{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T06:45:56Z","timestamp":1785653156651,"version":"3.56.0"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032316653","type":"print"},{"value":"9783032316660","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"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\/978-3-032-31666-0_21","type":"book-chapter","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:46:00Z","timestamp":1785649560000},"page":"312-327","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Following the\u00a0Teacher\u2019s Footsteps: Scheduled Checkpoint Distillation for\u00a0Domain-Specific LLMs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3861-0042","authenticated-orcid":false,"given":"Cheng","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1697-6932","authenticated-orcid":false,"given":"Chaoliang","family":"Zhong","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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4264-8932","authenticated-orcid":false,"given":"Yusuke","family":"Oishi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"21_CR1","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"240","key":"21_CR2","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., et al.: PaLM: scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"21_CR3","unstructured":"Zhang, S., et al.: OPT: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"21_CR4","unstructured":"Zheng, L., et al.: ALPA: automating inter- and intra-operator parallelism for distributed deep learning. In: 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22), pp. 559\u2013578 (2022)"},{"key":"21_CR5","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: DDK: distilling domain knowledge for efficient large language models. Adv. Neural. Inf. Process. Syst. 37, 9827\u201398319 (2024)","DOI":"10.52202\/079017-3119"},{"key":"21_CR7","unstructured":"Kang, M., Jeong, J., Lee, S., Cho, J., Hwang, S.J.: Distilling LLM agent into small models with retrieval and code tools. arXiv preprint arXiv:2505.17612 (2025)"},{"key":"21_CR8","unstructured":"Gu, Y., Dong, L., Wei, F., Huang, M.: MiniLLM: knowledge distillation of large language models. arXiv preprint arXiv:2306.08543 (2023)"},{"key":"21_CR9","unstructured":"Lopez-Paz, D., Bottou, L., Sch\u00f6lkopf, B., Vapnik, V.: Unifying distillation and privileged information. arXiv preprint arXiv:1511.03643 (2015)"},{"key":"21_CR10","unstructured":"Panigrahi, A., Liu, B., Malladi, S., et al.: Progressive distillation induces an implicit curriculum. In: The Thirteenth International Conference on Learning Representations."},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Mirzadeh, S. I., Farajtabar, M., Li, A., Levine, N., Matsukawa, A., Ghasemzadeh, H.: Improved knowledge distillation via teacher assistant. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 5191\u20135198 (2020)","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"21_CR12","unstructured":"Harutyunyan, H., Rawat, A. S., Menon, A. K., Kim, S., Kumar, S.: Supervision complexity and its role in knowledge distillation. In: The Eleventh International Conference on Learning Representations"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Jafari, A., Rezagholizadeh, M., Sharma, P., Ghodsi, A.: Annealing knowledge distillation. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 2493\u20132504 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.212"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Shi, W., Song, Y., Zhou, H., Li, B., Li, L.: Follow your path: a progressive method for knowledge distillation. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 596\u2013611. Springer (2021)","DOI":"10.1007\/978-3-030-86523-8_36"},{"key":"21_CR15","unstructured":"DTO-KD: dynamic trade-off optimization for effective knowledge distillation. (2025). https:\/\/openreview.net\/forum?id=QMItTyQW92"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Li, P., Ping, C., Wang, W., Song, M.: Sample-level adaptive knowledge distillation for action recognition. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 544\u2013552 (2025)","DOI":"10.1145\/3746027.3755514"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Wen, Y., Li, Z., Du, W., Mou, L.: F-divergence minimization for sequence-level knowledge distillation. arXiv preprint arXiv:2307.15190 (2023)","DOI":"10.18653\/v1\/2023.acl-long.605"},{"key":"21_CR18","unstructured":"Shing, M., Misaki, K., Bao, H., et al.: TAID: Temporally adaptive interpolated distillation for efficient knowledge transfer in language models. arXiv preprint arXiv:2501.16937 (2025)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31666-0_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:46:03Z","timestamp":1785649563000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31666-0_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"ISBN":["9783032316653","9783032316660"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31666-0_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"3 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}