{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:11:23Z","timestamp":1774631483954,"version":"3.50.1"},"reference-count":430,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62331009"],"award-info":[{"award-number":["62331009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62401642"],"award-info":[{"award-number":["62401642"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Provincial NSF","award":["BG2024004"],"award-info":[{"award-number":["BG2024004"]}]},{"name":"Jiangsu Provincial NSF","award":["BM2023016"],"award-info":[{"award-number":["BM2023016"]}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Emerg. Sel. Topics Circuits Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/jetcas.2025.3575272","type":"journal-article","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T17:42:40Z","timestamp":1749231760000},"page":"149-185","source":"Crossref","is-referenced-by-count":3,"title":["Generative AI Through CAS Lens: An Integrated Overview of Algorithmic Optimizations, Architectural Advances, and Automated Designs"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7736-6487","authenticated-orcid":false,"given":"Chuan","family":"Zhang","sequence":"first","affiliation":[{"name":"LEADS, the National Mobile Communications Research Laboratory, and the Frontiers Science Center for Mobile Information Communication and Security, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9584-733X","authenticated-orcid":false,"given":"You","family":"You","sequence":"additional","affiliation":[{"name":"LEADS, the National Mobile Communications Research Laboratory, and the Frontiers Science Center for Mobile Information Communication and Security, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7664-0061","authenticated-orcid":false,"given":"Naigang","family":"Wang","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3251-0024","authenticated-orcid":false,"given":"Jongsun","family":"Park","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4535-3200","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering, University of Leeds, Leeds, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123618"},{"issue":"21","key":"ref2","first-page":"495","article-title":"Nature\u2019s 10","volume":"624","author":"Kalahasti","year":"2023","journal-title":"Nature"},{"key":"ref3","article-title":"DeepSeek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv:2501.12948"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00894-021-04674-8"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.5753\/webmedia_estendido.2023.234354"},{"key":"ref6","article-title":"AI-native interconnect framework for integration of large language model technologies in 6G systems","author":"Tarkoma","year":"2023","journal-title":"arXiv:2311.05842"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18178\/jaai.2024.2.1.1-26"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.61969\/jai.1337500"},{"key":"ref9","article-title":"Generative AI is already widespread in the public sector","author":"Bright","year":"2024","journal-title":"arXiv:2401.01291"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5594\/JMI.2023.3297238"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW59549.2023.00082"},{"key":"ref12","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref13","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv:2312.11805"},{"key":"ref14","article-title":"Nemotron-4 340B technical report","volume-title":"arXiv:2406.11704","author":"Adler","year":"2024"},{"key":"ref15","article-title":"Qwen2.5 technical report","volume-title":"arXiv:2412.15115","author":"Yang","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.adh2586"},{"key":"ref17","article-title":"Learning to generate research idea with dynamic control","author":"Li","year":"2024","journal-title":"arXiv:2412.14626"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-023-00500-8"},{"key":"ref19","article-title":"Data analysis in the era of generative AI","author":"Priya Inala","year":"2024","journal-title":"arXiv:2409.18475"},{"key":"ref20","article-title":"Generative AI in writing research papers: A new type of algorithmic bias and uncertainty in scholarly work","author":"Jain","year":"2023","journal-title":"arXiv:2312.10057"},{"key":"ref21","volume-title":"Principles and Guidelines for Generative Artificial Intelligence (GenAI) in Teaching and Learning","author":"Columbia","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-024-01543-1"},{"key":"ref23","volume-title":"Guidelines for Students on the Use of Generative Artificial Intelligence","author":"Univ","year":"2025"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3317169"},{"key":"ref25","first-page":"338","article-title":"RM-STC: Row-merge dataflow inspired GPU sparse tensor core for energy-efficient sparse acceleration","volume-title":"Proc. 56th Annu. IEEE\/ACM Int. Symp. Microarchitecture","author":"Huang"},{"key":"ref26","first-page":"324","article-title":"Eureka: Efficient tensor cores for one-sided unstructured sparsity in DNN inference","volume-title":"Proc. 56th Annu. IEEE\/ACM