{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T10:54:09Z","timestamp":1775645649582,"version":"3.50.1"},"reference-count":32,"publisher":"Association for Computing Machinery (ACM)","issue":"5","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62350610270, 62374034, 62235009, 62141407 and 61929102"],"award-info":[{"award-number":["62350610270, 62374034, 62235009, 62141407 and 61929102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The Innovation Program of Shanghai Municipal Education Commission","award":["2021-01-07-00-07-E00077"],"award-info":[{"award-number":["2021-01-07-00-07-E00077"]}]},{"name":"Natural Science Foundation of Shanghai","award":["24JD1401000, 24JD1400600, 25TS1410200 and 25DP1501800"],"award-info":[{"award-number":["24JD1401000, 24JD1400600, 25TS1410200 and 25DP1501800"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2026,9,30]]},"abstract":"<jats:p>As semiconductor technology node advances, the number of parameters in the modern device compact model increases drastically. Manual extraction of these model parameters becomes not only tedious but also impossible, and the automatic method is strongly desired. Traditional black-box optimization suffers from poor scalability due to the curse of dimensionality, while deep learning\u2013based methods typically require large amounts of training data. To address these challenges, we propose CDRPE: a combined deep learning and self-attention enhanced reinforcement learning framework for automatically extracting a large set of DCM parameters across multiple electrical characteristics. The framework leverages a pre-trained multilayer perceptron to initialize core parameters, incorporates device physics knowledge to guide the search, and employs a self-attention\u2013enhanced RL agent for efficient exploration in high-dimensional parameter spaces. Experimental results on BSIM4, BSIMSOI, and BSIMCMG demonstrate that CDRPE can automatically extract 100 parameters with root-mean-square error below 5% relative to TCAD and silicon data. Compared with existing methods, the proposed framework achieves a 7.7x speed up. Moreover, the generated models show good convergence in both digital and analog circuit simulations, exhibiting the potential of this framework for future practical applications.<\/jats:p>","DOI":"10.1145\/3795797","type":"journal-article","created":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T21:05:31Z","timestamp":1770239131000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CDRPE: A Combined Deep Learning and Self-Attention Enhanced Reinforcement Learning Framework for Automated Compact Model Parameter Extraction"],"prefix":"10.1145","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4708-7000","authenticated-orcid":false,"given":"Gongteng","family":"Xiao","sequence":"first","affiliation":[{"name":"Fudan University State Key Lab. of Integrated Chips and Systems","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0739-1326","authenticated-orcid":false,"given":"Jing","family":"Leng","sequence":"additional","affiliation":[{"name":"Fudan University State Key Lab. of Integrated Chips and Systems","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5748-4333","authenticated-orcid":false,"given":"Yijia","family":"Shao","sequence":"additional","affiliation":[{"name":"Fudan University State Key Lab. of Integrated Chips and Systems","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4552-883X","authenticated-orcid":false,"given":"Zhenhua","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7376-2132","authenticated-orcid":false,"given":"Shisheng","family":"Xiong","sequence":"additional","affiliation":[{"name":"Fudan University","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7315-3150","authenticated-orcid":false,"given":"Zhaori","family":"Bi","sequence":"additional","affiliation":[{"name":"Fudan University State Key Lab. of Integrated Chips and Systems","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8097-4053","authenticated-orcid":false,"given":"Xuan","family":"Zeng","sequence":"additional","affiliation":[{"name":"Microelectronics, Fudan University State Key Lab. of Integrated Chips and Systems","place":["Shanghai, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9054-2644","authenticated-orcid":false,"given":"Ye","family":"Lu","sequence":"additional","affiliation":[{"name":"Fudan University State Key Lab. of Integrated Chips and Systems","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"key":"e_1_3_2_2_2","volume-title":"MOSFET Models for VLSI Circuit Simulation: Theory and Practice","author":"Arora N.","year":"2021","unstructured":"N. Arora. 2021. MOSFET Models for VLSI Circuit Simulation: Theory and Practice. Springer."},{"issue":"9","key":"e_1_3_2_3_2","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1109\/55.863106","article-title":"Analytic description of short-channel effects in fully-depleted double-gate and cylindrical, surrounding-gate MOSFETs","volume":"21","author":"Oh S.","year":"2000","unstructured":"S. Oh, D. Monroe, and J. M. Hergenrother. 