{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T13:20:36Z","timestamp":1793107236391,"version":"4.5.0"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62436007"],"award-info":[{"award-number":["62436007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62325602"],"award-info":[{"award-number":["62325602"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036010"],"award-info":[{"award-number":["62036010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62506342"],"award-info":[{"award-number":["62506342"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.neunet.2025.108276","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:30:31Z","timestamp":1762302631000},"page":"108276","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":6,"special_numbering":"C","title":["Improving large models with small models: Lower costs and better performance"],"prefix":"10.1016","volume":"195","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4859-1757","authenticated-orcid":false,"given":"Dong","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5168-8011","authenticated-orcid":false,"given":"Fei","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3143-0474","authenticated-orcid":false,"given":"Shuo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9017-2508","authenticated-orcid":false,"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7356-9711","authenticated-orcid":false,"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1154-2927","authenticated-orcid":false,"given":"Qidong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0017-3936","authenticated-orcid":false,"given":"Hua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8046-722X","authenticated-orcid":false,"given":"Xin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6885-3451","authenticated-orcid":false,"given":"Mingliang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.108276_bib0001","series-title":"The twelfth international conference on learning representations","article-title":"On-policy distillation of language models: Learning from self-generated mistakes","author":"Agarwal","year":"2024"},{"key":"10.1016\/j.neunet.2025.108276_bib0002","first-page":"23","article-title":"Flamingo: A visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108276_bib0003","series-title":"Role of chat gpt in education","first-page":"01","volume":"1","author":"Biswas","year":"2023"},{"key":"10.1016\/j.neunet.2025.108276_bib0004","unstructured":"Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., & Brunskill, E. (2021). On the opportunities and risks of foundation models. arXiv: 2108.07258."},{"key":"10.1016\/j.neunet.2025.108276_bib0005","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108276_bib0006","unstructured":"Chen, D., Hu, Z., Fan, P., Zhuang, Y., Yafei, L., Liu, Q., Jiang, X., & Xu, M. (2025). KKA: Improving vision anomaly detection through anomaly-related knowledge from large language models. arXiv: 2502.14880."},{"key":"10.1016\/j.neunet.2025.108276_bib0007","doi-asserted-by":"crossref","unstructured":"Chen, D., Zhang, S., Gao, F., Zhuang, Y., Siliang, T., Liu, Q., & Xu, M. (2024a). Logic Distillation: Learning from Code Function by Function for Decision-making Tasks. Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 7338\u20137346.","DOI":"10.24963\/ijcai.2024\/816"},{"key":"10.1016\/j.neunet.2025.108276_bib0008","first-page":"257","article-title":"Data shunt: Collaboration of small and large models for lower costs and better performance","volume":"38","author":"Chen","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.1016\/j.neunet.2025.108276_bib0009","unstructured":"Chen, L., Zaharia, M., & Zou, J. (2023). FrugalGPT: How to use large language models while reducing cost and improving performance. arXiv: 2305.05176."},{"key":"10.1016\/j.neunet.2025.108276_bib0010","unstructured":"Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., & Gehrmann, S. (2022). PALM: Scaling language modeling with pathways. arXiv: 2204.02311."},{"key":"10.1016\/j.neunet.2025.108276_bib0011","unstructured":"Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K., (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv: 1810.04805."},{"issue":"4","key":"10.1016\/j.neunet.2025.108276_bib0012","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/S1364-6613(99)01294-2","article-title":"Catastrophic forgetting in connectionist networks","volume":"3","author":"French","year":"1999","journal-title":"Trends in cognitive sciences"},{"key":"10.1016\/j.neunet.2025.108276_bib0013","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"7346","article-title":"WorldGPT: Empowering llm as multimodal world model","author":"Ge","year":"2024"},{"key":"10.1016\/j.neunet.2025.108276_bib0014","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: A survey","volume":"129","author":"Gou","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2025.108276_bib0015","series-title":"The twelfth international conference on learning representations","article-title":"Knowledge distillation of large language models","author":"Gu","year":"2024"},{"key":"10.1016\/j.neunet.2025.108276_bib0016","series-title":"Proceedings of the ieee conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2025.108276_bib0017","series-title":"Proceedings of the 25th international conference on world wide web","first-page":"507","article-title":"Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2025.108276_bib0018","series-title":"2007 IEEE International conference on acoustics, speech and signal