Int. Symp. Microarchitecture","author":"Gondimalla"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/FPL64840.2024.00054"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS58744.2024.10558631"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530585"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.23919\/vlsitechnologyandcir57934.2023.10185403"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3213521"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2023.3282046"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3058217"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3626184.3639780"},{"key":"ref35","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","volume":"27","author":"Goodfellow"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref37","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref38","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv:2210.17323"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25433"},{"key":"ref40","first-page":"1","article-title":"BOOT: Data-free distillation of denoising diffusion models with bootstrapping","volume-title":"Proc. Mach. Learn. Res. (ICML)","author":"Gu"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3280805"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/sc41406.2024.00096"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00093"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00070"},{"key":"ref45","volume-title":"NVIDIA Ampere GA102 GPU Architecture Whitepaper","year":"2020"},{"key":"ref46","volume-title":"Unlocking On-device Generative AI With an NPU and Heterogeneous Computing","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/mi14050897"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CISS53076.2022.9751185"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.346"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3394053"},{"key":"ref51","article-title":"ChipNeMo: Domain-adapted LLMs for chip design","author":"Liu","year":"2023","journal-title":"arXiv:2311.00176"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3380446.3430634"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691698"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITSA60681.2024.10546365"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3570926"},{"key":"ref56","article-title":"CorrectBench: Automatic testbench generation with functional self-correction using LLMs for HDL design","author":"Qiu","year":"2024","journal-title":"arXiv:2411.08510"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS58744.2024.10558482"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10137086"},{"key":"ref59","article-title":"ChipGPT: How far are we from natural language hardware design","author":"Chang","year":"2023","journal-title":"arXiv:2305.14019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT56998.2023.10306417"},{"key":"ref61","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref62","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref63","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref64","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref65","article-title":"CodeGen: An open large language model for code with multi-turn program synthesis","author":"Nijkamp","year":"2022","journal-title":"arXiv:2203.13474"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29503"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26208"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30493"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01556"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28201"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3156949"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3306356"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3226689"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3069195"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i4.25557"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3126478"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v20i1.31875"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29423"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.183"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3495719"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28904"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28733"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30138"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00750"},{"key":"ref85","article-title":"OD-VAE: An omni-dimensional video compressor for improving latent video diffusion model","author":"Chen","year":"2024","journal-title":"arXiv:2409.01199"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645710"},{"key":"ref87","first-page":"545","article-title":"Accelerating the training of LLM using efficient activation rematerialization and optimal hybrid parallelism","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Yuan"},{"key":"ref88","article-title":"Stacking your transformers: A closer look at model growth for efficient LLM pre-training","author":"Du","year":"2024","journal-title":"arXiv:2405.15319"},{"key":"ref89","article-title":"MaskLLM: Learnable semi-structured sparsity for large language models","author":"Fang","year":"2024","journal-title":"arXiv:2409.17481"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00046"},{"key":"ref91","first-page":"579","article-title":"FwdLLM: Efficient federated finetuning of large language models with perturbed inferences","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Xu"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30160"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640383"},{"key":"ref94","article-title":"OceanGPT: A large language model for ocean science tasks","author":"Bi","year":"2023","journal-title":"arXiv:2310.02031"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.164"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref97","article-title":"DeepSeek LLM: Scaling