{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T20:07:51Z","timestamp":1780603671600,"version":"3.54.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62404256"],"award-info":[{"award-number":["62404256"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20241206180301003"],"award-info":[{"award-number":["JCYJ20241206180301003"]}]},{"name":"Shenzhen Science and Technology Program","award":["ZDCY20250901095901002"],"award-info":[{"award-number":["ZDCY20250901095901002"]}]},{"name":"Key Project of Shenzhen Basic Research Program","award":["JCYJ20241206180301003"],"award-info":[{"award-number":["JCYJ20241206180301003"]}]},{"DOI":"10.13039\/501100001809","name":"High-Performance Computing Public Platform (Shenzhen Campus) of Sun Yat-sen University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. VLSI Syst."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tvlsi.2026.3666193","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:55:38Z","timestamp":1772571338000},"page":"1712-1722","source":"Crossref","is-referenced-by-count":0,"title":["DayPQ: Dynamic Layerwise Pruning and Quantization for LLM Inference Acceleration"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4043-1655","authenticated-orcid":false,"given":"Yongchao","family":"Xu","sequence":"first","affiliation":[{"name":"School of Integrated Circuits, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingxuan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziying","family":"Zhuo","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinzhe","family":"Zhi","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4570-4613","authenticated-orcid":false,"given":"Tianyu","family":"Jia","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9553-3640","authenticated-orcid":false,"given":"Meiqi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref2","article-title":"Compressing LLMs: The truth is rarely pure and never simple","author":"Jaiswal","year":"2023","journal-title":"arXiv:2310.01382"},{"key":"ref3","article-title":"Structural pruning of large language models via neural architecture search","volume-title":"Proc. AutoML Conf. (Workshop)","author":"Klein","year":"2023"},{"key":"ref4","article-title":"Streamlining redundant layers to compress large language models","author":"Chen","year":"2024","journal-title":"arXiv:2403.19135"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3714983.3714987"},{"key":"ref6","article-title":"PrefixQuant: Eliminating outliers by prefixed tokens for large language models quantization","author":"Chen","year":"2024","journal-title":"arXiv:2410.05265"},{"key":"ref7","article-title":"OstQuant: Refining large language model quantization with orthogonal and scaling transformations for better distribution fitting","author":"Hu","year":"2025","journal-title":"arXiv:2501.13987"},{"key":"ref8","article-title":"A tighter complexity analysis of SparseGPT","author":"Li","year":"2024","journal-title":"arXiv:2408.12151"},{"key":"ref9","article-title":"SliceGPT: Compress large language models by deleting rows and columns","author":"Ashkboos","year":"2024","journal-title":"arXiv:2401.15024"},{"key":"ref10","article-title":"What does the knowledge neuron thesis have to do with knowledge?","author":"Niu","year":"2024","journal-title":"arXiv:2405.02421"},{"key":"ref11","first-page":"22137","article-title":"Deja Vu: Contextual sparsity for efficient LLMs at inference time","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695964"},{"key":"ref13","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":"ref14","article-title":"QuaRot: Outlier-free 4-bit inference in rotated LLMs","author":"Ashkboos","year":"2024","journal-title":"arXiv:2404.00456"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0782"},{"key":"ref16","first-page":"33319","article-title":"ShiftAddViT: Mixture of multiplication primitives towards efficient vision transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"You"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2025.3585054"},{"key":"ref18","article-title":"Layer by layer: Uncovering hidden representations in language models","author":"Skean","year":"2025","journal-title":"arXiv:2502.02013"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref20","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref21","article-title":"I-LLM: Efficient integer-only inference for fully-quantized low-bit large language models","author":"Hu","year":"2024","journal-title":"arXiv:2405.17849"},{"key":"ref22","article-title":"Quantization hurts reasoning? An empirical study on quantized reasoning models","author":"Liu","year":"2025","journal-title":"arXiv:2504.04823"},{"key":"ref23","article-title":"Massive values in self-attention modules are the key to contextual knowledge understanding","author":"Jin","year":"2025","journal-title":"arXiv:2502.01563"},{"key":"ref24","article-title":"Rethinking the outlier distribution in large language models: An in-depth study","author":"Raman","year":"2025","journal-title":"arXiv:2505.21670"},{"key":"ref25","article-title":"DeepSeek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv:2501.12948"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.39"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3712285.3759852"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00064"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00080"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4487"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2018.2880742"},{"key":"ref32","article-title":"HuggingFace\u2019s transformers: State-of-the-art natural language processing","author":"Wolf","year":"2019","journal-title":"arXiv:1910.03771"},{"key":"ref33","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv:1609.07843"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2023.3333759"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401196"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00093"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2025.3596228"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"}],"container-title":["IEEE Transactions on Very Large Scale Integration (VLSI) Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/92\/11547350\/11419640.pdf?arnumber=11419640","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:59:28Z","timestamp":1780603168000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11419640\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":42,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tvlsi.2026.3666193","relation":{},"ISSN":["1063-8210","1557-9999"],"issn-type":[{"value":"1063-8210","type":"print"},{"value":"1557-9999","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}