{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T08:47:29Z","timestamp":1782204449875,"version":"3.54.5"},"reference-count":56,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.knosys.2026.116244","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T15:29:31Z","timestamp":1781105371000},"page":"116244","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["RS-MoE: Coupled expert compression via activation-peak guided collaborative decomposition"],"prefix":"10.1016","volume":"349","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5576-7678","authenticated-orcid":false,"given":"Jiajun","family":"Lai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2320-2791","authenticated-orcid":false,"given":"Shijie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3940-2159","authenticated-orcid":false,"given":"Haoqin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8533-7515","authenticated-orcid":false,"given":"Ying","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0634-3085","authenticated-orcid":false,"given":"Huaiguang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116244_b1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TKDE.2025.3554028","article-title":"A survey on mixture of experts in large language models","author":"Cai","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.knosys.2026.116244_b2","series-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"10.1016\/j.knosys.2026.116244_b3","series-title":"DeepSeek-V3 technical report","author":"DeepSeek-AI","year":"2025"},{"key":"10.1016\/j.knosys.2026.116244_b4","series-title":"Mixtral of experts","author":"Jiang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116244_b5","series-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"issue":"8","key":"10.1016\/j.knosys.2026.116244_b6","doi-asserted-by":"crossref","first-page":"3825","DOI":"10.1109\/TCYB.2025.3569333","article-title":"Causal intervention is what large language models need for spatio-temporal forecasting","volume":"55","author":"Li","year":"2025","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.knosys.2026.116244_b7","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"10456","article-title":"MoE-I2: Compressing mixture of experts models through inter-expert pruning and intra-expert low-rank decomposition","author":"Yang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116244_b8","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024","first-page":"6159","article-title":"Not all experts are equal: Efficient expert pruning and skipping for mixture-of-experts large language models","author":"Lu","year":"2024"},{"key":"10.1016\/j.knosys.2026.116244_b9","series-title":"MoE-pruner: Pruning mixture-of-experts large language model using the hints from its router","author":"Xie","year":"2024"},{"key":"10.1016\/j.knosys.2026.116244_b10","series-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","article-title":"Merge, then compress: Demystify efficient SMoE with hints from its routing policy","author":"Li","year":"2024"},{"key":"10.1016\/j.knosys.2026.116244_b11","unstructured":"I.-C. Chen, H.-S. Liu, W.-F. Sun, C.-H. Chao, Y.-C. Hsu, C.-Y. Lee, Retraining-Free Merging of Sparse MoE via Hierarchical Clustering, in: International Conference on Machine Learning, ICML, 2025."},{"key":"10.1016\/j.knosys.2026.116244_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2025.127227","article-title":"RSynLLM: A risk-aware routing mixture-of-experts large language model for multi-energy load forecasting in large-scale distribution networks","volume":"406","author":"Li","year":"2026","journal-title":"Appl. Energy"},{"issue":"2","key":"10.1016\/j.knosys.2026.116244_b13","doi-asserted-by":"crossref","first-page":"3324","DOI":"10.1109\/TVT.2025.3599157","article-title":"Mixture of experts-based semantic communication for secure artificial intelligence of things","volume":"75","author":"He","year":"2026","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.knosys.2026.116244_b14","series-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025","article-title":"R-sparse: Rank-aware activation sparsity for efficient LLM inference","author":"Zhang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116244_b15","series-title":"Unveiling super experts in mixture-of-experts large language models","author":"Su","year":"2025"},{"key":"10.1016\/j.knosys.2026.116244_b16","doi-asserted-by":"crossref","first-page":"30318","DOI":"10.52202\/068431-2198","article-title":"Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale","volume":"35","author":"Dettmers","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.116244_b17","series-title":"GPTQ: accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022"},{"issue":"4","key":"10.1016\/j.knosys.2026.116244_b18","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1145\/3714983.3714987","article-title":"AWQ: activation-aware weight quantization for on-device LLM compression and acceleration","volume":"28","author":"Lin","year":"2024","journal-title":"GetMobile Mob. Comput. Commun."