processing-ICASSP\u201907","article-title":"Approximating the kullback leibler divergence between gaussian mixture models","volume":"4","author":"Hershey","year":"2007"},{"key":"10.1016\/j.neunet.2025.108276_bib0019","doi-asserted-by":"crossref","unstructured":"Hoffmann, J., Borgeaud, S., Mensch, A., Buchatskaya, E., Cai, T., Rutherford, E., Casas, D. D. L., Hendricks, L. A., Welbl, J., & Clark, A. (2022). Training compute-optimal large language models. arXiv: 2203.15556.","DOI":"10.52202\/068431-2176"},{"issue":"8","key":"10.1016\/j.neunet.2025.108276_bib0020","doi-asserted-by":"crossref","first-page":"1563","DOI":"10.1162\/neco_a_01296","article-title":"On a scalable entropic breaching of the overfitting barrier for small data problems in machine learning","volume":"32","author":"Horenko","year":"2020","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2025.108276_bib0021","series-title":"International conference on learning representations","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"10.1016\/j.neunet.2025.108276_bib0022","unstructured":"Kim, Y. (2014). Convolutional neural networks for sentence classification. arXiv: 1408.5882."},{"key":"10.1016\/j.neunet.2025.108276_bib0023","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2019). AlBERT: A lite BERT for self-supervised learning of language representations. arXiv: 1909.11942."},{"key":"10.1016\/j.neunet.2025.108276_bib0024","doi-asserted-by":"crossref","unstructured":"Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019). Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv: 1910.13461.","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"10.1016\/j.neunet.2025.108276_bib0025","series-title":"Proceedings of the ieee\/cvf conference on computer vision and pattern recognition","first-page":"6970","article-title":"Trustworthy long-tailed classification","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2025.108276_bib0026","doi-asserted-by":"crossref","unstructured":"Li, J., Gao, M., Wei, L., Tang, S., Zhang, W., Li, M., Ji, W., Tian, Q., Chua, T.-S., & Zhuang, Y. (2023a). Gradient-regulated meta-prompt learning for generalizable vision-language models. IEEE\/CVF International Conference on Computer Vision (ICCV), 2551\u20132562.","DOI":"10.1109\/ICCV51070.2023.00241"},{"key":"10.1016\/j.neunet.2025.108276_bib0027","first-page":"7290","article-title":"Fine-grained semantically aligned vision-language pre-training","volume":"35","author":"Li","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108276_bib0028","unstructured":"Li, J., Li, D., Savarese, S., & Hoi, S. (2023b). BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv: 2301.12597."},{"key":"10.1016\/j.neunet.2025.108276_bib0029","unstructured":"Li, J., Pan, K., Ge, Z., Gao, M., Zhang, H., Ji, W., Zhang, W., Chua, T.-S., Tang, S., & Zhuang, Y. (2023c). Fine-tuning multimodal LLMs to follow zero-shot demonstrative instructions. arXiv: 2308.04152."},{"key":"10.1016\/j.neunet.2025.108276_bib0030","series-title":"Computer vision-ECCV 2014: 13th european conference","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"issue":"9","key":"10.1016\/j.neunet.2025.108276_bib0031","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu","year":"2023","journal-title":"ACM Computing Surveys"},{"issue":"1","key":"10.1016\/j.neunet.2025.108276_bib0032","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1038\/s41524-025-01564-y","article-title":"Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities","volume":"11","author":"Lu","year":"2025","journal-title":"Computational Materials"},{"key":"10.1016\/j.neunet.2025.108276_bib0033","doi-asserted-by":"crossref","unstructured":"Lv, Z., Zhan, T., Wang, W., Lin, X., Zhang, S., Zhang, W., Li, J., Kuang, K., & Wu, F. (2025). Collaboration of large language models and small recommendation models for device-cloud recommendation. arXiv: 2501.05647.","DOI":"10.1145\/3690624.3709335"},{"key":"10.1016\/j.neunet.2025.108276_bib0034","series-title":"Proceedings of the 38th international acm sigir conference on research and development in information retrieval","first-page":"43","article-title":"Image-based recommendations on styles and substitutes","author":"Mcauley","year":"2015"},{"key":"10.1016\/j.neunet.2025.108276_bib0035","unstructured":"Meta, A. (2024). Introducing meta LLAMA 3: The most capable openly available llm to date. Meta AI.Retrieved November 10, 2025, from https:\/\/ai.meta.com\/blog\/meta-llama-3\/."},{"key":"10.1016\/j.neunet.2025.108276_bib0036","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing","article-title":"What can we learn from collective human opinions on natural language inference data?","author":"Nie","year":"2020"},{"key":"10.1016\/j.neunet.2025.108276_bib0037","doi-asserted-by":"crossref","unstructured":"Oksuz, K., Cam, B. C., Kalkan, S., & Akbas, E. (2020). Imbalance problems in object detection: A review. IEEE transactions on pattern analysis and machine intelligence(vol. 43) 103388\u20133415.","DOI":"10.1109\/TPAMI.2020.2981890"},{"key":"10.1016\/j.neunet.2025.108276_bib0038","first-page":"27","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.108276_bib0039","series-title":"Proceedings of the ieee conference on computer vision and pattern recognition","first-page":"864","article-title":"Factors in finetuning deep model for object detection with long-tail distribution","author":"Ouyang","year":"2016"},{"key":"10.1016\/j.neunet.2025.108276_bib0040","series-title":"Proceedings of the 40th annual meeting of the association for computational linguistics","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.neunet.2025.108276_bib0041","unstructured":"Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019). DistilBERT, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv: 1910.01108."