{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T21:02:18Z","timestamp":1784408538986,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234097","type":"print"},{"value":"9789819234103","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"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\/978-981-92-3410-3_33","type":"book-chapter","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:09:39Z","timestamp":1784405379000},"page":"389-399","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CAGE-MoE: Cross-Projection Alignment-Guided Compression for MoE Models"],"prefix":"10.1007","author":[{"given":"Tianhao","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhunchen","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guotong","family":"Geng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenpeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"33_CR1","unstructured":"Vaswani, A. et al.: Attention is all you need. Adv. Neural Inf. Proces. Syst. 30 (2017)"},{"issue":"1","key":"33_CR2","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79\u201387 (1991)","journal-title":"Neural Comput."},{"key":"33_CR3","unstructured":"Yang, A., et al.: Qwen3 technical report. arXiv preprint https:\/\/arxiv.org\/abs\/2505.09388 (2025)"},{"key":"33_CR4","unstructured":"Liu, A., et al.: Deepseek-v3 technical report. arXiv preprint https:\/\/arxiv.org\/abs\/2412.19437 (2024)"},{"key":"33_CR5","unstructured":"Team, K., et al.: Kimi k2: Open agentic intelligence. arXiv preprint https:\/\/arxiv.org\/abs\/2507.20534 (2025)"},{"key":"33_CR6","unstructured":"Gu, H., et al.: Delta decom pression for moe-based llms compression. arXiv preprint https:\/\/arxiv.org\/abs\/2502.17298 (2025)"},{"key":"33_CR7","unstructured":"Liu, Z., et al.: Molae: Mix ture of latent experts for parameter-efficient language models. arXiv preprint https:\/\/arxiv.org\/abs\/2503.23100 (2025)"},{"key":"33_CR8","unstructured":"Chen, X., Ha, M., Lan, Z., Zhang, J., Li, J.: Mobe: Mixture-of-basis-experts for compressing moe-based llms. arXiv preprint https:\/\/arxiv.org\/abs\/2508.05257 (2025)"},{"key":"33_CR9","unstructured":"Liu, A., et al.: Deepseek-v2: A strong, economical, and efficient mixture of-experts language model. arXiv preprint https:\/\/arxiv.org\/abs\/2405.04434 (2024)"},{"key":"33_CR10","unstructured":"Team, L., et al.: Every flop counts: Scaling a 300b mixture-of-experts ling llm without premium gpus. arXiv preprint https:\/\/arxiv.org\/abs\/2503.05139 (2025)"},{"key":"33_CR11","unstructured":"Hendrycks, D. et al.: Measuring massive multitask language understanding. arXiv preprint https:\/\/arxiv.org\/abs\/2009.03300 (2020)"},{"key":"33_CR12","doi-asserted-by":"publisher","first-page":"11260","DOI":"10.18653\/v1\/2024.findings-acl.671","volume-title":"Findings of the Association for Computational Linguistics: ACL 2024","author":"H Li","year":"2024","unstructured":"Li, H. et al.: Cmmlu: Measuring massive multitask language understanding in Chinese. In: Findings of the Association for Computational Linguistics: ACL 2024, pp. 11260\u201311285 (2024)"},{"key":"33_CR13","doi-asserted-by":"publisher","first-page":"62991","DOI":"10.52202\/075280-2749","volume":"36","author":"Y Huang","year":"2023","unstructured":"Huang, Y., et al.: C-eval: a multi-level multi-discipline chinese evaluation suite for foundation models. Adv. Neural Inf. Proces. Syst. 36, 62991\u201363010 (2023)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"33_CR14","unstructured":"Cobbe, K., et al.: Training verifiers to solve math word problems. arXiv preprint https:\/\/arxiv.org\/abs\/2110.14168 (2021)"},{"key":"33_CR15","unstructured":"Chen, M., et al.: Evaluating large language models trained on code. arXiv preprint https:\/\/arxiv.org\/abs\/2107.03374 (2021)"},{"key":"33_CR16","unstructured":"Xie, Y. et al.: Moe-pruner: Pruning mixture-of-experts large language model using the hints from its router. arXiv preprint https:\/\/arxiv.org\/abs\/2410.12013 (2024)"},{"key":"33_CR17","doi-asserted-by":"publisher","first-page":"6159","DOI":"10.18653\/v1\/2024.acl-long.334","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"X Lu","year":"2024","unstructured":"Lu, X. et al.: Not all experts are equal: Efficient expert pruning and skipping for mixture-of-experts large language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 6159\u20136172 (2024)"},{"key":"33_CR18","doi-asserted-by":"publisher","first-page":"10456","DOI":"10.18653\/v1\/2024.findings-emnlp.612","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","author":"C Yang","year":"2024","unstructured":"Yang, C. et al.: Moe-i2: Compressing mixture of experts models through inter-expert pruning and intra-expert low-rank decomposition. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 10456\u201310466 (2024)"},{"key":"33_CR19","unstructured":"Li, P. et al.: Merge, then compress: demystify efficient smoe with hints from its routing policy. arXiv preprint https:\/\/arxiv.org\/abs\/2310.01334 (2023)"},{"key":"33_CR20","unstructured":"Chen, I., et al.: Retraining-free merging of sparse moe via hierarchical clustering. arXiv preprint https:\/\/arxiv.org\/abs\/2410.08589 (2024)"},{"key":"33_CR21","first-page":"22994","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"L Li","year":"2026","unstructured":"Li, L. et al.: Sub-moe: efficient mixture-of-expert LLMS compression via subspace expert merging. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, pp. 22994\u201323002 (2026)"},{"key":"33_CR22","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint https:\/\/arxiv.org\/abs\/1412.6980 (2014)"}],"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\/978-981-92-3410-3_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:09:41Z","timestamp":1784405381000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3410-3_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"ISBN":["9789819234097","9789819234103"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3410-3_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"19 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"}}]}}