{"id":"https://openalex.org/W4414272280","doi":"https://doi.org/10.1109/ichms65439.2025.11154251","title":"LLM-Based Model Compression for Efficient on-Device Learning","display_name":"LLM-Based Model Compression for Efficient on-Device Learning","publication_year":2025,"publication_date":"2025-05-26","ids":{"openalex":"https://openalex.org/W4414272280","doi":"https://doi.org/10.1109/ichms65439.2025.11154251"},"language":"en","primary_location":{"id":"doi:10.1109/ichms65439.2025.11154251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichms65439.2025.11154251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 5th International Conference on Human-Machine Systems (ICHMS)","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/A5108300361","display_name":"Aryan Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138251","display_name":"Indian Institute of Information Technology, Nagpur","ror":"https://ror.org/03e2e3s57","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210138251"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Aryan Raj","raw_affiliation_strings":["IIIT, Naya Raipur,Computer Science and Engineering,Raipur,India"],"affiliations":[{"raw_affiliation_string":"IIIT, Naya Raipur,Computer Science and Engineering,Raipur,India","institution_ids":["https://openalex.org/I4210138251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110533933","display_name":"K. G. Srinivasa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srinivasa K G","raw_affiliation_strings":["IIIT, Naya Raipur,Data Science and Artificial Intelligence,Raipur,India"],"affiliations":[{"raw_affiliation_string":"IIIT, Naya Raipur,Data Science and Artificial Intelligence,Raipur,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093314516","display_name":"Harshit Kumar Chaubey","orcid":"https://orcid.org/0009-0007-4417-8707"},"institutions":[{"id":"https://openalex.org/I4210138251","display_name":"Indian Institute of Information Technology, Nagpur","ror":"https://ror.org/03e2e3s57","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210138251"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Harshit Kumar Chaubey","raw_affiliation_strings":["IIIT, Naya Raipur,Computer Science and Engineering,Raipur,India"],"affiliations":[{"raw_affiliation_string":"IIIT, Naya Raipur,Computer Science and Engineering,Raipur,India","institution_ids":["https://openalex.org/I4210138251"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093314517","display_name":"Siri Arelli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siri Arelli","raw_affiliation_strings":["IIIT, Naya Raipur,Data Science and Artificial Intelligence,Raipur,India"],"affiliations":[{"raw_affiliation_string":"IIIT, Naya Raipur,Data Science and Artificial Intelligence,Raipur,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108300361"],"corresponding_institution_ids":["https://openalex.org/I4210138251"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26296124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"251","last_page":"256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9641000032424927,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9641000032424927,"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/software-deployment","display_name":"Software deployment","score":0.6137999892234802},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5393999814987183},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5149999856948853},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4065000116825104},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.36239999532699585},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.32679998874664307},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.3215000033378601}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7164000272750854},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6137999892234802},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5393999814987183},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.36239999532699585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C58546491","wikidata":"https://www.wikidata.org/wiki/Q1150207","display_name":"Competitive advantage","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2542000114917755},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ichms65439.2025.11154251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ichms65439.2025.11154251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 5th International Conference on Human-Machine Systems (ICHMS)","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"deployment":[1],"of":[2,102],"large":[3],"language":[4],"models":[5,105],"(LLMs)":[6],"on":[7,62,123,138],"edge":[8],"devices":[9],"remains":[10],"a":[11,45,72,116],"significant":[12],"challenge":[13],"due":[14],"to":[15,37,39,52,133],"their":[16],"substantial":[17],"computational":[18],"and":[19,106,147],"memory":[20],"requirements.":[21],"Building":[22],"upon":[23],"established":[24],"model":[25,54],"compression":[26],"techniques":[27],"for":[28,119,144],"deep":[29],"learning":[30],"models,":[31],"this":[32],"work":[33],"extends":[34],"these":[35],"methodologies":[36],"LLMs":[38,122,137],"facilitate":[40],"on-device":[41,149],"learning.":[42],"We":[43],"present":[44],"comprehensive":[46],"approach":[47],"that":[48,97,129],"integrates":[49],"quantization":[50,84],"strategies":[51],"reduce":[53],"size":[55,81],"without":[56],"compromising":[57],"performance.":[58],"Specifically,":[59],"we":[60,92],"focus":[61],"the":[63,99,110,142],"Microsoft":[64],"Phi-":[65],"<tex":[66,73],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[67,74],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{3.":[68],"5}$</tex>":[69],"model,":[70],"achieving":[71],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{5":[75],"0":[76],"\\%}$</tex>":[77],"reduction":[78],"in":[79],"its":[80,87],"through":[82,109],"meticulous":[83],"while":[85],"maintaining":[86],"original":[88],"performance":[89],"levels.":[90],"Additionally,":[91],"developed":[93],"an":[94],"Android-based":[95],"interface":[96],"supports":[98],"seamless":[100],"import":[101],"both":[103],"custom":[104],"those":[107],"available":[108],"Hugging":[111],"Face":[112],"repository,":[113],"thereby":[114],"providing":[115],"versatile":[117],"platform":[118],"deploying":[120],"compressed":[121],"mobile":[124],"devices.":[125],"Our":[126],"results":[127],"demonstrate":[128],"it":[130],"is":[131],"feasible":[132],"implement":[134],"efficient,":[135],"highperforming":[136],"resource-constrained":[139],"devices,":[140],"paving":[141],"way":[143],"more":[145],"accessible":[146],"responsive":[148],"intelligent":[150],"applications.":[151]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}