{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:00:51Z","timestamp":1780639251716,"version":"3.54.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,20]]},"DOI":"10.23919\/date69613.2026.11539489","type":"proceedings-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:53:10Z","timestamp":1780602790000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["IterQuant: Iterative Quantization Framework for Mixed-Precision LLM Compression"],"prefix":"10.23919","author":[{"given":"Hyungyo","family":"Jeong","sequence":"first","affiliation":[{"name":"POSTECH,Department of Electrical Engineering,Pohang,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiwoo","family":"Kim","sequence":"additional","affiliation":[{"name":"POSTECH,Department of Electrical Engineering,Pohang,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyeokjun","family":"Kwon","sequence":"additional","affiliation":[{"name":"ETRI,Daejeon,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaeho","family":"Lee","sequence":"additional","affiliation":[{"name":"POSTECH,Department of Electrical Engineering,Pohang,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youngjoo","family":"Lee","sequence":"additional","affiliation":[{"name":"KAIST,School of Electrical Engineering,Daejeon,Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2024.3373763"},{"key":"ref2","article-title":"Introducing openai o1","year":"2024"},{"key":"ref3","article-title":"Claude 3.7 sonnet","year":"2025"},{"key":"ref4","article-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0950"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16969"},{"key":"ref7","first-page":"87","article-title":"Awq: Activation-aware weight quantization for on-device llm compression and acceleration","volume-title":"Proceedings of machine learning and systems","volume":"6","author":"Lin"},{"key":"ref8","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on machine learning","author":"Xiao"},{"key":"ref9","article-title":"Qserve: W4a8kv4 quantization and system co-design for efficient llm serving","author":"Lin","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3180"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0323"},{"key":"ref13","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29237"},{"key":"ref15","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_16"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref19","first-page":"1","article-title":"Aptq: Attention-aware post-training mixed-precision quantization for large language models","volume-title":"Proceedings of the 61st ACM\/IEEE Design Automation Conference, DAC \u201924","author":"Guan"},{"key":"ref20","article-title":"A practical mixed precision algorithm for post-training quantization","author":"Pandey","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0782"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00085"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2198"},{"key":"ref24","article-title":"Spinquant: Llm quantization with learned rotations","author":"Liu","year":"2024"},{"key":"ref25","article-title":"Mobilellm: Optimizing sub-billion parameter language models for on-device use cases","volume-title":"Forty-first International Conference on Machine Learning","author":"Liu"},{"key":"ref26","first-page":"arXiv","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref27","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"issue":"140","key":"ref28","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref29","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref30","article-title":"Eleutherai\/lm-evaluation-harness: v0.3.0","author":"Gao","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref33","article-title":"Think you have solved question answering? try arc, the ai2 reasoning challenge","author":"Clark","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"ref35","article-title":"Measuring massive multitask language understanding","author":"Hendrycks","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3085572"}],"event":{"name":"2026 Design, Automation & Test in Europe Conference (DATE)","location":"Verona, Italy","start":{"date-parts":[[2026,4,20]]},"end":{"date-parts":[[2026,4,22]]}},"container-title":["2026 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11539023\/11539024\/11539489.pdf?arnumber=11539489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:09:14Z","timestamp":1780636154000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539489\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":36,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539489","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}