{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:51:43Z","timestamp":1784299903100,"version":"3.55.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T00:00:00Z","timestamp":1726790400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T00:00:00Z","timestamp":1726790400000},"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":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s11432-024-4101-6","type":"journal-article","created":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:01:53Z","timestamp":1727049713000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["SpikingMiniLM: energy-efficient spiking transformer for natural language understanding"],"prefix":"10.1007","volume":"67","author":[{"given":"Jiayu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangrong","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeke","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinghai","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huajin","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,20]]},"reference":[{"key":"4101_CR1","unstructured":"Devlin J, Chang M W, Lee K, et al. BERT: pre-training of deep bidirectional transformers for language understanding. 2018. ArXiv:1810.04805"},{"key":"4101_CR2","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N, et al. Language models are few-shot learners. In: Proceedings of Advances in Neural Information Processing Systems, 2020. 33: 1877\u20131901","journal-title":"Proceedings of Advances in Neural Information Processing Systems"},{"key":"4101_CR3","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"Z Zhou","year":"2022","unstructured":"Zhou Z, Zhu Y, He C, et al. Spikformer: when spiking neural network meets transformer. In: Proceedings of the 11th International Conference on Learning Representations, 2022"},{"key":"4101_CR4","unstructured":"Yao M, Hu J, Zhou Z, et al. Spike-driven transformer. 2023. ArXiv:2307.01694"},{"key":"4101_CR5","first-page":"8801","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Zhang","year":"2022","unstructured":"Zhang J, Dong B, Zhang H, et al. Spiking transformers for event-based single object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022. 8801\u20138810"},{"key":"4101_CR6","unstructured":"Bal M, Sengupta A. SpikingBERT: distilling BERT to train spiking language models using implicit differentiation. 2023. ArXiv:2308.10873"},{"key":"4101_CR7","unstructured":"Lv C, Li T, Xu J, et al. SpikeBERT: a language Spikformer trained with two-stage knowledge distillation from BERT. 2023. ArXiv:2308.15122"},{"key":"4101_CR8","unstructured":"Zhou C, Yu L, Zhou Z, et al. Spikingformer: spike-driven residual learning for transformer-based spiking neural network. 2023. ArXiv:2304.11954"},{"key":"4101_CR9","unstructured":"Zhou C, Zhang H, Zhou Z, et al. Enhancing the performance of transformer-based spiking neural networks by improved downsampling with precise gradient backpropagation. 2023. ArXiv:2305.05954"},{"key":"4101_CR10","unstructured":"Zou S, Mu Y, Zuo X, et al. Event-based human pose tracking by spiking spatiotemporal transformer. 2023. ArXiv:2303.09681"},{"key":"4101_CR11","unstructured":"Zhou Z, Che K, Fang W, et al. Spikformer V2: join the high accuracy club on ImageNet with an SNN ticket. 2024. ArXiv:2401.02020"},{"key":"4101_CR12","doi-asserted-by":"crossref","unstructured":"Leroux N, Finkbeiner J, Neftci E. Online transformers with spiking neurons for fast prosthetic hand control. 2023. ArXiv:2303.11860","DOI":"10.1109\/BioCAS58349.2023.10388996"},{"key":"4101_CR13","unstructured":"Wang Z, Zhao Q, Cui J, et al. AutoST: training-free neural architecture search for spiking transformers. 2023. ArXiv:2307.00293"},{"key":"4101_CR14","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"M Yao","year":"2024","unstructured":"Yao M, Hu J, Hu T, et al. Spike-driven transformer V2: meta spiking neural network architecture inspiring the design of next-generation neuromorphic chips. In: Proceedings of the 12th International Conference on Learning Representations, 2024"},{"key":"4101_CR15","unstructured":"Zhu R J, Zhao Q, Eshraghian J K. SpikeGPT: generative pre-trained language model with spiking neural networks. 