{"id":"https://openalex.org/W7154128239","doi":"https://doi.org/10.48550/arxiv.2604.09547","title":"Tango: Taming Visual Signals for Efficient Video Large Language Models","display_name":"Tango: Taming Visual Signals for Efficient Video Large Language Models","publication_year":2026,"publication_date":"2026-04-10","ids":{"openalex":"https://openalex.org/W7154128239","doi":"https://doi.org/10.48550/arxiv.2604.09547"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.09547","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09547","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":null,"license_id":null,"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.2604.09547","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073775343","display_name":"Shukang Yin","orcid":"https://orcid.org/0000-0002-5356-1800"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Shukang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133495296","display_name":"Sirui Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Sirui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133529439","display_name":"Hanchao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hanchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125257983","display_name":"Baozhi Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Baozhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133547229","display_name":"Xianquan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xianquan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014172220","display_name":"Chaoyou Fu","orcid":"https://orcid.org/0000-0002-0079-7668"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Chaoyou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133503292","display_name":"Enhong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Enhong","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":0.9621999859809875,"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":0.9621999859809875,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.007899999618530273,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.006899999920278788,"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/selection","display_name":"Selection (genetic algorithm)","score":0.6277999877929688},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5249000191688538},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.517799973487854},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5156000256538391},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.510699987411499},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.49309998750686646},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.46700000762939453},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.39160001277923584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7806000113487244},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6277999877929688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557699978351593},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5249000191688538},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.517799973487854},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5156000256538391},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4309999942779541},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33399999141693115},{"id":"https://openalex.org/C2780760462","wikidata":"https://www.wikidata.org/wiki/Q7927952","display_name":"Video modeling","level":4,"score":0.32910001277923584},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31349998712539673},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.09547","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09547","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.09547","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09547","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.44602110981941223,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Token":[0],"pruning":[1],"has":[2],"emerged":[3],"as":[4],"a":[5,85,98,158],"mainstream":[6],"approach":[7],"for":[8,50],"developing":[9],"efficient":[10],"Video":[11,124],"Large":[12],"Language":[13],"Models":[14],"(Video":[15],"LLMs).":[16],"This":[17],"work":[18],"revisits":[19],"and":[20,29,59,63,106,126,133],"advances":[21],"the":[22,51,91,131,144,151],"two":[23,35],"predominant":[24],"token-pruning":[25],"paradigms:":[26],"attention-based":[27,103],"selection":[28,44],"similarity-based":[30,66],"clustering.":[31],"Our":[32],"study":[33],"reveals":[34],"critical":[36],"limitations":[37],"in":[38,61,73],"existing":[39],"methods:":[40],"(1)":[41],"conventional":[42],"top-k":[43],"strategies":[45],"fail":[46],"to":[47,89,101,113],"fully":[48],"account":[49],"attention":[52],"distribution,":[53],"which":[54],"is":[55],"often":[56],"spatially":[57],"multi-modal":[58],"long-tailed":[60],"magnitude;":[62],"(2)":[64],"direct":[65],"clustering":[67],"frequently":[68],"generates":[69],"fragmented":[70],"clusters,":[71],"resulting":[72],"distorted":[74],"representations":[75],"after":[76],"pooling.":[77],"To":[78],"address":[79],"these":[80],"bottlenecks,":[81],"we":[82],"propose":[83],"Tango,":[84],"novel":[86],"framework":[87],"designed":[88],"optimize":[90],"utilization":[92],"of":[93,135,143,150],"visual":[94],"signals.":[95],"Tango":[96,147],"integrates":[97],"diversity-driven":[99],"strategy":[100],"enhance":[102],"token":[104],"selection,":[105],"introduces":[107],"Spatio-temporal":[108],"Rotary":[109],"Position":[110],"Embedding":[111],"(ST-RoPE)":[112],"preserve":[114],"geometric":[115],"structure":[116],"via":[117],"locality":[118],"priors.":[119],"Comprehensive":[120],"experiments":[121],"across":[122],"various":[123],"LLMs":[125],"video":[127,145],"understanding":[128],"benchmarks":[129],"demonstrate":[130],"effectiveness":[132],"generalizability":[134],"our":[136],"approach.":[137],"Notably,":[138],"when":[139],"retaining":[140],"only":[141],"10%":[142],"tokens,":[146],"preserves":[148],"98.9%":[149],"original":[152],"performance":[153],"on":[154],"LLaVA-OV":[155],"while":[156],"delivering":[157],"1.88$\\times$":[159],"inference":[160],"speedup.":[161]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-14T00:00:00"}