},{"key":"10.1016\/j.knosys.2026.116244_b19","series-title":"International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA","first-page":"22137","article-title":"Deja vu: Contextual sparsity for efficient LLMs at inference time","volume":"vol. 202","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116244_b20","doi-asserted-by":"crossref","unstructured":"Y. Xu, X. Han, Y. Zhang, Y. Wang, Y. Liu, S. Ji, Q. Zhu, W. Che, Camera: Multi-matrix joint compression for moe models via micro-expert redundancy analysis, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2026, pp. 27395\u201327404.","DOI":"10.1609\/aaai.v40i32.39957"},{"key":"10.1016\/j.knosys.2026.116244_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112122","article-title":"ARLP: Automatic multi-agent transformer reinforcement learning pruner for one-shot neural network pruning","volume":"300","author":"Guo","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116244_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2021.107988","article-title":"DNN compression by ADMM-based joint pruning","volume":"239","author":"Lee","year":"2022","journal-title":"Knowl.-Based Syst."},{"issue":"12","key":"10.1016\/j.knosys.2026.116244_b23","doi-asserted-by":"crossref","first-page":"5928","DOI":"10.1109\/TAI.2024.3428519","article-title":"A survey on symbolic knowledge distillation of large language models","volume":"5","author":"Acharya","year":"2024","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.knosys.2026.116244_b24","series-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025","article-title":"MiniPLM: Knowledge distillation for pre-training language models","author":"Gu","year":"2025"},{"key":"10.1016\/j.knosys.2026.116244_b25","series-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025","article-title":"SVD-LLM: truncation-aware singular value decomposition for large language model compression","author":"Wang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116244_b26","series-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"10.1016\/j.knosys.2026.116244_b27","series-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","article-title":"A simple and effective pruning approach for large language models","author":"Sun","year":"2024"},{"key":"10.1016\/j.knosys.2026.116244_b28","series-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025","article-title":"Dynamic low-rank sparse adaptation for large language models","author":"Huang","year":"2025"},{"issue":"6","key":"10.1016\/j.knosys.2026.116244_b29","doi-asserted-by":"crossref","first-page":"5500","DOI":"10.1109\/TSG.2024.3408640","article-title":"Real-time robust state estimation for large-scale low-observability power-transportation system based on meta physics-informed graph TimesNet","volume":"15","author":"Li","year":"2024","journal-title":"IEEE Trans. Smart Grid"},{"issue":"6","key":"10.1016\/j.knosys.2026.116244_b30","doi-asserted-by":"crossref","first-page":"8129","DOI":"10.1109\/TMC.2025.3648576","article-title":"Incentivizing pseudonym exchange with trajectory prediction for privacy-enhanced vehicular metaverses: A diffusion-based auction approach","volume":"25","author":"Luo","year":"2026","journal-title":"IEEE Trans. Mob. Comput."},{"key":"10.1016\/j.knosys.2026.116244_b31","article-title":"CarbonGPT: Meta causal graph-enhanced large language models for carbon emission forecasting in large-scale power distribution networks","volume":"early access","author":"Li","year":"2026","journal-title":"IEEE Trans. Smart Grid"},{"issue":"1","key":"10.1016\/j.knosys.2026.116244_b32","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/TPWRS.2025.3598366","article-title":"Efficient net load forecasting in large-scale power distribution systems via dual-branch experts fusion memory network","volume":"41","author":"Li","year":"2026","journal-title":"IEEE Trans. Power Syst."},{"issue":"10","key":"10.1016\/j.knosys.2026.116244_b33","doi-asserted-by":"crossref","first-page":"7531","DOI":"10.1109\/TII.2025.3576846","article-title":"Transferable nonintrusive load monitoring in smart grids via frequency-division fusion scattering time-series transformer","volume":"21","author":"Li","year":"2025","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.knosys.2026.116244_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.110386","article-title":"Iterative clustering pruning for convolutional neural networks","volume":"265","author":"Chang","year":"2023","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.116244_b35","article-title":"Lightweight semantic feature extraction model with direction awareness for aerial traffic object detection","author":"Shen","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.knosys.2026.116244_b36","article-title":"KACNet: Enhancing CNN feature representation with Kolmogorov-Arnold networks for medical image segmentation and classification","author":"Li","year":"2025","journal-title":"Inform. Sci."},{"key":"10.1016\/j.knosys.2026.116244_b37","series-title":"Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2025 - Volume 1: Long Papers, Albuquerque, New Mexico, USA, April 29 - May 4, 2025","first-page":"4287","article-title":"SVD-LLM V2: optimizing singular value truncation for large language model compression","author":"Wang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116244_b38","unstructured":"H. Gu, W. Li, L. Li, Z. Qiyuan, M.G. Lee, S. Sun, W. Xue, Y. Guo, Delta Decompression for MoE-based LLMs Compression, in: Proceedings of the 41th International Conference on Machine Learning, ICML 2025, 2025."