open-source language models with longtermism","author":"Bi","year":"2024","journal-title":"arXiv:2401.02954"},{"key":"ref98","article-title":"DeepSeek-v2: A strong, economical, and efficient mixture-of-experts language model","author":"Liu","year":"2024","journal-title":"arXiv:2405.04434"},{"key":"ref99","article-title":"DeepSeek-V3 technical report","volume-title":"arXiv:2412.19437","author":"Liu","year":"2024"},{"key":"ref100","article-title":"DeepSeek-VL: Towards real-world vision-language understanding","author":"Lu","year":"2024","journal-title":"arXiv:2403.05525"},{"key":"ref101","article-title":"DeepSeek-VL2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv:2412.10302"},{"key":"ref102","article-title":"DeepSeek-coder: When the large language model meets programming {-} the rise of code intelligence","author":"Guo","year":"2024","journal-title":"arXiv:2401.14196"},{"key":"ref103","article-title":"DeepSeek-Coder-v2: Breaking the barrier of closed-source models in code intelligence","author":"Zhu","year":"2024","journal-title":"arXiv:2406.11931"},{"key":"ref104","article-title":"Diffusion model for data-driven black-box optimization","author":"Li","year":"2024","journal-title":"arXiv:2403.13219"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02098"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28736"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00735"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29470"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.114"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3357568"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.215"},{"key":"ref112","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref113","article-title":"Jetfire: Efficient and accurate transformer pretraining with INT8 data flow and per-block quantization","author":"Xi","year":"2024","journal-title":"arXiv:2403.12422"},{"key":"ref114","first-page":"10088","article-title":"QLoRA: Efficient finetuning of quantized LLMs","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","volume":"36","author":"Dettmers"},{"key":"ref115","first-page":"4396","article-title":"QuIP: 2-bit quantization of large language models with guarantees","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","volume":"36","author":"Chee"},{"key":"ref116","article-title":"BiDM: Pushing the limit of quantization for diffusion models","author":"Zheng","year":"2024","journal-title":"arXiv:2412.05926"},{"key":"ref117","first-page":"87","article-title":"AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration","volume-title":"Proc. Mach. Learn. Syst. (MLSys)","author":"Lin"},{"key":"ref118","article-title":"SqueezeLLM: Dense-and-sparse quantization","author":"Kim","year":"2023","journal-title":"arXiv:2306.07629"},{"key":"ref119","article-title":"Extreme compression of large language models via additive quantization","author":"Egiazarian","year":"2024","journal-title":"arXiv:2401.06118"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/tcad.2024.3488572"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00080"},{"key":"ref122","first-page":"1","article-title":"Compressing large language models by joint sparsification and quantization","volume-title":"Proc. Mach. Learn. Res. (ICML)","author":"Guo"},{"key":"ref123","first-page":"1","article-title":"Outlier-aware slicing for post-training quantization in vision transformer","volume-title":"Proc. Mach. Learn. Res. (ICML)","author":"Ma"},{"key":"ref124","article-title":"Accurate LoRA-finetuning quantization of LLMs via information retention","author":"Qin","year":"2024","journal-title":"arXiv:2402.05445"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.1"},{"key":"ref126","first-page":"1","article-title":"Efficient multi-task LLM quantization and serving for multiple LoRA adapters","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Xia"},{"key":"ref127","first-page":"21702","article-title":"LLM-pruner: On the structural pruning of large language models","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","author":"Ma"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28960"},{"key":"ref129","article-title":"EDGE-LLM: Enabling efficient large language model adaptation on edge devices via layerwise unified compression and adaptive layer tuning and voting","author":"Yu","year":"2024","journal-title":"arXiv:2406.15758"},{"key":"ref130","article-title":"Outlier weighed layerwise sparsity (OWL): A missing secret sauce for pruning LLMs to high sparsity","author":"Yin","year":"2023","journal-title":"arXiv:2310.05175"},{"key":"ref131","article-title":"DISP-LLM: Dimension-independent structural pruning for large language models","author":"Gao","year":"2024","journal-title":"arXiv:2410.11988"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071047"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00755"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.377"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29100"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28271"},{"key":"ref137","first-page":"31521","article-title":"MetricGAN-OKD: Multi-metric optimization of MetricGAN via online knowledge distillation for speech enhancement","volume-title":"Proc. Mach. Learn. Res. (ICML)","author":"Shin"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.272"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ISQED65160.2025.11014425"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.199"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.58"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01949"},{"key":"ref143","first-page":"18241","article-title":"Information-theoretic