{"id":"https://openalex.org/W7169837641","doi":"https://doi.org/10.48550/arxiv.2607.16305","title":"LookME: Lookup-Based Multimodal Embeddings for Layer Injection in Vision-Language Models","display_name":"LookME: Lookup-Based Multimodal Embeddings for Layer Injection in Vision-Language Models","publication_year":2026,"publication_date":"2026-07-14","ids":{"openalex":"https://openalex.org/W7169837641","doi":"https://doi.org/10.48550/arxiv.2607.16305"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.16305","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.16305","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,"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.2607.16305","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074075623","display_name":"Zeyu Xu","orcid":"https://orcid.org/0000-0002-2149-9109"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zeyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013989244","display_name":"Xingzhong Hou","orcid":"https://orcid.org/0000-0003-1330-740X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hou, Xingzhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141247420","display_name":"Pengkai Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Pengkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141228792","display_name":"Siling Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Siling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103458235","display_name":"X X Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109587250","display_name":"Menghua Zhai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhai, Menghua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141249672","display_name":"Haoyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Haoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141243523","display_name":"Yunke Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yunke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082387577","display_name":"F T Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Fei","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":0.989799976348877,"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":0.989799976348877,"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":0.0020000000949949026,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.00139999995008111,"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/embedding","display_name":"Embedding","score":0.8773999810218811},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5037000179290771},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4722999930381775},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4668999910354614},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4641000032424927},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.46230000257492065},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.43209999799728394},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.420199990272522}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8773999810218811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8130000233650208},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5037000179290771},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33219999074935913},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2583000063896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.16305","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.16305","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,"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.2607.16305","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.16305","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,"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":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4526505172252655}],"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],"have":[3],"achieved":[4],"strong":[5],"progress":[6],"in":[7,23,60,96,123],"multimodal":[8,99,121,137,182,220],"understanding.":[9],"However,":[10],"scaling":[11,52],"dense":[12],"or":[13],"sparse":[14,172],"Mixture-of-Experts":[15],"(MoE)":[16],"models":[17,53],"to":[18,27,68,72,87,160],"improve":[19],"performance":[20],"limits":[21],"deployment":[22],"resource-constrained":[24],"environments":[25],"due":[26,86],"the":[28,44,88,113,158,161,167,195,216],"trade-off":[29,196],"between":[30],"high":[31],"memory":[32,62],"usage":[33],"from":[34,40,139,157],"full":[35],"loading":[36],"and":[37,64,129,186,201],"increased":[38],"latency":[39],"on-demand":[41,130],"loading.":[42,131],"Recently,":[43],"Per-Layer":[45],"Embedding":[46],"(PLE)":[47],"architecture":[48],"addresses":[49],"this":[50,108],"by":[51],"with":[54,170],"large":[55],"external":[56],"embedding":[57,141,188,221],"tables":[58],"stored":[59],"read-only":[61],"(ROM)":[63],"performing":[65],"lightweight":[66],"lookup":[67,134,148,168],"retrieve":[69],"relevant":[70],"embeddings":[71,85,100,122,138,179,183],"enhance":[73],"token":[74],"representations.":[75],"Nevertheless,":[76],"existing":[77],"PLE-style":[78,213],"methods":[79],"are":[80],"primarily":[81],"designed":[82],"for":[83,104,120],"text":[84],"convenience":[89],"of":[90,218],"ID-based":[91],"retrieval,":[92],"limiting":[93],"their":[94],"effectiveness":[95,217],"VLMs":[97,124],"where":[98],"contain":[101],"richer":[102],"information":[103],"visual":[105,206],"tasks.":[106],"In":[107],"paper,":[109],"we":[110,143,165],"propose":[111,144],"LookME,":[112],"first":[114],"framework":[115],"that":[116,154,209],"enables":[117],"lookup-based":[118,219],"enhancement":[119],"while":[125],"supporting":[126],"partitioned":[127],"storage":[128],"To":[132],"efficiently":[133],"arbitrary":[135],"continuous":[136],"large-scale":[140],"tables,":[142],"a":[145,151,171],"hierarchical":[146],"two-level":[147],"method":[149,169],"employing":[150],"coarse-to-fine":[152],"strategy":[153],"performs":[155],"lookups":[156],"scene-level":[159],"intra-scene":[162],"primitive-level.":[163],"Furthermore,":[164],"integrate":[166],"injection":[173],"strategy,":[174],"which":[175],"adaptively":[176],"prioritizes":[177],"critical":[178],"over":[180],"voluminous":[181],"within":[184],"layers,":[185,193],"facilitates":[187],"table":[189],"reuse":[190],"across":[191],"neighboring":[192],"improving":[194],"among":[197],"efficiency,":[198],"model":[199],"size,":[200],"performance.":[202],"Experiments":[203],"on":[204],"multiple":[205],"benchmarks":[207],"show":[208],"LookME":[210],"outperforms":[211],"text-only":[212],"methods,":[214],"validating":[215],"enhancement.":[222]},"counts_by_year":[],"updated_date":"2026-08-12T07:12:00.856984","created_date":"2026-07-22T00:00:00"}