{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T06:12:56Z","timestamp":1783923176667,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":42,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234400","type":"print"},{"value":"9789819234417","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-3441-7_38","type":"book-chapter","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:38:24Z","timestamp":1783921104000},"page":"455-466","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Structural Transition and Residual-Guided Local Swap for Post-Training Pruning of Large Language Models"],"prefix":"10.1007","author":[{"given":"He","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuqiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keqin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqing","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongwei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"38_CR1","volume-title":"Advances in Neural Information Processing Systems","author":"A Ahmadian","year":"2023","unstructured":"Ahmadian, A., Dash, S., Chen, H., Venkitesh, B., Gou, S., Blunsom, P., et al.: Intriguing properties of quantization at scale. In: Advances in Neural Information Processing Systems (2023)"},{"key":"38_CR2","first-page":"129","volume":"2","author":"D Blalock","year":"2020","unstructured":"Blalock, D., Gonzalez Ortiz, J.J., Frankle, J., Guttag, J.: What is the State of Neural Network Pruning? Proceedings of Machine Learning and Systems. 2, 129\u2013146 (2020)","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"38_CR3","unstructured":"Bubeck, S., et al.: Sparks of artificial general intelligence: Early experiments with GPT-4. arXiv preprint https:\/\/arxiv.org\/abs\/2303.12712 (2023)"},{"key":"38_CR4","volume-title":"Advances in Neural Information Processing Systems","author":"T Dettmers","year":"2022","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., Zettlemoyer, L.: LLM.int8(): 8-bit matrix multiplication for transformers at scale. In: Advances in Neural Information Processing Systems (2022)"},{"key":"38_CR5","first-page":"10323","volume":"202","author":"E Frantar","year":"2023","unstructured":"Frantar, E., Alistarh, D.: SparseGPT: Massive Language Models Can be Accurately Pruned in One-Shot. In: Proceedings of the 40th International Conference on Machine Learning (ICML 2023). Proceedings of Machine Learning Research. 202, 10323\u201310337 (2023)","journal-title":"Proceedings of Machine Learning Research"},{"key":"38_CR6","volume-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"E Frantar","year":"2023","unstructured":"Frantar, E., Ashkboos, S., Hoefler, T., Alistarh, D.: GPTQ: Accurate post-training quantization for generative pre-trained transformers. International Conference on Learning Representations, In (2023)"},{"key":"38_CR7","volume-title":"Advances in Neural Information Processing Systems","author":"S Han","year":"2015","unstructured":"Han, S., Pool, J., Tran, J., Dally, W.: Learning both weights and connections for efficient neural networks. In: Advances in Neural Information Processing Systems (2015)"},{"key":"38_CR8","volume-title":"International Conference on Learning Representations","author":"S Han","year":"2016","unstructured":"Han, S., Mao, H., Dally, W.J.: Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. In: International Conference on Learning Representations (2016)"},{"key":"38_CR9","unstructured":"LeCun, Y., Denker, J., Solla, S.: Optimal brain damage. Adv. Neur. Inform. Process. Syst. 2 (1989)"},{"key":"38_CR10","volume-title":"International Conference on Learning Representations","author":"N Lee","year":"2019","unstructured":"Lee, N., Ajanthan, T., Torr, P.H.S.: SNIP: Single-shot network pruning based on connection sensitivity. In: International Conference on Learning Representations (2019)"},{"key":"38_CR11","volume-title":"International Conference on Learning Representations","author":"Z Liu","year":"2019","unstructured":"Liu, Z., Sun, M., Zhou, T., Huang, G., Darrell, T.: Rethinking the value of network pruning. In: International Conference on Learning Representations (2019)"},{"key":"38_CR12","volume-title":"International Conference on Learning Representations","author":"C Louizos","year":"2018","unstructured":"Louizos, C., Welling, M., Kingma, D.P.: Learning sparse neural networks through l0 regularization. In: International Conference on Learning Representations (2018)"},{"key":"38_CR13","doi-asserted-by":"publisher","first-page":"21702","DOI":"10.52202\/075280-0950","volume":"36","author":"X Ma","year":"2023","unstructured":"Ma, X., Fang, G., Wang, X.: LLM-Pruner: On the Structural Pruning of Large Language Models. Advances in Neural Information Processing Systems. 