2023. ArXiv:2302.13939"},{"key":"4101_CR16","doi-asserted-by":"crossref","unstructured":"Peng B, Alcaide E, Anthony Q, et al. RWKV: reinventing RNNs for the transformer era. 2023. ArXiv:2305.13048","DOI":"10.18653\/v1\/2023.findings-emnlp.936"},{"key":"4101_CR17","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1109\/TASLP.2022.3221011","volume":"31","author":"R Xiao","year":"2023","unstructured":"Xiao R, Wan Y, Yang B S, et al. Towards energy-preserving natural language understanding with spiking neural networks. IEEE ACM Trans Audio Speech Lang Process, 2023, 31: 439\u2013447","journal-title":"IEEE ACM Trans Audio Speech Lang Process"},{"key":"4101_CR18","volume-title":"Proceedings of the 11th International Conference on Learning Representations","author":"C Lv","year":"2022","unstructured":"Lv C, Xu J, Zheng X. Spiking convolutional neural networks for text classification. In: Proceedings of the 11th International Conference on Learning Representations, 2022"},{"key":"4101_CR19","first-page":"2661","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"W Fang","year":"2021","unstructured":"Fang W, Yu Z, Chen Y, et al. Incorporating learnable membrane time constant to enhance learning of spiking neural networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021. 2661\u20132671"},{"key":"4101_CR20","doi-asserted-by":"publisher","first-page":"014003","DOI":"10.1088\/2634-4386\/acb2f0","volume":"3","author":"J Huang","year":"2023","unstructured":"Huang J, Serb A, Stathopoulos S, et al. Text classification in memristor-based spiking neural networks. Neuromorph Comput Eng, 2023, 3: 014003","journal-title":"Neuromorph Comput Eng"},{"key":"4101_CR21","first-page":"30","volume-title":"Proceedings of Advances in Neural Information Processing Systems","author":"A Vaswani","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of Advances in Neural Information Processing Systems, 2017. 30"},{"key":"4101_CR22","first-page":"1352","volume-title":"Proceedings of Uncertainty in Artificial Intelligence","author":"T Bachlechner","year":"2021","unstructured":"Bachlechner T, Majumder B P, Mao H, et al. ReZero is all you need: fast convergence at large depth. In: Proceedings of Uncertainty in Artificial Intelligence, 2021. 1352\u20131361"},{"key":"4101_CR23","first-page":"114","volume":"2","author":"S R Bowling","year":"2009","unstructured":"Bowling S R, Khasawneh M T, Kaewkuekool S, et al. A logistic approximation to the cumulative normal distribution. J Indust Eng Manag, 2009, 2: 114\u2013127","journal-title":"J Indust Eng Manag"},{"key":"4101_CR24","doi-asserted-by":"crossref","unstructured":"Wang A, Singh A, Michael J, et al. GLUE: a multi-task benchmark and analysis platform for natural language understanding. 2018. ArXiv:1804.07461","DOI":"10.18653\/v1\/W18-5446"},{"key":"4101_CR25","doi-asserted-by":"crossref","unstructured":"Wang W, Bao H, Huang S, et al. MiniLMv2: multi-head self-attention relation distillation for compressing pretrained transformers. 2020. ArXiv:2012.15828","DOI":"10.18653\/v1\/2021.findings-acl.188"},{"key":"4101_CR26","unstructured":"Phang J, F\u00e9vry T, Bowman S R. Sentence encoders on stilts: supplementary training on intermediate labeled-data tasks. 2018. ArXiv:1811.01088"},{"key":"4101_CR27","unstructured":"Turc I, Chang M W, Lee K, et al. Well-read students learn better: on the importance of pre-training compact models. 2019. ArXiv:1908.08962"},{"key":"4101_CR28","first-page":"125","volume-title":"Proceedings of the 2nd Workshop on Insights from Negative Results in NLP","author":"P Bhargava","year":"2021","unstructured":"Bhargava P, Drozd A, Rogers A. Generalization in NLI: ways (not) to go beyond simple heuristics. In: Proceedings of the 2nd Workshop on Insights from Negative Results in NLP, 2021. 125\u2013135"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4101-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-024-4101-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-024-4101-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T20:23:37Z","timestamp":1763583817000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-024-4101-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,20]]},"references-count":28,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["4101"],"URL":"https:\/\/doi.org\/10.1007\/s11432-024-4101-6","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,20]]},"assertion":[{"value":"3 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 September 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"200406"}}