{"id":"https://openalex.org/W7126263173","doi":"https://doi.org/10.1109/jiot.2026.3659676","title":"Reliable and Efficient LLM Inference on Resource-Constrained Mobile Devices via Dynamic Scheduling","display_name":"Reliable and Efficient LLM Inference on Resource-Constrained Mobile Devices via Dynamic Scheduling","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7126263173","doi":"https://doi.org/10.1109/jiot.2026.3659676"},"language":null,"primary_location":{"id":"doi:10.1109/jiot.2026.3659676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2026.3659676","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-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/A5124389473","display_name":"Aoxing Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aoxing Liang","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-0932-9553","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124457754","display_name":"Chengfan Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengfan Hong","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124434791","display_name":"Yunzhe Li","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunzhe Li","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5073-5561","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071050711","display_name":"Hongzi Zhu","orcid":"https://orcid.org/0000-0001-8657-5064"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzi Zhu","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8657-5064","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07760577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"9","first_page":"19751","last_page":"19754"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.1589999943971634,"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"}},"topics":[{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.1589999943971634,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.06639999896287918,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.0649000033736229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.8004999756813049},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.7717000246047974},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6625000238418579},{"id":"https://openalex.org/keywords/spare-part","display_name":"Spare part","score":0.48410001397132874},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45019999146461487},{"id":"https://openalex.org/keywords/mobile-computing","display_name":"Mobile computing","score":0.43459999561309814}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8758000135421753},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8004999756813049},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.7717000246047974},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6625000238418579},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5181000232696533},{"id":"https://openalex.org/C194648553","wikidata":"https://www.wikidata.org/wiki/Q1364774","display_name":"Spare part","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.3955000042915344},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.3707999885082245},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.36739999055862427},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3292999863624573},{"id":"https://openalex.org/C2994410016","wikidata":"https://www.wikidata.org/wiki/Q180910","display_name":"Spare time","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2709999978542328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2026.3659676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2026.3659676","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"exceptional":[6],"natural":[7],"language":[8],"understanding":[9],"and":[10,63,83],"generation":[11],"capabilities":[12],"in":[13,97],"many":[14],"emerging":[15],"applications.":[16],"However,":[17],"providing":[18],"end":[19],"users":[20],"with":[21],"real-time":[22,84],"LLM":[23,40],"inference":[24,41,85],"on":[25],"their":[26],"mobile":[27,49],"devices":[28,50],"poses":[29],"substantial":[30],"challenges.":[31],"In":[32],"this":[33],"work,":[34],"we":[35],"propose":[36],"a":[37],"fully":[38],"distributed":[39],"framework,":[42],"where":[43],"spare":[44],"computational":[45],"resources":[46],"across":[47],"heterogeneous":[48],"are":[51],"effectively":[52],"harnessed.":[53],"Our":[54],"approach":[55],"integrates":[56],"two":[57,71],"key":[58],"components:":[59],"initial":[60],"model":[61],"preloading":[62,76],"layer-wise":[64],"execution":[65],"scheduling.":[66],"The":[67],"proposed":[68],"methods":[69],"tackle":[70],"major":[72],"challenges,":[73],"optimal":[74],"parameter":[75],"without":[77],"prior":[78],"knowledge":[79],"of":[80,94],"device":[81],"availability":[82],"scheduling":[86],"under":[87],"dynamic":[88],"conditions.":[89],"We":[90],"evaluate":[91],"the":[92],"performance":[93],"our":[95],"framework":[96],"real-world":[98],"environments,":[99],"experimental":[100],"results":[101],"show":[102],"that":[103],"it":[104],"significantly":[105],"reduces":[106],"end-to-end":[107],"delay":[108],"by":[109],"44%\u223c83%":[110],"compared":[111],"to":[112],"existing":[113],"approaches.":[114]},"counts_by_year":[],"updated_date":"2026-04-25T06:01:18.069262","created_date":"2026-02-01T00:00:00"}