{"id":"https://openalex.org/W7134271819","doi":"https://doi.org/10.48550/arxiv.2603.05950","title":"Energy-Driven Adaptive Visual Token Pruning for Efficient Vision-Language Models","display_name":"Energy-Driven Adaptive Visual Token Pruning for Efficient Vision-Language Models","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7134271819","doi":"https://doi.org/10.48550/arxiv.2603.05950"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.05950","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128447955","display_name":"Jialuo He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Jialuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014199941","display_name":"Huangxun Chen","orcid":"https://orcid.org/0000-0002-0313-4421"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Huangxun","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29924953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9182000160217285,"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":0.9182000160217285,"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":0.024700000882148743,"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":0.017999999225139618,"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":0.7907000184059143},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5853999853134155},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5435000061988831},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4496000111103058},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4023999869823456},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3276999890804291}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7907000184059143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6248999834060669},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5853999853134155},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5435000061988831},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4350999891757965},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34130001068115234},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33230000734329224},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C126537357","wikidata":"https://www.wikidata.org/wiki/Q372948","display_name":"Hue","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29750001430511475},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.05950","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.05950","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.05950","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":"pmh:doi:10.48550/arxiv.2603.05950","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.40237733721733093}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"token":[1,42,97],"reduction":[2],"is":[3,128],"critical":[4],"for":[5],"accelerating":[6],"Vision-Language":[7],"Models":[8],"(VLMs),":[9],"yet":[10],"most":[11],"existing":[12],"approaches":[13],"rely":[14],"on":[15,83,115],"a":[16,56,110],"fixed":[17],"budget":[18,43],"shared":[19],"across":[20],"all":[21],"inputs,":[22],"overlooking":[23],"the":[24,41,45,50,116,125],"substantial":[25],"variation":[26],"in":[27],"image":[28],"information":[29],"density.":[30],"We":[31,80],"propose":[32],"E-AdaPrune,":[33],"an":[34,102],"energy-driven":[35],"adaptive":[36],"pruning":[37],"framework":[38],"that":[39],"determines":[40],"from":[44],"singular":[46,122],"value":[47,123],"spectrum":[48],"of":[49,59,105],"visual":[51],"features":[52],"space.":[53],"By":[54],"preserving":[55],"certain":[57],"proportion":[58],"spectral":[60],"energy,":[61],"our":[62],"method":[63],"allocates":[64],"more":[65],"tokens":[66],"to":[67,107,130],"information-dense":[68],"scenes":[69],"while":[70],"aggressively":[71],"compressing":[72],"redundant":[73],"ones,":[74],"without":[75],"introducing":[76],"additional":[77,126],"learnable":[78],"parameters.":[79],"evaluate":[81],"E-AdaPrune":[82,99],"nine":[84],"benchmarks":[85],"and":[86,92],"three":[87],"VLM":[88],"backbones,":[89],"LLaVA-1.5-7B,":[90],"LLaVA-1.5-13B,":[91],"LLaVA-NeXT-8B.":[93],"Under":[94],"matched":[95],"average":[96,103],"budgets,":[98],"consistently":[100],"yields":[101],"improvement":[104],"up":[106],"0.6\\%,":[108],"including":[109],"significant":[111],"+5.1\\%":[112],"relative":[113],"boost":[114],"MMVet":[117],"reasoning":[118],"task.":[119],"Using":[120],"randomized":[121],"decomposition,":[124],"latency":[127],"limited":[129],"8ms":[131],"per":[132],"image.":[133]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-03-10T00:00:00"}