GAN compression with variational energy-based model","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","volume":"35","author":"Kang"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.128"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.791"},{"key":"ref146","article-title":"DistiLLM: Towards streamlined distillation for large language models","author":"Ko","year":"2024","journal-title":"arXiv:2402.03898"},{"key":"ref147","article-title":"Embodied CoT distillation from LLM to off-the-shelf agents","author":"Choi","year":"2024","journal-title":"arXiv:2412.11499"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.603"},{"key":"ref149","article-title":"Keypoint-based progressive chain-of-thought distillation for LLMs","author":"Feng","year":"2024","journal-title":"arXiv:2405.16064"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.766"},{"key":"ref151","first-page":"19274","article-title":"Fast inference from transformers via speculative decoding","volume-title":"Proc. Mach. Learn. Res. (ICML)","author":"Leviathan"},{"key":"ref152","article-title":"Accelerating large language model decoding with speculative sampling","author":"Chen","year":"2023","journal-title":"arXiv:2302.01318"},{"key":"ref153","first-page":"30222","article-title":"SpecTr: Fast speculative decoding via optimal transport","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","author":"Sun"},{"key":"ref154","first-page":"1","article-title":"Accelerated speculative sampling based on tree Monte Carlo","volume-title":"Proc. Mach. Learn. Res. (ICML)","author":"Hu"},{"key":"ref155","article-title":"SpecInfer: Accelerating generative large language model serving with tree-based speculative inference and verification","author":"Miao","year":"2023","journal-title":"arXiv:2305.09781"},{"key":"ref156","article-title":"Sequoia: Scalable, robust, and hardware-aware speculative decoding","author":"Chen","year":"2024","journal-title":"arXiv:2402.12374"},{"key":"ref157","first-page":"16342","article-title":"SpecExec: Massively parallel speculative decoding for interactive LLM inference on consumer devices","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","volume":"37","author":"Svirschevski"},{"key":"ref158","article-title":"Medusa: Simple LLM inference acceleration framework with multiple decoding heads","author":"Cai","year":"2024","journal-title":"arXiv:2401.10774"},{"key":"ref159","article-title":"EAGLE: Speculative sampling requires rethinking feature uncertainty","author":"Li","year":"2024","journal-title":"arXiv:2401.15077"},{"key":"ref160","article-title":"DistillSpec: Improving speculative decoding via knowledge distillation","author":"Zhou","year":"2023","journal-title":"arXiv:2310.08461"},{"key":"ref161","article-title":"Predictive pipelined decoding: A compute-latency trade-off for exact LLM decoding","author":"Yang","year":"2023","journal-title":"arXiv:2307.05908"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1609\/aaaiss.v5i1.35586"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3240511"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2024.3463392"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2024.3509269"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2024.3490609"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2025.3532093"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.257"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02169"},{"key":"ref170","first-page":"16344","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","author":"Dao"},{"key":"ref171","first-page":"1","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dao"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00089"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607102"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3269530"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00043"},{"key":"ref176","article-title":"Hardware-aware parallel prompt decoding for memory-efficient acceleration of LLM inference","author":"Mark Chen","year":"2024","journal-title":"arXiv:2405.18628"},{"key":"ref177","article-title":"DuoDecoding: Hardware-aware heterogeneous speculative decoding with dynamic multi-sequence drafting","author":"Lv","year":"2025","journal-title":"arXiv:2503.00784"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00077"},{"key":"ref179","first-page":"18015","article-title":"S3: Increasing GPU utilization during generative inference for higher throughput","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","volume":"36","author":"Jin"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02170"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323725"},{"key":"ref182","first-page":"75","article-title":"Power-aware deep learning model serving with \u03bc-serve","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Qiu"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/mdat.2024.3521320"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00078"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref186","first-page":"699","article-title":"Quant-LLM: Accelerating the serving of large language models via FP6-centric algorithm-system co-design on modern GPUs","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC)","author":"Xia"},{"key":"ref187","article-title":"A dataflow compiler for efficient LLM inference using custom microscaling