{"id":"https://openalex.org/W7152633838","doi":"https://doi.org/10.1145/3774904.3792382","title":"<scp>LaTune</scp> : Lightweight and Adaptive Configuration Tuning for LLM Inference on Edge Devices","display_name":"<scp>LaTune</scp> : Lightweight and Adaptive Configuration Tuning for LLM Inference on Edge Devices","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152633838","doi":"https://doi.org/10.1145/3774904.3792382"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792382","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792382","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792382","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123704118","display_name":"Siqi Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siqi Zhong","raw_affiliation_strings":["Institute for Artificial Intelligence, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0134-2683","affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104285228","display_name":"Mugeng Liu","orcid":"https://orcid.org/0009-0002-7625-8721"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mugeng Liu","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-7625-8721","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100568210","display_name":"Haiyang Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Shen","raw_affiliation_strings":["Institute for Artificial Intelligence, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-4599-3198","affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044039411","display_name":"C PAN","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongyang Pan","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-6159-5761","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101614814","display_name":"Yun Ma","orcid":"https://orcid.org/0000-0001-7866-4075"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Ma","raw_affiliation_strings":["Institute for Artificial Intelligence, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7866-4075","affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53175159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5404","last_page":"5414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.0754999965429306,"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/T12127","display_name":"Software System Performance and Reliability","score":0.0754999965429306,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.07169999927282333,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.058400001376867294,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.420199990272522},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.34299999475479126},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3336000144481659},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3212999999523163},{"id":"https://openalex.org/keywords/edge-detection","display_name":"Edge detection","score":0.3109000027179718},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3086000084877014},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3012000024318695}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5734000205993652},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3458999991416931},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.34299999475479126},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3336000144481659},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.33309999108314514},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.3109000027179718},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3012000024318695},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.298799991607666},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2802000045776367},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25920000672340393},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792382","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792382","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792382","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792382","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1905847227","https://openalex.org/W1994005439","https://openalex.org/W2100218206","https://openalex.org/W2103434431","https://openalex.org/W2112474496","https://openalex.org/W2613206411","https://openalex.org/W2760770811","https://openalex.org/W2948513753","https://openalex.org/W2982479999","https://openalex.org/W3130689885","https://openalex.org/W3174969457","https://openalex.org/W4221062824","https://openalex.org/W4312397585","https://openalex.org/W4380925941","https://openalex.org/W4386443196","https://openalex.org/W4386528681","https://openalex.org/W4387321091","https://openalex.org/W4389518760","https://openalex.org/W4401856679","https://openalex.org/W4409131852","https://openalex.org/W4409362537","https://openalex.org/W4409657546","https://openalex.org/W4409671048","https://openalex.org/W4412378055","https://openalex.org/W4412875517"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"deployed":[6],"on":[7,24,42],"edge":[8,43],"devices":[9,44],"to":[10,46],"address":[11],"privacy":[12],"and":[13,50],"latency":[14],"concerns":[15],"in":[16],"modern":[17],"Web":[18],"applications.":[19],"While":[20],"numerous":[21],"studies":[22],"focus":[23],"inference":[25],"frameworks,":[26],"the":[27,51],"critical":[28],"problem":[29],"of":[30,54],"tuning":[31],"runtime":[32],"configurations":[33],"remains":[34],"largely":[35],"underexplored.":[36],"This":[37],"endeavor":[38],"is":[39],"particularly":[40],"challenging":[41],"due":[45],"severe":[47],"budget":[48],"limitations":[49],"dynamic":[52],"variability":[53],"system":[55],"resources.":[56]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-10T00:00:00"}