{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:19:45Z","timestamp":1774365585271,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB1403400"],"award-info":[{"award-number":["2018YFB1403400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61834006"],"award-info":[{"award-number":["61834006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004921","name":"Wu Wen Jun Honorary Doctoral Scholarship, AI Institute, Shanghai Jiao Tong University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004921","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1109\/tcad.2022.3181541","type":"journal-article","created":{"date-parts":[[2022,6,8]],"date-time":"2022-06-08T19:33:50Z","timestamp":1654716830000},"page":"509-520","source":"Crossref","is-referenced-by-count":26,"title":["DTATrans: Leveraging Dynamic Token-Based Quantization With Accuracy Compensation Mechanism for Efficient Transformer Architecture"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8588-9483","authenticated-orcid":false,"given":"Tao","family":"Yang","sequence":"first","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Fei","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Xiaoling","family":"Li","sequence":"additional","affiliation":[{"name":"Inceptio Technology Institute, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8769-293X","authenticated-orcid":false,"given":"Fangxin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Yilong","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6357-236X","authenticated-orcid":false,"given":"Zhezhi","family":"He","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7353-8798","authenticated-orcid":false,"given":"Li","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"ref2","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguist. Human Lang. Technol.","author":"Devlin"},{"key":"ref3","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv:1907.11692"},{"key":"ref4","first-page":"1","article-title":"Language models are unsupervised multitask learners","volume-title":"Proc. OpenAI Blog","author":"Radford"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-5446"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref9","first-page":"1","article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and Huffman coding","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Han"},{"key":"ref10","first-page":"1","article-title":"Hardware-oriented approximation of convolutional neural networks","volume-title":"Proc. ICLR","author":"Gysel"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00215"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3467476"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6409"},{"key":"ref14","first-page":"1","article-title":"I-BERT: Integer-only BERT quantization","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00086"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322214"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref18","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"ref19","first-page":"1","article-title":"Improving language understanding by generative pre-training","volume-title":"Proc. OpenAI Blog","author":"Radford"},{"key":"ref20","article-title":"Language models are few-shot learners","volume-title":"Advances in Neural Information Processing Systems","author":"Brown","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/520"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080246"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586216"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"ref28","article-title":"Practical Bayesian optimization of machine learning algorithms","volume-title":"Advances in Neural Information Processing Systems","author":"Snoek","year":"2012"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3206.001.0001"},{"key":"ref31","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv:1609.07843"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref33","article-title":"CACTI 6.0: A Tool to model large caches","author":"Muralimanohar","year":"2009"},{"key":"ref34","article-title":"Q-ViT: Fully differentiable quantization for vision transformer","author":"Li","year":"2022","journal-title":"arXiv:2201.07703"},{"key":"ref35","article-title":"Post-training quantization for vision transformer","volume-title":"Advances in Neural Information Processing Systems","author":"Liu","year":"2021"},{"key":"ref36","article-title":"Are sixteen heads really better than one?","volume-title":"Advances in Neural Information Processing Systems","author":"Michel","year":"2019"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/43\/10021949\/09790868.pdf?arnumber=9790868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:25:22Z","timestamp":1706757922000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9790868\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":36,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2022.3181541","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]}}}