{"id":"https://openalex.org/W7125907807","doi":"https://doi.org/10.1109/smc58881.2025.11343501","title":"Tuning Distillation to Generate Edge-friendly All-rounder Models","display_name":"Tuning Distillation to Generate Edge-friendly All-rounder Models","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125907807","doi":"https://doi.org/10.1109/smc58881.2025.11343501"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5025308099","display_name":"S. Dey","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Swarnava Dey","raw_affiliation_strings":["Tata Consultancy Services Limited,TCS Research,Kolkata,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tata Consultancy Services Limited,TCS Research,Kolkata,India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124063916","display_name":"Arijit Mukherjee","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arijit Mukherjee","raw_affiliation_strings":["Tata Consultancy Services Limited,TCS Research,Kolkata,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tata Consultancy Services Limited,TCS Research,Kolkata,India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080227829","display_name":"Arpan Pal","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arpan Pal","raw_affiliation_strings":["Tata Consultancy Services Limited,TCS Research,Kolkata,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tata Consultancy Services Limited,TCS Research,Kolkata,India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60287215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3855","last_page":"3860"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6269000172615051,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.6269000172615051,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07270000129938126,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.043299999088048935,"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/adaptability","display_name":"Adaptability","score":0.6794999837875366},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6424000263214111},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6394000053405762},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4799000024795532},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4271000027656555},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.3723999857902527},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.36579999327659607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383000254631042},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.6794999837875366},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6424000263214111},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6394000053405762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6211000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5530999898910522},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.36579999327659607},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3321000039577484},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7417077422142029,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2296073425","https://openalex.org/W2326925005","https://openalex.org/W2798991696","https://openalex.org/W3105966348","https://openalex.org/W3108655343","https://openalex.org/W3109689953","https://openalex.org/W3171007011","https://openalex.org/W3176732771","https://openalex.org/W4210537645","https://openalex.org/W4317926940","https://openalex.org/W4380928218","https://openalex.org/W4381746925","https://openalex.org/W4381747112","https://openalex.org/W4388502411","https://openalex.org/W4390874575","https://openalex.org/W4395028770","https://openalex.org/W4395054533","https://openalex.org/W4399534560"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1,100],"models":[2,17],"for":[3,81,139],"edge":[4],"deployments":[5],"must":[6],"be":[7],"small,":[8],"efficient,":[9],"and":[10,54,64,105,119,158],"robust.":[11],"Knowledge":[12],"distillation":[13,72,83],"from":[14,27],"large":[15],"foundation":[16],"(FMs)":[18],"can":[19],"help,":[20],"as":[21],"they":[22],"capture":[23],"rich,":[24],"transferable":[25],"representations":[26],"large,":[28],"multimodal":[29],"datasets.":[30],"However,":[31],"two":[32],"key":[33],"challenges":[34],"hinder":[35],"this":[36],"process:":[37],"(1)":[38],"extreme":[39],"model":[40,113],"compression":[41],"based":[42],"on":[43,127,133],"a":[44,65,76,110,123],"test":[45],"dataset":[46,69],"often":[47],"leads":[48],"to":[49,84,116],"brittleness":[50],"under":[51],"distribution":[52,57],"shifts,":[53],"(2)":[55],"the":[56],"gap":[58],"between":[59],"an":[60],"FM\u2019s":[61],"training":[62,147],"data":[63],"small":[66,91],"model\u2019s":[67],"target":[68],"makes":[70],"standard":[71],"methods":[73],"ineffective.We":[74],"propose":[75],"tunable":[77],"dynamic":[78],"loss":[79],"curriculum":[80],"knowledge":[82],"address":[85],"these":[86],"issues.":[87],"Experiments":[88],"show":[89],"that":[90],"encoders":[92],"trained":[93,126],"with":[94],"our":[95,150],"approach":[96],"achieve":[97],"balanced":[98],"transfer":[99],"performance":[101],"across":[102,155],"both":[103],"primary":[104],"out-of-distribution":[106],"tasks.":[107,159],"For":[108],"instance,":[109],"tiny":[111,124,140],"GPT-like":[112],"effectively":[114],"transfers":[115],"sentiment":[117],"classification":[118],"language":[120],"modeling.":[121],"Likewise,":[122],"ResNet":[125],"CIFAR-10":[128,135],"achieves":[129],"10%":[130],"higher":[131],"accuracy":[132],"corrupted":[134],"than":[136],"state-of-the-art":[137],"baselines":[138],"models.":[141],"While":[142],"it":[143],"trails":[144],"dedicated":[145],"robustness":[146],"by":[148],"4%,":[149],"method":[151],"ensures":[152],"superior":[153],"adaptability":[154],"diverse":[156],"datasets":[157]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-29T00:00:00"}