{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:23:43Z","timestamp":1767705823259,"version":"3.40.5"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information and communications Technology Planning and Evaluation (IITP) funded by Ministry of Science and Information and Communication Technology","award":["RS-2021-II211343"],"award-info":[{"award-number":["RS-2021-II211343"]}]},{"name":"NRF funded by MSIT of Korean Government","award":["2021R1A2C3006659"],"award-info":[{"award-number":["2021R1A2C3006659"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3566307","type":"journal-article","created":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T17:17:39Z","timestamp":1746206259000},"page":"79534-79547","source":"Crossref","is-referenced-by-count":3,"title":["WAPS-Quant: Low-Bit Post-Training Quantization Using Weight-Activation Product Scaling"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6502-8207","authenticated-orcid":false,"given":"Geunjae","family":"Choi","sequence":"first","affiliation":[{"name":"Graduate School of Convergence Science and Technology, Seoul National University, Gwanak-gu, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4608-147X","authenticated-orcid":false,"given":"Kamin","family":"Lee","sequence":"additional","affiliation":[{"name":"Graduate School of Convergence Science and Technology, Seoul National University, Gwanak-gu, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1792-0327","authenticated-orcid":false,"given":"Nojun","family":"Kwak","sequence":"additional","affiliation":[{"name":"Graduate School of Convergence Science and Technology, Seoul National University, Gwanak-gu, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015","journal-title":"arXiv:1510.00149"},{"key":"ref2","first-page":"1","article-title":"Learning to prune deep neural networks via layer-wise optimal brain surgeon","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref3","first-page":"1","article-title":"Network pruning via transformable architecture search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref5","article-title":"Towards the limit of network quantization","author":"Choi","year":"2016","journal-title":"arXiv:1612.01543"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref8","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021","journal-title":"arXiv:2106.08295"},{"key":"ref9","article-title":"Learned step size quantization","author":"Esser","year":"2019","journal-title":"arXiv:1902.08153"},{"key":"ref10","article-title":"Alternating multi-bit quantization for recurrent neural networks","author":"Xu","year":"2018","journal-title":"arXiv:1802.00150"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"ref12","first-page":"20415","article-title":"Position-based scaled gradient for model quantization and pruning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref13","article-title":"And the bit goes down: Revisiting the quantization of neural networks","author":"Stock","year":"2019","journal-title":"arXiv:1907.05686"},{"key":"ref14","first-page":"9847","article-title":"Towards accurate post-training network quantization via bit-split and stitching","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"1","author":"Wang"},{"key":"ref15","article-title":"BRECQ: Pushing the limit of post-training quantization by block reconstruction","author":"Li","year":"2021","journal-title":"arXiv:2102.05426"},{"key":"ref16","first-page":"7197","article-title":"Up or down? Adaptive rounding for post-training quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nagel"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01201"},{"key":"ref18","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv:2210.17323"},{"key":"ref19","article-title":"AWQ: Activation-aware weight quantization for LLM compression and acceleration","author":"Lin","year":"2023","journal-title":"arXiv:2306.00978"},{"key":"ref20","article-title":"SqueezeLLM: Dense-and-Sparse quantization","author":"Kim","year":"2023","journal-title":"arXiv:2306.07629"},{"key":"ref21","article-title":"QDrop: Randomly dropping quantization for extremely low-bit post-training quantization","author":"Wei","year":"2022","journal-title":"arXiv:2203.05740"},{"key":"ref22","first-page":"6666","article-title":"Leveraging inter-layer dependency for post-training quantization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zheng"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_23"},{"key":"ref24","article-title":"Integer quantization for deep learning inference: Principles and empirical evaluation","author":"Wu","year":"2020","journal-title":"arXiv:2004.09602"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00452"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"},{"key":"ref28","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00525"},{"key":"ref30","first-page":"10271","article-title":"Pushing the limits of narrow precision inferencing at cloud scale with Microsoft floating point","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Rouhani"},{"key":"ref31","article-title":"RPTQ: Reorder-based post-training quantization for large language models","author":"Yuan","year":"2023","journal-title":"arXiv:2304.01089"},{"key":"ref32","article-title":"Improving post training neural quantization: Layer-wise calibration and integer programming","author":"Hubara","year":"2020","journal-title":"arXiv:2006.10518"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109780"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3310916"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2022.3188899"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3141050"},{"key":"ref37","article-title":"Fighting quantization bias with bias","author":"Finkelstein","year":"2019","journal-title":"arXiv:1906.03193"},{"key":"ref38","first-page":"4900","article-title":"Hybrid 8-bit floating point (HFP8) training and inference for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Sun"},{"key":"ref39","article-title":"PTQ4 ViT: Post-training quantization for vision transformers with twin uniform quantization","author":"Yuan","year":"2021","journal-title":"arXiv:2111.12293"},{"key":"ref40","article-title":"Learning sparse neural networks through L0 regularization","author":"Louizos","year":"2017","journal-title":"arXiv:1712.01312"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref42","article-title":"FlexRound: Learnable rounding based on element-wise division for post-training quantization","author":"Hyun Lee","year":"2023","journal-title":"arXiv:2306.00317"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref47","article-title":"The era of 1-bit LLMs: All large language models are in 1.58 bits","author":"Ma","year":"2024","journal-title":"arXiv:2402.17764"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref49","article-title":"Gemmini: Enabling systematic deep-learning architecture evaluation via full-stack integration","author":"Genc","year":"2019","journal-title":"arXiv:1911.09925"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2016.2587683"},{"key":"ref51","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10982219.pdf?arnumber=10982219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T04:23:57Z","timestamp":1746764637000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10982219\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3566307","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}