{"id":"https://openalex.org/W7150939104","doi":"https://doi.org/10.48550/arxiv.2604.03072","title":"MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMs","display_name":"MI-Pruner: Crossmodal Mutual Information-guided Token Pruner for Efficient MLLMs","publication_year":2026,"publication_date":"2026-04-03","ids":{"openalex":"https://openalex.org/W7150939104","doi":"https://doi.org/10.48550/arxiv.2604.03072"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.03072","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03072","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.2604.03072","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053783274","display_name":"Jiameng Li","orcid":"https://orcid.org/0000-0002-3486-3758"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiameng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133039946","display_name":"Aleksei Tiulpin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiulpin, Aleksei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133021917","display_name":"Matthew B. Blaschko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Blaschko, Matthew B.","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":0.9519000053405762,"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":0.9519000053405762,"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/T10028","display_name":"Topic Modeling","score":0.011599999852478504,"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/T10799","display_name":"Data Visualization and Analytics","score":0.0052999998442828655,"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/crossmodal","display_name":"Crossmodal","score":0.6869999766349792},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.6642000079154968},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6171000003814697},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5795000195503235},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5680999755859375},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5358999967575073},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5151000022888184},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.43389999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196000218391418},{"id":"https://openalex.org/C60115397","wikidata":"https://www.wikidata.org/wiki/Q5188732","display_name":"Crossmodal","level":4,"score":0.6869999766349792},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6171000003814697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5946000218391418},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5795000195503235},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5680999755859375},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5151000022888184},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.350600004196167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.32109999656677246},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30070000886917114},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2702000141143799},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.03072","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03072","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.2604.03072","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03072","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6090008616447449}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"For":[0],"multimodal":[1],"large":[2],"language":[3],"models":[4],"(MLLMs),":[5],"visual":[6,19,38,47,80],"information":[7],"is":[8,103],"relatively":[9],"sparse":[10],"compared":[11],"with":[12,49,129],"text.":[13],"As":[14],"a":[15,61],"result,":[16],"research":[17],"on":[18,32,70],"pruning":[20,54,127],"emerges":[21],"for":[22],"efficient":[23,105],"inference.":[24],"Current":[25],"approaches":[26],"typically":[27],"measure":[28,94],"token":[29],"importance":[30],"based":[31],"the":[33,37,42,98],"attention":[34,51,113],"scores":[35,52],"in":[36,41],"encoder":[39],"or":[40,115],"LLM":[43],"decoder,":[44],"then":[45],"select":[46],"tokens":[48],"high":[50],"while":[53],"others.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,73],"pursue":[60],"different":[62],"and":[63,81,106],"more":[64],"surgical":[65],"approach.":[66],"Instead":[67],"of":[68],"relying":[69],"mechanism-specific":[71],"signals,":[72],"directly":[74],"compute":[75],"Mutual":[76],"Information":[77],"(MI)":[78],"between":[79],"textual":[82],"features":[83],"themselves,":[84],"prior":[85],"to":[86,92,111],"their":[87],"interaction.":[88],"This":[89],"allows":[90],"us":[91],"explicitly":[93],"crossmodal":[95],"dependency":[96],"at":[97],"feature":[99],"levels.":[100],"Our":[101],"MI-Pruner":[102],"simple,":[104],"non-intrusive,":[107],"requiring":[108],"no":[109],"access":[110],"internal":[112],"maps":[114],"architectural":[116],"modifications.":[117],"Experimental":[118],"results":[119],"demonstrate":[120],"that":[121],"our":[122],"approach":[123],"outperforms":[124],"previous":[125],"attention-based":[126],"methods":[128],"minimal":[130],"latency.":[131]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-07T00:00:00"}