{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T05:10:15Z","timestamp":1756357815181,"version":"3.44.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:00:00Z","timestamp":1751760000000},"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":[[2025,7,6]]},"DOI":"10.1109\/isvlsi65124.2025.11130227","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T18:20:15Z","timestamp":1756318815000},"page":"1-2","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Neural Network Compression for Fast Inference on Hardware"],"prefix":"10.1109","author":[{"given":"Jingcun","family":"Wang","sequence":"first","affiliation":[{"name":"Technical University of Darmstadt"}]},{"given":"Mengnan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt"}]},{"given":"Grace Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"Technical University of Darmstadt"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Optimal brain damage","volume":"2","author":"LeCun","year":"1989","journal-title":"Advances in neural information processing systems"},{"article-title":"Pruning filters for efficient convnets","volume-title":"ICLR","author":"Li","key":"ref2"},{"article-title":"Trainability preserving neural pruning","volume-title":"ICLR","author":"Wang","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3156047"},{"key":"ref6","article-title":"Network trimming: A data-driven neuron pruning approach towards efficient deep architectures","author":"Hu","year":"2016","journal-title":"arXiv preprint arXiv:1607.03250"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref8","first-page":"24 604","article-title":"Chip: Channel independence-based pruning for compact neural networks","volume":"34","author":"Sui","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref10","article-title":"Gate decorator: Global filter pruning method for accelerating deep convolutional neural networks","volume":"32","author":"You","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247868"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00982"},{"article-title":"Loss-aware weight quantization of deep networks","volume-title":"arXiv preprint arXiv:1802.08635","author":"Hou","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00916"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ECCTD.2017.8093264"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088904"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10137171"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref19","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv preprint arXiv:1412.6550"},{"key":"ref20","article-title":"Kdgan: Knowledge distillation with generative adversarial networks","volume":"31","author":"Wang","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16865"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546606"},{"key":"ref23","article-title":"Convolutional neural network compression based on low-rank decomposition","author":"He","year":"2024","journal-title":"arXiv preprint arXiv:2408.16289"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00807"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_31"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/447"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"article-title":"Multi-scale dense networks for resource efficient image classification","volume-title":"ICLR 2018","author":"Huang","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00198"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411973"},{"key":"ref31","first-page":"3301","article-title":"Shallow-deep networks: Understanding and mitigating network overthinking","volume-title":"International conference on machine learning","author":"Kaya"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_22"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.sustainlp-1.5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.344"},{"article-title":"Universal transformers","volume-title":"International Conference on Learning Representations","author":"Dehghani","key":"ref35"},{"article-title":"Dynamic layer tying for parameter-efficient transformers","volume-title":"The Twelfth International Conference on Learning Representations","author":"Hay","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546870"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS59952.2024.10595861"},{"article-title":"Basis sharing: Cross-layer parameter sharing for large language model compression","volume-title":"International Conference on Learning Representations","author":"Wang","key":"ref39"}],"event":{"name":"2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","start":{"date-parts":[[2025,7,6]]},"location":"Kalamata, Greece","end":{"date-parts":[[2025,7,9]]}},"container-title":["2025 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11129697\/11130193\/11130227.pdf?arnumber=11130227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T04:31:17Z","timestamp":1756355477000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11130227\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/isvlsi65124.2025.11130227","relation":{},"subject":[],"published":{"date-parts":[[2025,7,6]]}}}