formats","author":"Cheng","year":"2023","journal-title":"arXiv:2307.15517"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441578"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1145\/3696443.3708944"},{"key":"ref190","article-title":"Lean attention: Hardware-aware scalable attention mechanism for the decode-phase of transformers","author":"Sanovar","year":"2024","journal-title":"arXiv:2405.10480"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2023.3305569"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3443692"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2024.3426653"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/tcad.2024.3513265"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00071"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3121264"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00065"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3170848"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3373592"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3181541"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774692"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/tcad.2024.3487781"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2024.3350661"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00079"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/FPL57034.2022.00015"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1145\/3658617.3697562"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3657325"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"ref211","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","volume-title":"Proc. 12th USENIX Symp. Oper. Syst. Design Implement.","author":"Abadi"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref214","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"Proc. 13th USENIX Symp. Operating Syst. Design Implement. (OSDI)","author":"Chen"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462176"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546747"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071058"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.14778\/3626292.3626303"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323775"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/IA356718.2022.00009"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3288520"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3365942"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI54635.2022.00051"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926300"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1145\/3617689"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695964"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref229","article-title":"JENGA: Effective memory management for serving LLM with heterogeneity","author":"Zhang","year":"2025","journal-title":"arXiv:2503.18292"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363545"},{"key":"ref231","first-page":"31094","article-title":"FlexGen: High-throughput generative inference of large language models with a single GPU","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sheng"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00368"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/ICTA60488.2023.10364277"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2022.3206262"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569665"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00088"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392751"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00051"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1145\/3549937"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/FPL60245.2023.00041"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCAS62034.2024.10652850"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1145\/3370748.3406567"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1145\/3453688.3461739"},{"key":"ref246","first-page":"1","article-title":"Towards a reconfigurable systolic array with multi-level packing for transformers","volume-title":"Proc. Archit. Syst. Support Transformer Models (ASSYST)","author":"Zhao"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1145\/3626202.3637562"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1145\/3649476.3658810"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/FPL60245.2023.00012"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC58780.2024.10473976"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM57271.2023.00049"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1145\/3656177"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/FPL64840.2024.00037"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323910"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3107746"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1684\/1\/012063"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00044"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1109\/CSCloud-EdgeCom58631.2023.00085"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1038\/s44335-024-00004-2"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2024.3402174"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2023.3337777"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191521"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2024.3397189"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1109\/apccas62602.2024.10808854"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446749"