{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:23:15Z","timestamp":1771950195158,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10445737","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11296-11300","source":"Crossref","is-referenced-by-count":21,"title":["One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models"],"prefix":"10.1109","author":[{"given":"Hang","family":"Shao","sequence":"first","affiliation":[{"name":"AI Institute,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence"}]},{"given":"Bei","family":"Liu","sequence":"additional","affiliation":[{"name":"AI Institute,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"AI Institute,Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.36"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref4","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.334"},{"key":"ref6","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022"},{"key":"ref7","article-title":"Zeroquant: Efficient and affordable post-training quantization for large-scale transformers","author":"Yao","year":"2022"},{"key":"ref8","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","author":"Xiao","year":"2022"},{"key":"ref9","article-title":"Spqr: A sparse-quantized representation for near-lossless llm weight compression","author":"Dettmers","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.496"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.279"},{"key":"ref12","article-title":"Prune once for all: Sparse pre-trained language models","author":"Zafrir"},{"key":"ref13","article-title":"Llm-pruner: On the structural pruning of large language models","author":"Ma"},{"key":"ref14","article-title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","author":"Frantar","year":"2023"},{"key":"ref15","first-page":"28092","article-title":"Post-training quantization for vision transformer","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"Degree-quant: Quantization-aware training for graph neural networks","author":"Tailor","year":"2020"},{"issue":"2","key":"ref17","article-title":"Poor man\u2019s bert: Smaller and faster transformer models","volume":"2","author":"Sajjad","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.496"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.829"},{"key":"ref20","article-title":"Optimal brain damage","author":"LeCun","year":"1989","journal-title":"Neural Information Processing Systems,Neural Information Processing Systems"},{"key":"ref21","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","author":"Hassibi","year":"1992","journal-title":"Neural Information Processing Systems, Neural Information Processing Systems"},{"key":"ref22","article-title":"Optimal brain compression: A framework for accurate post-training quantization and pruning","author":"Frantar","year":"2022"},{"key":"ref23","article-title":"Accelerated sparse neural training: A provable and efficient method to find n:m transposable masks","author":"Hubara","year":"2021","journal-title":"Neural Information Processing Systems, Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref25","article-title":"Hawq-v2: Hessian aware trace-weighted quantization of neural networks","author":"Dong","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1201\/b11822-37"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1944345.1944349"},{"key":"ref28","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref29","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref30","article-title":"Baichuan-7b","year":"2023"},{"key":"ref31","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075835"},{"key":"ref33","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-2607"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SSDM.2003.1214975"},{"key":"ref38","article-title":"To prune, or not to prune: exploring the efficacy of pruning for model compression","author":"Zhu","year":"2017"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10445737.pdf?arnumber=10445737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:37:19Z","timestamp":1722573439000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10445737\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10445737","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}