{"id":"https://openalex.org/W7138169001","doi":"https://doi.org/10.48550/arxiv.2603.14882","title":"LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language Models","display_name":"LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language Models","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7138169001","doi":"https://doi.org/10.48550/arxiv.2603.14882"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.14882","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14882","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.14882","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043879030","display_name":"Soumyaratna Debnath","orcid":"https://orcid.org/0000-0002-3690-7216"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Debnath, Soumyaratna","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093774792","display_name":"Bui Duc Manh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manh, Bui Duc","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129747657","display_name":"Zinan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zinan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129706367","display_name":"Lin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043879030"],"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":0.9840999841690063,"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":0.9840999841690063,"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":0.0035000001080334187,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0027000000700354576,"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/fidelity","display_name":"Fidelity","score":0.6710000038146973},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6074000000953674},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5641000270843506},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5404999852180481},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.5205000042915344},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5070000290870667},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4781000018119812},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4641000032424927},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4521999955177307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6819000244140625},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6710000038146973},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6074000000953674},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5641000270843506},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5622000098228455},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5404999852180481},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.5205000042915344},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.42160001397132874},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3984000086784363},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C4144372","wikidata":"https://www.wikidata.org/wiki/Q675287","display_name":"Magnification","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C89720835","wikidata":"https://www.wikidata.org/wiki/Q1531701","display_name":"Global illumination","level":3,"score":0.33709999918937683},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.14882","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14882","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.14882","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14882","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"typically":[3],"assume":[4],"a":[5,71,102,109],"uniform":[6,32,149,184],"spatial":[7],"fidelity":[8],"across":[9,154],"the":[10,23,47,69,142,201,211],"entire":[11],"field":[12],"of":[13,15,43,51,123,171,200,210],"view":[14],"visual":[16,53,159],"inputs,":[17],"dedicating":[18],"equal":[19],"precision":[20],"to":[21,85,100,134,183,195],"even":[22],"uninformative":[24],"regions.":[25],"By":[26],"contrast,":[27],"human":[28,83],"vision":[29,84],"is":[30,36,99,216],"neither":[31],"nor":[33],"static;":[34],"it":[35],"adaptive,":[37,87],"selective,":[38],"and":[39,61,79,150,157,178,198,208,219],"resource-efficient.":[40],"In":[41],"light":[42],"this,":[44],"we":[45,125],"present":[46],"first":[48],"systematic":[49],"analysis":[50],"bio-inspired":[52],"representation":[54],"methods,":[55],"providing":[56],"insights":[57],"for":[58,90],"more":[59],"efficient":[60,88],"adaptive":[62],"VLMs.":[63],"We":[64,145],"propose":[65],"LLMind":[66,147,192,215],"(Looking":[67],"Like":[68],"Mind),":[70],"novel":[72],"training-free":[73],"framework":[74],"that":[75,112],"mimics":[76],"foveated":[77],"encoding":[78],"cortical":[80],"magnification":[81],"in":[82],"achieve":[86],"representations":[89],"VLMs":[91,223],"under":[92,186],"tight":[93,187],"pixel":[94,188],"budgets.":[95,189],"Our":[96],"key":[97],"idea":[98],"explore":[101],"Bio-inspired":[103],"Adaptive":[104],"Sampling":[105],"Strategy":[106],"(BASS),":[107],"enabling":[108],"Mobius-parameterized":[110],"module":[111],"performs":[113],"non-uniform":[114],"sampling":[115,152,185],"while":[116],"preserving":[117],"global":[118],"scene":[119],"structure.":[120],"On":[121],"top":[122],"BASS,":[124],"introduce":[126],"closed-loop":[127],"semantic":[128],"feedback":[129],"(CSF)":[130],"via":[131],"test-time":[132],"adaptation":[133],"align":[135],"perceptual":[136],"saliency":[137],"with":[138,168,221],"textual":[139],"information":[140],"from":[141],"frozen":[143],"VLM.":[144],"evaluate":[146],"against":[148],"other":[151],"baselines":[153],"diverse":[155],"scene-level":[156],"region-guided":[158],"question":[160],"answering":[161],"benchmarks.":[162],"The":[163],"results":[164],"show":[165],"dramatic":[166],"gains,":[167],"average":[169],"improvements":[170],"+20%":[172],"on":[173,176,180],"VQAv2,":[174],"+38%":[175],"Seed-Bench,":[177],"+37%":[179],"A-OKVQA":[181],"compared":[182],"More":[190],"surprisingly,":[191],"retains":[193],"up":[194],"82%,":[196],"92%,":[197],"97%":[199],"full-resolution":[202],"performance":[203],"using":[204],"only":[205],"1%,":[206],"3%,":[207],"5%":[209],"pixels,":[212],"respectively.":[213],"Moreover,":[214],"lightweight,":[217],"plug-and-play,":[218],"compatible":[220],"existing":[222],"without":[224],"requiring":[225],"architectural":[226],"changes.":[227]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}