{"id":"https://openalex.org/W4416429633","doi":"https://doi.org/10.1109/iccad66269.2025.11240999","title":"Invited Paper: BitMedViT: Ternary-Quantized Vision Transformer for Medical AI Assistants on the Edge","display_name":"Invited Paper: BitMedViT: Ternary-Quantized Vision Transformer for Medical AI Assistants on the Edge","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W4416429633","doi":"https://doi.org/10.1109/iccad66269.2025.11240999"},"language":null,"primary_location":{"id":"doi:10.1109/iccad66269.2025.11240999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","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/A5055089670","display_name":"Mikolaj Walczak","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mikolaj Walczak","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061729841","display_name":"Uttej Kallakuri","orcid":"https://orcid.org/0009-0004-1150-3903"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Uttej Kallakuri","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023630054","display_name":"Edward Humes","orcid":"https://orcid.org/0009-0002-3945-0116"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Humes","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101610451","display_name":"Xiaomin Lin","orcid":"https://orcid.org/0000-0002-9764-5168"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaomin Lin","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084010501","display_name":"Tinoosh Mohsenin","orcid":"https://orcid.org/0000-0001-5551-2124"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tinoosh Mohsenin","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5055089670"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.428,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87354966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7854999899864197,"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":0.7854999899864197,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.03970000147819519,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.009999999776482582,"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/mobile-device","display_name":"Mobile device","score":0.45509999990463257},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.44609999656677246},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.39070001244544983},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.3776000142097473},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.34950000047683716},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.33640000224113464},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.33480000495910645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6000999808311462},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5055000185966492},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4056999981403351},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3776000142097473},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.34950000047683716},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.33640000224113464},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.33180001378059387},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3061999976634979},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28029999136924744},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad66269.2025.11240999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","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":25,"referenced_works":["https://openalex.org/W2088588705","https://openalex.org/W2194775991","https://openalex.org/W2962858109","https://openalex.org/W3095948197","https://openalex.org/W3122795696","https://openalex.org/W3199014868","https://openalex.org/W4223899585","https://openalex.org/W4283805541","https://openalex.org/W4317436377","https://openalex.org/W4324144441","https://openalex.org/W4382318854","https://openalex.org/W4383302399","https://openalex.org/W4386825386","https://openalex.org/W4389518760","https://openalex.org/W4392203599","https://openalex.org/W4392699793","https://openalex.org/W4394997664","https://openalex.org/W4399487171","https://openalex.org/W4404908318","https://openalex.org/W4409328865","https://openalex.org/W4410887601","https://openalex.org/W4411233357","https://openalex.org/W4412945527","https://openalex.org/W4414019041","https://openalex.org/W4414997241"],"related_works":[],"abstract_inverted_index":{"Vision":[0],"Transformers":[1],"(ViTs)":[2],"have":[3],"demonstrated":[4],"strong":[5],"capabilities":[6],"in":[7,24,32],"interpreting":[8],"complex":[9],"medical":[10,46,54,67,188],"imaging":[11,68,189],"data.":[12],"However,":[13],"their":[14],"significant":[15],"computational":[16],"and":[17,28,69,123,154,182,201],"memory":[18,120,150],"demands":[19],"pose":[20],"challenges":[21],"for":[22,66,118,186],"deployment":[23],"real-time,":[25],"resource-constrained":[26],"mobile":[27],"wearable":[29],"devices":[30],"used":[31],"clinical":[33,203],"environments.":[34],"We":[35],"introduce,":[36],"BitMedVit,":[37],"a":[38,71,91,106,114,180],"new":[39],"class":[40],"of":[41,53,167],"Edge":[42],"ViTs":[43,112,190],"serving":[44],"as":[45],"AI":[47],"assistants":[48],"that":[49,108,166],"perform":[50],"structured":[51],"analysis":[52],"images":[55],"directly":[56],"on":[57,126,139,173,192],"the":[58,110,127,174,193,196],"edge.":[59],"BitMedVit":[60,86,132],"utilizes":[61],"ternary-quantized":[62],"linear":[63],"layers":[64],"tailored":[65],"combines":[70],"training":[72],"procedure":[73],"with":[74,82],"multi-query":[75],"attention,":[76],"preserving":[77],"stability":[78],"under":[79],"ternary":[80],"weights":[81],"low-precision":[83],"activations.":[84],"Furthermore,":[85],"employs":[87],"task-aware":[88],"distillation":[89],"from":[90],"high-capacity":[92],"teacher":[93],"to":[94,99,113,164],"recover":[95],"accuracy":[96,136],"lost":[97],"due":[98],"extreme":[100],"quantization.":[101],"Lastly,":[102],"we":[103],"also":[104],"present":[105],"pipeline":[107],"maps":[109],"ternarized":[111],"custom":[115],"CUDA":[116],"kernel":[117],"efficient":[119],"bandwidth":[121],"utilization":[122],"latency":[124],"reduction":[125],"Jetson":[128],"Orin":[129,175],"Nano.":[130,176],"Finally,":[131],"achieves":[133],"86%":[134],"diagnostic":[135],"(89%":[137],"SOTA)":[138],"MedMNIST":[140],"across":[141],"12":[142],"datasets,":[143],"while":[144],"reducing":[145],"model":[146],"size":[147],"by":[148,152],"43\u00d7,":[149],"traffic":[151],"39\u00d7,":[153],"enabling":[155],"16.8":[156],"ms":[157],"inference":[158],"at":[159,170],"an":[160],"energy":[161],"efficiency":[162],"up":[163],"41\u00d7":[165],"SOTA":[168],"models":[169],"183.62":[171],"GOPs/J":[172],"Our":[177],"results":[178],"demonstrate":[179],"practical":[181],"scientifically":[183],"grounded":[184],"route":[185],"extreme-precision":[187],"deployable":[191,202],"edge,":[194],"narrowing":[195],"gap":[197],"between":[198],"algorithmic":[199],"advances":[200],"tools.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-20T00:00:00"}