{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T13:13:26Z","timestamp":1784207606988,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234349","type":"print"},{"value":"9789819234356","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"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\/978-981-92-3435-6_14","type":"book-chapter","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:22:48Z","timestamp":1784204568000},"page":"161-172","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ALP: Adaptive Layerwise Pruning in Large Language Models"],"prefix":"10.1007","author":[{"given":"Yuchuan","family":"Mu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuli","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianping","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"14_CR1","unstructured":"OpenAI, et al.: GPT-4 technical report. arXiv preprint https:\/\/arxiv.org\/abs\/2303.08774 (2023)."},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., Zettlemoyer, L.: LLM.int8(): 8-bit matrix multiplication for transformers at scale. In: NeurIPS, vol. 35, pp. 30318\u201330332 (2022).","DOI":"10.52202\/068431-2198"},{"key":"14_CR3","unstructured":"Gu, Y., Dong, L., Wei, F., Huang, M.: MiniLLM: Knowledge distillation of large language models. In: ICLR (2024)."},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Ma, X., Fang, G., Wang, X.: LLM-Pruner: On the structural pruning of large language models. In: NeurIPS, vol. 36, pp. 21702\u201321720 (2023).","DOI":"10.52202\/075280-0950"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"An, Y., Zhao, X., Yu, T., Tang, M., Wang, J.: Fluctuation-based adaptive structured pruning for large language models. In: AAAI, vol. 38, pp. 10865\u201310873 (2024).","DOI":"10.1609\/aaai.v38i10.28960"},{"key":"14_CR6","unstructured":"Wan, Z., et al.: Efficient large language models: A survey. Trans. Mach. Learn. Res. (2024)"},{"key":"14_CR7","unstructured":"Wang, W., et al.: Model compression and efficient inference for large language models: A survey. arXiv preprint https:\/\/arxiv.org\/abs\/2402.09748 (2024)."},{"key":"14_CR8","unstructured":"Frantar, E., Alistarh, D.: SparseGPT: Massive language models can be accurately pruned in one-shot. In: ICML, vol. 202, pp. 10323\u201310337 (2023)."},{"key":"14_CR9","unstructured":"Sun, M., Liu, Z., Bair, A., Kolter, J.Z.: A simple and effective pruning approach for large language models. In: ICLR (2024)."},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Plug-and-play: An efficient post-training pruning method for large language models. In: ICLR (2024).","DOI":"10.20944\/preprints202310.1487.v2"},{"key":"14_CR11","unstructured":"Yin, L., et al.: Outlier weighed layerwise sparsity (OWL): A missing secret sauce for pruning LLMs to high sparsity. In: ICML, vol. 235, pp. 57346\u201357367 (2024)."},{"key":"14_CR12","unstructured":"Lee, N., Ajanthan, T., Torr, P.H.S.: SNIP: Single-shot network pruning based on connection sensitivity. In: ICLR (2019)."},{"key":"14_CR13","unstructured":"Touvron, H., et al.: LLaMA: Open and efficient foundation language models. arXiv preprint https:\/\/arxiv.org\/abs\/2302.13971 (2023)."},{"key":"14_CR14","unstructured":"Touvron, H., et al.: Llama 2: Open foundation and fine-tuned chat models. arXiv preprint https:\/\/arxiv.org\/abs\/2307.09288 (2023)."},{"key":"14_CR15","unstructured":"Zhang, S., et al.: OPT: Open pre-trained transformer language models. arXiv preprint https:\/\/arxiv.org\/abs\/2205.01068 (2022)."},{"key":"14_CR16","unstructured":"Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer sentinel mixture models. In: ICLR (2017)."},{"key":"14_CR17","unstructured":"Clark, C., et al.: BoolQ: Exploring the surprising difficulty of natural yes\/no questions. In: NAACL-HLT, pp. 2924\u20132936 (2019)."},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Zellers, R., et al.: HellaSwag: Can a machine really finish your sentence? In: ACL, pp. 4791\u20134800 (2019).","DOI":"10.18653\/v1\/P19-1472"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Boratko, M., et al.: A systematic classification of knowledge, reasoning, and context within the ARC dataset. In: MRQA Workshop, pp. 60\u201370 (2018).","DOI":"10.18653\/v1\/W18-2607"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Williams, A., Nangia, N., Bowman, S.: A broad-coverage challenge corpus for sentence understanding through inference. In: NAACL-HLT, pp. 1112\u20131122 (2018).","DOI":"10.18653\/v1\/N18-1101"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Mihaylov, T., Clark, P., Khot, T., Sabharwal, A.: Can a suit of armor conduct electricity? A new dataset for open book question answering. In: EMNLP, pp. 2381\u20132391 (2018).","DOI":"10.18653\/v1\/D18-1260"},{"issue":"140","key":"14_CR22","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. JMLR. 21(140), 1\u201367 (2020)","journal-title":"JMLR"},{"key":"14_CR23","unstructured":"Frantar, E., Ashkboos, S., Hoefler, T., Alistarh, D.: OPTQ: Accurate quantization for generative pre-trained transformers. In: ICLR (2023)."}],"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\/978-981-92-3435-6_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:22:52Z","timestamp":1784204572000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3435-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"ISBN":["9789819234349","9789819234356"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3435-6_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,17]]},"assertion":[{"value":"17 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"}}]}}