2000. Analytic description of short-channel effects in fully-depleted double-gate and cylindrical, surrounding-gate MOSFETs. In IEEE Electron Device Letters 21, 9 (2000), 445\u2013447.","journal-title":"In IEEE Electron Device Letters"},{"key":"e_1_3_2_4_2","unstructured":"BSIM-SOI 4.6.1. 2017. Available: Retrieved from https:\/\/www.bsim.berkeley.edu\/models\/bsimsoi\/"},{"key":"e_1_3_2_5_2","unstructured":"BSIM-CMG 111.1.0. 2021. Available: Retrieved from https:\/\/bsim.berkeley.edu\/models\/bsimcmg\/"},{"key":"e_1_3_2_6_2","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1109\/SCED.2007.383996","volume-title":"Proceedings of the 2007 Spanish Conference on Electron Devices","author":"Moreno P.","year":"2007","unstructured":"P. Moreno, R. Picos, M. Roca, E. Garcia-Moreno, B. Iniguez, and M. Estrada. 2007. Parameter extraction method using genetic algorithms for an improved OTFT compact model. In Proceedings of the 2007 Spanish Conference on Electron Devices, Madrid, Spain, 64\u201367."},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1109\/ICMTS.2009.4814627","volume-title":"Proceedings of the 2009 IEEE International Conference on Microelectronic Test Structures","author":"Zhou Q.","year":"2009","unstructured":"Q. Zhou, W. Yao, W. Wu, X. Li, Z. Zhu, and G. Gildenblat. 2009. Parameter extraction for the PSP MOSFET model by the combination of genetic and Levenberg-Marquardt algorithms. In Proceedings of the 2009 IEEE International Conference on Microelectronic Test Structures. 137\u2013142."},{"key":"e_1_3_2_8_2","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.1109\/ECCE.2012.6342392","volume-title":"Proceedings of the 2012 IEEE Energy Conversion Congress and Exposition","author":"Chen Z.","year":"2012","unstructured":"Z. Chen and R. Lindeman. 2012. A modified MODPEX model for MOSFET and parameter optimization using excel-based genetic algorithm. In Proceedings of the 2012 IEEE Energy Conversion Congress and Exposition. 2616\u20132622."},{"key":"e_1_3_2_9_2","first-page":"1","volume-title":"Proceedings of the 2017 21st European Microelectronics and Packaging Conference and Exhibition","author":"Bisewski D.","year":"2017","unstructured":"D. Bisewski. 2017. Parameters estimation of SPICE models for silicon carbide devices. In Proceedings of the 2017 21st European Microelectronics and Packaging Conference and Exhibition. 1\u20135."},{"key":"e_1_3_2_10_2","first-page":"264","volume-title":"Proceedings of the 2018 IEEE 3rd International Conference on Integrated Circuits and Microsystems","author":"Cao Y.","year":"2018","unstructured":"Y. Cao, W. Zhang, J. Fu, N. Liu, Q. Wang, and L. Liu. 2018. Application of the genetic algorithm in MOSFET modeling and parameter extraction. In Proceedings of the 2018 IEEE 3rd International Conference on Integrated Circuits and Microsystems. 264\u2013267."},{"key":"e_1_3_2_11_2","first-page":"1","volume-title":"Proceedings of the 2021 28th IEEE International Conference on Electronics, Circuits, and Systems","author":"Alia G.","year":"2021","unstructured":"G. Alia, A. Buzo, H. Maier-Flaig, K. W. Pieper, L. Maurer and G. Pelz. 2021. Machine learning-based acceleration of genetic algorithms for parameter extraction of highly dimensional MOSFET compact models. In Proceedings of the 2021 28th IEEE International Conference on Electronics, Circuits, and Systems. Dubai, United Arab Emirates. 1\u20134."},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1109\/CAS52836.2021.9604125","volume-title":"Proceedings of the 2021 International Semiconductor Conference","author":"Huppmann M.","year":"2021","unstructured":"M. Huppmann, K. -W. Pieper, A. Buzo, L. Maurer, and G. Pelz. 2021. Utilizing differential evolution for an automated compact model parameter extraction. In Proceedings of the 2021 International Semiconductor Conference. 231\u2013234."},{"key":"e_1_3_2_13_2","first-page":"1","volume-title":"Proceedings of the 2023 IEEE Computer Society Annual Symposium on VLSI","author":"Bhat S.","year":"2023","unstructured":"S. Bhat, S. Kulkarni and C. A. Moritz. 2023. Compact model parameter extraction using bayesian machine learning. In Proceedings of the 2023 IEEE Computer Society Annual Symposium on VLSI. 1\u20136."},{"key":"e_1_3_2_14_2","first-page":"130","volume-title":"Proceedings of the 2007 International Workshop on Physics of Semiconductor Devices","author":"Thakker R. A.","unstructured":"R. A. Thakker, N. Gandhi, M. B. Patil, and K. G. Anil. Parameter extraction for PSP MOSFET model using particle swarm optimization. In Proceedings of the 2007 International Workshop on Physics of Semiconductor Devices. 130\u2013133."},{"key":"e_1_3_2_15_2","first-page":"1","volume-title":"Proceedings of the 2011 International Semiconductor Device Research Symposium","author":"Zheng X.","year":"2011","unstructured":"X. Zheng, G. Zhang and K. Chen. 2011. A parameter extraction method based on particle swarm optimization. In Proceedings of the 2011 International Semiconductor Device Research Symposium. 