{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T21:02:17Z","timestamp":1784408537509,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":31,"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_12","type":"book-chapter","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:09:59Z","timestamp":1784405399000},"page":"133-144","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MSR-Net: Multi-model Synergistic Residual Network for Efficient Large-Small Model Collaboration"],"prefix":"10.1007","author":[{"given":"Guangyu","family":"Dai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"12_CR1","volume-title":"The Twelfth International Conference on Learning Representations","author":"A Asai","year":"2024","unstructured":"Asai, A., Wu, Z., Wang, Y., Sil, A., Hajishirzi, H.: Self-RAG: learning to retrieve, generate, and critique through self-reflection. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=hSyW5go0v8"},{"key":"12_CR2","first-page":"2206","volume-title":"International Conference on Machine Learning","author":"S Borgeaud","year":"2022","unstructured":"Borgeaud, S., et al.: Improving language models by retrieving from trillions of tokens. In: International Conference on Machine Learning, pp. 2206\u20132240. PMLR (2022)"},{"key":"12_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.108276","volume":"195","author":"D Chen","year":"2025","unstructured":"Chen, D., et al.: Improving large models with small models: lower costs and better performance. Neural Netw. 195, 108276 (2025)","journal-title":"Neural Netw."},{"key":"12_CR4","first-page":"1124911257","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"D Chen","year":"2024","unstructured":"Chen, D., Zhuang, Y., Zhang, S., Liu, J., Dong, S., Tang, S.: Data shunt: collaboration of small and large models for lower costs and better performance. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, p. 1124911257 (2024)"},{"key":"12_CR5","unstructured":"Chen, L., Zaharia, M., Zou, J.: FrugalGPT: how to use large language models while reducing cost and improving performance. arXiv preprint https:\/\/arxiv.org\/abs\/2305.05176. (2023)"},{"key":"12_CR6","doi-asserted-by":"publisher","first-page":"2475","DOI":"10.18653\/v1\/D18-1269","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"A Conneau","year":"2018","unstructured":"Conneau, A., Lample, G., Rinott, R., et al.: XNLI: evaluating cross-lingual sentence representations. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2475\u20132485 (2018). https:\/\/arxiv.org\/abs\/1809.05053"},{"key":"12_CR7","unstructured":"Dai, G., Tang, S., Zhuang, Y.: KCM: KAN-based collaboration models enhance pretrained large models. arXiv preprint https:\/\/arxiv.org\/abs\/2510.20278. (2025)"},{"key":"12_CR8","first-page":"10088","volume-title":"Advances in Neural Information Processing Systems","author":"T Dettmers","year":"2023","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: QLoRA: efficient fine-tuning of quantized LLMs. In: Advances in Neural Information Processing Systems, vol. 36, pp. 10088\u201310115 (2023)"},{"issue":"6","key":"12_CR9","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","volume":"129","author":"J Gou","year":"2021","unstructured":"Gou, J., Yu, B., Maybank, S.J., Tao, D.: Knowledge distillation: a survey. Int. J. Comput. Vis. 129(6), 1789\u20131819 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"12_CR10","first-page":"39293938","volume-title":"International Conference on Machine Learning","author":"K Guu","year":"2020","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.: Retrieval augmented language model pre-training. In: International Conference on Machine Learning, p. 39293938. PMLR (2020)"},{"key":"12_CR11","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint https:\/\/arxiv.org\/abs\/1503.02531. (2015)"},{"key":"12_CR12","unstructured":"Hu, E.J., Shen, Y., Wallis, P., et al.: LoRA: low-rank adaptation of large language models. arXiv preprint https:\/\/arxiv.org\/abs\/2106.09685. (2021)"},{"key":"12_CR13","doi-asserted-by":"publisher","first-page":"7969","DOI":"10.18653\/v1\/2023.emnlp-main.495","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","author":"Z Jiang","year":"2023","unstructured":"Jiang, Z., et al.: Active retrieval augmented generation. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 7969\u20137992 (2023)"},{"key":"12_CR14","first-page":"2567","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing","author":"Q Jin","year":"2019","unstructured":"Jin, Q., Dhingra, B., Liu, Z., et al.: PubMedQA: a dataset for biomedical research question answering. