{"id":"https://openalex.org/W7124985210","doi":"https://doi.org/10.1109/cloudcom67567.2025.11331339","title":"ModelMap: Kernel-Level Zero-Copy On-Demand Model Loading for Edge AI","display_name":"ModelMap: Kernel-Level Zero-Copy On-Demand Model Loading for Edge AI","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W7124985210","doi":"https://doi.org/10.1109/cloudcom67567.2025.11331339"},"language":null,"primary_location":{"id":"doi:10.1109/cloudcom67567.2025.11331339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cloudcom67567.2025.11331339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123446144","display_name":"Fei Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fei Yi","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102730412","display_name":"Yuyi Wang","orcid":"https://orcid.org/0000-0001-7273-9873"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5123446144"],"corresponding_institution_ids":["https://openalex.org/I4210145761"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73143206,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.2800000011920929,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.2800000011920929,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.19519999623298645,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.14219999313354492,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/scalability","display_name":"Scalability","score":0.5936999917030334},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5410000085830688},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5196999907493591},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5009999871253967},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.4652999937534332},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4406999945640564},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.43619999289512634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764000296592712},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5936999917030334},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5410000085830688},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5196999907493591},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.4652999937534332},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4250999987125397},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.387800008058548},{"id":"https://openalex.org/C553261973","wikidata":"https://www.wikidata.org/wiki/Q14579","display_name":"Linux kernel","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.32659998536109924},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C10597312","wikidata":"https://www.wikidata.org/wiki/Q5473302","display_name":"Forwarding plane","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.26910001039505005},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.26089999079704285}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cloudcom67567.2025.11331339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cloudcom67567.2025.11331339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 lEEE International Conference on Cloud Computing Technology and Science (CloudCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2010150096","https://openalex.org/W2996801272","https://openalex.org/W3081168214","https://openalex.org/W3172744943","https://openalex.org/W3190496320","https://openalex.org/W4285137472","https://openalex.org/W4391093958","https://openalex.org/W4400649484","https://openalex.org/W4405082770","https://openalex.org/W4405754931","https://openalex.org/W4406014253","https://openalex.org/W4407513400","https://openalex.org/W4409048055"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,7,89,95],"growing":[2],"deployment":[3],"of":[4,26,80],"AI":[5,75],"at":[6],"edge,":[8],"running":[9],"inference":[10,148],"on":[11],"resource-constrained":[12],"devices":[13],"increasingly":[14],"requires":[15,144],"efficient":[16],"access":[17,72,136,158],"to":[18,73,105,121,138,147],"large":[19,74],"models.":[20],"However,":[21],"modern":[22],"models":[23,76,108],"contain":[24],"billions":[25],"parameters,":[27],"far":[28],"exceeding":[29],"local":[30],"memory,":[31],"while":[32],"TCP/IP-based":[33],"edge":[34,160],"networks":[35],"make":[36],"bulk":[37],"transfers":[38],"inefficient.":[39],"Existing":[40],"approaches,":[41],"such":[42],"as":[43,109],"full":[44],"downloads":[45],"or":[46],"network":[47,140],"file":[48],"systems,":[49],"incur":[50],"high":[51],"latency,":[52],"memory":[53],"overhead,":[54],"and":[55,92,124,134],"lack":[56],"fine-grained":[57],"control.":[58],"We":[59],"present":[60],"ModelMap,":[61],"a":[62,100],"zero-copy":[63],"remote":[64,101,107,156],"memory-mapped":[65],"storage":[66],"system":[67],"that":[68],"enables":[69],"transparent,":[70],"on-demand":[71],"over":[77],"TCP/IP.":[78],"Instead":[79],"preloading":[81],"entire":[82],"models,":[83],"ModelMap":[84,117,143],"intercepts":[85],"page":[86],"faults":[87],"in":[88,114,159],"Linux":[90],"kernel":[91,115,131],"fetches":[93],"only":[94],"needed":[96],"parameter":[97],"pages":[98],"from":[99],"server,":[102],"allowing":[103],"applications":[104],"treat":[106],"local.":[110],"By":[111],"operating":[112],"entirely":[113],"space,":[116],"reduces":[118],"latency":[119],"compared":[120],"user-space":[122],"methods":[123],"avoids":[125],"redundant":[126],"copies.":[127],"It":[128],"further":[129],"leverages":[130],"caching,":[132],"prefetching,":[133],"sequential":[135],"optimizations":[137],"mitigate":[139],"bottlenecks.":[141],"Crucially,":[142],"no":[145],"changes":[146],"code,":[149],"offering":[150],"an":[151],"efficient,":[152],"scalable":[153],"foundation":[154],"for":[155],"model":[157],"environments.":[161]},"counts_by_year":[],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2026-01-21T00:00:00"}
