{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T11:10:02Z","timestamp":1751109002868,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,13]]},"DOI":"10.1145\/3718391.3727883","type":"proceedings-article","created":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T10:34:10Z","timestamp":1751106850000},"page":"291-298","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A New 2-bit Model Quantization Method Based on Non-uniform Quantization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2314-0809","authenticated-orcid":false,"given":"Dongmin","family":"Li","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6616-3686","authenticated-orcid":false,"given":"Bowen","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4839-0234","authenticated-orcid":false,"given":"Dongyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, Sichuan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,28]]},"reference":[{"key":"e_1_3_3_1_1_2","volume-title":"A comprehensive overview of large language models[J]. arXiv preprint arXiv:2307.06435","author":"Naveed H","year":"2023","unstructured":"Naveed H, Khan A U, Qiu S, et al. A comprehensive overview of large language models[J]. arXiv preprint arXiv:2307.06435, 2023."},{"key":"e_1_3_3_1_2_2","volume-title":"12th ACM SIGKDD international conference on Knowledge discovery and data mining. 2006: 535-541","author":"Bucilu\u01ce C","unstructured":"Bucilu\u01ce C, Caruana R, Niculescu-Mizil A. Model compression[C]\/\/Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining. 2006: 535-541."},{"key":"e_1_3_3_1_3_2","volume-title":"A survey of model compression and acceleration for deep neural networks[J]. arXiv preprint arXiv:1710.09282","author":"Cheng Y","year":"2017","unstructured":"Cheng Y, Wang D, Zhou P, et al. A survey of model compression and acceleration for deep neural networks[J]. arXiv preprint arXiv:1710.09282, 2017."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09816-7"},{"issue":"3","key":"e_1_3_3_1_5_2","first-page":"26","article-title":"The Inspiration Brought by ChatGPT to LLM and the New Development Ideas of Multi-modal Large Model[J]","volume":"7","author":"Chaoyang Z","year":"2023","unstructured":"Chaoyang Z, Guibo Z, Jinqiao W. The Inspiration Brought by ChatGPT to LLM and the New Development Ideas of Multi-modal Large Model[J]. Data Analysis and Knowledge Discovery, 2023, 7(3): 26-35.","journal-title":"Data Analysis and Knowledge Discovery"},{"key":"e_1_3_3_1_6_2","volume-title":"To prune, or not to prune: exploring the efficacy of pruning for model compression[J]. arXiv preprint arXiv:1710.01878","author":"Zhu M","year":"2017","unstructured":"Zhu M, Gupta S. To prune, or not to prune: exploring the efficacy of pruning for model compression[J]. arXiv preprint arXiv:1710.01878, 2017."},{"key":"e_1_3_3_1_7_2","volume-title":"Adaptive quantization for deep neural network[C]\/\/Proceedings of the AAAI Conference on Artificial Intelligence","author":"Zhou Y","year":"2018","unstructured":"Zhou Y, Moosavi-Dezfooli S M, Cheung N M, et al. Adaptive quantization for deep neural network[C]\/\/Proceedings of the AAAI Conference on Artificial Intelligence. 2018, 32(1)."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Yang J Shen X Xing J et al. Quantization networks[C]\/\/Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019: 7308-7316.","DOI":"10.1109\/CVPR.2019.00748"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Jacob B Kligys S Chen B et al. Quantization and training of neural networks for efficient integer-arithmetic-only inference[C]\/\/Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 2704-2713.","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_3_1_10_2","volume-title":"Neural network quantization with ai model efficiency toolkit (aimet)[J]. arXiv preprint arXiv:2201.08442","author":"Siddegowda S","year":"2022","unstructured":"Siddegowda S, Fournarakis M, Nagel M, et al. Neural network quantization with ai model efficiency toolkit (aimet)[J]. arXiv preprint arXiv:2201.08442, 2022."},{"key":"e_1_3_3_1_11_2","first-page":"3009","article-title":"Low-bit quantization of neural networks for efficient inference[C]\/\/2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW)","volume":"2019","author":"Choukroun Y","unstructured":"Choukroun Y, Kravchik E, Yang F, et al. Low-bit quantization of neural networks for efficient inference[C]\/\/2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW). IEEE, 2019: 3009-3018.","journal-title":"IEEE"},{"key":"e_1_3_3_1_12_2","volume-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers[J]. arXiv preprint arXiv:2210.17323","author":"Frantar E","year":"2022","unstructured":"Frantar E, Ashkboos S, Hoefler T, et al. Gptq: Accurate post-training quantization for generative pre-trained transformers[J]. arXiv preprint arXiv:2210.17323, 2022."},{"key":"e_1_3_3_1_13_2","volume-title":"Rptq: Reorder-based post-training quantization for large language models[J]. arXiv preprint arXiv:2304.01089","author":"Yuan Z","year":"2023","unstructured":"Yuan Z, Niu L, Liu J, et al. Rptq: Reorder-based post-training quantization for large language models[J]. arXiv preprint arXiv:2304.01089, 2023."},{"key":"e_1_3_3_1_14_2","volume-title":"Spqr: A sparse-quantized representation for near-lossless llm weight compression[J]. arXiv preprint arXiv:2306.03078","author":"Dettmers T","year":"2023","unstructured":"Dettmers T, Svirschevski R, Egiazarian V, et al. Spqr: A sparse-quantized representation for near-lossless llm weight compression[J]. arXiv preprint arXiv:2306.03078, 2023."},{"key":"e_1_3_3_1_15_2","volume-title":"DB-LLM: Accurate dual-binarization for efficient LLMs[J]. arXiv preprint arXiv:2402.11960","author":"Chen H","year":"2024","unstructured":"Chen H, Lv C, Ding L, et al. DB-LLM: Accurate dual-binarization for efficient LLMs[J]. arXiv preprint arXiv:2402.11960, 2024."},{"key":"e_1_3_3_1_16_2","volume-title":"Billm: Pushing the limit of post-training quantization for llms[J]. arXiv preprint arXiv:2402.04291","author":"Huang W","year":"2024","unstructured":"Huang W, Liu Y, Qin H, et al. Billm: Pushing the limit of post-training quantization for llms[J]. arXiv preprint arXiv:2402.04291, 2024."},{"key":"e_1_3_3_1_17_2","volume-title":"Affinequant: Affine transformation quantization for large language models[J]. arXiv preprint arXiv:2403.12544","author":"Ma Y","year":"2024","unstructured":"Ma Y, Li H, Zheng X, et al. Affinequant: Affine transformation quantization for large language models[J]. arXiv preprint arXiv:2403.12544, 2024."},{"key":"e_1_3_3_1_18_2","volume-title":"PMLR","author":"Xiao G","unstructured":"Xiao G, Lin J, Seznec M, et al. Smoothquant: Accurate and efficient post-training quantization for large language models[C]\/\/International Conference on Machine Learning. PMLR, 2023: 38087-38099."}],"event":{"name":"ICIT 2024: 2024 the 12th International Conference on Information Technology (ICIT)","location":"Kuala Lumpur Malaysia","acronym":"ICIT 2024"},"container-title":["Proceedings of the 2024 the 12th International Conference on Information Technology (ICIT)"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3718391.3727883","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T10:34:37Z","timestamp":1751106877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3718391.3727883"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,13]]},"references-count":18,"alternative-id":["10.1145\/3718391.3727883","10.1145\/3718391"],"URL":"https:\/\/doi.org\/10.1145\/3718391.3727883","relation":{},"subject":[],"published":{"date-parts":[[2024,12,13]]},"assertion":[{"value":"2025-06-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}