{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:27:58Z","timestamp":1763191678308,"version":"3.45.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11229274","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["ALM-KD: Adaptive Layer Mapping Knowledge Distillation for LLMs"],"prefix":"10.1109","author":[{"given":"Xu","family":"Baizhou","sequence":"first","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}]},{"given":"Yang","family":"Zhilin","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}]},{"given":"Niu","family":"Xin","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}]},{"given":"Zhang","family":"Zhaoning","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}]},{"given":"Huang","family":"Zheng","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}]},{"given":"Qiao","family":"Linbo","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}]},{"given":"Qi","family":"Yafei","sequence":"additional","affiliation":[{"name":"Central South University,College of Computer Science and Technology,Changsha,China"}]}],"member":"263","reference":[{"journal-title":"Language models are unsupervised multitask learners","year":"2019","author":"A","key":"ref1"},{"journal-title":"Improving language understanding by generative pre-training","year":"2018","author":"A","key":"ref2"},{"key":"ref3","article-title":"Sequence-aware knowledge distillation for a lightweight event representation","volume":"1","author":"Chen","year":"2023","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"ref4","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.569"},{"issue":"7","key":"ref6","first-page":"38","article-title":"Distilling the knowledge in a neural network","volume":"14","author":"Hinton","year":"2015","journal-title":"Computer Science"},{"article-title":"Dynabert: Dynamic BERT with adaptive width and depth","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020","author":"Hou","key":"ref7"},{"journal-title":"Like what you like: Knowledge distill via neuron selectivity transfer","year":"2017","author":"Huang","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref11","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Kenton"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/s23031483"},{"key":"ref13","article-title":"Improving knowledge distillation with a customized teacher","volume":"22902299","author":"Liu","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref14","first-page":"3143","article-title":"Does BERT rediscover a classical NLP pipeline?","author":"Niu","year":"2022","journal-title":"COLING"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17610"},{"article-title":"Fitnets: Hints for thin deep nets","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Romero","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"article-title":"Language models are few-shot learners","year":"2020","author":"T","key":"ref18"},{"key":"ref19","article-title":"Distilling task-specific knowledge from BERT into simple neural networks","author":"Tang","year":"2019","journal-title":"CoRR abs\/1903.12136"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3639372"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.485"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11229274.pdf?arnumber=11229274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:24:01Z","timestamp":1763191441000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11229274\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11229274","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}