{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T21:58:25Z","timestamp":1781042305864,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819570744","type":"print"},{"value":"9789819570751","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-7075-1_33","type":"book-chapter","created":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T11:12:55Z","timestamp":1773486775000},"page":"509-522","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Proxy-Mamba: Training-Free Architecture Search for\u00a0Mamba via\u00a0Gradient-Weight Correlation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7567-7177","authenticated-orcid":false,"given":"Huigang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5627-7522","authenticated-orcid":false,"given":"Liuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0967-4859","authenticated-orcid":false,"given":"Jun","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,15]]},"reference":[{"key":"33_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Cavagnero, N., Robbiano, L., Caputo, B., Averta, G.: Freerea: training-free evolution-based architecture search. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1493\u20131502 (2023)","DOI":"10.1109\/WACV56688.2023.00154"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Chen, M., Peng, H., Fu, J., Ling, H.: Autoformer: searching transformers for visual recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12270\u201312280 (2021)","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"33_CR4","unstructured":"Chen, W., Gong, X., Wang, Z.: Neural architecture search on imagenet in four gpu hours: A theoretically inspired perspective. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"33_CR5","unstructured":"Chrabaszcz, P., Loshchilov, I., Hutter, F.: A downsampled variant of imagenet as an alternative to the cifar datasets. arXiv preprint arXiv:1707.08819 (2017)"},{"key":"33_CR6","unstructured":"Dao, T., Gu, A.: Transformers are ssms: generalized models and efficient algorithms through structured state space duality. arXiv preprint arXiv:2405.21060 (2024)"},{"key":"33_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, volume 1 (long and short papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"33_CR9","first-page":"3634","volume":"44","author":"X Dong","year":"2021","unstructured":"Dong, X., Liu, L., Musial, K., Gabrys, B.: Nats-bench: benchmarking nas algorithms for architecture topology and size. IEEE Trans. Pattern Anal. Mach. Intell. 44, 3634\u20133646 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"33_CR10","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"33_CR11","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396 (2021)"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Kautz, J.: Mambavision: a hybrid mamba-transformer vision backbone. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 25261\u201325270 (2025)","DOI":"10.1109\/CVPR52734.2025.02352"},{"key":"33_CR13","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"key":"33_CR14","unstructured":"Lee, N., Ajanthan, T., Torr, P.H.: Snip: single-shot network pruning based on connection sensitivity. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"33_CR15","unstructured":"Lieber, O., et\u00a0al.: Jamba: a hybrid transformer-mamba language model. arXiv preprint arXiv:2403.19887 (2024)"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Lin, M., et al.: Zen-nas: a zero-shot nas for high-performance image recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 347\u2013356 (2021)","DOI":"10.1109\/ICCV48922.2021.00040"},{"key":"33_CR17","unstructured":"Liu, H., Simonyan, K., Yang, Y.: Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018)"},{"key":"33_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1007\/978-3-030-86383-8_44","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2021","author":"V Lopes","year":"2021","unstructured":"Lopes, V., Alirezazadeh, S., Alexandre, L.A.: EPE-NAS: efficient performance estimation without training for neural architecture search. In: Farka\u0161, I., Masulli, P., Otte, S., Wermter, S. (eds.) ICANN 2021. LNCS, vol. 12895, pp. 552\u2013563. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86383-8_44"},{"key":"33_CR19","unstructured":"Mellor, J., Turner, J., Storkey, A., Crowley, E.J.: Neural architecture search without training. In: International Conference on Machine Learning, pp. 7588\u20137598. PMLR (2021)"},{"key":"33_CR20","unstructured":"Pham, H., Guan, M., Zoph, B., Le, Q., Dean, J.: Efficient neural architecture search via parameters sharing. In: International Conference on Machine Learning, pp. 4095\u20134104. PMLR (2018)"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 4780\u20134789 (2019)","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"33_CR22","unstructured":"Ren, L., Liu, Y., Lu, Y., Shen, Y., Liang, C., Chen, W.: Samba: simple hybrid state space models for efficient unlimited context language modeling. arXiv preprint arXiv:2406.07522 (2024)"},{"key":"33_CR23","first-page":"6377","volume":"33","author":"H Tanaka","year":"2020","unstructured":"Tanaka, H., Kunin, D., Yamins, D.L., Ganguli, S.: Pruning neural networks without any data by iteratively conserving synaptic flow. Adv. Neural. Inf. Process. Syst. 33, 6377\u20136389 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR24","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"33_CR25","unstructured":"Turner, J., Crowley, E.J., O\u2019Boyle, M., Storkey, A., Gray, G.: Blockswap: fisher-guided block substitution for network compression on a budget. arXiv preprint arXiv:1906.04113 (2019)"},{"key":"33_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"33_CR27","unstructured":"Wang, C., Zhang, G., Grosse, R.: Picking winning tickets before training by preserving gradient flow. arXiv preprint arXiv:2002.07376 (2020)"},{"key":"33_CR28","unstructured":"White, C., et al.: Neural architecture search: Insights from 1000 papers. arXiv preprint arXiv:2301.08727 (2023)"},{"key":"33_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, Q., et al.: Training-free transformer architecture search. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10894\u201310903 (2022)","DOI":"10.1109\/CVPR52688.2022.01062"},{"key":"33_CR30","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: efficient visual representation learning with bidirectional state space model. In: Proceedings of the 41st International Conference on Machine Learning (ICML) (2024)"},{"key":"33_CR31","unstructured":"Zoph, B., Le, Q.V.: Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578 (2016)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2025: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7075-1_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T21:27:00Z","timestamp":1781040420000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7075-1_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570744","9789819570751"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7075-1_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"15 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2025","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":"pricai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}