36, 21702\u201321720 (2023)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"38_CR14","volume-title":"International Conference on Learning Representations (ICLR 2017)","author":"S Merity","year":"2017","unstructured":"Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer Sentinel Mixture Models. In: International Conference on Learning Representations (ICLR 2017) (2017)"},{"key":"38_CR15","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"P Molchanov","year":"2019","unstructured":"Molchanov, P., Mallya, A., Tyree, S., Frosio, I., Kautz, J.: Importance estimation for neural network pruning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)"},{"key":"38_CR16","volume-title":"International Conference on Learning Representations","author":"P Molchanov","year":"2017","unstructured":"Molchanov, P., Tyree, S., Karras, T., Aila, T., Kautz, J.: Pruning convolutional neural networks for resource efficient inference. In: International Conference on Learning Representations (2017)"},{"issue":"140","key":"38_CR17","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., et al.: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. Journal of Machine Learning Research. 21(140), 1\u201367 (2020)","journal-title":"Journal of Machine Learning Research"},{"key":"38_CR18","volume-title":"International Conference on Learning Representations","author":"A Renda","year":"2020","unstructured":"Renda, A., Frankle, J., Carbin, M.: Comparing rewinding and fine-tuning in neural network pruning. In: International Conference on Learning Representations (2020)"},{"key":"38_CR19","volume-title":"Advances in Neural Information Processing Systems","author":"V Sanh","year":"2020","unstructured":"Sanh, V., Wolf, T., Rush, A.M.: Movement pruning: Adaptive sparsity by fine-tuning. In: Advances in Neural Information Processing Systems (2020)"},{"key":"38_CR20","volume-title":"International Conference on Learning Representations (ICLR 2024)","author":"M Sun","year":"2024","unstructured":"Sun, M., Liu, Z., Bair, A., Kolter, J.Z.: A Simple and Effective Pruning Approach for Large Language Models. In: International Conference on Learning Representations (ICLR 2024) (2024)"},{"key":"38_CR21","unstructured":"Touvron, H., et al.: LLaMA: Open and efficient foundation language models. arXiv preprint https:\/\/arxiv.org\/abs\/2302.13971 (2023)"},{"key":"38_CR22","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Wohlwend, J., Lei, T.: Structured pruning of large language models. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2020)"},{"key":"38_CR23","unstructured":"Wei, J., et al.: Emergent abilities of large language models. Trans. Mach. Learn. Res. (2022)"},{"key":"38_CR24","volume-title":"International Conference on Machine Learning","author":"G Xiao","year":"2023","unstructured":"Xiao, G., Lin, J., Seznec, M., Wu, H., Demouth, J., Han, S.: SmoothQuant: Accurate and efficient post-training quantization for large language models. In: International Conference on Machine Learning (2023)"},{"key":"38_CR25","volume-title":"Advances in Neural Information Processing Systems","author":"G Yuan","year":"2021","unstructured":"Yuan, G. et al.: MEST: Accurate and fast memory-economic sparse training framework on the edge. In: Advances in Neural Information Processing Systems (2021)"},{"key":"38_CR26","doi-asserted-by":"publisher","first-page":"4791","DOI":"10.18653\/v1\/P19-1472","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"R Zellers","year":"2019","unstructured":"Zellers, R., Holtzman, A., Bisk, Y., Farhadi, A., Choi, Y.: HellaSwag: Can a Machine Really Finish Your Sentence? In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4791\u20134800 (2019)"},{"key":"38_CR27","unstructured":"Zhang, S., et al.: OPT: Open pre-trained transformer language models. arXiv preprint https:\/\/arxiv.org\/abs\/2205.01068 (2022)"},{"key":"38_CR28","volume-title":"International Conference on Learning Representations (ICLR 2024)","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Bai, H., Lin, H., Zhao, J., Hou, L., Cannistraci, C.V.: Plug-and-Play: An Efficient Post-Training Pruning Method for Large Language Models. In: International Conference on Learning Representations (ICLR 2024) (2024)"},{"key":"38_CR29","first-page":"2924","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"C Clark","year":"2019","unstructured":"Clark, C., Lee, K., Chang, M.-W., Kwiatkowski, T., Collins, M., Toutanova, K.: BoolQ: Exploring the Surprising Difficulty of Natural Yes\/No Questions. