{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:52:52Z","timestamp":1781848372624,"version":"3.54.5"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"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":[[2026,5,24]]},"DOI":"10.1109\/iscas66217.2026.11562300","type":"proceedings-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:06:41Z","timestamp":1781813201000},"page":"539-543","source":"Crossref","is-referenced-by-count":0,"title":["SeVeDo: A Heterogeneous Transformer Accelerator for Low-Bit Inference via Hierarchical Group Quantization and SVD-Guided Mixed Precision"],"prefix":"10.1109","author":[{"given":"Yuseon","family":"Choi","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sangjin","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jungjun","family":"Oh","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byeongcheol","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hoi-Jun","family":"Yoo","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology (KAIST),Daejeon,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29237"},{"key":"ref3","first-page":"38087","article-title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML)","volume":"202","author":"Xiao"},{"key":"ref4","article-title":"Atom: Low-Bit Quantization for Efficient and Accurate LLM Serving","volume-title":"Proceedings of Machine Learning and Systems (MLSys)","volume":"6","author":"Zhao"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/isscc49661.2025.10904594"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/jetcas.2025.3558300"},{"key":"ref7","article-title":"SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Li"},{"key":"ref8","article-title":"VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference","author":"Dai","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/jssc.2023.3234893"},{"key":"ref10","article-title":"Microscaling data formats for deep learning","author":"Rouhani","year":"2023b"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/ISCA59077.2024.00080","article-title":"Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantization","volume-title":"Proc. 51st International Symposium on Computer Architecture (ISCA)","author":"Lee"},{"key":"ref12","article-title":"NVIDIA Blackwell Architecture"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/hpca61900.2025.00086"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067817"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/jssc.2024.3397189"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/isscc49661.2025.10904514"}],"event":{"name":"2026 IEEE International Symposium on Circuits and Systems (ISCAS)","location":"Shanghai, China","start":{"date-parts":[[2026,5,24]]},"end":{"date-parts":[[2026,5,28]]}},"container-title":["2026 IEEE International Symposium on Circuits and Systems (ISCAS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11561899\/11561804\/11562300.pdf?arnumber=11562300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T05:28:06Z","timestamp":1781846886000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11562300\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,24]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/iscas66217.2026.11562300","relation":{},"subject":[],"published":{"date-parts":[[2026,5,24]]}}}