{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T04:11:33Z","timestamp":1779250293976,"version":"3.51.4"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tcad.2024.3438995","type":"journal-article","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T18:40:50Z","timestamp":1730918450000},"page":"3626-3637","source":"Crossref","is-referenced-by-count":9,"title":["EASTER: Learning to Split Transformers at the Edge Robustly"],"prefix":"10.1109","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4540-9013","authenticated-orcid":false,"given":"Xiaotian","family":"Guo","sequence":"first","affiliation":[{"name":"Informatics Institute, University of Amsterdam, Amsterdam, XH, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2197-7791","authenticated-orcid":false,"given":"Quan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Computer Science and Technology Department, Nanjing Agricultural University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8447-872X","authenticated-orcid":false,"given":"Yixian","family":"Shen","sequence":"additional","affiliation":[{"name":"Informatics Institute, University of Amsterdam, Amsterdam, XH, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2043-4469","authenticated-orcid":false,"given":"Andy D.","family":"Pimentel","sequence":"additional","affiliation":[{"name":"Informatics Institute, University of Amsterdam, Amsterdam, XH, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6006-9366","authenticated-orcid":false,"given":"Todor","family":"Stefanov","sequence":"additional","affiliation":[{"name":"Leiden Institute of Advanced Computer Science, Leiden University, Leiden, CA, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A comprehensive survey of AI-generated content (AIGC): A history of generative AI from GAN to ChatGPT","author":"Cao","year":"2023","journal-title":"arXiv:2303.04226"},{"key":"ref2","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s42488-020-00027-x"},{"key":"ref4","first-page":"1","article-title":"Judging LLM-as-a-judge with MT-bench and Chatbot arena","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref5","article-title":"AWQ: Activation-aware weight Quantization for LLM compression and acceleration","author":"Lin","year":"2023","journal-title":"arXiv:2306.00978"},{"key":"ref6","article-title":"A survey on model compression for large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2308.07633"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-021-00712-3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3318216.3363312"},{"key":"ref9","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"key":"ref10","first-page":"663","article-title":"AlpaServe: Statistical multiplexing with model parallelism for deep learning serving","volume-title":"Proc. OSDI","author":"Li"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"issue":"8","key":"ref14","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA58977.2023.00104"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.627"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01565"},{"key":"ref18","first-page":"1","article-title":"Nasvit: Neural architecture search for efficient vision transformers with gradient conflict aware supernet training","volume-title":"Proc. ICLR","author":"Gong"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3212767"},{"key":"ref20","first-page":"1","article-title":"Nat: Neural architecture transformer for accurate and compact architectures","volume-title":"Proc. NeurIPS","author":"Guo"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582049"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-6034-7_6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2016.10.006"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/DSD57027.2022.00048"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3237572"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3322474"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3573037"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13188"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"ref30","first-page":"1","article-title":"LLM-pruner: On the structural pruning of large language models","volume-title":"Proc. NIPS","author":"Ma"},{"key":"ref31","first-page":"10524","article-title":"On layer normalization in the transformer architecture","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiong"},{"key":"ref32","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. OSDI 18","author":"Chen"},{"key":"ref33","article-title":"IREE: An MLIR-based compiler and runtime for ML models from multiple frameworks.","author":"Ben","year":"2019"},{"key":"ref34","article-title":"Huggingface\u2019s transformers: State-of-the-art natural language processing","author":"Wolf","year":"2019","journal-title":"arXiv:1910.03771"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"ref36","first-page":"638","article-title":"Torch. FX: Practical program capture and transformation for deep learning in python","volume-title":"Proc. Mach. Learn. Syst.","author":"Reed"},{"key":"ref37","article-title":"NCNN.","author":"Tencent","year":"2017"},{"key":"ref38","first-page":"583","article-title":"Design and implementation of heartbeat in multi-machine environment","volume-title":"Proc. AINA\u201917","author":"Hou"},{"key":"ref39","volume-title":"A Framework for Few-Shot Language Model Evaluation","author":"Gao","year":"2023"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/10745760\/10745835.pdf?arnumber=10745835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T13:58:15Z","timestamp":1732715895000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10745835\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":39,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2024.3438995","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}