{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T09:47:17Z","timestamp":1774000037744,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,12]]},"DOI":"10.1145\/3788149.3788206","type":"proceedings-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:35:19Z","timestamp":1773988519000},"page":"132-139","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SWSC: Compressing Large Language Models via Sharing Weights for Similar Channels"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-0890-858X","authenticated-orcid":false,"given":"Binrui","family":"Zeng","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7378-8949","authenticated-orcid":false,"given":"Yongtao","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5508-5051","authenticated-orcid":false,"given":"Bin","family":"Ji","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9800-6886","authenticated-orcid":false,"given":"Xiaodong","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8695-5591","authenticated-orcid":false,"given":"Xiaopeng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1545-7010","authenticated-orcid":false,"given":"Jie","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Rishabh Agarwal Nino Vieillard Yongchao Zhou Piotr Stanczyk Sabela Ramos Matthieu Geist and Olivier Bachem. 2024. On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes. arxiv:https:\/\/arXiv.org\/abs\/2306.13649\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2306.13649"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"e_1_3_3_2_4_2","unstructured":"Christopher Clark Kenton Lee Ming-Wei Chang Tom Kwiatkowski Michael Collins and Kristina Toutanova. 2019. BoolQ: Exploring the surprising difficulty of natural yes\/no questions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1905.10044 (2019)."},{"key":"e_1_3_3_2_5_2","unstructured":"Peter Clark Isaac Cowhey Oren Etzioni Tushar Khot Ashish Sabharwal Carissa Schoenick and Oyvind Tafjord. 2018. Think you have solved question answering? try arc the ai2 reasoning challenge. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1803.05457 (2018)."},{"key":"e_1_3_3_2_6_2","unstructured":"Vage Egiazarian Andrei Panferov Denis Kuznedelev Elias Frantar Artem Babenko and Dan Alistarh. 2024. Extreme compression of large language models via additive quantization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.06118 (2024)."},{"key":"e_1_3_3_2_7_2","first-page":"10323","volume-title":"International Conference on Machine Learning","author":"Frantar Elias","year":"2023","unstructured":"Elias Frantar and Dan Alistarh. 2023. Sparsegpt: Massive language models can be accurately pruned in one-shot. In International Conference on Machine Learning. PMLR, 10323\u201310337."},{"key":"e_1_3_3_2_8_2","unstructured":"Elias Frantar Saleh Ashkboos Torsten Hoefler and Dan Alistarh. 2022. Gptq: Accurate post-training quantization for generative pre-trained transformers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.17323 (2022)."},{"key":"e_1_3_3_2_9_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gu Yuxian","year":"2024","unstructured":"Yuxian Gu, Li Dong, Furu Wei, and Minlie Huang. 2024. MiniLLM: Knowledge distillation of large language models. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_2_10_2","unstructured":"Yukun Huang Yanda Chen Zhou Yu and Kathleen McKeown. 2022. In-context learning distillation: Transferring few-shot learning ability of pre-trained language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.10670 (2022)."},{"key":"e_1_3_3_2_11_2","unstructured":"Yuxin Jiang Chunkit Chan Mingyang Chen and Wei Wang. 2023. Lion: Adversarial Distillation of Proprietary Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2305.12870\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2305.12870"},{"key":"e_1_3_3_2_12_2","unstructured":"Shiyang Li Jianshu Chen Yelong Shen Zhiyu Chen Xinlu Zhang Zekun Li Hong Wang Jing Qian Baolin Peng Yi Mao Wenhu Chen and Xifeng Yan. 2022. Explanations from Large Language Models Make Small Reasoners Better. arxiv:https:\/\/arXiv.org\/abs\/2210.06726\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2210.06726"},{"key":"e_1_3_3_2_13_2","unstructured":"Haokun Lin Haobo Xu Yichen Wu Jingzhi Cui Yingtao Zhang Linzhan Mou Linqi Song Zhenan Sun and Ying Wei. 2024. DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs. arxiv:https:\/\/arXiv.org\/abs\/2406.01721\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2406.01721"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"Yifei Liu Jicheng Wen Yang Wang Shengyu Ye Li\u00a0Lyna Zhang Ting Cao Cheng Li and Mao Yang. 2024. Vptq: Extreme low-bit vector post-training quantization for large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.17066 (2024).","DOI":"10.18653\/v1\/2024.emnlp-main.467"},{"key":"e_1_3_3_2_15_2","unstructured":"Zechun Liu Barlas Oguz Changsheng Zhao Ernie Chang Pierre Stock Yashar Mehdad Yangyang Shi Raghuraman Krishnamoorthi and Vikas Chandra. 