{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:55:52Z","timestamp":1765310152000,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFE0202900"],"award-info":[{"award-number":["2024YFE0202900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62436001, 62176020"],"award-info":[{"award-number":["62436001, 62176020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Joint Foundation of the Ministry of Education for Innovation team","award":["8091B042235"],"award-info":[{"award-number":["8091B042235"]}]},{"DOI":"10.13039\/501100005023","name":"State Key Laboratory of Rail Traffic Control and Safety","doi-asserted-by":"publisher","award":["RCS2023K006"],"award-info":[{"award-number":["RCS2023K006"]}],"id":[{"id":"10.13039\/501100005023","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755683","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:38Z","timestamp":1761377198000},"page":"11062-11070","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Maximum Redundancy Pruning: A Principle-Driven Layerwise Sparsity Allocation for LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4009-426X","authenticated-orcid":false,"given":"Chang","family":"Gao","sequence":"first","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7672-3229","authenticated-orcid":false,"given":"Kang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0800-3954","authenticated-orcid":false,"given":"Runqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9279-6098","authenticated-orcid":false,"given":"Jianfei","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7578-3407","authenticated-orcid":false,"given":"Liping","family":"Jing","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Yuanzhi Li, Scott Lundberg, et al.","author":"Bubeck S\u00e9bastien","year":"2023","unstructured":"S\u00e9bastien Bubeck, Varun Chadrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, et al., 2023. Sparks of artificial general intelligence: Early experiments with gpt-4."},{"key":"e_1_3_2_1_2_1","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al., 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, Vol. 24, 240 (2023), 1-113.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_3_1","unstructured":"Yu-Neng Chuang Songchen Li Jiayi Yuan Guanchu Wang Kwei-Herng Lai Leisheng Yu Sirui Ding Chia-Yuan Chang Qiaoyu Tan Daochen Zha et al. 2024. Understanding different design choices in training large time series models. arXiv e-prints (2024) arXiv-2406."},{"key":"e_1_3_2_1_4_1","volume-title":"BoolQ: Exploring the surprising difficulty of natural yes\/no questions. arXiv preprint arXiv:1905.10044","author":"Clark Christopher","year":"2019","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:1905.10044 (2019)."},{"key":"e_1_3_2_1_5_1","volume-title":"Think you have solved question answering? try arc, the ai2 reasoning challenge. arXiv preprint arXiv:1803.05457","author":"Clark Peter","year":"2018","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:1803.05457 (2018)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_7_1","volume-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635","author":"Frankle Jonathan","year":"2018","unstructured":"Jonathan Frankle and Michael Carbin. 2018. The lottery ticket hypothesis: Finding sparse, trainable neural networks. arXiv preprint arXiv:1803.03635 (2018)."},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Machine Learning. PMLR, 10323-10337","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, 10323-10337."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298572"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"e_1_3_2_1_11_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_12_1","volume-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint arXiv:1607.03250","author":"H Hu.","year":"2016","unstructured":"H Hu. 2016. Network trimming: A data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint arXiv:1607.03250 (2016)."},{"key":"e_1_3_2_1_13_1","volume-title":"Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al.","author":"Jiang Albert Q","year":"2024","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al., 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"Optimal brain damage. Advances in neural information processing systems","author":"LeCun Yann","year":"1989","unstructured":"Yann LeCun, John Denker, and Sara Solla. 1989. Optimal brain damage. Advances in neural information processing systems, Vol. 2 (1989)."},{"key":"e_1_3_2_1_15_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems.","author":"Li Lujun","year":"2024","unstructured":"Lujun Li, Peijie Dong, Zhenheng Tang, Xiang Liu, Qiang Wang, Wenhan Luo, Wei Xue, Qifeng Liu, Xiaowen Chu, and Yike Guo. 2024a. Discovering sparsity allocation for layer-wise pruning of large language models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_16_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems.","author":"Li Wei","year":"2024","unstructured":"Wei Li, Lujun Li, Mark G Lee, and Shengjie Sun. 2024b. Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00291"},{"key":"e_1_3_2_1_18_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Machine Learning. PMLR, 7021-7032","author":"Liu Liyang","year":"2021","unstructured":"Liyang Liu, Shilong Zhang, Zhanghui Kuang, Aojun Zhou, Jing-Hao Xue, Xinjiang Wang, Yimin Chen, Wenming Yang, Qingmin Liao, and Wayne Zhang. 2021. Group fisher pruning for practical network compression. In International Conference on Machine Learning. PMLR, 7021-7032."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_1_21_1","first-page":"1","article-title":"Estimating the carbon footprint of bloom, a 176b parameter language model","volume":"24","author":"Luccioni Alexandra Sasha","year":"2023","unstructured":"Alexandra Sasha Luccioni, Sylvain Viguier, and Anne-Laure Ligozat. 2023. Estimating the carbon footprint of bloom, a 176b parameter language model. Journal of Machine Learning Research, Vol. 24, 253 (2023), 1-15.