{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T04:51:47Z","timestamp":1776315107194,"version":"3.50.1"},"reference-count":27,"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\/icme59968.2025.11210235","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Elastic Architecture Search for Efficient Language Models"],"prefix":"10.1109","author":[{"given":"Shang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref2","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"issue":"8","key":"ref3","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref4","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"ref6","first-page":"33716","article-title":"Knowledge distillation from a stronger teacher","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Huang","year":"2022"},{"key":"ref7","article-title":"Well-read students learn better: On the importance of pre-training compact models","author":"Turc","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref9","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref11","first-page":"5776","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/341"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467262"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.123"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21311"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref17","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"International conference on machine learning","author":"Kornblith"},{"key":"ref18","first-page":"15394","article-title":"Pkd: General distillation framework for object detectors via pearson correlation coefficient","volume":"35","author":"Cao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref21","article-title":"SlimPajama: A 627B token cleaned and deduplicated version of RedPajama","author":"Soboleva","year":"2023"},{"key":"ref22","article-title":"Free dolly: Introducing the world\u2019s first truly open instruction-tuned llm","author":"Conover","year":"2023"},{"key":"ref23","article-title":"Minillm: Knowledge distillation of large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref25","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.806"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11210235.pdf?arnumber=11210235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:51Z","timestamp":1761888831000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210235\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210235","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}