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2021.3127517"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00031"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365862"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00029"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC54236.2022.00096"},{"key":"ref272","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2003.02989"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00059"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067422"},{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46769.2022.9830276"},{"key":"ref276","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3122905"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3140414"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3140753"},{"key":"ref279","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2023.3343457"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3139015"},{"key":"ref281","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2960488"},{"key":"ref282","doi-asserted-by":"publisher","DOI":"10.1109\/HCS59251.2023.10254703"},{"key":"ref283","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49657.2024.10454441"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3258906"},{"key":"ref285","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3067593"},{"key":"ref286","article-title":"SpiNNaker2: A large-scale neuromorphic system for event-based and asynchronous machine learning","author":"Gonzalez","year":"2024","journal-title":"arXiv:2401.04491"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.615279"},{"key":"ref288","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS59952.2024.10595910"},{"key":"ref289","doi-asserted-by":"publisher","DOI":"10.1109\/ICONS62911.2024.00018"},{"key":"ref290","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS54282.2022.9869925"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1109\/MSSC.2022.3201783"},{"key":"ref292","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9020286"},{"key":"ref293","doi-asserted-by":"publisher","DOI":"10.1109\/A-SSCC48613.2020.9336128"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI51109.2021.00036"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1109\/NEWCAS49341.2020.9159773"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1109\/ITherm55375.2024.10709430"},{"key":"ref297","doi-asserted-by":"publisher","DOI":"10.1115\/DETC2023-116429"},{"key":"ref298","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2023.113072"},{"key":"ref299","doi-asserted-by":"publisher","DOI":"10.1109\/MPEL.2024.3398448"},{"key":"ref300","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.3040800"},{"key":"ref301","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"ref302","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS47522.2019.9020515"},{"key":"ref303","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.2983975"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.1109\/CSTIC.2018.8369333"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2020.2969325"},{"key":"ref306","doi-asserted-by":"publisher","DOI":"10.1109\/ASICON58565.2023.10396119"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2024.3366282"},{"key":"ref308","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4277-0"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691788"},{"key":"ref310","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691683"},{"key":"ref311","article-title":"Make every move count: LLM-based high-quality RTL code generation using MCTS","author":"DeLorenzo","year":"2024","journal-title":"arXiv:2402.03289"},{"key":"ref312","doi-asserted-by":"publisher","DOI":"10.1145\/3643681"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC58780.2024.10473904"},{"key":"ref314","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691810"},{"key":"ref315","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323812"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691836"},{"key":"ref317","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD62225.2024.10740201"},{"key":"ref318","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691770"},{"key":"ref319","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691798"},{"key":"ref320","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD62225.2024.10740226"},{"key":"ref321","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3657356"},{"key":"ref322","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691738"},{"key":"ref323","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3420904"},{"key":"ref324","article-title":"SA-DS: A dataset for large language model-driven AI accelerator design generation","author":"Vungarala","year":"2024","journal-title":"arXiv:2404.10875"},{"key":"ref325","doi-asserted-by":"publisher","DOI":"10.1145\/3649476.3658738"},{"key":"ref326","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD62225.2024.10740247"},{"key":"ref327","article-title":"The power of large language models for wireless communication system development: A case study on FPGA platforms","author":"Du","year":"2023","journal-title":"arXiv:2307.07319"},{"key":"ref328","article-title":"SynthAI: A multi agent generative AI framework for automated modular HLS design generation","author":"Sheikholeslam","year":"2024","journal-title":"arXiv:2405.16072"},{"key":"ref329","first-page":"1","article-title":"Improving large language model hardware generating quality through post-LLM search","volume-title":"Proc. Mach. Learn. Syst.","author":"Chang"},{"key":"ref330","article-title":"RTLFixer: