{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T15:42:18Z","timestamp":1778600538316,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,26]]},"DOI":"10.1109\/iccad66269.2025.11240999","type":"proceedings-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:39:34Z","timestamp":1763663974000},"page":"1-7","source":"Crossref","is-referenced-by-count":2,"title":["Invited Paper: BitMedViT: Ternary-Quantized Vision Transformer for Medical AI Assistants on the Edge"],"prefix":"10.1109","author":[{"given":"Mikolaj","family":"Walczak","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering"}]},{"given":"Uttej","family":"Kallakuri","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering"}]},{"given":"Edward","family":"Humes","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering"}]},{"given":"Xiaomin","family":"Lin","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering"}]},{"given":"Tinoosh","family":"Mohsenin","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED65160.2025.11014425"},{"key":"ref2","article-title":"Medmambalite: Hardware-aware mamba for medical image classification","volume-title":"IEEE BioCAS 2025]","author":"Aalishah"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-010-9449-4"},{"key":"ref5","article-title":"Palm 2 technical report","author":"Anil","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109507"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110424"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2021.3110250"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3649476.3658699"},{"key":"ref12","article-title":"Enabling on-device medical ai assistants via input-driven saliency adaptation","author":"Kallakuri","year":"2025","journal-title":"arXiv preprint arXiv:2506.11105 [Accepted in IEEE BioCAS 2025]"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3766068"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-022-00793-7"},{"key":"ref15","article-title":"Qkd: Quantization-aware knowledge distillation","author":"Kim","year":"2019"},{"key":"ref16","article-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020"},{"issue":"4","key":"ref17","article-title":"The era of 1-bit llms: All large language models are in 1.58 bits","volume":"17764","author":"Ma","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/OJCAS.2020.3043737"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106791"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2025.114045"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.9458"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3316433"},{"key":"ref23","volume-title":"Bitnet gpu inference kernels","year":"2025"},{"key":"ref24","volume-title":"NVIDIA Nsight Compute","year":"2024"},{"key":"ref25","volume-title":"NVIDIA Nsight Systems","year":"2024"},{"key":"ref26","volume-title":"NVIDIA TensorRT: High-performance deep learning inference optimizer and runtime","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-31514-x"},{"key":"ref28","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"Tinyvqa: Compact multimodal deep neural network for visual question answering on resource-constrained devices","author":"Rashid","year":"2024","journal-title":"CoRR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SusTech63138.2025.11025634"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2024.101504"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15070929"},{"key":"ref34","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.457"},{"key":"ref36","article-title":"Tervit: An efficient ternary vision transformer","author":"Xu","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434062"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01721-8"},{"key":"ref39","article-title":"Tereffic: Highly efficient ternary llm inference on fpga","author":"Yin","year":"2025"},{"key":"ref40","article-title":"Vit-1.58 b: Mobile vision transformers in the 1-bit era","author":"Yuan","year":"2024"},{"key":"ref41","author":"Yue","year":"2024","journal-title":"Medmamba: Vision mamba for medical image classification"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108238"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26354"},{"key":"ref44","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024"}],"event":{"name":"2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","location":"Munich, Germany","start":{"date-parts":[[2025,10,26]]},"end":{"date-parts":[[2025,10,30]]}},"container-title":["2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11240608\/11240621\/11240999.pdf?arnumber=11240999","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:47:27Z","timestamp":1763704047000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240999\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccad66269.2025.11240999","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}