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, pp. 2567\u20132577 (2019). https:\/\/arxiv.org\/abs\/1909.06146"},{"key":"12_CR15","unstructured":"Khandelwal, U., Levy, O., Jurafsky, D., Zettlemoyer, L., Lewis, M.: Generalization through memorization: nearest neighbor language models. arXiv preprint https:\/\/arxiv.org\/abs\/1911.00172. (2019)"},{"key":"12_CR16","unstructured":"Krizhevsky, A.: Learning multiple layers of features from tiny images. Tech. rep., University of Toronto (2009). https:\/\/www.cs.toronto.edu\/kriz\/learning-features2009-TR.pdf"},{"issue":"1","key":"12_CR17","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1214\/aoms\/1177729694","volume":"22","author":"S Kullback","year":"1951","unstructured":"Kullback, S., Leibler, R.A.: On information and sufficiency. Ann. Math. Stat. 22(1), 79\u201386 (1951)","journal-title":"Ann. Math. Stat."},{"key":"12_CR18","first-page":"1927419286","volume-title":"International Conference on Machine Learning","author":"Y Leviathan","year":"2023","unstructured":"Leviathan, Y., Kalman, M., Matias, Y.: Fast inference from transformers via speculative decoding. In: International Conference on Machine Learning, p. 1927419286 (2023). https:\/\/arxiv.org\/abs\/2211.17192"},{"key":"12_CR19","first-page":"9459","volume-title":"Advances in Neural Information Processing Systems","author":"P Lewis","year":"2020","unstructured":"Lewis, P., Perez, E., Piktus, A., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Advances in Neural Information Processing Systems, vol. 33, pp. 9459\u20139474 (2020). https:\/\/arxiv.org\/abs\/2005.11401"},{"key":"12_CR20","first-page":"4582","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics","author":"XL Li","year":"2021","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics, pp. 4582\u20134597 (2021). https:\/\/arxiv.org\/abs\/2101.00190"},{"key":"12_CR21","first-page":"13110","volume-title":"Advances in Neural Information Processing Systems","author":"Z Lin","year":"2023","unstructured":"Lin, Z., et al.: ResMem: learn what you can and memorize the rest. In: Advances in Neural Information Processing Systems, vol. 36, pp. 13110\u201313123 (2023)"},{"key":"12_CR22","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","author":"X Liu","year":"2022","unstructured":"Liu, X., Ji, K., Fu, Y., et al.: P-tuning v2: prompt tuning can be comparable to fine-tuning universally across scales and tasks. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (2022). https:\/\/arxiv.org\/abs\/2110.07602"},{"key":"12_CR23","volume-title":"Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","author":"Y Lu","year":"2025","unstructured":"Lu, Y., et al.: Dynamic uncertainty ranking: enhancing retrieval-augmented in-context learning for long-tail knowledge in LLMs. In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). NAACL (2025)"},{"key":"12_CR24","volume-title":"International Conference on Learning Representations","author":"AK Menon","year":"2021","unstructured":"Menon, A.K., Jayasumana, S., Rawat, A.S., et al.: Long-tail learning via logit adjustment. In: International Conference on Learning Representations (2021). https:\/\/arxiv.org\/abs\/2007.07314"},{"issue":"6","key":"12_CR25","first-page":"1","volume":"16","author":"F Wang","year":"2025","unstructured":"Wang, F., et al.: A comprehensive survey of small language models in the era of large language models: techniques, enhancements, applications, collaboration with LLMs, and trustworthiness. ACM Trans. Intell. Syst. Technol. 16(6), 1\u201387 (2025)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"issue":"6","key":"12_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1","volume":"18","author":"L Wang","year":"2024","unstructured":"Wang, L., et al.: A survey on large language model based autonomous agents. Front. Comp. Sci. 18(6), 186345 (2024)","journal-title":"Front. Comp. Sci."},{"key":"12_CR27","unstructured":"Wang, P., Bai, S., Tan, S., et al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint https:\/\/arxiv.org\/abs\/2409.12191. (2024)"},{"key":"12_CR28","unstructured":"Xu, X., et al.: A survey on knowledge distillation of large language models. arXiv preprint https:\/\/arxiv.org\/abs\/2402.13116. (2024)"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Yan, S.Q., Gu, J.C., Zhu, Y., Ling, Z.H.: Corrective retrieval augmented generation. arXiv preprint https:\/\/arxiv.org\/abs\/2401.15884. (2024)","DOI":"10.2139\/ssrn.5267341"},{"key":"12_CR30","unstructured":"Yang, A., Yang, B., Zhang, B., et al.: Qwen2.5 technical report. arXiv preprint https:\/\/arxiv.org\/abs\/2412.15115. (2024)"},{"key":"12_CR31","first-page":"10795","volume-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., et al.: Deep long-tailed learning: a survey. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, pp. 10795\u201310816 (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\/978-981-92-3410-3_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:10:03Z","timestamp":1784405403000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3410-3_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"ISBN":["9789819234097","9789819234103"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3410-3_12","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"}}]}}