},{"key":"10.1016\/j.knosys.2026.116244_b39","series-title":"Findings of the Association for Computational Linguistics, ACL 2025, Vienna, Austria, July 27 - August 1, 2025","first-page":"5065","article-title":"BlockPruner: Fine-grained pruning for large language models","author":"Zhong","year":"2025"},{"key":"10.1016\/j.knosys.2026.116244_b40","series-title":"DipSVD: Dual-importance protected SVD for efficient LLM compression","author":"Ding","year":"2025"},{"key":"10.1016\/j.knosys.2026.116244_b41","series-title":"MINE: mutual information neural estimation","author":"Belghazi","year":"2018"},{"key":"10.1016\/j.knosys.2026.116244_b42","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2024, Bangkok, Thailand, August 11-16, 2024","first-page":"1280","article-title":"DeepSeekMoE: Towards ultimate expert specialization in mixture-of-experts language models","author":"Dai","year":"2024"},{"key":"10.1016\/j.knosys.2026.116244_b43","series-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2017"},{"issue":"2","key":"10.1016\/j.knosys.2026.116244_b44","first-page":"313","article-title":"Building a large annotated corpus of English: The Penn Treebank","volume":"19","author":"Marcus","year":"1993","journal-title":"Comput. Linguist."},{"key":"10.1016\/j.knosys.2026.116244_b45","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.knosys.2026.116244_b46","series-title":"Think you have solved question answering? Try ARC, the AI2 reasoning challenge","author":"Clark","year":"2018"},{"key":"10.1016\/j.knosys.2026.116244_b47","series-title":"Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers","first-page":"4791","article-title":"HellaSwag: Can a machine really finish your sentence?","author":"Zellers","year":"2019"},{"key":"10.1016\/j.knosys.2026.116244_b48","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2-7, 2019, Volume 1 (Long and Short Papers)","first-page":"2357","article-title":"MathQA: Towards interpretable math word problem solving with operation-based formalisms","author":"Amini","year":"2019"},{"key":"10.1016\/j.knosys.2026.116244_b49","series-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October 31 - November 4, 2018","first-page":"2381","article-title":"Can a suit of armor conduct electricity? A new dataset for open book question answering","author":"Mihaylov","year":"2018"},{"key":"10.1016\/j.knosys.2026.116244_b50","first-page":"7432","article-title":"PIQA: reasoning about physical commonsense in natural language","author":"Bisk","year":"2020"},{"key":"10.1016\/j.knosys.2026.116244_b51","first-page":"8732","article-title":"WinoGrande: An adversarial winograd schema challenge at scale","author":"Sakaguchi","year":"2020"},{"key":"10.1016\/j.knosys.2026.116244_b52","doi-asserted-by":"crossref","unstructured":"M. Matena, C. Raffel, Merging Models with Fisher-Weighted Averaging, in: S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, A. Oh (Eds.), Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, 2022.","DOI":"10.52202\/068431-1287"},{"key":"10.1016\/j.knosys.2026.116244_b53","doi-asserted-by":"crossref","unstructured":"P. Yadav, D. Tam, L. Choshen, C.A. Raffel, M. Bansal, TIES-Merging: Resolving Interference When Merging Models, in: A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, S. Levine (Eds.), Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, 2023.","DOI":"10.52202\/075280-0310"},{"key":"10.1016\/j.knosys.2026.116244_b54","doi-asserted-by":"crossref","unstructured":"G. Du, J. Lee, J. Li, R. Jiang, Y. Guo, S. Yu, H. Liu, S.K. Goh, H.-K. Tang, D. He, M. Zhang, Parameter Competition Balancing for Model Merging, in: The Thirty-Eighth Annual Conference on Neural Information Processing Systems, NeurIPS, 2024.","DOI":"10.52202\/079017-2691"},{"key":"10.1016\/j.knosys.2026.116244_b55","series-title":"Proceedings of the 29th International Conference on Neural Information Processing Systems - Volume 1","first-page":"1693","article-title":"Teaching machines to read and comprehend","author":"Hermann","year":"2015"},{"key":"10.1016\/j.knosys.2026.116244_b56","series-title":"Text Summarization Branches Out","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"Lin","year":"2004"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009706?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009706?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T07:55:38Z","timestamp":1782201338000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126009706"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":56,"alternative-id":["S0950705126009706"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116244","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"RS-MoE: Coupled expert compression via activation-peak guided collaborative decomposition","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116244","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"116244"}}