2023. LLM-QAT: Data-Free Quantization Aware Training for Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2305.17888\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2305.17888"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Xinyin Ma Gongfan Fang and Xinchao Wang. 2023. Llm-pruner: On the structural pruning of large language models. Advances in neural information processing systems 36 (2023) 21702\u201321720.","DOI":"10.52202\/075280-0950"},{"key":"e_1_3_3_2_17_2","unstructured":"Stephen Merity Caiming Xiong James Bradbury and Richard Socher. 2016. Pointer sentinel mixture models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1609.07843 (2016)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Lan Mingjing Xia Yi Zhou Gang Huan Ningbo Li Zhufeng and Wu Hao. 2024. LLM4QA: Leveraging Large Language Model for Efficient Knowledge Graph Reasoning with SPARQL Query. Journal of Advances in Information Technology 15 10 (2024) 1157\u20131162.","DOI":"10.12720\/jait.15.10.1157-1162"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Keisuke Sakaguchi Ronan\u00a0Le Bras Chandra Bhagavatula and Yejin Choi. 2021. Winogrande: An adversarial winograd schema challenge at scale. Commun. ACM 64 9 (2021) 99\u2013106.","DOI":"10.1145\/3474381"},{"key":"e_1_3_3_2_20_2","unstructured":"Mingjie Sun Zhuang Liu Anna Bair and J.\u00a0Zico Kolter. 2024. A Simple and Effective Pruning Approach for Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2306.11695\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2306.11695"},{"key":"e_1_3_3_2_21_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et\u00a0al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.09288 (2023)."},{"key":"e_1_3_3_2_22_2","unstructured":"Mart Van\u00a0Baalen Andrey Kuzmin Markus Nagel Peter Couperus Cedric Bastoul Eric Mahurin Tijmen Blankevoort and Paul Whatmough. 2024. Gptvq: The blessing of dimensionality for llm quantization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.15319 (2024)."},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"John Von\u00a0Neumann and Herman\u00a0Heine Goldstine. 1947. Numerical inverting of matrices of high order. Psychometrika (1947).","DOI":"10.1090\/S0002-9904-1947-08909-6"},{"key":"e_1_3_3_2_24_2","first-page":"38087","volume-title":"International Conference on Machine Learning","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, and Song Han. 2023. Smoothquant: Accurate and efficient post-training quantization for large language models. In International Conference on Machine Learning. PMLR, 38087\u201338099."},{"key":"e_1_3_3_2_25_2","unstructured":"Zhewei Yao Xiaoxia Wu Cheng Li Stephen Youn and Yuxiong He. 2023. Zeroquant-v2: Exploring post-training quantization in llms from comprehensive study to low rank compensation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08302 (2023)."},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Rowan Zellers Ari Holtzman Yonatan Bisk Ali Farhadi and Yejin Choi. 2019. Hellaswag: Can a machine really finish your sentence? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1905.07830 (2019).","DOI":"10.18653\/v1\/P19-1472"},{"key":"e_1_3_3_2_27_2","unstructured":"Mingyang Zhang Hao Chen Chunhua Shen Zhen Yang Linlin Ou Xinyi Yu and Bohan Zhuang. 2024. LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning. arxiv:https:\/\/arXiv.org\/abs\/2305.18403\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2305.18403"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Xunyu Zhu Jian Li Yong Liu Can Ma and Weiping Wang. 2024. A survey on model compression for large language models. Transactions of the Association for Computational Linguistics 12 (2024) 1556\u20131577.","DOI":"10.1162\/tacl_a_00704"}],"event":{"name":"CSAI 2025: 2025 The 9th International Conference on Computer Science and Artificial Intelligence","location":"Beijing China","acronym":"CSAI 2025"},"container-title":["Proceedings of the 2025 9th International Conference on Computer Science and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3788149.3788206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:36:37Z","timestamp":1773988597000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788149.3788206"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,12]]},"references-count":27,"alternative-id":["10.1145\/3788149.3788206","10.1145\/3788149"],"URL":"https:\/\/doi.org\/10.1145\/3788149.3788206","relation":{},"subject":[],"published":{"date-parts":[[2025,12,12]]},"assertion":[{"value":"2026-03-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}