{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T23:19:46Z","timestamp":1768519186505,"version":"3.49.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"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":[[2025,12,14]]},"DOI":"10.1109\/icpads67057.2025.11323095","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["FUPS: Fusion-Based Parallel Structured Pruning for Large Language Models"],"prefix":"10.1109","author":[{"given":"Shouyuan","family":"Qin","sequence":"first","affiliation":[{"name":"Hubei Normal University,Huangshi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guixia","family":"Wang","sequence":"additional","affiliation":[{"name":"South China Normal University,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuhui","family":"Xiong","sequence":"additional","affiliation":[{"name":"Hubei Normal University,Huangshi,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS61541.2024.00034"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0336"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3524255"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3456549"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107899"},{"key":"ref6","first-page":"129","article-title":"What is the state of neural network pruning?","volume-title":"Proceedings of machine learning and systems","volume":"2","author":"Blalock","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055564"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0491"},{"key":"ref10","article-title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","volume-title":"7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA","author":"Frankle","year":"2019"},{"key":"ref11","first-page":"21702","article-title":"Llm-pruner: On the structural pruning of large language models","volume":"36","author":"Ma","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2305"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28960"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3744244"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0289"},{"key":"ref16","article-title":"Learning both weights and connections for efficient neural network","volume":"28","author":"Han","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref18","article-title":"Dynamic network surgery for efficient dnns","volume":"29","author":"Guo","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"6682","article-title":"Proving the lottery ticket hypothesis: Pruning is all you need","volume-title":"International Conference on Machine Learning","author":"Malach","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/7902.7903"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3437801.3441593"},{"key":"ref22","first-page":"7937","article-title":"Memory-efficient pipeline-parallel dnn training","volume-title":"International Conference on Machine Learning","author":"Narayanan","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/12.75137"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1811.06965"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref26","first-page":"4150","article-title":"Pipetransformer: Automated elastic pipelining for distributed training of large-scale models","volume-title":"International Conference on Machine Learning","author":"He","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.01.125"},{"key":"ref28","first-page":"1","article-title":"Beyond data and model parallelism for deep neural networks","volume-title":"Proceedings of Machine Learning and Systems","volume":"1","author":"Jia","year":"2019"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3458817.3476209","article-title":"Efficient large-scale language model training on gpu clusters using megatron-lm","volume-title":"Proceedings of the international conference for high performance computing, networking, storage and analysis","author":"Narayanan","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref31","first-page":"10323","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","volume-title":"International Conference on Machine Learning (ICML)","author":"Frantar","year":"2023"},{"key":"ref32","article-title":"SliceGPT: Compress large language models by deleting rows and columns","author":"Ashkboos","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0248"}],"event":{"name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","location":"Hefei, China","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11322805\/11322871\/11323095.pdf?arnumber=11323095","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:26:07Z","timestamp":1768461967000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323095\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323095","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}