1\u20132."},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3453198"},{"key":"e_1_3_2_17_2","first-page":"20","volume-title":"Proceedings of the 2023 IEEE International Symposium on Radio-Frequency Integration Technology","author":"Chavez F.","year":"2023","unstructured":"F. Chavez, J. H. Chen, C. T. Tung, C. Hu, and S. Khandelwal. 2023. I-V global parameter extraction for industry standard FinFET compact model using deep learning. In Proceedings of the 2023 IEEE International Symposium on Radio-Frequency Integration Technology. 20\u201322."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2022.3181536"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2023.3278615"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2024.3381917"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/LED.2022.3197800"},{"key":"e_1_3_2_22_2","first-page":"1","volume-title":"Proceedings of the 2020 5th IEEE International Conference on Emerging Electronics","author":"Dutta A.","year":"2020","unstructured":"A. Dutta, D. Rajasekharan, and Y. S. Chauhan. 2020. Compact model parameter extraction using modular Q learning for Nano-Scale transistors. In Proceedings of the 2020 5th IEEE International Conference on Emerging Electronics. 1\u20134."},{"key":"e_1_3_2_23_2","first-page":"1","volume-title":"Proceedings of the 2024 Panhellenic Conference on Electronics and Telecommunications","author":"Papageorgiou E.","year":"2024","unstructured":"E. Papageorgiou, G. Alia, A. Buzo, G. Pelz, and T. Noulis. 2024. MOSFET model parameter extraction using reinforcement learning. In Proceedings of the 2024 Panhellenic Conference on Electronics and Telecommunications. 1\u20135."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"e_1_3_2_25_2","first-page":"83","volume-title":"Proceedings of the 2023 3rd International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics","author":"Mueangprasert M.","year":"2023","unstructured":"M. Mueangprasert, P. Chermprayong, and K. Boonlong. 2023. Robot arm movement control by model-based reinforcement learning using machine learning regression techniques and particle swarm optimiza-tion. In Proceedings of the 2023 3rd International Symposium on Instrumentation, Control, Artificial Intelligence, and Robotics. 83\u201386."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"e_1_3_2_27_2","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, \u0141. Kaiser, and I. Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems (NeurIPS) 30 (2017), 5998\u20136008.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_2_28_2","unstructured":"S. Kucherenko D. Albrecht and A. Saltelli. Exploring multi-dimensional spaces: A comparison of latin hypercube and quasi monte carlo sampling techniques. arXiv:1505.02350. Retrieved from https:\/\/arxiv.org\/abs\/1505.02350"},{"key":"e_1_3_2_29_2","unstructured":"J. Schulman F. Wolski P. Dhariwal A. Radford and O. Klimov. 2017. Proximal policy optimization algorithms. arXiv:1707.06347. Retrieved from https:\/\/arxiv.org\/abs\/1707.06347"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3398554"},{"key":"e_1_3_2_31_2","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1109\/DAC18074.2021.9586189","volume-title":"Proceedings of the 2021 58th ACM\/IEEE Design Automation Conference","author":"Somayaji N. S. K.","year":"2021","unstructured":"N. S. K. Somayaji, H. Hu, and P. Li. 2021. Prioritized reinforcement learning for analog circuit optimization with design knowledge. In Proceedings of the 2021 58th ACM\/IEEE Design Automation Conference. 1231\u20131236."},{"key":"e_1_3_2_32_2","first-page":"907","volume-title":"Proceedings of the IEEE Transactions on Electron Devices","author":"Huo Q.","year":"2020","unstructured":"Q. Huo, Z. Wu, X. Wang, W. Huang, J. Yao, J. Bu, F. Zhang, L. Li, and M. Liu. 2020. Physics-Based device-circuit Co-optimization scheme for 7-nm technology node SRAM design and beyond. In Proceedings of the IEEE Transactions on Electron Devices. 907-914."},{"key":"e_1_3_2_33_2","first-page":"5.1","volume-title":"Proceedings of the 2017 IEEE International Electron Devices Meeting","volume":"29","author":"Narasimha S.","year":"2017","unstructured":"S. Narasimha et al. 2017. A 7nm CMOS technology platform for mobile and high performance compute application. In Proceedings of the 2017 IEEE International Electron Devices Meeting. 29, 5.1\u201329.5.4."}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3795797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T10:05:30Z","timestamp":1775642730000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3795797"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,8]]},"references-count":32,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,30]]}},"alternative-id":["10.1145\/3795797"],"URL":"https:\/\/doi.org\/10.1145\/3795797","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,8]]},"assertion":[{"value":"2025-09-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}