},{"key":"10.1016\/j.neunet.2025.108276_bib0042","unstructured":"Smith, S., Patwary, M., Norick, B., Legresley, P., Rajbhandari, S., Casper, J., Liu, Z., Prabhumoye, S., Zerveas, G., & Korthikanti, V. (2022). Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model. arXiv: 2201.11990."},{"issue":"1","key":"10.1016\/j.neunet.2025.108276_bib0043","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1109\/TPAMI.2022.3148210","article-title":"From show to tell: A survey on deep learning-based image captioning","volume":"45","author":"Stefanini","year":"2022","journal-title":"EEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"01","key":"10.1016\/j.neunet.2025.108276_bib0044","doi-asserted-by":"crossref","first-page":"17","DOI":"10.55529\/ijitc.31.17.22","article-title":"Use chat gpt to solve programming bugs","volume":"3","author":"Surameery","year":"2023","journal-title":"International Journal of Information Technology & Computer Engineering (IJITC)"},{"key":"10.1016\/j.neunet.2025.108276_bib0045","doi-asserted-by":"crossref","unstructured":"Wang, X., Liu, Y., Cheng, W., Zhao, X., Chen, Z., Yu, W., Fu, Y., & Chen, H. (2025). MixLLM: Dynamic routing in mixed large language models. arXiv: 2502.18482.","DOI":"10.32388\/NS4GU3"},{"key":"10.1016\/j.neunet.2025.108276_bib0046","series-title":"Proceedings of the 2016 conference on empirical methods in natural language processing","first-page":"606","article-title":"Attention-based LSTM for aspect-level sentiment classification","author":"Wang","year":"2016"},{"key":"10.1016\/j.neunet.2025.108276_bib0047","unstructured":"Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., & Metzler, D. (2022). Emergent abilities of large language models. arXiv: 2206.07682."},{"key":"10.1016\/j.neunet.2025.108276_bib0048","series-title":"International conference on machine learning","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"Xu","year":"2015"},{"key":"10.1016\/j.neunet.2025.108276_bib0049","doi-asserted-by":"crossref","first-page":"12113","DOI":"10.1109\/TPAMI.2023.3275156","article-title":"Multimodal learning with transformers: A survey","volume":"45","author":"Xu","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108276_bib0050","unstructured":"Xu, X., Li, M., Tao, C., Shen, T., Cheng, R., Li, J., Xu, C., Tao, D., & Zhou, T. (2024). A survey on knowledge distillation of large language models. arXiv: 2402.13116."},{"key":"10.1016\/j.neunet.2025.108276_bib0051","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"10.1016\/j.neunet.2025.108276_bib0052","doi-asserted-by":"crossref","unstructured":"Yu, Q., Li, J., Wei, L., Pang, L., Ye, W., Qin, B., Tang, S., Tian, Q., & Zhuang, Y. (2023). Hallucidoctor: Mitigating hallucinatory toxicity in visual instruction data. arXiv: 2311.13614.","DOI":"10.1109\/CVPR52733.2024.01230"},{"key":"10.1016\/j.neunet.2025.108276_bib0053","first-page":"3156","article-title":"X 2-VLM: All-in-one pre-trained model for vision-language tasks","volume":"46(5)","author":"Zeng","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108276_bib0054","doi-asserted-by":"crossref","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-language models for vision tasks: A survey","volume":"46(8)","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108276_bib0055","unstructured":"Zhang, S., Roller, S., Goyal, N., Artetxe, M., Chen, M., Chen, S., Dewan, C., Diab, M., Li, X., & Lin, X. V. (2022). OPT: Open pre-trained transformer language models. arXiv: 2205.01068."},{"key":"10.1016\/j.neunet.2025.108276_bib0056","series-title":"Proceedings of the ieee international conference on computer vision","first-page":"5409","article-title":"Range loss for deep face recognition with long-tailed training data","author":"Zhang","year":"2017"},{"key":"10.1016\/j.neunet.2025.108276_bib0057","first-page":"559","article-title":"Alpa: Automating inter-and {PLXIntra-Operator} parallelism for distributed deep learning","volume":"22","author":"Zheng","year":"2022","journal-title":"16th USENIX Symposium on Operating Systems Design and Implementation"},{"key":"10.1016\/j.neunet.2025.108276_bib0058","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.patcog.2018.03.003","article-title":"Deep super-class learning for long-tail distributed image classification","volume":"80","author":"Zhou","year":"2018","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.108276_bib0059","series-title":"Proceedings of the ieee\/cvf conference on computer vision and pattern recognition","first-page":"9516","article-title":"Visual prompt multi-modal tracking","author":"Zhu","year":"2023"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025011578?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025011578?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T04:37:39Z","timestamp":1773808659000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025011578"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":59,"alternative-id":["S0893608025011578"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108276","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Improving large models with small models: Lower costs and better performance","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108276","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108276"}}