Automatically fixing RTL syntax errors with large language models","author":"Tsai","year":"2023","journal-title":"arXiv:2311.16543"},{"key":"ref331","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD58807.2023.10299874"},{"key":"ref332","article-title":"AutoChip: Automating HDL generation using LLM feedback","author":"Thakur","year":"2023","journal-title":"arXiv:2311.04887"},{"key":"ref333","article-title":"Advanced large language model (LLM)-driven verilog development: Enhancing power, performance, and area optimization in code synthesis","author":"Thorat","year":"2023","journal-title":"arXiv:2312.01022"},{"key":"ref334","article-title":"BetterV: Controlled verilog generation with discriminative guidance","author":"Pei","year":"2024","journal-title":"arXiv:2402.03375"},{"key":"ref335","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323953"},{"key":"ref336","doi-asserted-by":"publisher","DOI":"10.1109\/ISEDA62518.2024.10618053"},{"key":"ref337","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-37703-7_18"},{"key":"ref338","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676679"},{"key":"ref339","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691753"},{"key":"ref340","doi-asserted-by":"publisher","DOI":"10.1145\/3734524"},{"key":"ref341","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD62225.2024.10740262"},{"key":"ref342","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676781"},{"key":"ref343","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC62300.2024.10737751"},{"key":"ref344","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3658493"},{"key":"ref345","article-title":"The graph\u2019s apprentice: Teaching an LLM low level knowledge for circuit quality estimation","author":"Moravej","year":"2024","journal-title":"arXiv:2411.00843"},{"key":"ref346","article-title":"Deep inverse design for high-level synthesis","author":"Chang","year":"2024","journal-title":"arXiv:2407.08797"},{"key":"ref347","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS55109.2022.00041"},{"key":"ref348","doi-asserted-by":"publisher","DOI":"10.1145\/3444950.3447283"},{"key":"ref349","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774721"},{"key":"ref350","first-page":"402","article-title":"SyFAxO-GeN: Synthesizing FPGA-based approximate operators with generative networks","volume-title":"Proc. 28th Asia South Pacific Design Autom. Conf. (ASP-DAC)","author":"Ranjan"},{"key":"ref351","article-title":"SeaDAG: Semi-autoregressive diffusion for conditional directed acyclic graph generation","author":"Zhou","year":"2024","journal-title":"arXiv:2410.16119"},{"key":"ref352","article-title":"Circuit transformer: A transformer that preserves logical equivalence","author":"Li","year":"2024","journal-title":"arXiv:2403.13838"},{"key":"ref353","article-title":"Logic synthesis with generative deep neural networks","author":"Li","year":"2024","journal-title":"arXiv:2406.04699"},{"key":"ref354","doi-asserted-by":"publisher","DOI":"10.1109\/MECO62516.2024.10577923"},{"key":"ref355","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC58780.2024.10473927"},{"key":"ref356","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3383347"},{"key":"ref357","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691849"},{"key":"ref358","doi-asserted-by":"publisher","DOI":"10.1109\/CAE59785.2024.10487167"},{"key":"ref359","doi-asserted-by":"publisher","DOI":"10.1109\/ICONS62911.2024.00024"},{"key":"ref360","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2024.3404117"},{"key":"ref361","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3129647"},{"key":"ref362","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD58817.2023.00056"},{"key":"ref363","doi-asserted-by":"publisher","DOI":"10.1145\/3658617.3703143"},{"key":"ref364","doi-asserted-by":"publisher","DOI":"10.1109\/MCSoC64144.2024.00066"},{"key":"ref365","doi-asserted-by":"publisher","DOI":"10.1145\/3569052.3572993"},{"key":"ref366","doi-asserted-by":"publisher","DOI":"10.1145\/3636461"},{"key":"ref367","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942063"},{"key":"ref368","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3122109"},{"key":"ref369","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323611"},{"key":"ref370","doi-asserted-by":"publisher","DOI":"10.1145\/3564930"},{"key":"ref371","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323630"},{"key":"ref372","first-page":"264","article-title":"BufFormer: A generative ML framework for scalable buffering","volume-title":"Proc. 28th Asia South Pacific Design Autom. Conf. (ASP-DAC)","author":"Liang"},{"key":"ref373","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3656232"},{"key":"ref374","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13091704"},{"key":"ref375","doi-asserted-by":"publisher","DOI":"10.1145\/3626184.3633328"},{"key":"ref376","first-page":"32468","article-title":"Circuit as set of points","volume-title":"Proc. Adv. Neural Inf. Proces. Syst. (NeurIPS)","volume":"36","author":"Zou"},{"key":"ref377","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643435"},{"key":"ref378","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13112003"},{"key":"ref379","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3438379"},{"key":"ref380","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.013.2300485"},{"key":"ref381","doi-asserted-by":"publisher","DOI":"10.1145\/3626184.3635277"},{"key":"ref382","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD62225.2024.10740250"},{"key":"ref383","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691801"},{"key":"ref384","doi-asserted-by":"publisher","DOI":"10.1109\/LAD62341.2024.10691874"},{"key":"ref385","article-title":"LLM-aided