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 2924\u20132936 (2019)"},{"key":"38_CR30","first-page":"1112","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"A Williams","year":"2018","unstructured":"Williams, A., Nangia, N., Bowman, S.R.: A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1, pp. 1112\u20131122 (2018)"},{"issue":"05","key":"38_CR31","doi-asserted-by":"publisher","first-page":"8732","DOI":"10.1609\/aaai.v34i05.6399","volume":"34","author":"K Sakaguchi","year":"2020","unstructured":"Sakaguchi, K., Le Bras, R., Bhagavatula, C., Choi, Y.: WinoGrande: An Adversarial Winograd Schema Challenge at Scale. Proceedings of the AAAI Conference on Artificial Intelligence. 34(05), 8732\u20138740 (2020)","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"38_CR32","doi-asserted-by":"publisher","first-page":"353","DOI":"10.18653\/v1\/W18-5446","volume-title":"Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","author":"A Wang","year":"2018","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding. In: Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pp. 353\u2013355 (2018)"},{"key":"38_CR33","volume-title":"International Conference on Learning Representations","author":"J Frankle","year":"2019","unstructured":"Frankle, J., Carbin, M.: The lottery ticket hypothesis: Finding sparse, trainable neural networks. In: International Conference on Learning Representations (2019)"},{"key":"38_CR34","volume-title":"International Conference on Machine Learning","author":"U Evci","year":"2020","unstructured":"Evci, U., Gale, T., Menick, J., Castro, P.S., Elsen, E.: Rigging the lottery: Making all tickets winners. In: International Conference on Machine Learning (2020)"},{"key":"38_CR35","unstructured":"Zhu, M., Gupta, S.: To prune, or not to prune: Exploring the efficacy of pruning for model compression. arXiv preprint https:\/\/arxiv.org\/abs\/1710.01878 (2017)"},{"key":"38_CR36","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/ICNN.1993.298572","volume-title":"IEEE International Conference on Neural Networks","author":"B Hassibi","year":"1993","unstructured":"Hassibi, B., Stork, D.G., Wolff, G.J.: Optimal brain surgeon and general network pruning. In: IEEE International Conference on Neural Networks, pp. 293\u2013299 (1993)"},{"key":"38_CR37","volume-title":"Advances in Neural Information Processing Systems","author":"J Pool","year":"2021","unstructured":"Pool, J., Yu, C.: Channel permutations for N:M sparsity. In: Advances in Neural Information Processing Systems (2021)"},{"key":"38_CR38","volume-title":"Advances in Neural Information Processing Systems","author":"I Hubara","year":"2021","unstructured":"Hubara, I., Chmiel, B., Island, M., Banner, R., Naor, J., Soudry, D.: Accelerated sparse neural training: A provable and efficient method to find N:M transposable masks. In: Advances in Neural Information Processing Systems (2021)"},{"key":"38_CR39","volume-title":"International Conference on Learning Representations (ICLR 2021)","author":"A Zhou","year":"2021","unstructured":"Zhou, A., Ma, Y., Zhu, J., Liu, J., Zhang, Z., Yuan, K., et al.: Learning N:M Fine-Grained Structured Sparse Neural Networks from Scratch. In: International Conference on Learning Representations (ICLR 2021) (2021)"},{"key":"38_CR40","doi-asserted-by":"publisher","unstructured":"Gao, L., et al.: A Framework for Few-Shot Language Model Evaluation. Zenodo. (2021). https:\/\/doi.org\/10.5281\/zenodo.5371629","DOI":"10.5281\/zenodo.5371629"},{"key":"38_CR41","volume-title":"International Conference on Learning Representations (ICLR 2024)","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Zhao, L., Lin, M., Sun, Y., Yao, Y., Han, X., et al.: Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs. In: International Conference on Learning Representations (ICLR 2024) (2024)"},{"key":"38_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1007\/978-3-030-84529-2_44","volume-title":"Intelligent Computing Theories and Application. ICIC 2021","author":"C Wei","year":"2021","unstructured":"Wei, C., Lu, Z., Lin, Z., Zhong, C.: Research on Deep Neural Network Model Compression Based on Quantification Pruning and Huffmann Encoding. In: Huang, D.-S., Jo, K.-H., Li, J., Gribova, V., Hussain, A. (eds.) Intelligent Computing Theories and Application. ICIC 2021 Lecture Notes in Computer Science, vol. 12837, pp. 522\u2013531. Springer, Cham (2021)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3441-7_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T05:38:30Z","timestamp":1783921110000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3441-7_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"ISBN":["9789819234400","9789819234417"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3441-7_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"14 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}