{"id":"https://openalex.org/W7214093136","doi":"https://doi.org/10.1016/j.sysarc.2026.104016","title":"CADE: Context-aware dispatch engine for energy-efficient VLM inference on heterogeneous edge with discrete neural processing units","display_name":"CADE: Context-aware dispatch engine for energy-efficient VLM inference on heterogeneous edge with discrete neural processing units","publication_year":2026,"publication_date":"2026-09-23","ids":{"openalex":"https://openalex.org/W7214093136","doi":"https://doi.org/10.1016/j.sysarc.2026.104016"},"language":"en","primary_location":{"id":"doi:10.1016/j.sysarc.2026.104016","doi":"https://doi.org/10.1016/j.sysarc.2026.104016","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.sysarc.2026.104016","pdf_url":null,"source":{"id":"https://openalex.org/S127660348","display_name":"Journal of Systems Architecture","issn_l":"1383-7621","issn":["1383-7621","1873-6165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-d","jufo-2","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems Architecture","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5152506851","display_name":"Seongjin Yun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongjin Yun","raw_affiliation_strings":["Artificial Intelligence Computing Research Laboratory, Electronics and Telecommunications Research Institute, 218 Gajeong-ro, Yuseong-gu, Daejeon, 34129, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Computing Research Laboratory, Electronics and Telecommunications Research Institute, 218 Gajeong-ro, Yuseong-gu, Daejeon, 34129, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062319303","display_name":"Jeong-Si Kim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jeong-Si Kim","raw_affiliation_strings":["Artificial Intelligence Computing Research Laboratory, Electronics and Telecommunications Research Institute, 218 Gajeong-ro, Yuseong-gu, Daejeon, 34129, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Computing Research Laboratory, Electronics and Telecommunications Research Institute, 218 Gajeong-ro, Yuseong-gu, Daejeon, 34129, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062319303"],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":{"value":2540,"currency":"USD","value_usd":2540},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68826087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"181","issue":null,"first_page":"104016","last_page":"104016"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6714000105857849,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6714000105857849,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.24549999833106995,"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":0.04190000146627426,"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":0.8970000147819519},{"id":"https://openalex.org/keywords/edge-inference","display_name":"edge inference","score":0.5329999923706055},{"id":"https://openalex.org/keywords/request-routing","display_name":"request routing","score":0.656000018119812},{"id":"https://openalex.org/keywords/energy-efficiency","display_name":"energy efficiency","score":0.753000020980835},{"id":"https://openalex.org/keywords/nvidia-jetson-agx-orin","display_name":"NVIDIA Jetson AGX Orin","score":0.8360000252723694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8978999853134155},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5978999733924866},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4397999942302704},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.4221000075340271},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.34880000352859497},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3483000099658966},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29499998688697815},{"id":"https://openalex.org/C2988105877","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference system","level":5,"score":0.273499995470047},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.258899986743927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2565999925136566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.sysarc.2026.104016","doi":"https://doi.org/10.1016/j.sysarc.2026.104016","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.sysarc.2026.104016","pdf_url":null,"source":{"id":"https://openalex.org/S127660348","display_name":"Journal of Systems Architecture","issn_l":"1383-7621","issn":["1383-7621","1873-6165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-b","cwts-core","dongbi-d","jufo-2","norway-1","poland-70","russia-white-list-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Systems Architecture","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2769328306","https://openalex.org/W2783882151","https://openalex.org/W2963610939","https://openalex.org/W3156973125","https://openalex.org/W3175888430","https://openalex.org/W3175961224","https://openalex.org/W4319300748","https://openalex.org/W4390263770","https://openalex.org/W4396669842","https://openalex.org/W4400446017","https://openalex.org/W4401402799","https://openalex.org/W4404401018","https://openalex.org/W4408891426","https://openalex.org/W4409167686","https://openalex.org/W4409736305","https://openalex.org/W4410579485","https://openalex.org/W4411232024","https://openalex.org/W4411465418","https://openalex.org/W4411486537","https://openalex.org/W4415296517","https://openalex.org/W7089626961"],"related_works":["https://openalex.org/W7168414276","https://openalex.org/W4413361501","https://openalex.org/W7202205216","https://openalex.org/W7169858310","https://openalex.org/W7164818176","https://openalex.org/W7161886606","https://openalex.org/W4415250928","https://openalex.org/W7164126783","https://openalex.org/W7221146288","https://openalex.org/W7171655919"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-10-03T13:16:28.481748","created_date":"2026-09-24T00:00:00"}
