{"id":"https://openalex.org/W7161010454","doi":"https://doi.org/10.48550/arxiv.2605.11477","title":"LDDR: Linear-DPP-Based Dynamic-Resolution Frame Sampling for Video MLLMs","display_name":"LDDR: Linear-DPP-Based Dynamic-Resolution Frame Sampling for Video MLLMs","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7161010454","doi":"https://doi.org/10.48550/arxiv.2605.11477"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.11477","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11477","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":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.2605.11477","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084302554","display_name":"Jingfeng Chen","orcid":"https://orcid.org/0000-0001-6383-6532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jingfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134912964","display_name":"Jiawen Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Jiawen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136069865","display_name":"Wendi Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Wendi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016681207","display_name":"Yinuo Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yinuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136087654","display_name":"Jiaqi Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Jiaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136078549","display_name":"Sicong Leng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leng, Sicong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019866898","display_name":"Raghuveer Thirukovalluru","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thirukovalluru, Raghuveer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136032941","display_name":"Bhuwan Dhingra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhingra, Bhuwan","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/T10812","display_name":"Human Pose and Action Recognition","score":0.2328999936580658,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.2328999936580658,"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":0.211899995803833,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1704999953508377,"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":0.5788000226020813},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5785999894142151},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.535099983215332},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.503000020980835},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4758000075817108},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.47049999237060547},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.45159998536109924},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4465000033378601},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4343999922275543},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.38929998874664307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7883999943733215},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5788000226020813},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5785999894142151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5514000058174133},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.503000020980835},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.47049999237060547},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45339998602867126},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.45159998536109924},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4465000033378601},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4099999964237213},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.38929998874664307},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.37689998745918274},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.3433000147342682},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.33959999680519104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C88871306","wikidata":"https://www.wikidata.org/wiki/Q7208287","display_name":"Point process","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C204641915","wikidata":"https://www.wikidata.org/wiki/Q7315509","display_name":"Residual frame","level":4,"score":0.289900004863739},{"id":"https://openalex.org/C39394851","wikidata":"https://www.wikidata.org/wiki/Q921594","display_name":"Inter frame","level":4,"score":0.2809000015258789},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.11477","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11477","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":"doi:10.48550/arxiv.2605.11477","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11477","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4530577063560486}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0],"understanding":[1],"in":[2,68,139],"multimodal":[3],"large":[4],"language":[5],"models":[6],"requires":[7],"selecting":[8],"informative":[9],"frames":[10,104,162],"from":[11],"long,":[12],"redundant":[13],"videos":[14],"under":[15,133],"limited":[16],"visual-token":[17],"budgets.":[18],"Existing":[19],"methods":[20],"often":[21],"rely":[22],"on":[23],"uniform":[24],"sampling,":[25],"point-wise":[26],"relevance":[27],"scoring,":[28],"chunk-wise":[29],"selection,":[30],"or":[31,39,107],"agentic":[32],"exploration,":[33],"which":[34],"either":[35],"miss":[36],"global":[37],"dependencies":[38],"introduce":[40],"substantial":[41],"overhead.":[42],"We":[43],"propose":[44],"LDDR":[45,59,122],"(Linear":[46],"DPP-Based":[47],"Dynamic":[48],"Resolution),":[49],"a":[50,69,74,85,167],"training-free,":[51],"plug-and-play,":[52],"and":[53,94,119,136,154,165],"budget-aware":[54],"video":[55,114,172],"frame":[56,66,92],"sampling":[57],"framework.":[58],"performs":[60],"query-aware":[61],"Determinantal":[62],"Point":[63],"Process":[64],"(DPP)":[65],"selection":[67],"task-conditioned":[70],"feature":[71],"space,":[72],"achieving":[73,128],"3x":[75],"runtime":[76],"speedup":[77],"over":[78],"standard":[79],"DPP":[80,87],"baselines.":[81],"It":[82],"further":[83],"introduces":[84],"Group":[86],"importance":[88],"metric":[89],"to":[90,101],"guide":[91],"retention":[93],"dynamic":[95],"resolution":[96],"allocation,":[97],"assigning":[98],"more":[99],"tokens":[100],"informative,":[102],"non-redundant":[103],"while":[105],"downscaling":[106],"pruning":[108],"less":[109],"useful":[110],"ones.":[111],"Across":[112],"four":[113],"benchmarks":[115],"spanning":[116],"short-,":[117],"medium-,":[118],"long-range":[120],"videos,":[121],"consistently":[123,145],"outperforms":[124],"the":[125],"next-best":[126],"baselines,":[127],"gains":[129],"of":[130],"2.5":[131],"points":[132,138],"budget-constrained":[134],"settings":[135],"1.6":[137],"high-budget":[140],"scenarios.":[141],"These":[142],"improvements":[143],"are":[144,163],"observed":[146],"across":[147],"multiple":[148],"MLLM":[149],"backbones,":[150],"including":[151],"both":[152],"open-":[153],"closed-source":[155],"models.":[156],"Qualitative":[157],"analysis":[158],"confirms":[159],"that":[160],"relevant":[161],"selected":[164],"allocated":[166],"higher":[168],"budget,":[169],"facilitating":[170],"improved":[171],"understanding.":[173]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-14T00:00:00"}