testbench generation and bug detection for finite-state machines","author":"Bhandari","year":"2024","journal-title":"arXiv:2406.17132"},{"key":"ref386","doi-asserted-by":"publisher","DOI":"10.1109\/VTS60656.2024.10538589"},{"key":"ref387","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546729"},{"key":"ref388","doi-asserted-by":"publisher","DOI":"10.1109\/ETS61313.2024.10567741"},{"key":"ref389","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546707"},{"key":"ref390","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD62225.2024.10740218"},{"key":"ref391","doi-asserted-by":"publisher","DOI":"10.1145\/3698364.3705347"},{"key":"ref392","doi-asserted-by":"publisher","DOI":"10.1109\/TCPMT.2021.3126083"},{"key":"ref393","article-title":"Wafer map defect classification using autoencoder-based data augmentation and convolutional neural network","author":"Bao","year":"2024","journal-title":"arXiv:2411.11029"},{"key":"ref394","doi-asserted-by":"publisher","DOI":"10.1109\/TSM.2021.3107720"},{"key":"ref395","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489422"},{"key":"ref396","doi-asserted-by":"publisher","DOI":"10.1109\/TSM.2020.3004483"},{"key":"ref397","doi-asserted-by":"publisher","DOI":"10.1109\/TSM.2019.2940334"},{"key":"ref398","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3013492"},{"key":"ref399","doi-asserted-by":"publisher","DOI":"10.1109\/ITC44778.2020.9325225"},{"key":"ref400","doi-asserted-by":"publisher","DOI":"10.1109\/ITC50671.2022.00026"},{"key":"ref401","doi-asserted-by":"publisher","DOI":"10.1109\/TSM.2019.2925361"},{"key":"ref402","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA55696.2022.00025"},{"key":"ref403","doi-asserted-by":"publisher","DOI":"10.3390\/app13095507"},{"key":"ref404","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3351802"},{"key":"ref405","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3092372"},{"key":"ref406","doi-asserted-by":"publisher","DOI":"10.1109\/VTS60656.2024.10538654"},{"key":"ref407","doi-asserted-by":"publisher","DOI":"10.1109\/IRPS48228.2024.10529397"},{"key":"ref408","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/ac9ed3"},{"key":"ref409","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD62225.2024.10740163"},{"key":"ref410","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19639-3"},{"key":"ref411","article-title":"Observational and experimental insights into machine learning-based defect classification in wafers","author":"Taha","year":"2023","journal-title":"arXiv:2310.10705"},{"key":"ref412","doi-asserted-by":"publisher","DOI":"10.1109\/TSM.2014.2364237"},{"key":"ref413","doi-asserted-by":"publisher","DOI":"10.1109\/ITC51657.2024.00030"},{"key":"ref414","doi-asserted-by":"publisher","DOI":"10.1109\/ITCAsia55616.2022.00016"},{"key":"ref415","doi-asserted-by":"publisher","DOI":"10.1109\/ASP-DAC52403.2022.9712592"},{"key":"ref416","first-page":"1","article-title":"WellGAN: Generative-adversarial-network-guided well generation for analog\/mixed-signal circuit layout","volume-title":"Proc. 56th ACM\/IEEE Design Autom. Conf. (DAC)","author":"Xu"},{"key":"ref417","article-title":"LADAC: Large language model-driven auto-designer for analog circuits","author":"Liu","year":"2024","journal-title":"techrxiv:170473941.10097233"},{"key":"ref418","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i1.32016"},{"key":"ref419","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942164"},{"key":"ref420","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2022.3172869"},{"key":"ref421","first-page":"1","article-title":"Align: Open-source analog layout automation from the ground up","volume-title":"Proc. 56th Annu. Design Autom. Conf. 2019","author":"Kunal"},{"key":"ref422","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2020.3042177"},{"key":"ref423","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546515"},{"key":"ref424","doi-asserted-by":"publisher","DOI":"10.1109\/JAC-ECC61002.2023.10479617"},{"key":"ref425","doi-asserted-by":"publisher","DOI":"10.23919\/SISPAD57422.2023.10319551"},{"key":"ref426","doi-asserted-by":"publisher","DOI":"10.1109\/APCCAS62602.2024.10808823"},{"key":"ref427","doi-asserted-by":"publisher","DOI":"10.1109\/MLCAD62225.2024.10740211"},{"key":"ref428","doi-asserted-by":"publisher","DOI":"10.1145\/3580477"},{"key":"ref429","first-page":"1","article-title":"A customized graph neural network model for guiding analog IC placement","volume-title":"Proc. IEEE\/ACM Int. Conf. Comput. Aided Design (ICCAD)","author":"Li"},{"key":"ref430","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.2977605"}],"container-title":["IEEE Journal on Emerging and Selected Topics in Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5503868\/11050007\/11024158.pdf?arnumber=11024158","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T17:43:47Z","timestamp":1750959827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11024158\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":430,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jetcas.2025.3575272","relation":{},"ISSN":["2156-3357","2156-3365"],"issn-type":[{"value":"2156-3357","type":"print"},{"value":"2156-3365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}