{"id":"https://openalex.org/W7161585240","doi":"https://doi.org/10.48550/arxiv.2605.15621","title":"LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMs","display_name":"LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMs","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161585240","doi":"https://doi.org/10.48550/arxiv.2605.15621"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.15621","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15621","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.2605.15621","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136417447","display_name":"Hongyu Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Hongyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136442096","display_name":"Feng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026838971","display_name":"Wenwei Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Wenwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136426989","display_name":"Huanling Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Huanling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136366613","display_name":"Tianjun Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Tianjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136387284","display_name":"Shikai Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Shikai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136424336","display_name":"Yao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136428095","display_name":"Jiawei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiawei","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":0.6847000122070312,"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":0.6847000122070312,"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":0.08079999685287476,"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":0.06710000336170197,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.765999972820282},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6118999719619751},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.48019999265670776},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46639999747276306},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4632999897003174},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4471000134944916},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43849998712539673},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.39719998836517334}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.765999972820282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113000154495239},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6118999719619751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5181999802589417},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.48019999265670776},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43849998712539673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41690000891685486},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C115067241","wikidata":"https://www.wikidata.org/wiki/Q1639854","display_name":"Token passing","level":3,"score":0.3386000096797943},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28780001401901245},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2590000033378601}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.15621","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15621","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.2605.15621","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15621","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"vision-language":[1],"models":[2,78],"(LVLMs)":[3],"achieve":[4],"strong":[5],"multimodal":[6],"understanding,":[7],"but":[8],"their":[9],"inference":[10],"cost":[11],"grows":[12],"rapidly":[13],"with":[14,92,169,181],"the":[15,55,59,72,123,151,165,177],"number":[16],"of":[17,58,74,104,127,164,176],"visual":[18,45,60,68,84,128],"tokens,":[19],"especially":[20],"for":[21],"high-resolution":[22],"images":[23],"and":[24,79,132,174],"long":[25],"videos.":[26],"Existing":[27],"attention-based":[28],"methods":[29,43],"estimate":[30],"token":[31,61,69,85,136,172,184],"importance":[32],"from":[33,71],"attention":[34],"scores,":[35],"which":[36],"may":[37],"introduce":[38],"positional":[39],"bias,":[40],"while":[41],"representation-based":[42],"reduce":[44],"redundancy":[46],"based":[47],"on":[48],"feature":[49],"relations":[50],"or":[51],"reconstruction":[52],"errors,":[53],"overlooking":[54],"global":[56],"structure":[57],"set.":[62],"In":[63],"this":[64,111,142],"paper,":[65],"we":[66,81,113],"revisit":[67],"compression":[70,118],"perspective":[73],"low-rank":[75,90,125,152],"compressibility.":[76],"Across":[77],"datasets,":[80],"observe":[82],"that":[83,96,120,146,157],"representations":[86],"exhibit":[87],"a":[88,93,101,116],"pronounced":[89],"structure,":[91],"dominant":[94,124],"subspace":[95,126],"remains":[97],"stable":[98],"even":[99],"after":[100],"large":[102],"fraction":[103],"tokens":[105,129,145],"is":[106],"randomly":[107],"removed.":[108],"Motivated":[109],"by":[110,137,150],"finding,":[112],"propose":[114],"LRCP,":[115],"training-free":[117],"framework":[119],"first":[121],"estimates":[122],"via":[130],"PCA,":[131],"then":[133],"scores":[134],"each":[135],"its":[138],"projection":[139],"residual":[140],"onto":[141],"subspace,":[143],"retaining":[144],"are":[147],"poorly":[148],"explained":[149],"background.":[153],"Extensive":[154],"experiments":[155],"show":[156],"LRCP":[158],"achieves":[159],"superior":[160],"results,":[161],"preserving":[162],"94.7%":[163],"original":[166],"image-understanding":[167],"performance":[168],"an":[170,182],"88.9%":[171],"reduction":[173],"97.8%":[175],"average":[178],"video-understanding":[179],"accuracy":[180],"87.5%":[183],"reduction.":[185]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-19T00:00:00"}