{"id":"https://openalex.org/W7131216967","doi":"https://doi.org/10.1109/vcip67698.2025.11396917","title":"Quadtree Partitioning-based Visual Token Pruning for MLLMs Considering Information Density","display_name":"Quadtree Partitioning-based Visual Token Pruning for MLLMs Considering Information Density","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7131216967","doi":"https://doi.org/10.1109/vcip67698.2025.11396917"},"language":null,"primary_location":{"id":"doi:10.1109/vcip67698.2025.11396917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126664453","display_name":"Yuntao Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuntao Wei","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126691662","display_name":"Jinming Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinming Liu","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,P.R. China,315200"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,P.R. China,315200","institution_ids":["https://openalex.org/I4210165339"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101102569","display_name":"Shengyang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyang Zhao","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,P.R. China,315200"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,P.R. China,315200","institution_ids":["https://openalex.org/I4210165339"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126737322","display_name":"Zhibo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibo Chen","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124096975","display_name":"Wenjun Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Zeng","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,P.R. China,315200"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,P.R. China,315200","institution_ids":["https://openalex.org/I4210165339"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101896775","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0001-7394-0210"},"institutions":[{"id":"https://openalex.org/I4210165339","display_name":"Ningbo Institute of Industrial Technology","ror":"https://ror.org/05nqg3g04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165339"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,P.R. China,315200"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology,Ningbo Institute of Digital Twin,Ningbo,P.R. China,315200","institution_ids":["https://openalex.org/I4210165339"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.6612446,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.16949999332427979,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.16949999332427979,"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":0.10610000044107437,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0860000029206276,"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/security-token","display_name":"Security token","score":0.7749000191688538},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6171000003814697},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5335000157356262},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.48510000109672546},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.459199994802475},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4307999908924103},{"id":"https://openalex.org/keywords/quadtree","display_name":"Quadtree","score":0.4036000072956085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777899980545044},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7749000191688538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6177999973297119},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6171000003814697},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5335000157356262},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C151416825","wikidata":"https://www.wikidata.org/wiki/Q934791","display_name":"Quadtree","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.366100013256073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3107999861240387},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30079999566078186},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27239999175071716}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip67698.2025.11396917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip67698.2025.11396917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2505609860","https://openalex.org/W2963622213","https://openalex.org/W2979382951","https://openalex.org/W4321636575","https://openalex.org/W4385245566","https://openalex.org/W4389523832","https://openalex.org/W4402716381","https://openalex.org/W4402727764","https://openalex.org/W4403939369","https://openalex.org/W4404782803","https://openalex.org/W4404784276","https://openalex.org/W4409363282","https://openalex.org/W4409367031","https://openalex.org/W4411725552","https://openalex.org/W4416707474"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"excel":[5],"at":[6,142],"comprehensive":[7],"understanding":[8],"by":[9,22,149,157],"integrating":[10],"visual":[11,24,111],"and":[12,125,156],"textual":[13],"information.":[14],"However,":[15],"their":[16,80],"inference":[17],"speed":[18],"is":[19],"often":[20],"bottlenecked":[21],"redundant":[23],"token":[25,41,60,145],"inputs.":[26],"Existing":[27],"methods":[28],"tend":[29],"to":[30,44,79,108,118,151,154,160],"alleviate":[31],"this":[32,53],"issue":[33],"with":[34,103],"a":[35,57,65,93,143],"heuristic":[36],"pruning":[37,61],"strategy":[38],"based":[39,63],"on":[40,64,88,123],"importance,":[42],"tailored":[43],"certain":[45],"commonly":[46],"adopted":[47],"vision":[48],"encoders":[49],"like":[50],"CLIP.":[51],"In":[52],"paper,":[54],"we":[55,72,90,99],"propose":[56,92],"novel":[58],"training-free":[59],"method":[62,132],"well-designed":[66],"metric":[67],"of":[68,138],"information":[69,85],"density,":[70],"where":[71],"decide":[73],"which":[74,98],"tokens":[75,102,117],"are":[76],"retained":[77],"according":[78],"entropy,":[81],"following":[82],"the":[83,110,161],"classic":[84],"theory.":[86],"Based":[87],"that,":[89],"further":[91],"quadtree":[94],"partitioning":[95],"strategy,":[96],"in":[97],"retain":[100],"these":[101],"higher":[104],"entropy":[105],"so":[106],"as":[107],"preserve":[109],"spatial":[112],"structure":[113],"while":[114],"allocating":[115],"more":[116,119],"informative":[120],"regions.":[121],"Experiments":[122],"LLaVA-v1.5-7B":[124],"13B":[126],"across":[127],"six":[128],"benchmarks":[129],"show":[130],"our":[131],"achieves":[133],"state-of-the-art":[134],"performance\u2014retaining":[135],"over":[136],"90%":[137],"full-token":[139],"accuracy":[140],"even":[141],"6.25%":[144],"budget\u2014while":[146],"cutting":[147],"TFLOPs":[148],"up":[150],"20%":[152],"compared":[153,159],"FastV":[155],"81%":[158],"original":[162],"LLaVA-v1.5.":[163]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-25T00:00:00"}