,149,162,165],"per-frame":[120],"token":[121],"budget":[122],"as":[123],"discrete":[125],"optimization":[126],"problem":[127],"solved":[128],"dynamic":[130],"programming.":[131],"Under":[132],"32-frame":[134],"budget,":[135],"our":[136],"selector":[137,161],"improves":[138],"over":[139],"uniform":[140],"sampling":[141],"up":[143],"6.4":[145],"points":[146],"on":[147],"Video-MME":[148],"outperforms":[150],"prior":[151],"training-based":[152],"selectors":[153],"under":[154],"matched":[155],"budgets,":[157],"while":[158],"generalizing":[159],"across":[160,166],"answerer":[163],"backbones,":[164],"tasks,":[167],"retraining.":[169]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-21T00:00:00"}