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_22_1","volume-title":"Llm-pruner: On the structural pruning of large language models. Advances in neural information processing systems","author":"Ma Xinyin","year":"2023","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, Vol. 36 (2023), 21702-21720."},{"key":"e_1_3_2_1_23_1","volume-title":"Can a suit of armor conduct electricity? a new dataset for open book question answering. arXiv preprint arXiv:1809.02789","author":"Mihaylov Todor","year":"2018","unstructured":"Todor Mihaylov, Peter Clark, Tushar Khot, and Ashish Sabharwal. 2018. Can a suit of armor conduct electricity? a new dataset for open book question answering. arXiv preprint arXiv:1809.02789 (2018)."},{"key":"e_1_3_2_1_24_1","volume-title":"Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nature communications","author":"Mocanu Decebal Constantin","year":"2018","unstructured":"Decebal Constantin Mocanu, Elena Mocanu, Peter Stone, Phuong H Nguyen, Madeleine Gibescu, and Antonio Liotta. 2018. Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nature communications, Vol. 9, 1 (2018), 2383."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"e_1_3_2_1_26_1","volume-title":"Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440","author":"Molchanov Pavlo","year":"2016","unstructured":"Pavlo Molchanov, Stephen Tyree, Tero Karras, Timo Aila, and Jan Kautz. 2016. Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440 (2016)."},{"key":"e_1_3_2_1_27_1","unstructured":"NeuralMagic. 2021. DeepSparse Engine. https:\/\/github.com\/neuralmagic\/deepsparse"},{"key":"e_1_3_2_1_28_1","volume-title":"SOSP: Efficiently capturing global correlations by second-order structured pruning. arXiv preprint arXiv:2110.11395","author":"Nonnenmacher Manuel","year":"2021","unstructured":"Manuel Nonnenmacher, Thomas Pfeil, Ingo Steinwart, and David Reeb. 2021. SOSP: Efficiently capturing global correlations by second-order structured pruning. arXiv preprint arXiv:2110.11395 (2021)."},{"key":"e_1_3_2_1_29_1","volume-title":"Carbon emissions and large neural network training. arXiv preprint arXiv:2104.10350","author":"Patterson David","year":"2021","unstructured":"David Patterson, Joseph Gonzalez, Quoc Le, Chen Liang, Lluis-Miquel Munguia, Daniel Rothchild, David So, Maud Texier, and Jeff Dean. 2021. Carbon emissions and large neural network training. arXiv preprint arXiv:2104.10350 (2021)."},{"key":"e_1_3_2_1_30_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, Vol. 21, 140 (2020), 1-67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the Twelfth International Conference on Learning Representations (ICLR).","author":"Sun Mingjie","year":"2024","unstructured":"Mingjie Sun, Zhuang Liu, Anna Bair, and J Zico Kolter. 2024. A Simple and Effective Pruning Approach for Large Language Models. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_33_1","volume-title":"Galactica: A large language model for science. arXiv preprint arXiv:2211.09085","author":"Taylor Ross","year":"2022","unstructured":"Ross Taylor, Marcin Kardas, Guillem Cucurull, Thomas Scialom, Anthony Hartshorn, Elvis Saravia, Andrew Poulton, Viktor Kerkez, and Robert Stojnic. 2022. Galactica: A large language model for science. arXiv preprint arXiv:2211.09085 (2022)."},{"key":"e_1_3_2_1_34_1","volume-title":"International conference on machine learning. PMLR, 10347-10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347-10357."},{"key":"e_1_3_2_1_35_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Glue: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461","author":"Wang Alex","year":"2018","unstructured":"Alex Wang. 2018. Glue: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)."},{"key":"e_1_3_2_1_37_1","volume-title":"Besa: Pruning large language models with blockwise parameter-efficient sparsity allocation. arXiv preprint arXiv:2402.16880","author":"Xu Peng","year":"2024","unstructured":"Peng Xu, Wenqi Shao, Mengzhao Chen, Shitao Tang, Kaipeng Zhang, Peng Gao, Fengwei An, Yu Qiao, and Ping Luo. 2024. Besa: Pruning large language models with blockwise parameter-efficient sparsity allocation. arXiv preprint arXiv:2402.16880 (2024)."},{"key":"e_1_3_2_1_38_1","volume-title":"International Conference on Machine Learning.","author":"Yin Lu","year":"2024","unstructured":"Lu Yin, You Wu, Zhenyu Zhang, Cheng-Yu Hsieh, Yaqing Wang, Yiling Jia, Gen Li, Ajay Jaiswal, Mykola Pechenizkiy, Yi Liang, et al., 2024. Outlier weighed layerwise sparsity (owl): A missing secret sauce for pruning llms to high sparsity. In International Conference on Machine Learning."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00630"},{"key":"e_1_3_2_1_40_1","volume-title":"AMIA Annual Symposium Proceedings","volume":"2023","author":"Yuan Jiayi","year":"2024","unstructured":"Jiayi Yuan, Ruixiang Tang, Xiaoqian Jiang, and Xia Hu. 2024. Large language models for healthcare data augmentation: An example on patient-trial matching. In AMIA Annual Symposium Proceedings, Vol. 2023. 1324."},{"key":"e_1_3_2_1_41_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al., 2022b. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3147269"},{"key":"e_1_3_2_1_43_1","first-page":"46595","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"36","author":"Zheng Lianmin","year":"2023","unstructured":"Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, et al., 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems, Vol. 36 (2023), 46595-46623.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_44_1","volume-title":"Perp: Rethinking the prune-retrain paradigm in the era of llms. arXiv preprint arXiv:2312.15230","author":"Zimmer Max","year":"2023","unstructured":"Max Zimmer, Megi Andoni, Christoph Spiegel, and Sebastian Pokutta. 2023. Perp: Rethinking the prune-retrain paradigm in the era of llms. arXiv preprint arXiv:2312.15230 (2023)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:52:02Z","timestamp":1765309922000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755683"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":44,"alternative-id":["10.1145\/3746027.3755683","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755683","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}