{"id":"https://openalex.org/W7224076953","doi":"https://doi.org/10.48550/arxiv.2610.37019","title":"V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models","display_name":"V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224076953","doi":"https://doi.org/10.48550/arxiv.2610.37019"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.37019","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37019","pdf_url":"https://arxiv.org/pdf/2610.37019","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.37019","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111027793","display_name":"Miso Choi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Choi, Miso","raw_affiliation_strings":["Dept. of Computer Science and Engineering , Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering , Korea University","institution_ids":["https://openalex.org/I197347611","https://openalex.org/I4210161052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160048253","display_name":"Daekeun Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Kim, Daekeun","raw_affiliation_strings":["Dept. of Computer Science and Engineering , Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering , Korea University","institution_ids":["https://openalex.org/I197347611","https://openalex.org/I4210161052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160021251","display_name":"Eunji Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kim, Eunji","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159996662","display_name":"Jungbeom Lee","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]},{"id":"https://openalex.org/I4210161052","display_name":"Korea University","ror":"https://ror.org/05m1gnk07","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210161052"]}],"countries":["JP","KR"],"is_corresponding":false,"raw_author_name":"Lee, Jungbeom","raw_affiliation_strings":["Dept. of Computer Science and Engineering , Korea University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering , Korea University","institution_ids":["https://openalex.org/I197347611","https://openalex.org/I4210161052"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":1.0,"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":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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":0.0,"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/vision-language-models","display_name":"vision-language models","score":0.9940000176429749},{"id":"https://openalex.org/keywords/zero-shot-transfer","display_name":"zero-shot transfer","score":0.656000018119812},{"id":"https://openalex.org/keywords/lora-adapters","display_name":"LoRA adapters","score":0.5619999766349792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727400004863739},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6585000157356262},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6520000100135803},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5684000253677368},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49559998512268066},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4278999865055084},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3734000027179718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3723999857902527},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C178278151","wikidata":"https://www.wikidata.org/wiki/Q7936607","display_name":"Visual memory","level":3,"score":0.33629998564720154},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C200756006","wikidata":"https://www.wikidata.org/wiki/Q336092","display_name":"Visual angle","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C58632812","wikidata":"https://www.wikidata.org/wiki/Q7936625","display_name":"Visual short-term memory","level":4,"score":0.25870001316070557},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.37019","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37019","pdf_url":"https://arxiv.org/pdf/2610.37019","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.37019","doi":"https://doi.org/10.48550/arxiv.2610.37019","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.37019","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.37019","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.37019","pdf_url":"https://arxiv.org/pdf/2610.37019","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2835782617","display_name":null,"funder_award_id":"RS-2026-25522672","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G2943653263","display_name":null,"funder_award_id":"RS-2024-00397085","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4001346034","display_name":null,"funder_award_id":"RS-2022-II220043","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4286615259","display_name":null,"funder_award_id":"RS-2022-","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G446496831","display_name":null,"funder_award_id":"IITP-2025-RS-2022-00156295","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4734332584","display_name":null,"funder_award_id":"IITP-2026-RS-2025-02304828","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4736896955","display_name":null,"funder_award_id":"IITP-2026-RS-2024-00397085","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G5073717115","display_name":null,"funder_award_id":"2026-RS-2020-II201819","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G6038997514","display_name":null,"funder_award_id":"IITP-2026-RS-2025-02304828","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8262039678","display_name":null,"funder_award_id":"IITP-2026-RS-2020-II201819","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G9001174746","display_name":null,"funder_award_id":"RS-2026-25621049","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224076953.pdf","grobid_xml":"https://content.openalex.org/works/W7224076953.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7169837641","https://openalex.org/W4396822212","https://openalex.org/W7172005688","https://openalex.org/W4416342050","https://openalex.org/W7215839340","https://openalex.org/W4399114997","https://openalex.org/W4416074408","https://openalex.org/W7212303983","https://openalex.org/W4391801217","https://openalex.org/W4377865926"],"abstract_inverted_index":{"Embedding-level":[0],"scaling":[1],"expands":[2],"the":[3,86,92,121],"capacity":[4,137,153,176],"of":[5,131],"language":[6],"models":[7,26],"through":[8,70,94],"lookup-based":[9],"memory":[10,54,68,149],"rather":[11,155,180],"than":[12,156,181],"by":[13],"increasing":[14],"model":[15],"depth,":[16],"width,":[17],"or":[18,134],"dense":[19],"computation.":[20],"Extending":[21],"this":[22,175],"idea":[23],"to":[24,113],"vision-language":[25],"(VLMs)":[27],"is":[28,83,150,164,186],"challenging":[29],"because":[30],"visual":[31,52,59,148],"features":[32,60],"are":[33,89,118],"continuous,":[34],"spatially":[35,66],"structured,":[36],"and":[37,74,85,110,169],"query-dependent,":[38],"unlike":[39],"discrete":[40],"text":[41],"tokens":[42],"that":[43,146],"naturally":[44],"support":[45],"n-gram":[46],"lookup.":[47],"We":[48],"introduce":[49],"V-LUMEN,":[50],"a":[51,62,95,106,125,132,157],"lookup":[53,162],"for":[55],"VLMs.":[56],"V-LUMEN":[57,103,139],"discretizes":[58],"with":[61,77],"frozen":[63,107],"codebook,":[64],"builds":[65],"aware":[67],"keys":[69],"spatial":[71],"aggregation-based":[72],"hashing,":[73],"modulates":[75],"them":[76],"text-conditioned":[78],"relevance":[79],"signals;":[80],"all":[81],"addressing":[82],"non-parametric,":[84],"retrieved":[87],"embeddings":[88],"fused":[90],"into":[91,138],"backbone":[93,109],"gated":[96],"residual":[97],"pathway.":[98],"On":[99],"five":[100],"reasoning-intensive":[101],"benchmarks,":[102],"substantially":[104],"improves":[105],"Qwen3-VL-2B":[108],"transfers":[111],"zero-shot":[112],"three":[114],"benchmarks":[115],"whose":[116],"images":[117],"disjoint":[119],"from":[120],"training":[122],"data.":[123],"At":[124],"matched":[126],"parameter":[127],"budget,":[128],"moving":[129],"part":[130],"LoRA":[133],"MoE":[135],"adapter's":[136],"preserves":[140],"accuracy":[141],"on":[142],"two":[143],"backbones,":[144],"indicating":[145],"external":[147],"an":[151],"independent":[152],"axis":[154],"stronger":[158],"adaptation":[159],"method.":[160],"Because":[161],"cost":[163],"constant":[165],"in":[166,178,182],"table":[167],"size":[168],"incurred":[170],"only":[171],"once":[172],"at":[173,188],"prefill,":[174],"grows":[177],"storage":[179],"per-token":[183],"compute.":[184],"Code":[185],"available":[187],"https://github.com/miso-choi/V-Lumen.":[189]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-29T00:00:00"}