{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T07:32:15Z","timestamp":1773127935613,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"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":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342731","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"6461-6466","source":"Crossref","is-referenced-by-count":1,"title":["SmoothRot: Combining Channel-Wise Scaling and Rotation for Quantization-Friendly LLMs"],"prefix":"10.1109","author":[{"given":"Patrik","family":"Czak\u00f3","sequence":"first","affiliation":[{"name":"Obuda University,Doctoral School of Applied Informatics and Applied Mathematics,Budapest,Hungary"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"G\u00e1bor","family":"Kert\u00e9sz","sequence":"additional","affiliation":[{"name":"Obuda University,John von Neumann Faculty of Informatics,Budapest,Hungary"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S\u00e1ndor","family":"Sz\u00e9n\u00e1si","sequence":"additional","affiliation":[{"name":"Obuda University,John von Neumann Faculty of Informatics,Budapest,Hungary"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","author":"Touvron","year":"2023"},{"key":"ref2","article-title":"The Llama 3 Herd of Models","author":"Grattafiori","year":"2024"},{"key":"ref3","article-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.12700\/APH.20.5.2023.5.11"},{"key":"ref5","article-title":"Model Compression and Efficient Inference for Large Language Models: A Survey","author":"Wang","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref7","first-page":"23 901","article-title":"SqueezeLLM: Dense-and-Sparse Quantization","volume-title":"presented at the Proceedings of Machine Learning Research","volume":"235","author":"Kim"},{"key":"ref8","first-page":"48 630","article-title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","volume-title":"presented at the Proceedings of Machine Learning Research","volume":"235","author":"Tseng"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/access.2025.3568702"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/saci66288.2025.11030191"},{"key":"ref11","first-page":"38 087","article-title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","volume-title":"presented at the Proceedings of Machine Learning Research","volume":"202","author":"Xiao"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3180"},{"key":"ref13","article-title":"OPTQ: Accurate quantization for generative pre-trained transformers","volume-title":"presented at the 11th International Conference on Learning Representations, ICLR 2023","author":"Frantar"},{"key":"ref14","article-title":"SpinQuant: LLM quantization with learned rotations","author":"Liu","year":"2024"},{"key":"ref15","article-title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","volume":"35","author":"Dettmers","year":"2022","journal-title":"presented at the Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"Massive Activations in Large Language Models","author":"Sun","year":"2024"},{"key":"ref17","article-title":"Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs","author":"Yang","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.134"},{"key":"ref19","article-title":"FlatQuant: Flatness Matters for LLM Quantization","author":"Sun","year":"2024"},{"key":"ref20","article-title":"AffineQuant: Affine Transformation Quantization for Large Language Models","volume-title":"presented at the 12th International Conference on Learning Representations, ICLR 2024","author":"Ma"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2786"},{"key":"ref22","article-title":"DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined Rotation","author":"Xiang","year":"2024"},{"key":"ref23","article-title":"Pointer Sentinel Mixture Models","volume-title":"presented at the International Conference on Learning Representations","author":"Merity"},{"issue":"1","key":"ref24","first-page":"140:5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1472"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1144"},{"key":"ref29","article-title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","author":"Clark","year":"2018"},{"key":"ref30","article-title":"A framework for few-shot language model evaluation","author":"Gao","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342731.pdf?arnumber=11342731","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:53:13Z","timestamp":1770843193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342731\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342731","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}